Author: "Denis Kouame" / Search Limiters: Full Text - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Denis Kouame"' showing total 112 results

Start Over Author "Denis Kouame" Search Limiters Full Text

112 results on '"Denis Kouame"'

1. Quantum Mechanics-Based Signal and Image Representation: Application to Denoising

Author: Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouame
Subjects: Adaptive signal and image representation, adaptive transformation, denoising, quantum mechanics, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract: Decomposition of digital signals and images into other basis or dictionaries than time or space domains is a very common approach in signal and image processing and analysis. Such a decomposition is commonly obtained using fixed transforms (e.g., Fourier or wavelet) or dictionaries learned from example databases or from the signal or image itself. In this work, we investigate in detail a new approach of constructing such a signal or image-dependent bases inspired by quantum mechanics tools, i.e., by considering the signal or image as a potential in the discretized Schroedinger equation. To illustrate the potential of the proposed decomposition, denoising results are reported in the case of Gaussian, Poisson, and speckle noise and compared to the state of the art algorithms based on wavelet shrinkage, total variation regularization or patch-wise sparse coding in learned dictionaries, non-local means image denoising, and graph signal processing.
Published: 2021
Full Text: View/download PDF

2. Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images

Author: Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouame
Subjects: Poisson deconvolution, plug-and-play, ADMM, quantum denoiser, adaptive denoiser, quantum image processing, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract: A new Plug-and-Play (PnP) alternating direction of multipliers (ADMM) scheme is proposed in this paper, by embedding a recently introduced adaptive denoiser using the Schroedinger equation’s solutions of quantum physics. The potential of the proposed model is studied for Poisson image deconvolution, which is a common problem occurring in number of imaging applications, such as limited photon acquisition or X-ray computed tomography. Numerical results show the efficiency and good adaptability of the proposed scheme compared to recent state-of-the-art techniques, for both high and low signal-to-noise ratio scenarios. This performance gain regardless of the amount of noise affecting the observations is explained by the flexibility of the embedded quantum denoiser constructed without anticipating any prior statistics about the noise, which is one of the main advantages of this method. The main novelty of this work resided in the integration of a modified quantum denoiser into the PnP-ADMM framework and the numerical proof of convergence of the resulting algorithm.
Published: 2021
Full Text: View/download PDF

3. Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version

Author: Marie-Caroline, Corbineau, Denis, Kouamé, Emilie, Chouzenoux, Jean-Yves, Tourneret, and Jean-Christophe, Pesquet
Subjects: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract: Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopting a hierarchical Bayesian model, we propose an accelerated Markov chain Monte Carlo scheme where the tissue reflectivity function is sampled thanks to a recently introduced proximal unadjusted Langevin algorithm. This new approach is combined with a forward-backward step and a preconditioning strategy to accelerate the convergence, and with a method based on the majorization-minimization principle to solve the inner nonconvex minimization problems. As demonstrated in numerical experiments conducted on both simulated and in vivo ultrasound images, the proposed method provides high-quality restoration and segmentation results and is up to six times faster than an existing Hamiltonian Monte Carlo method.
Published: 2019
Full Text: View/download PDF

4. CX-DaGAN: Domain Adaptation for Pneumonia Diagnosis on a Small Chest X-Ray Dataset

Author: Karen Sanchez, Carlos Hinojosa, Henry Arguello, Denis Kouame, Olivier Meyrignac, and Adrian Basarab
Subjects: Nicardipine, Deep Learning, Radiological and Ultrasound Technology, X-Rays, Humans, Neural Networks, Computer, Pneumonia, Electrical and Electronic Engineering, Software, Computer Science Applications
Abstract: Recent advances in deep learning led to several algorithms for the accurate diagnosis of pneumonia from chest X-rays. However, these models require large training medical datasets, which are sparse, isolated, and generally private. Furthermore, these models in medical imaging are known to over-fit to a particular data domain source, i.e., these algorithms do not conserve the same accuracy when tested on a dataset from another medical center, mainly due to image distribution discrepancies. In this work, a domain adaptation and classification technique is proposed to overcome the over-fit challenges on a small dataset. This method uses a private-small dataset (target domain), a public-large labeled dataset from another medical center (source domain), and consists of three steps. First, it performs a data selection of the source domain's most representative images based on similarity constraints through principal component analysis subspaces. Second, the selected samples from the source domain are fit to the target distribution through an image to image translation based on a cycle-generative adversarial network. Finally, the target train dataset and the adapted images from the source dataset are used within a convolutional neural network to explore different settings to adjust the layers and perform the classification of the target test dataset. It is shown that fine-tuning a few specific layers together with the selected-adapted images increases the sorting accuracy while reducing the trainable parameters. The proposed approach achieved a notable increase in the target dataset's overall classification accuracy, reaching up to 97.78 % compared to 90.03 % by standard transfer learning.
Published: 2022

5. Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images

Author: Denis Kouame, Adrian Basarab, Sayantan Dutta, Bertrand Georgeot, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Laboratoire de Physique Théorique (LPT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), and Université Fédérale Toulouse Midi-Pyrénées
Subjects: General Computer Science, Computer science, 020209 energy, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Poisson deconvolution, 02 engineering and technology, plug-and-play, quantum image processing, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Convergence (routing), 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, General Materials Science, [INFO]Computer Science [cs], Electrical and Electronic Engineering, Quantum, Image restoration, Noise measurement, Image and Video Processing (eess.IV), General Engineering, Electrical Engineering and Systems Science - Image and Video Processing, TK1-9971, Noise, adaptive denoiser, Embedding, 020201 artificial intelligence & image processing, Deconvolution, Electrical engineering. Electronics. Nuclear engineering, quantum denoiser, ADMM, Algorithm
Abstract: A new Plug-and-Play (PnP) alternating direction of multipliers (ADMM) scheme is proposed in this paper, by embedding a recently introduced adaptive denoiser using the Schroedinger equation's solutions of quantum physics. The potential of the proposed model is studied for Poisson image deconvolution, which is a common problem occurring in number of imaging applications, such as limited photon acquisition or X-ray computed tomography. Numerical results show the efficiency and good adaptability of the proposed scheme compared to recent state-of-the-art techniques, for both high and low signal-to-noise ratio scenarios. This performance gain regardless of the amount of noise affecting the observations is explained by the flexibility of the embedded quantum denoiser constructed without anticipating any prior statistics about the noise, which is one of the main advantages of this method. The main novelty of this work resided in the integration of a modified quantum denoiser into the PnP-ADMM framework and the numerical proof of convergence of the resulting algorithm., Comment: 22 pages, 13 figures; complements and expands arXiv:2010.09321
Published: 2021

6. Evaluation of Four Rapid Tests for Detection of Hepatitis B Surface Antigen in Ivory Coast

Author: Aimé Cézaire Adiko, Mathieu Kabran, Rodrigue Denis Kouame, Emile Allah-Kouadio, André Inwoley, Vanessa Goha, Roseline Affi-Aboli, Bamory Dembele, and Daouda Sevede
Subjects: Hepatitis B virus, 2019-20 coronavirus outbreak, HBsAg, Article Subject, Coronavirus disease 2019 (COVID-19), Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), Immunology, Antibodies, Viral, medicine.disease_cause, Hepatitis b surface antigen, Sensitivity and Specificity, 03 medical and health sciences, Liver disease, 0302 clinical medicine, Predictive Value of Tests, parasitic diseases, medicine, Humans, Mass Screening, Immunology and Allergy, Serologic Tests, 030212 general & internal medicine, False Negative Reactions, Hepatitis B Surface Antigens, business.industry, Reproducibility of Results, virus diseases, Diagnostic test, General Medicine, RC581-607, Reference Standards, Hepatitis B, medicine.disease, Virology, digestive system diseases, Cote d'Ivoire, Cross-Sectional Studies, 030211 gastroenterology & hepatology, Immunologic diseases. Allergy, business, Algorithms, Research Article
Abstract: Background. Hepatitis B virus (HBV) infection is a leading cause of liver disease worldwide. Hepatitis B surface antigen (HBsAg) rapid diagnostic tests (RDTs) could be an ideal tool for a large-scale HBV screening in settings with high endemicity but limited infrastructure. The aim of this study was to evaluate the diagnosis performance of such RDTs for screening HBV infection in Ivory Coast. Methods. From September 2018 to January 2019, a cross-sectional phase I evaluation study of RDTs was conducted in three laboratories of Abidjan (CeDReS, CNTS and IPCI), on a panel of 405 whole blood samples and 699 plasmas. Four HBsAg RDTs (Determine™ HBsAg, SD Bioline HBsAg WB®, Standard Q HBsAg® and Vikia HBsAg®) were evaluated. The diagnostic performance (sensitivity and specificity) was calculated in comparison to the reference sequential algorithms of two EIA tests (Dia.Pro HBsAg® one version ULTRA and Monolisa™ HBsAg ULTRA). Results. The Determine™ HBsAg and Vikia HBsAg® tests performed well, with 100% of sensitivity, specificity both on plasma and on whole blood. For SD Bioline HBsAg WB® and Standard Q HBsAg®, the specificities were 99.8% and the sensitivities 99.3% and 97.1% respectively. Finally, there were a total of 19 false negative results: 3 with SD Bioline HBsAg WB® and 16 with Standard Q HBsAg®. Conclusion. Determine HBsAg® from Alere and Vikia HBsAg® from Biomérieux are the most suitable RDTs for screening for HBV in Ivory Coast. A phase II evaluation must be initiated.
Published: 2020

7. Image Denoising Inspired by Quantum Many-Body physics

Author: Adrian Basarab, Sayantan Dutta, Bertrand Georgeot, Denis Kouame, Laboratoire de Physique Théorique (LPT), Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, IEEE, Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), and Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)
Subjects: quantum denoising, Similarity (geometry), Computer science, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), Image processing, 02 engineering and technology, quantum image processing, symbols.namesake, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Digital image processing, 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Noise (signal processing), Image and Video Processing (eess.IV), Wavelet transform, 020207 software engineering, Quantum many-body interaction, Electrical Engineering and Systems Science - Image and Video Processing, adaptive transform, Additive white Gaussian noise, Computer Science::Computer Vision and Pattern Recognition, symbols, 020201 artificial intelligence & image processing, Algorithm
Abstract: Decomposing an image through Fourier, DCT or wavelet transforms is still a common approach in digital image processing, in number of applications such as denoising. In this context, data-driven dictionaries and in particular exploiting the redundancy withing patches extracted from one or several images allowed important improvements. This paper proposes an original idea of constructing such an image-dependent basis inspired by the principles of quantum many-body physics. The similarity between two image patches is introduced in the formalism through a term akin to interaction terms in quantum mechanics. The main contribution of the paper is thus to introduce this original way of exploiting quantum many-body ideas in image processing, which opens interesting perspectives in image denoising. The potential of the proposed adaptive decomposition is illustrated through image denoising in presence of additive white Gaussian noise, but the method can be used for other types of noise such as image-dependent noise as well. Finally, the results show that our method achieves comparable or slightly better results than existing approaches., Comment: 5 pages, 4 figures
Published: 2021

8. Quantum mechanics-based signal and image representation: application to denoising

Author: Adrian Basarab, Bertrand Georgeot, Sayantan Dutta, Denis Kouame, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Information et Chaos Quantiques (LPT), Laboratoire de Physique Théorique (LPT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)
Subjects: Signal Processing (eess.SP), Computer science, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, 02 engineering and technology, Signal, [SPI]Engineering Sciences [physics], Wavelet, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Quantum mechanics, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, denoising, [INFO]Computer Science [cs], Electrical Engineering and Systems Science - Signal Processing, Signal processing, Basis (linear algebra), adaptive signal and image representation, Image and Video Processing (eess.IV), quantum mechanics, 020206 networking & telecommunications, Speckle noise, Total variation denoising, Electrical Engineering and Systems Science - Image and Video Processing, TK1-9971, adaptive transformation, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Electrical engineering. Electronics. Nuclear engineering
Abstract: Decomposition of digital signals and images into other basis or dictionaries than time or space domains is a very common approach in signal and image processing and analysis. Such a decomposition is commonly obtained using fixed transforms (e.g., Fourier or wavelet) or dictionaries learned from example databases or from the signal or image itself. In this work, we investigate in detail a new approach of constructing such a signal or image-dependent bases inspired by quantum mechanics tools, i.e., by considering the signal or image as a potential in the discretized Schroedinger equation. To illustrate the potential of the proposed decomposition, denoising results are reported in the case of Gaussian, Poisson, and speckle noise and compared to the state of the art algorithms based on wavelet shrinkage, total variation regularization or patch-wise sparse coding in learned dictionaries, non-local means image denoising, and graph signal processing., 17 pages, 18 figures; complements and expands arXiv:1802.02358
Published: 2021

9. Fast High Resolution Blood Flow Estimation and Clutter Rejection via an Alternating Optimization Problem

Author: Jean-Pierre Remenieras, Duong-Hung Pham, Adrian Basarab, Denis Kouame, Paul Rodriguez, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Imagerie et cerveau (iBrain - Inserm U1253 - UNIV Tours ), Université de Tours (UT)-Institut National de la Santé et de la Recherche Médicale (INSERM), Pontifical Catholic University of Peru, ANR-11-INBS-0006,FLI,France Life Imaging(2011), Université de Tours-Institut National de la Santé et de la Recherche Médicale (INSERM), PHAM, Duong-Hung, Infrastructures - France Life Imaging - - FLI2011 - ANR-11-INBS-0006 - INBS - VALID, Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), and Pontificia Universidad Católica del Perú = Pontifical Catholic University of Peru (PUCP)
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Blind deconvolution, Optimization problem, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer science, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 010103 numerical & computational mathematics, 02 engineering and technology, [MATH.MATH-FA]Mathematics [math]/Functional Analysis [math.FA], 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], symbols.namesake, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, FOS: Electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, blood flow, 0101 mathematics, Sequence, 021103 operations research, Image and Video Processing (eess.IV), [MATH.MATH-FA] Mathematics [math]/Functional Analysis [math.FA], Doppler, ultrafast ultrasound, Blood flow, Electrical Engineering and Systems Science - Image and Video Processing, clutter suppression, robust PCA, blind deconvolution, symbols, Clutter, Deconvolution, Robust principal component analysis, Doppler effect, Algorithm
Abstract: This paper introduces a computationally efficient technique for estimating high-resolution Doppler blood flow from an ultrafast ultrasound image sequence. More precisely, it consists in a new fast alternating minimization algorithm that implements a blind deconvolution method based on robust principal component analysis. Numerical investigation carried out on \textit{in vivo} data shows the efficiency of the proposed approach in comparison with state-of-the-art methods., 4 pages, 5 figures
Published: 2020

10. A Novel Fast 3D Single Image Super-Resolution Algorithm

Author: Denis Kouame, Adrian Basarab, Nwigbo Kenule Tuador, Duong-Hung Pham, Jérôme Michetti, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Petroleum Technology Development Fund (PTDF) overseas scholarship under the government of Nigeria, IEEE Signal Processing Society (SPS), and IEEE Engineering in Medicine and Biology Society (EMBS)
Subjects: FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Solid modeling, [MATH.MATH-FA]Mathematics [math]/Functional Analysis [math.FA], Regularization (mathematics), 030218 nuclear medicine & medical imaging, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Tikhonov regularization, 03 medical and health sciences, 0302 clinical medicine, Operator (computer programming), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Decomposition (computer science), [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 3D single image super-resolution, Decimation, Image and Video Processing (eess.IV), Volume (computing), 020206 networking & telecommunications, Electrical Engineering and Systems Science - Image and Video Processing, total variation, Frequency domain, ADMM, Algorithm
Abstract: This paper introduces a novel computationally efficient method of solving the 3D single image super-resolution (SR) problem, i.e., reconstruction of a high-resolution volume from its low-resolution counterpart. The main contribution lies in the original way of handling simultaneously the associated decimation and blurring operators, based on their underlying properties in the frequency domain. In particular, the proposed decomposition technique of the 3D decimation operator allows a straightforward implementation for Tikhonov regularization, and can be further used to take into consideration other regularization functions such as the total variation, enabling the computational cost of state-of-the-art algorithms to be considerably decreased. Numerical experiments carried out showed that the proposed approach outperforms existing 3D SR methods., 5 pages, 2 figures
Published: 2020

11. Constrained Bundle Adjustment Applied to Wing 3D Reconstruction with Mechanical Limitations

Author: Adrian Basarab, Quentin Demoulin, Jean-Yves Tourneret, Francois Lefebvre-Albaret, Denis Kouame, Airbus [France], CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Télécommunications Spatiales et Aéronautiques - Telecommunications for Space ant Aeronautics (TéSA), Laboratoire de recherche coopératif dans les télécommunications spatiales et aéronautiques (TESA), Institut National Polytechnique (Toulouse) (Toulouse INP), Airbus (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Laboratoire de recherche en télécommunications spatiales et aéronautiques - TéSA (FRANCE), and Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France)
Subjects: 020301 aerospace & aeronautics, Wing, Computer science, 3D reconstruction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Bundle adjustment, 02 engineering and technology, Video processing, Three-dimensional image, Mechanical limits, Optimization underconstraints, Photogrammetry, 0203 mechanical engineering, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Control theory, 0202 electrical engineering, electronic engineering, information engineering, Wing deformations, Traitement du signal et de l'image, 020201 artificial intelligence & image processing
Abstract: International audience; Aircraft certification procedures require the estimation ofwing deformation, which is a very challenging problem inphotogrammetry applications. Indeed, in real flight condi-tions with varying environment, 3D reconstruction is stronglydegraded. To cope with this issue, we propose to introduceprior knowledge about the wing mechanical limits in thephotogrammetry reconstruction method. These mechanicallimits are expressed as appropriate regularizations that areincluded into the classical bundle adjustment step. The pro-posed approach is evaluated using data acquired on a realaircraft yielding promising results.
Published: 2020

12. Ultrasound Image Deconvolution Using Fundamental and Harmonic Images

Author: Denis Kouame, Mohamad Hourani, Adrian Basarab, and Jean-Yves Tourneret
Subjects: Point spread function, Physics, Acoustics and Ultrasonics, Context (language use), 01 natural sciences, Harmonic analysis, Nonlinear system, 0103 physical sciences, Harmonic, Deconvolution, Radio frequency, Electrical and Electronic Engineering, 010301 acoustics, Instrumentation, Algorithm, Image restoration
Abstract: Ultrasound (US) image restoration from radio frequency (RF) signals is generally addressed by deconvolution techniques mitigating the effect of the system point spread function (PSF). Most of the existing methods estimate the tissue reflectivity function (TRF) from the so-called fundamental US images, based on an image model assuming the linear US wave propagation. However, several human tissues or tissues with contrast agents have a nonlinear behavior when interacting with US waves leading to harmonic images. This work takes this nonlinearity into account in the context of TRF restoration, by considering both fundamental and harmonic RF signals. Starting from two observation models (for the fundamental and harmonic images), TRF estimation is expressed as the minimization of a cost function defined as the sum of two data fidelity terms and one sparsity-based regularization stabilizing the solution. The high attenuation with a depth of harmonic echoes is integrated into the direct model that relates the observed harmonic image to the TRF. The interest of the proposed method is shown through synthetic and in vivo results and compared with other restoration methods.
Published: 2020

13. Ultrasound and magnetic resonance image fusion using a patch-wise polynomial model

Author: Denis Kouame, Adrian Basarab, O. El Mansouri, Jean-Yves Tourneret, Mário A. T. Figueiredo, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), SpaceAble (FRANCE), Laboratoire de recherche en télécommunications spatiales et aéronautiques - TéSA (FRANCE), Universidade de Lisboa - ULisboa (PORTUGAL), Télécommunications Spatiales et Aéronautiques - Telecommunications for Space ant Aeronautics (TéSA), Laboratoire de recherche coopératif dans les télécommunications spatiales et aéronautiques (TESA), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Instituto de Telecomunicações [Lisboa, Portugal], and Institut National Polytechnique (Toulouse) (Toulouse INP)
Subjects: Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, 030218 nuclear medicine & medical imaging, Image (mathematics), Despeckling, Patch-based method, 03 medical and health sciences, 0302 clinical medicine, Signal-to-noise ratio, Polynomial and rational function modeling, Magnetic resonance imaging, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, medicine, Traitement du signal et de l'image, Image fusion, Image resolution, Modality (human–computer interaction), medicine.diagnostic_test, business.industry, Ultrasound, Function (mathematics), Superresolution, Nonlinear system, Computer Science::Computer Vision and Pattern Recognition, Super-resolution, Image enhancement, Ultrasound imaging, 020201 artificial intelligence & image processing, business, Algorithm
Abstract: International audience; This paper introduces a novel algorithm for the fusion of magnetic resonance and ultrasound images, based on a patch-wise polynomial model relating the gray levels of the two imaging systems (called modalities). Starting from observation models adapted to each modality and exploiting a patch-wise polynomial model, the fusion problem is expressed as the minimization of a cost function including two data fidelity terms and two regularizations. This minimization is performed using a PALM-based algorithm, given its ability to handle nonlinear and possibly non-convex functions. The efficiency of the proposed method is evaluated on phantom data. The resulting fused image is shown to contain complementary information from both magnetic resonance (MR) and ultrasound (US) images, i.e., with a good contrast (as for the MR image) and a good spatial resolution (as for the US image).
Published: 2020

14. Joint Blind Deconvolution and Robust Principal Component Analysis for Blood Flow Estimation in Medical Ultrasound Imaging

Author: Ilyess Zemmoura, Jean-Pierre Remenieras, Duong-Hung Pham, Denis Kouame, Adrian Basarab, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Imagerie et cerveau (iBrain - Inserm U1253 - UNIV Tours ), Université de Tours (UT)-Institut National de la Santé et de la Recherche Médicale (INSERM), PHAM, Duong-Hung, Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), and Université de Tours-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: FOS: Computer and information sciences, Blind deconvolution, Point spread function, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Acoustics and Ultrasonics, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Context (language use), 02 engineering and technology, [MATH.MATH-FA]Mathematics [math]/Functional Analysis [math.FA], 01 natural sciences, medical ultrasound, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Singular value decomposition, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Image Processing, Computer-Assisted, blood flow, Electrical and Electronic Engineering, 010301 acoustics, Instrumentation, Ultrasonography, Principal Component Analysis, Phantoms, Imaging, Image and Video Processing (eess.IV), [MATH.MATH-FA] Mathematics [math]/Functional Analysis [math.FA], Electrical Engineering and Systems Science - Image and Video Processing, Inverse problem, clutter separation, robust PCA, blind deconvolution, sensitive Doppler, Clutter, 020201 artificial intelligence & image processing, Deconvolution, Robust principal component analysis, Algorithm, Blood Flow Velocity
Abstract: This paper addresses the problem of high-resolution Doppler blood flow estimation from an ultrafast sequence of ultrasound images. Formulating the separation of clutter and blood components as an inverse problem has been shown in the literature to be a good alternative to spatio-temporal singular value decomposition (SVD)-based clutter filtering. In particular, a deconvolution step has recently been embedded in such a problem to mitigate the influence of the experimentally measured point spread function (PSF) of the imaging system. Deconvolution was shown in this context to improve the accuracy of the blood flow reconstruction. However, measuring the PSF requires non-trivial experimental setups. To overcome this limitation, we propose herein a blind deconvolution method able to estimate both the blood component and the PSF from Doppler data. Numerical experiments conducted on simulated and in vivo data demonstrate qualitatively and quantitatively the effectiveness of the proposed approach in comparison with the previous method based on experimentally measured PSF and two other state-of-the-art approaches., 9 pages, 7 figures
Published: 2020

15. Single Image Super-Resolution of Noisy 3D Dental CT Images Using Tucker Decomposition

Author: Adrian Basarab, Jerome Michetti, Denis Kouame, M. Gyongy, and J. Hatvaniy
Subjects: business.industry, Noise (signal processing), Computer science, Noise reduction, Image and Video Processing (eess.IV), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), Pattern recognition, 010103 numerical & computational mathematics, Electrical Engineering and Systems Science - Image and Video Processing, 01 natural sciences, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Robustness (computer science), Computer Science::Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Decomposition (computer science), Segmentation, Artificial intelligence, Deconvolution, 0101 mathematics, business, Tucker decomposition
Abstract: Tensor decomposition has proven to be a strong tool in various 3D image processing tasks such as denoising and super-resolution. In this context, we recently proposed a canonical polyadic decomposition (CPD) based algorithm for single image super-resolution (SISR). The algorithm has shown to be an order of magnitude faster than popular optimization-based techniques. In this work, we investigated the added value brought by Tucker decomposition. While CPD allows a joint implementation of the denoising and deconvolution steps of the SISR model, with Tucker decomposition the denoising is realized first, followed by deconvolution. This way the ill-posedness of the deconvolution caused by noise is partially mitigated. The results achieved using the two different tensor decomposition techniques were compared, and the robustness against noise was investigated. For validation, we used dental images. The superiority of the proposed method is shown in terms of peak signal-to-ratio, structural similarity index, the canal segmentation accuracy, and runtime., 4 pages, 3 figures
Published: 2020

16. Autoregressive model-based reconstruction of quantitative acoustic maps from RF signals sampled at innovation rate

Author: Adrian Basarab, Denis Kouame, Jonghoon Kim, Alin Achim, Jonathan Mamou, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Bristol (UNITED KINGDOM), Riverside Research (USA), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, F. L. Lizzi Center for Biomedical Engineering, Riverside Research, University of Bristol [Bristol], and Université Toulouse III - Paul Sabatier (UT3)
Subjects: Computer science, Acoustics, Acoustic microscopy, 02 engineering and technology, 01 natural sciences, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Sampling (signal processing), 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Finite rate ofinnovation, 010301 acoustics, Parametric statistics, Auto-regressive model, 020206 networking & telecommunications, Computer Science Applications, QAM, Computational Mathematics, Autoregressive model, Finite rate of innovation, Signal Processing, Parametric model, Radio frequency, Scanning acoustic microscopy, Quadrature amplitude modulation
Abstract: International audience; The principle of quantitative acoustic microscopy (QAM) is to form two-dimensional (2D) acoustic parameter maps from a collection of radiofrequency (RF) signals acquired by raster scanning a biological sample. Despite their relatively simple structure consisting of two main reflections, RF signals are currently sampled at very high frequencies, e.g., at 2.5 GHz for QAM system employing a single-element transducer with a center frequency of 250-MHz. The use of such high sampling frequencies is challenging because of the potentially large amount of acquired data and the cost of the necessary analog to digital converters. Based on a parametric model characterizing QAM RF signals, the objective of this paper is to use the finite rate of innovation (FRI) framework in order to significantly reduce the number of acquired samples. These are then used to compute Fourier coefficients that are directly fed into a state-of-theart autoregressive (AR)-based method to estimate the model parameters, which finally leads to the reconstruction of accurate 2D maps. The combination of FRI and AR model for sampling and parametric map recovery allows decreasing the required number of samples per RF signal up to a factor of 18 compared to a conventional approach, with a minimal accuracy loss of quantitative acoustic maps, as proven by visual evaluations and numerical results, i.e. PSNR of 24:50 dB and 24:51 dB for the reconstructed speed of sound map and acoustic impedance map respectively.
Published: 2020

17. Deconvolution for improved multifractal characterization of tissues in ultrasound images

Author: Herwig Wendt, Denis Kouame, Adrian Basarab, Mohamad Hourani, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Centre National de la Recherche Scientifique (CNRS), Université Toulouse III - Paul Sabatier (UT3), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), and Université Toulouse 1 Capitole - UT1 (FRANCE)
Subjects: Scanner, business.industry, Computer science, Ultrasound, Pattern recognition, 02 engineering and technology, Multifractal system, 01 natural sciences, Reflectivity, Characterization (materials science), Fractal, Tissue characterization, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Multifractal analysis, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Ultrasound imaging, Traitement du signal et de l'image, 020201 artificial intelligence & image processing, Deconvolution, Artificial intelligence, business, 010301 acoustics
Abstract: International audience; Several existing studies showed the interest of estimating the multifractal properties of tissues in ultrasound (US) imaging. However, US images are not carrying information only about the tissues, but also about the US scanner. Deconvolution methods are a common way to restore the tissue reflectivity function, but, to our knowledge, their impact on estimated fractal or multifractal behavior has not been studied yet. The objective of this paper is to investigate this influence through a dedicated simulation pipeline and an in vivo experiment.
Published: 2020

18. Blind deconvolution of fundamental and harmonic ultrasound images

Author: Giulia Matrone, Jean-Yves Tourneret, Oleg V. Michailovich, Adrian Basarab, Alessandro Ramalli, Denis Kouame, Mohamad Hourani, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), University of Waterloo [Waterloo], Università degli Studi di Pavia, Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Institut National Polytechnique (Toulouse) (Toulouse INP), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Katholieke Universiteit Leuven - KU LEUVEN (BELGIUM), University of Waterloo (CANADA), and Università di Pavia (ITALY)
Subjects: Blind deconvolution, Point spread function, Scattering, Computer science, business.industry, Ultrasound, Harmonic ultrasound imaging, Function (mathematics), Inverse problem, 01 natural sciences, Image (mathematics), Convolution, Image restoration, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Ultrasound imaging, Harmonic, Traitement du signal et de l'image, business, 010301 acoustics, Algorithm
Abstract: International audience; Restoring the tissue reflectivity function (TRF) from ultrasound (US) images is an extensively explored research field. It is well-known that human tissues and contrast agents have a non-linear behavior when interacting with US waves. In this work, we investigate this non-linearity and the interest of including harmonic US images in the TRF restoration process. Therefore, we introduce a new US image restoration method taking advantage of the fundamental and harmonic components of the observed radiofrequency (RF) image. The depth information contained in the fundamental component and the good resolution of the harmonic image are combined to create an image with better properties than the fundamental and harmonic images considered separately. Under the hypothesis of weak scattering, the RF image is modeled as the 2D convolution between the TRF and the system point spread function (PSF). An inverse problem is formulated based on this model able to jointly estimate the TRF and the PSF. The interest of the proposed blind deconvolution algorithm is shown through an in vivo result and compared to a conventional US restoration method.
Published: 2020

19. Fusion of Magnetic Resonance and Ultrasound Images for Endometriosis Detection

Author: Fabien Vidal, Jean-Yves Tourneret, Oumaima El Mansouri, Pierre Payoux, Adrian Basarab, Denis Kouame, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées, Télécommunications Spatiales et Aéronautiques - Telecommunications for Space ant Aeronautics (TéSA), Laboratoire de recherche coopératif dans les télécommunications spatiales et aéronautiques (TESA), Université Toulouse III - Paul Sabatier (UT3), Toulouse Neuro Imaging Center (ToNIC), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de la Santé et de la Recherche Médicale (INSERM)-Toulouse Mind & Brain Institut (TMBI), Institut National Polytechnique (Toulouse) (Toulouse INP), (OATAO), Open Archive Toulouse Archive Ouverte, Centre National d'Études Spatiales - CNES (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Santé et de la Recherche Médicale - INSERM (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Laboratoire de recherche en télécommunications spatiales et aéronautiques - TéSA (FRANCE), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de la Santé et de la Recherche Médicale (INSERM)-Hôpital Purpan [Toulouse], and CHU Toulouse [Toulouse]-CHU Toulouse [Toulouse]
Subjects: Polynomial, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Image (mathematics), Despeckling, Signal-to-noise ratio, Magnetic resonance imaging, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, medicine, Traitement du signal et de l'image, Image fusion, Computer vision, Image resolution, medicine.diagnostic_test, business.industry, Ultrasound, Inverse problem, Computer Graphics and Computer-Aided Design, Superresolution, Proximal alternating linearized minimization, Computer Science::Computer Vision and Pattern Recognition, Super-resolution, Ultrasound imaging, 020201 artificial intelligence & image processing, Artificial intelligence, business, Software
Abstract: International audience; This paper introduces a new fusion method for magnetic resonance (MR) and ultrasound (US) images, which aims at combining the advantages of each modality, i.e., good contrast and signal to noise ratio for the MR image and good spatial resolution for the US image. The proposed algorithm is on an inverse problem, performing a super-resolution of the MR image and a denoising of the US image. A polynomial function is introduced to model the relationships between the gray levels of the MR and US images. The resulting inverse problem is solved using a proximal alternating linearized minimization algorithm. The accuracy and the interest of the fusion algorithm are shown quantitatively and qualitatively via evaluations on synthetic and experimental phantom data.
Published: 2020

20. Outlier detection at the parcel-level in wheat and rapeseed crops using multispectral and SAR time series

Author: Florian Mouret, Denis Kouame, Mohanad Albughdadi, Sylvie Duthoit, Jean-Yves Tourneret, Guillaume Rieu, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, TerraNIS, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), TerraNIS (FRANCE), Laboratoire de recherche en télécommunications spatiales et aéronautiques - TéSA (FRANCE), and Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France)
Subjects: Synthetic aperture radar, FOS: Computer and information sciences, Computer Science - Machine Learning, 010504 meteorology & atmospheric sciences, Science, Multispectral image, 0211 other engineering and technologies, Machine Learning (stat.ML), Anomaly detection, 02 engineering and technology, Isolation forest, Unsupervised learning, 01 natural sciences, Normalized Difference Vegetation Index, Machine Learning (cs.LG), vigor, Statistics - Machine Learning, [SDV.SA.STA]Life Sciences [q-bio]/Agricultural sciences/Sciences and technics of agriculture, FOS: Electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, unsupervised, Preprocessor, crop monitoring, Sentinel-1, Sentinel-2, isolation forest, anomaly detection, heterogeneity, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Remote sensing, Mathematics, 2. Zero hunger, [SDE.IE]Environmental Sciences/Environmental Engineering, Image and Video Processing (eess.IV), Vegetation, Electrical Engineering and Systems Science - Image and Video Processing, Crop monitoring, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Outlier, General Earth and Planetary Sciences
Abstract: International audience; This paper studies the detection of anomalous crop development at the parcel-level based on an unsupervised outlier detection technique. The experimental validation is conducted on rapeseed and wheat parcels located in Beauce (France). The proposed methodology consists of four sequential steps: (1) preprocessing of synthetic aperture radar (SAR) and multispectral images acquired using Sentinel-1 and Sentinel-2 satellites, (2) extraction of SAR and multispectral pixel-level features, (3) computation of parcel-level features using zonal statistics and (4) outlier detection. The different types of anomalies that can affect the studied crops are analyzed and described. The different factors that can influence the outlier detection results are investigated with a particular attention devoted to the synergy between Sentinel-1 and Sentinel-2 data. Overall, the best performance is obtained when using jointly a selection of Sentinel-1 and Sentinel-2 features with the isolation forest algorithm. The selected features are co-polarized (VV) and cross-polarized (VH) backscattering coefficients for Sentinel-1 and five Vegetation Indexes for Sentinel-2 (among us, the Normalized Difference Vegetation Index and two variants of the Normalized Difference Water). When using these features with an outlier ratio of 10%, the percentage of detected true positives (i.e., crop anomalies) is equal to 94.1% for rapeseed parcels and 95.5% for wheat parcels.
Published: 2020
Full Text: View/download PDF

21. Joint Deconvolution of Fundamental and Harmonic Ultrasound Images

Author: Adrian Basarab, Denis Kouame, Jean-Yves Tourneret, Mohamad Hourani, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), and Institut National Polytechnique (Toulouse) (Toulouse INP)
Subjects: Blind deconvolution, Image formation, Physics, Optimization, Attenuation, 020208 electrical & electronic engineering, Harmonic ultrasound imaging, 02 engineering and technology, Synthetic data, 030218 nuclear medicine & medical imaging, Harmonic analysis, 03 medical and health sciences, Image restoration, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Norm (mathematics), 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Deconvolution, ADMM, Algorithm, Ultrasound imaging, Joint deconvolution
Abstract: International audience; This paper studies the interest of using harmonic ultrasound (US) images in the process of tissue reflectivity function restoration from RF data. To this end, two direct models (one for fundamental and another for harmonique images) derived from the equation of US wave propagation are proposed. In particular, an axially varying attenuation matrix is used within the harmonic image model in order to account for the attenuation of harmonic echoes. Based on these two image formation models, a joint deconvolution problem is investigated. The solution of this problem is obtained by minimizing a cost function composed of two data fidelity terms representing the linear and non-linear model components,regularized by an ℓ 1 -norm regularization. The tissue reflectivity function minimizing this function is finally determined using an alternating direction method of multipliers. The performance of the proposed algorithm is quantitatively and qualitatively evaluated on synthetic data, and compared with a classical restoration method used for US images.
Published: 2019

22. On the design of a pelvic phantom for magnetic resonance and ultrasound image fusion

Author: Adrian Basarab, Fabien Vidal, Oumaima El Mansouri, Denis Kouame, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, and Université Toulouse III - Paul Sabatier (UT3)
Subjects: Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pelvic phantom, Imaging phantom, 030218 nuclear medicine & medical imaging, Manufactured phantoms, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, medicine, Numerical simulations, Traitement du signal et de l'image, Computer vision, ComputingMethodologies_COMPUTERGRAPHICS, Flexibility (engineering), Image fusion, 030219 obstetrics & reproductive medicine, Modality (human–computer interaction), medicine.diagnostic_test, business.industry, Ultrasound, Magnetic resonance imaging, Phantom experiments, Multimodality phantom, Ultrasound image fusion, Magnetic resonance, MRI-ultrasound fusion, Artificial intelligence, business
Abstract: International audience; The purpose of this paper is to introduce a customized multi- modality phantom designed to facilitate the proof-of-concept of MRI/ultrasound fusion approaches. Phantom experiments are often required before in vivo validation, giving access to more challenging data than numerical simulations. Nevertheless, manufactured phantoms are expensive and usually lack of flexibility. In contrast, the proposed model was inexpensive and accurately designed to overcome multimodal registration issues.
Published: 2019

23. An Axially Variant Kernel Imaging Model Applied to Ultrasound Image Reconstruction

Author: Sergiy A. Vorobyov, Denis Kouame, Mihai I. Florea, Adrian Basarab, Aalto University, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Aalto University (FINLAND), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Subjects: Signal Processing (eess.SP), Image formation, Forward model, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Deconvolution, 02 engineering and technology, 01 natural sciences, Imaging, Convolution, Axially varying, Matrix-free, Ultrasound, Point-spread function, 0103 physical sciences, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Boundary value problem, Electrical Engineering and Systems Science - Signal Processing, Electrical and Electronic Engineering, Invariant (mathematics), 010301 acoustics, Circulant matrix, ta213, Ultrasonic imaging, Applied Mathematics, 92C55, Computational modeling, Inverse problem, Modélisation et simulation, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Kernel, Kernel (image processing), Image reconstruction, Signal Processing, 020201 artificial intelligence & image processing, Algorithm
Abstract: International audience; Existing ultrasound deconvolution approaches unrealistically assume, primarily for computational reasons, that the convolution model relies on a spatially invariant kernel and circulant boundary conditions. We discard both restrictions and introduce an image formation model applicable to ultrasound imaging and deconvolution based on an axially varying kernel, which accounts for arbitrary boundary conditions. Our model has the same computational complexity as the one employing spatially invariant convolution and has negligible memory requirements. To accommodate the state-of-the-art deconvolution approaches when applied to a variety of inverse problem formulations, we also provide an equally efficient adjoint expression for our model. Simulation results confirm the tractability of our model for the deconvolution of large images. Moreover, in terms of accuracy metrics, the quality of reconstruction using our model is superior to that obtained using spatially invariant convolution.
Published: 2018

24. Beamforming Through Regularized Inverse Problems in Ultrasound Medical Imaging

Author: Denis Kouame, Teodora Szasz, Adrian Basarab, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: FOS: Computer and information sciences, Beamforming, Acoustics and Ultrasonics, Computational complexity theory, Computer science, Computer Vision and Pattern Recognition (cs.CV), Gaussian, Computer Science - Computer Vision and Pattern Recognition, Thyroid Gland, Basis pursuit (BP), 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 030218 nuclear medicine & medical imaging, Traitement des images, 03 medical and health sciences, symbols.namesake, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Robustness (computer science), 0103 physical sciences, Image Processing, Computer-Assisted, Medical imaging, Humans, Traitement du signal et de l'image, Adaptive beamforming (BF), Electrical and Electronic Engineering, Synthèse d'image et réalité virtuelle, 010301 acoustics, Instrumentation, Image resolution, Ultrasonography, Phantoms, Imaging, Linear model, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Vision par ordinateur et reconnaissance de formes, Intelligence artificielle, Inverse problem, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Carotid Arteries, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Linear inverse problems, Least squares (LS), symbols, Beamspace processing, Algorithm
Abstract: Beamforming in ultrasound imaging has significant impact on the quality of the final image, controlling its resolution and contrast. Despite its low spatial resolution and contrast, delay-and-sum is still extensively used nowadays in clinical applications, due to its real-time capabilities. The most common alternatives are minimum variance method and its variants, which overcome the drawbacks of delay-and-sum, at the cost of higher computational complexity that limits its utilization in real-time applications. In this paper, we propose to perform beamforming in ultrasound imaging through a regularized inverse problem based on a linear model relating the reflected echoes to the signal to be recovered. Our approach presents two major advantages: i) its flexibility in the choice of statistical assumptions on the signal to be beamformed (Laplacian and Gaussian statistics are tested herein) and ii) its robustness to a reduced number of pulse emissions. The proposed framework is flexible and allows for choosing the right trade-off between noise suppression and sharpness of the resulted image. We illustrate the performance of our approach on both simulated and experimental data, with \textit{in vivo} examples of carotid and thyroid. Compared to delay-and-sum, minimimum variance and two other recently published beamforming techniques, our method offers better spatial resolution, respectively contrast, when using Laplacian and Gaussian priors.
Published: 2016

25. Brain Segmentation from Super-Resolved Magnetic Resonance Images

Author: Ahmad Diab, Muriel Mescam, Denis Kouame, Adrian Basarab, Farah Bazzi, Juan D. Rodriguez-Callejas, Hassan Amoud, Caroline Fonta, Omar Falou, Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées, Centre de recherche cerveau et cognition (CERCO), Institut des sciences du cerveau de Toulouse. (ISCT), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-CHU Toulouse [Toulouse]-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-CHU Toulouse [Toulouse]-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Lebanese University [Beirut] (LU), Azm Center for Biotechnology Research, Lebanese University [Beirut] (LU)-Agence universitaire de la Francophonie (Beyrouth, Lebanon), Laboratoire Modélisation et Sûreté des Systèmes (LM2S), Institut Charles Delaunay (ICD), Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS), Doctoral School of Sciences and Technology [Lebanese University], American University of Culture & Education (AUCE), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Association of Azm w Saade (AWS) and Doctoral School of Science and Technology - Tripoli, Liban, Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Agence universitaire de la Francophonie (Beyrouth, Lebanon)-Lebanese University [Beirut] (LU), Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), Fonta, Caroline, Université de Toulouse (UT), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), and Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole)
Subjects: Point spread function, Deblurring, Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 030218 nuclear medicine & medical imaging, White matter, 03 medical and health sciences, 0302 clinical medicine, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Brain segmentation, Segmentation, structural MRI, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Ground truth, marmoset, medicine.diagnostic_test, business.industry, segmentation, Single image super-resolution, Magnetic resonance imaging, Pattern recognition, Fast algorithm, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, medicine.anatomical_structure, ICV, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery, cerebral aging
Abstract: International audience; The objective of this work is to investigate the ability of a 2D super resolution (SR) technique in 3D restoration and enhancement of brain magnetic resonance images to facilitate the study of cerebral aging bio-markers. The SR method exploits the joint properties of the system point spread function and sub-sampling operators to derive a fast algorithm. Brain images of the common marmoset, Callithrix jacchus, acquired at different ages are used in this study. The evaluation of the final outcome of our method is done by computing the intracranial volume from the segmentation of the brain compartments: gray matter, white matter and cerebrospinal fluid. Results show that the deblurring of the images improves the segmentation process with respect to the ground truth. However, super resolution leads to the best quantification of the intracranial volume when compared to the deblurred and the original images. Therefore, despite its sub-optimality, the 2D SR method provides reliable results for improving the quality of the images used in the study of aging in terms of precision of reconstruction and computational time.
Published: 2019

26. Development of ultrasensitive Doppler imaging method for the surgical management of open-brain tumors

Author: S. Beuve, Denis Kouame, J.-P. Remenieras, A. Bassarab, Jl. Gennisson, I. Zemmoura, E. Koury, C. Barthelemy, Imagerie et cerveau (iBrain - Inserm U1253 - UNIV Tours ), Université de Tours (UT)-Institut National de la Santé et de la Recherche Médicale (INSERM), Imagerie par Résonance Magnétique Médicale et Multi-Modalités (IR4M), Université Paris-Sud - Paris 11 (UP11)-Hôpital Bicêtre-Centre National de la Recherche Scientifique (CNRS), Service Hospitalier Frédéric Joliot (SHFJ), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Commissariat à l'Energie Atomique et aux énergies alternatives - CEA (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Santé et de la Recherche Médicale - INSERM (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Université de Tours (FRANCE), Université Paris-Sud 11 (FRANCE), Université de Tours-Institut National de la Santé et de la Recherche Médicale (INSERM), and Centre National de la Recherche Scientifique (CNRS)-Hôpital Bicêtre-Université Paris-Sud - Paris 11 (UP11)
Subjects: Optimization, medicine.medical_specialty, Neo-angiogenosis, Sensitive Doppler, Doppler imaging, 030218 nuclear medicine & medical imaging, Tumor excision, 03 medical and health sciences, 0302 clinical medicine, Conflicting objectives, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Parenchyma, Traitement du signal et de l'image, Medicine, Neurological deficit, Robust PCA, business.industry, Brain, Glioma surgery, Viscoelasticity, Blood flow, 3. Good health, Cerebral tumors, Radiology, business
Abstract: International audience; Gliomas are infiltrating tumors in the healthy brain parenchyma with no clear boundaries and can be located near or within "functional" brain zones driving as an example, motor skills, sensitivity, cognition or vision. Two conflicting objectives must be achieved during cerebral glioma surgery: (1) to obtain a tumor excision as complete as possible, the oncological prognosis being improved by surgery; and (2) to limit the risk of definitive neurological deficit by respecting the brain areas infiltrated by the tumor remaining functional. The objective of our work is to develop an intraoperative biomecanical analysis and a micro vascularization imaging method and validate the interest of these techniques for the diagnosis of tumor neo-angiogenesis and ultimately to target the surgical procedure during surgery.
Published: 2019

27. Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images

Author: Denis Kouame, Marie-Caroline Corbineau, Emilie Chouzenoux, Jean-Christophe Pesquet, Jean-Yves Tourneret, Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec, Université Paris-Saclay, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Télécommunications Spatiales et Aéronautiques - Telecommunications for Space ant Aeronautics (TéSA), Laboratoire de recherche coopératif dans les télécommunications spatiales et aéronautiques (TESA), Institut National Polytechnique (Toulouse) (Toulouse INP), ANR-17-CE40-0004,MajIC,Algorithmes de Majoration-Minimisation pour le traitement d'images(2017), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Recherche en Informatique et en Automatique - INRIA (FRANCE), Université Paris-Saclay (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), CentraleSupélec (FRANCE), Direction Générale de l’Aviation Civile - DGAC (FRANCE), Laboratoire de recherche en télécommunications spatiales et aéronautiques - TéSA (FRANCE), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), and Université Fédérale Toulouse Midi-Pyrénées
Subjects: Computer science, Segmentation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Deconvolution, Bayesian inference, Hybrid Monte Carlo, symbols.namesake, Traitement des images, [INFO.INFO-MC]Computer Science [cs]/Mobile Computing, Ultrasound, 0202 electrical engineering, electronic engineering, information engineering, Medical imaging, Electrical and Electronic Engineering, Applied Mathematics, Informatique mobile, 020206 networking & telecommunications, Markov chain Monte Carlo, Proximity operator, Markov chain Monte Carlo method, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, symbols, Algorithm
Abstract: International audience; Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopt- ing a hierarchical Bayesian model, we propose an accelerated Markov chain Monte Carlo scheme where the tissue reflectivity function is sampled thanks to a recently introduced proximal unadjusted Langevin algorithm. This new approach is combined with a forward-backward step and a preconditioning strategy to accelerate the convergence, and with a method based on the majorization-minimization principle to solve the inner noncon- vex minimization problems. As demonstrated in numerical ex- periments conducted on both simulated and in vivo ultrasound images, the proposed method provides high-quality restoration and segmentation results and is up to six times faster than an existing Hamiltonian Monte Carlo method.
Published: 2019

28. High-resolution and high-sensitivity blood flow estimation using optimization approaches with application to vascularization imaging

Author: Adrian Basarab, C. Barthelemy, Y. Zemmoura, H. Shen, Denis Kouame, E. Khoury, and J.-P. Remenieras
Subjects: business.industry, Computer science, Pattern recognition, 02 engineering and technology, Blood flow, Filter (signal processing), Inverse problem, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, symbols.namesake, 0302 clinical medicine, Computer Science::Computer Vision and Pattern Recognition, Singular value decomposition, 0202 electrical engineering, electronic engineering, information engineering, Filtering problem, symbols, Clutter, 020201 artificial intelligence & image processing, Deconvolution, Sensitivity (control systems), Artificial intelligence, business, Doppler effect, Robust principal component analysis
Abstract: In this paper, we address the problem of high-resolution flow estimation in medical ultrasound images. Imaging methods based on ultrafast sequences associated with adaptive spatiotemporal SVD clutter filtering have recently improved blood flow detection. Herein, we investigate a new way of addressing the clutter filtering problem in order to obtain a high-resolution flow estimation, through solving an inverse problem corresponding to both deconvolution and robust principal component analysis. Applied to tissue vascularization imaging via power Doppler images, the proposed method highlights finer details on experimental data compared to existing approaches.
Published: 2019

29. Tensor-Factorization-Based 3D Single Image Super-Resolution with Semi-Blind Point Spread Function Estimation

Author: Janka Hatvani, Jerome Michetti, Adrian Basarab, Denis Kouame, Miklós Gyöngy, Pázmány Péter Catholic University, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), and Pázmány Péter Catholic University - PPCU (HUNGARY)
Subjects: Point spread function, Image quality, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Computed tomography, 02 engineering and technology, Iterative reconstruction, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Traitement des images, 0302 clinical medicine, 0202 electrical engineering, electronic engineering, information engineering, medicine, Single image, Image resolution, 3D super-resolution, Tensor factorization, medicine.diagnostic_test, 3D computed tomography, Total variation denoising, Superresolution, Kernel (image processing), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Image enhancement, 020201 artificial intelligence & image processing, Semi-blind deconvolution, Algorithm
Abstract: International audience; A volumetric non-blind single image super-resolution technique using tensor factorization has been recently introduced by our group. That method allowed a 2-order-of-magnitude faster high-resolution image reconstruction with equivalent image quality compared to state-of-the-art algorithms. In this work a joint alternating recovery of the high-resolution image and of the unknown point spread function parameters is proposed. The method is evaluated on dental computed tomography images. The algorithm was compared to an existing 3D super-resolution method using low-rank and total variation regularization, combined with the same alternating PSF-optimization. The two algorithms have shown similar improvement in PSNR, but our method converged roughly 40 times faster, under 6 minutes both in simulation and on experimental dental computed tomography data
Published: 2019

30. A convolutional neural network for 250-MHz quantitative acoustic-microscopy resolution enhancement

Author: Jonathan Mamou, Denis Kouame, Thomas Pellegrini, Adrian Basarab, F. L. Lizzi Center for Biomedical Engineering, Riverside Research, Équipe Structuration, Analyse et MOdélisation de documents Vidéo et Audio (IRIT-SAMoVA), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, CoMputational imagINg anD viSion (IRIT-MINDS), Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), and Riverside Research (USA)
Subjects: Point spread function, Computer science, 0206 medical engineering, Transducers, Microscopy, Acoustic, Acoustic microscopy, Breast Neoplasms, 02 engineering and technology, Signal-To-Noise Ratio, Convolutional neural network, Regularization (mathematics), Convolution, Machine Learning, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Probability density function, Electric Impedance, 0202 electrical engineering, electronic engineering, information engineering, Humans, Traitement du signal et de l'image, Training, Image resolution, Decimation, Ground truth, Spatial resolution, business.industry, Two dimensional displays, Pattern recognition, Acoustics, 020601 biomedical engineering, Noise, Transducer, 020201 artificial intelligence & image processing, Lymph Nodes, Neural Networks, Computer, Artificial intelligence, business
Abstract: International audience; Quantitative acoustic microscopy (QAM) permits the formation of quantitative two-dimensional (2D) maps of acoustic and mechanical properties of soft tissues at microscopic resolution. The 2D maps formed using our custom SAM systems employing a 250-MHz and a 500-MHz single-element transducer have a nominal resolution of 7 μm and 4μm, respectively. In a previous study, the potential of single-image super-resolution (SR) image post-processing to enhance the spatial resolution of 2D SAM maps was demonstrated using a forward model accounting for blur, decimation, and noise. However, results obtained when the SR method was applied to soft tissue data were not entirely satisfactory because of the limitation of the convolution model considered and by the difficulty of estimating the system point spread function and designing the appropriate regularization term. Therefore, in this study, a machine learning approach based on convolutional neural networks was implemented. For training, data acquired on the same samples at 250 and 500 MHz were used. The resulting trained network was tested on 2D impedance maps (2DZMs) of human lymph nodes acquired from breast-cancer patients. Visual inspection of the reconstructed enhanced 2DZMs were found similar to the 2DZMs obtained at 500 MHz which were used as ground truth. In addition, the enhanced 250-MHz 2DZMs obtained from the proposed method yielded better peak signal to noise ratio and normalized mean square error than those obtained with the previous SR method. This improvement was also demonstrated by the statistical analyses. This pioneering work could significantly reduce challenges and costs associated with current very high-frequency SAM systems while providing enhanced spatial resolution.
Published: 2019

31. On Single-Image Super-Resolution in 3D Brain Magnetic Resonance Imaging

Author: Denis Kouame, Adrian Basarab, Muriel Mescam, Farah Bazzi, (OATAO), Open Archive Toulouse Archive Ouverte, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées, Centre de recherche cerveau et cognition (CERCO), Institut des sciences du cerveau de Toulouse. (ISCT), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre Hospitalier Universitaire de Toulouse (CHU Toulouse)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Université Toulouse III - Paul Sabatier (UT3), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-CHU Toulouse [Toulouse]-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-CHU Toulouse [Toulouse]-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)
Subjects: [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer science, Low rank, Tensors, Regularization (mathematics), 030218 nuclear medicine & medical imaging, White matter, 03 medical and health sciences, Segmentation, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Image Processing, Computer-Assisted, medicine, Humans, Traitement du signal et de l'image, Gray Matter, Image resolution, Image restoration, Ground truth, medicine.diagnostic_test, business.industry, Brain, Single image super-resolution, Pattern recognition, Magnetic resonance imaging, Total variation regularization, Image segmentation, Total variation denoising, Inverse problem, Magnetic Resonance Imaging, White Matter, Superresolution, 030227 psychiatry, Structural MRI, medicine.anatomical_structure, Artificial intelligence, business, Algorithms
Abstract: International audience; The objective of this work is to apply 3D super resolution (SR) techniques to brain magnetic resonance (MR) image restoration. Two 3D SR methods are considered following different trends: one recently proposed tensor-based approach and one inverse problem algorithm based on total variation and low rank regularization. The evaluation of their effectiveness is assessed through the segmentation of brain compartments: gray matter, white matter and cerebrospinal fluid. The two algorithms are qualitatively and quantitatively evaluated on simulated images with ground truth available and on experimental data. The originality of this work is to consider the SR methods as an initial step towards the final segmentation task. The results show the ability of both methods to overcome the loss of spatial resolution and to facilitate the segmentation of brain structures with improved accuracy compared to native low-resolution MR images. Both algorithms achieved almost equivalent results with a highly reduced computational time cost for the tensor-based approach.
Published: 2019

32. A Tensor Factorization Method for 3-D Super Resolution With Application to Dental CT

Author: Adrian Basarab, Jean-Yves Tourneret, Miklós Gyöngy, Denis Kouame, Janka Hatvani, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Institut National Polytechnique (Toulouse) (Toulouse INP), Pázmány Péter Catholic University, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Pázmány Péter Catholic University - PPCU (HUNGARY), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: FOS: Computer and information sciences, Point spread function, Cone beam computed tomography, Databases, Factual, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Dental application, computer.software_genre, 030218 nuclear medicine & medical imaging, Image (mathematics), 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, Factorization, Voxel, Radiography, Dental, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Segmentation, Electrical and Electronic Engineering, Image resolution, Imagerie médicale, Hyperparameter, 3D super-resolution, Radiological and Ultrasound Technology, Tensor factorization, Cone-Beam Computed Tomography, Superresolution, Computer Science Applications, Single image super, Resolution, Tooth, Algorithm, computer, Algorithms, Software
Abstract: Available super-resolution techniques for 3D images are either computationally inefficient prior-knowledge-based iterative techniques or deep learning methods which require a large database of known low- and high-resolution image pairs. A recently introduced tensor-factorization-based approach offers a fast solution without the use of known image pairs or strict prior assumptions. In this article this factorization framework is investigated for single image resolution enhancement with an off-line estimate of the system point spread function. The technique is applied to 3D cone beam computed tomography for dental image resolution enhancement. To demonstrate the efficiency of our method, it is compared to a recent state-of-the-art iterative technique using low-rank and total variation regularizations. In contrast to this comparative technique, the proposed reconstruction technique gives a 2-order-of-magnitude improvement in running time -- 2 minutes compared to 2 hours for a dental volume of 282$\times$266$\times$392 voxels. Furthermore, it also offers slightly improved quantitative results (peak signal-to-noise ratio, segmentation quality). Another advantage of the presented technique is the low number of hyperparameters. As demonstrated in this paper, the framework is not sensitive to small changes of its parameters, proposing an ease of use., This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
Published: 2019

33. ON MULTIFRACTAL TISSUE CHARACTERIZATION IN ULTRASOUND IMAGING

Author: Edouard Villain, Denis Kouame, Herwig Wendt, Adrian Basarab, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées, Équipe DIagnostic, Supervision et COnduite (LAAS-DISCO), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse III - Paul Sabatier (UPS), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse 1 Capitole (UT1)-Université Toulouse - Jean Jaurès (UT2J)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse 1 Capitole (UT1)-Université Toulouse - Jean Jaurès (UT2J), Université Toulouse 1 Capitole (UT1)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UPS), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Centre National de la Recherche Scientifique (CNRS), and Université Toulouse III - Paul Sabatier (UT3)
Subjects: Computer science, business.industry, Quantitative Biology::Tissues and Organs, Physics::Medical Physics, Pattern recognition, Multifractal system, Tissue characterization, 01 natural sciences, multifractal analy- sis, Fractal, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Multifractal analysis, 0103 physical sciences, Ultrasound imaging, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Traitement du signal et de l'image, Artificial intelligence, 010306 general physics, business, tissue characterization, 010301 acoustics, Index Terms-Ultrasound imaging
Abstract: International audience; Tissue characterization based on ultrasound (US) images is an extensively explored research field. Most of the existing techniques are focused on the estimation of statistical or acoustic parameters from the backscattered radio-frequency signals, thus complementing the visual inspection of the conventional B-mode images. Additionally, a few studies show the interest of analyzing the fractal or multifractal behavior of human tissues, in particular of tumors. While biological experiments sustain such multifractal behaviors, the observations on US images are rather empirical. To our knowledge, there is no theoretical or practical study relating the fractal or multifractal parameters extracted from US images to those of the imaged tissues. The aim of this paper is to investigate how multifractal properties of a tissue correlate with the ones estimated from a simulated US image for the same tissue. To this end, an original simulation pipeline of multifractal tissues and their corresponding US images is proposed. Simulation results are compared to those in an in vivo experiment.
Published: 2019

34. Fusion Of Magnetic Resonance And Ultrasound Images: A Preliminary Study On Simulated Data

Author: Adrian Basarab, Oumaima El Mansouri, Fabien Vidal, Jean-Yves Tourneret, Denis Kouame, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Institut National Polytechnique (Toulouse) (Toulouse INP), and IEEE
Subjects: Polynomial, Computer science, Physics::Medical Physics, super-resolution, 02 engineering and technology, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Signal-to-noise ratio, 0202 electrical engineering, electronic engineering, information engineering, medicine, [INFO]Computer Science [cs], Image resolution, despeckling, medicine.diagnostic_test, business.industry, Ultrasound, alternating direction method of multipliers, Pattern recognition, Magnetic resonance imaging, Inverse problem, Total variation denoising, Superresolution, fusion MRI and ultrasound, 020201 artificial intelligence & image processing, Artificial intelligence, business, total variation regularization
Abstract: International audience; We propose a new fusion method for magnetic resonance imaging (MRI) and ultrasound (US) data combining two inverse problems: MRI reconstruction using super-resolution and US image despeckling, using a model relating the two modalities through an unknown polynomial function. We demonstrate the accuracy of the proposed fusion algorithm by quantitative and qualitative evaluation using synthetic data. The resulting fused image is shown to have an improved signal to noise ratio and spatial resolution compared to the native MRI and US images.
Published: 2019

35. Iterative Reconstruction of Medical Ultrasound Images Using Spectrally Constrained Phase Updates

Author: Adrian Basarab, Oleg V. Michailovich, Denis Kouame, University of Waterloo [Waterloo], CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Waterloo (CANADA), and Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France)
Subjects: Point spread function, Blind deconvolution, Medical ultrasound, Alternating minimization, business.industry, Computer science, Ultrasound, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Iterative reconstruction, 01 natural sciences, Rendering (computer graphics), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, All-pass filtering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Traitement du signal et de l'image, Computer vision, Deconvolution, Artificial intelligence, business, 010301 acoustics
Abstract: International audience; Image deconvolution is a standard numerical procedure used in medical ultrasound imaging for improving the resolution and contrast of diagnostic sonograms. However, due to the intrinsic bandlimitedness of ultrasound scanners and the adverse effect of measurement noises, image deconvolution is known to be exceedingly sensitive to the errors incurred during inference of the point spread function (PSF) that characterizes the imaging system in use. In this case, even the slightest errors in specification of the PSF are likely to result in significant artifacts, rendering the reconstructed images worthless. To address the aforementioned problem, this paper describes a new method for blind deconvolution of ultrasound images, in which the errors due to inaccuracies in specification of the PSF are eliminated concurrently with estimation of tissue reflectivity directly from its associated radio-frequency data. A principal derivation and justification of the proposed method are supported by experimental results which demonstrate the effectiveness and viability of the new technique.
Published: 2019

36. Deep Learning-Based Super-Resolution Applied to Dental Computed Tomography

Author: Janka Hatvani, Adrian Basarab, Andras Horvath, Denis Kouame, Miklós Gyöngy, Jerome Michetti, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Pázmány Péter Catholic University - PPCU (HUNGARY), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Ground truth, Computer science, business.industry, Computed tomography (CT)- Convolutional neural networks (CNNs)- Deconvolution, Super-resolution (SR)- U-net, Pattern recognition, Iterative reconstruction, Vision par ordinateur et reconnaissance de formes, Total variation denoising, Informatique, Convolutional neural network, Subpixel rendering, Atomic and Molecular Physics, and Optics, Image analysis, Test set, Medical imaging, Radiology, Nuclear Medicine and imaging, Artificial intelligence, business, Instrumentation, Image resolution, Imagerie médicale, Dental applications
Abstract: The resolution of dental computed tomography (CT) images is limited by detector geometry, sensitivity, patient movement, the reconstruction technique and the need to minimize radiation dose. Recently, the use of convolutional neural network (CNN) architectures has shown promise as a resolution enhancement method. In the current work, two CNN architectures—a subpixel network and the so called U-net—have been considered for the resolution enhancement of 2-D cone-beam CT image slices of ex vivo teeth. To do so, a training set of 5680 cross-sectional slices of 13 teeth and a test set of 1824 slices of 4 structurally different teeth were used. Two existing reconstruction-based super-resolution methods using $\boldsymbol {\ell _{2}}$ -norm and total variation regularization were used for comparison. The results were evaluated with different metrics (peak signal-to-noise ratio, structure similarity index, and other objective measures estimating human perception) and subsequent image-segmentation-based analysis. In the evaluation, micro-CT images were used as ground truth. The results suggest the superiority of the proposed CNN-based approaches over reconstruction-based methods in the case of dental CT images, allowing better detection of medically salient features, such as the size, shape, or curvature of the root canal.
Published: 2019

37. Spatio-temporal compressed quantitative acoustic microscopy

Author: Adrian Basarab, Jonathan Mamou, J-H. Kim, Alin Achim, Denis Kouame, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Bristol (UNITED KINGDOM), Riverside Research (USA), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Lizzi Center for Biomedical Engineering, Riverside Research Institute, University of Bristol [Bristol], and Université Toulouse III - Paul Sabatier (UT3)
Subjects: Compressive sampling, Computer science, 0206 medical engineering, Quantitative acoustic microscopy, Acoustic microscopy, 020206 networking & telecommunications, 02 engineering and technology, Iterative reconstruction, 020601 biomedical engineering, Parametric representation, QAM, Compressed sensing, Data acquisition, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Finite rate of innovation, Microscopy, 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Raster scan, Algorithm, Sparsity, Quadrature amplitude modulation, Parametric statistics
Abstract: International audience; This study proposes an elegant spatio-temporal compressed sensing scheme to significantly reduce the amount of data required to form quantitative acoustic microscopy (QAM) images. QAM systems form two-dimensional acoustic parameter maps of thin section of soft tissues. QAM data collection consists in raster scanning a sample in 2D and digitizing backscattered RF signals at each scan location. Therefore, the raw QAM data is three-dimensional and when using this conventional data acquisition process, data sets can be large causing processing and storage limitations. Our previous work demonstrated that the amount of QAM data can be remarkably reduced either spatially or temporally by using compressive sampling (CS) or finite rate of innovation (FRI) approaches, respectively. These approaches take advantage of the properties of QAM data, i.e., the sparsity of 2D maps and the parametric representation of RF signals. Therefore, in this study both approaches were combined into a single spatio-temporal solution. Results yielded a new data volume size of only 2.6% of the data originated by classical sampling techniques without significant deterioration of the 2D maps.
Published: 2019

38. Fast Single Image Super-Resolution Using a New Analytical Solution for <tex-math notation='LaTeX'>$\ell _{2}$ </tex-math> – <tex-math notation='LaTeX'>$\ell _{2}$ </tex-math> Problems

Author: Adrian Basarab, Jean-Yves Tourneret, Ningning Zhao, Qi Wei, Denis Kouame, and Nicolas Dobigeon
Subjects: Mathematical optimization, Decimation, Optimization problem, Gaussian, 020206 networking & telecommunications, 02 engineering and technology, Computer Graphics and Computer-Aided Design, Regularization (mathematics), Matrix decomposition, Convolution, symbols.namesake, Prior probability, 0202 electrical engineering, electronic engineering, information engineering, symbols, 020201 artificial intelligence & image processing, Deconvolution, Algorithm, Software, Mathematics
Abstract: This paper addresses the problem of single image super-resolution (SR), which consists of recovering a high-resolution image from its blurred, decimated, and noisy version. The existing algorithms for single image SR use different strategies to handle the decimation and blurring operators. In addition to the traditional first-order gradient methods, recent techniques investigate splitting-based methods dividing the SR problem into up-sampling and deconvolution steps that can be easily solved. Instead of following this splitting strategy, we propose to deal with the decimation and blurring operators simultaneously by taking advantage of their particular properties in the frequency domain, leading to a new fast SR approach. Specifically, an analytical solution is derived and implemented efficiently for the Gaussian prior or any other regularization that can be formulated into an $\ell _{2}$ -regularized quadratic model, i.e., an $\ell _{2}$ – $\ell _{2}$ optimization problem. The flexibility of the proposed SR scheme is shown through the use of various priors/regularizations, ranging from generic image priors to learning-based approaches. In the case of non-Gaussian priors, we show how the analytical solution derived from the Gaussian case can be embedded into traditional splitting frameworks, allowing the computation cost of existing algorithms to be decreased significantly. Simulation results conducted on several images with different priors illustrate the effectiveness of our fast SR approach compared with existing techniques.
Published: 2016

39. Adaptive transform via quantum signal processing: application to signal and image denoising

Author: Denis Kouame, Bertrand Georgeot, Raphael Smith, Adrian Basarab, Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, CoMputational imagINg anD viSion (IRIT-MINDS), Université Toulouse III - Paul Sabatier (UT3), Information et Chaos Quantiques (LPT), Laboratoire de Physique Théorique (LPT), Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)
Subjects: Signal Processing (eess.SP), Signal processing, Noise measurement, Computer science, Noise (signal processing), Noise reduction, 020206 networking & telecommunications, Image processing, 02 engineering and technology, Signal, Schrödinger equation, symbols.namesake, Signal-to-noise ratio, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, symbols, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Electrical Engineering and Systems Science - Signal Processing, Algorithm
Abstract: International audience; The main scope of this paper is to show how tools from quantum mechanics, in particular the Schroedinger equation, can be used to construct an adaptive transform suitable for signal and image processing applications. The proposed dictionary is obtained by considering the signal or image as a discrete potential in Schroedinger equation, further used to construct the Hamiltonien operator. In order to illustrate its practical interest in signal and image processing, we provide denoising results in the case of signal-dependent noise, which is the noise type the most adapted to the proposed approach.
Published: 2018

40. Restoration of ultrasonic images using non-linear system identification and deconvolution

Author: Adrian Basarab, Denis Kouame, Jean-Marc Girault, Jean-Yves Tourneret, Mohamad Hourani, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Université de Tours (FRANCE), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Subjects: Image formation, Optimization, Polynomial, Non-linear model, Computer science, System identification, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Function (mathematics), Deconvolution, Polynomial Ham-merstein model, Harmonic ultrasonic imaging, 01 natural sciences, Regularization (mathematics), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, 0103 physical sciences, Traitement du signal et de l'image, Ultrasonic sensor, ADMM, 010301 acoustics, Algorithm, Impulse response
Abstract: This paper studies a new ultrasound image restoration method based on a non-linear forward model. A Hammerstein polynomial-based non-linear image formation model is considered to identify the system impulse response in baseband and around the second harmonic. The identification process is followed by a joint deconvolution technique minimizing an appropriate cost function. This cost function is constructed from two data fidelity terms exploiting the linear and non-linear model components, penalized by an additive-norm regularization enforcing sparsity of the solution. An alternating optimization approach is considered to minimize the penalized cost function, allowing the tissue reflectivity function to be estimated. Results on synthetic ultrasound images are finally presented to evaluate the algorithm performance.
Published: 2018

41. Restoration of ultrasound images using spatially-variant kernel deconvolution

Author: Adrian Basarab, Mihai I. Flarea, Denis Kouame, Sergiy A. Vorobyov, Aalto University, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Aalto University (FINLAND), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Subjects: Point spread function, Elastic net regularization, ta113, ta213, Computer science, Spatially varying, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 01 natural sciences, Convexity, Convolution, Kernel (image processing), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Restoration, 0103 physical sciences, Point-spread function, Ultrasound, Traitement du signal et de l'image, Deconvolution, Reconstruction, 010301 acoustics, Gradient method, Algorithm, Circulant matrix, Accelerated Composite Gradient Method, Image restoration
Abstract: International audience; Most of the existing ultrasound image restoration methods consider a spatially-invariant point-spread function (PSF) model and circulant boundary conditions. While computationally efficient, this model is not realistic and severely limits the quality of reconstructed images. In this work, we address ultrasound image restoration under the hypothesis of piece-wise linear vertical variation of the PSF based on a small number of prototypes. No assumption is made on the structure of the prototype PSFs. To regularize the solution, we use the classical elastic net constraint. Existing methodologies are rendered impractical either due to their reliance on matrix inversion or due to their inability to exploit the strong convexity of the objective. Therefore, we propose an optimization algorithm based on the Accelerated Composite Gradient Method, adapted and optimized for this task. Our method is guaranteed to converge at a linear rate and is able to adaptively estimate unknown problem parameters. We support our theoretical results with simulation examples.
Published: 2018

42. Approximate message passing reconstruction of quantitative acoustic microscopy images

Author: Denis Kouame, Adrian Basarab, Alin Achim, Paul R. Hill, Nishan Canagarajah, Jonathan Mamou, Jonghoon Kim, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Bristol (UNITED KINGDOM), Riverside Research (USA), and Frederic L. Lizzi Center for Biomedical Engineering (New York, USA)
Subjects: Acoustics and Ultrasonics, Compressive sensing (CS) - Quantitative acoustic microscopy (QAM), Computer science, Cauchy distribution, 020206 networking & telecommunications, 02 engineering and technology, Iterative reconstruction, Approximate massage passing (AMP), QAM, Data acquisition, Wavelet, Compressed sensing, 0202 electrical engineering, electronic engineering, information engineering, Maximum a posteriori estimation, Electronic engineering, Traitement du signal et de l'image, 020201 artificial intelligence & image processing, Electrical and Electronic Engineering, Instrumentation, Algorithm, Quadrature amplitude modulation
Abstract: A novel framework for compressive sensing (CS) data acquisition and reconstruction in quantitative acoustic microscopy (QAM) is presented. Three different compressive sensing patterns, adapted to the specifics of QAM systems, were investigated as an alternative to the current raster-scanning approach. They consist of diagonal sampling, a row random and a spiral scanning pattern and they can all significantly reduce both the acquisition time and the amount of sampled data. For subsequent image reconstruction, we design and implement an innovative technique, whereby a recently proposed approximate message passing (AMP) method is adapted to account for the underlying data statistics. A Cauchy maximum a posteriori (MAP) image denoising algorithm is thus employed to account for the non-Gaussianity of QAM wavelet coefficients. The proposed methods were tested retrospectively on experimental data acquired with a 250-MHz or 500-MHz QAM system. The experimental data were obtained from a human lymph node sample (250 MHz) and human cornea (500 MHz). Reconstruction results showed that the best performance is obtained using a spiral sensing pattern combined with the Cauchy denoiser in the wavelet domain. The spiral sensing matrix reduced the number of spatial samples by a factor of 2 and led to an excellent PSNR of 43.21 dB when reconstructing QAM speed-of-sound images of a human lymph node. These results demonstrate that the CS approach could significantly improve scanning time, while reducing costs of future QAM systems.
Published: 2018

43. Semi-blind ultrasound image deconvolution from compressed measurements

Author: Denis Kouame, Adrian Basarab, Zhouye Chen, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Heriot-Watt University (UNITED KINGDOM), and Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France)
Subjects: Blind deconvolution, Point spread function, Compressive sampling, Computer science, Biomedical Engineering, Biophysics, 02 engineering and technology, Vision par ordinateur et reconnaissance de formes, Fixed point, Informatique, 01 natural sciences, Convolution, Image (mathematics), Compressed sensing, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Deconvolution, 010301 acoustics, Algorithm, Image resolution, Ultrasound imaging, Imagerie médicale
Abstract: The recently proposed framework of ultrasound compressive deconvolution offers the possibility of decreasing the acquired data while improving the image spatial resolution. By combining compressive sampling and image deconvolution, the direct model of compressive deconvolution combines random projections and 2D convolution with a spatially invariant point spread function. Considering the point spread function known, existing algorithms have shown the ability of this framework to reconstruct enhanced ultrasound images from compressed measurements by inverting the forward linear model. In this paper, we propose an extension of the previous approach for compressive blind deconvolution, whose aim is to jointly estimate the ultrasound image and the system point spread function. The performance of the method is evaluated on both simulated and in vivo ultrasound data.
Published: 2018

44. Reconstruction of Quantitative Acoustic Microscopy Images from RF Signals Sampled at Innovation Rate

Author: Denis Kouame, J-H. Kim, Adrian Basarab, Alin Achim, Jonathan Mamou, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Bristol (UNITED KINGDOM), Riverside Research (USA), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Computer science, Acoustics, Scanning Acoustic Microscopy, Acoustic microscopy, 020206 networking & telecommunications, 02 engineering and technology, Iterative reconstruction, 01 natural sciences, QAM, Transducer, Sampling (signal processing), Finite rate of innovation, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Radio frequency, Center frequency, 010301 acoustics, Quadrature amplitude modulation, Auto-regressive model
Abstract: The principle of quantitative acoustic microscopy (QAM) is to form two-dimensional acoustic parameter maps from a collection of radiofrequency (RF) signals acquired by raster scanning a biological sample. Despite their relatively simple structure, i.e. two main reflections, QAM RF signals are currently sampled at very high frequencies, e.g., at 2.5 GHz for QAM system employing a single-element transducer with a center frequency of 250-MHz. The use of such high sampling frequencies is challenging because of the potentially large amount of acquired data and the cost of the necessary analog to digital converters. In this work, we propose a sampling scheme based on the finite rate of innovation theory that exploits the limited numbers of degrees of freedom of QAM RF signals and allows the reconstruction of accurate acoustic maps from a very limited number of samples.
Published: 2018

45. Compressed quantitative acoustic microscopy

Author: Daniel Rohrbach, Denis Kouame, Jonghoon Kim, Jonathan Mamou, Alin Achim, Paul R. Hill, Adrian Basarab, Nishan Canagarajah, University of Bristol [Bristol], Riverside Research Institute, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), University of Bristol (UNITED KINGDOM), Riverside Research (USA), and Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France)
Subjects: Materials science, Compressive sampling, business.industry, Acoustic microscopy, 020206 networking & telecommunications, 02 engineering and technology, Iterative reconstruction, 01 natural sciences, Wavelet, Compressed sensing, Transducer, Optics, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Approximate message passing, Speed of sound, 0103 physical sciences, Microscopy, 0202 electrical engineering, electronic engineering, information engineering, Maximum a posteriori estimation, Cauchy distribution, Traitement du signal et de l'image, [PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det], business, 010301 acoustics, Scanning acoustic microscopy
Abstract: International audience; Scanning acoustic microscopy is a well-accepted modality for forming quantitative 2D maps of acoustic properties of soft tissues at microscopic scales. In our studies, the sample is raster-scanned with a spatial step size of 2 μm using a 250 MHz transducer resulting in 3D RF data cubes. Each RF signal is processed to obtain, for each spatial location, acoustic parameters, e.g., the speed of sound. The scanning time is directly dependent on the sample size and can range from few minutes to hours. In order to maintain constant experimental conditions for the sensitive thin sectioned samples, the scanning time is an important practical issue. Hence, the main objective of this work is to reduce the scanning time by reconstructing acoustic microscopy images from spatially under sampled measurements, based on the theory of compressive sampling. A recently proposed approximate message passing method using a Cauchy maximum a posteriori image denoising algorithm is thus employed to account for the non-Gaussianity of quantitative acoustic microscopy wavelet coefficients.
Published: 2017

46. Dental root canal segmentation from super-resolved 3D cone beam computed tomography data

Author: Adrian Basarab, Jerome Michetti, Rose Sfeir, Frank Diemer, Bilal Chebaro, Denis Kouame, Centre National de la Recherche Scientifique - CNRS (FRANCE), Ecole nationale supérieure des Mines d'Albi-Carmaux - IMT Mines Albi (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National des Sciences Appliquées de Toulouse - INSA (FRANCE), Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE), Lebanese University - LU (LEBANON), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Faculté de Chirurgie Dentaire (Toulouse, France), Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Lebanese University [Beirut] (LU), Faculté de chirurgie dentaire, Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Institut Clément Ader (ICA), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-IMT École nationale supérieure des Mines d'Albi-Carmaux (IMT Mines Albi), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), CoMputational imagINg anD viSion (IRIT-MINDS), Université de Toulouse (UT)-Université de Toulouse (UT), Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-IMT École nationale supérieure des Mines d'Albi-Carmaux (IMT Mines Albi), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Inverse problems, medicine.medical_specialty, Cone beam computed tomography, Endodontics -Image segmentation, Computer science, Root canal, Micro computed tomography, Image processing, 02 engineering and technology, urologic and male genital diseases, 03 medical and health sciences, 0302 clinical medicine, stomatognathic system, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0202 electrical engineering, electronic engineering, information engineering, medicine, Segmentation, Image resolution, Imagerie médicale, 030206 dentistry, Image segmentation, respiratory system, Endodontics, equipment and supplies, Superresolution, medicine.anatomical_structure, Super-resolution, 020201 artificial intelligence & image processing, Biomedical engineering
Abstract: National audience; This paper aims at evaluating the potential of super-resolution (SR) image processing to enhance the resolution of Cone Beam Computed Tomography (CBCT) images and to further improve the root canal segmentation in endodontics. First we perform SR based on a linear model, then, we apply an automated segmentation procedure to native and super-resolved CBCT volumes in order to extract the root canal structure. Seven intact extracted teeth have been used to evaluate the potential of SR CBCT in detecting the dental root canal. For all the considered teeth, the SR CBCT volumes provided a smaller error compared to the native CBCT data.
Published: 2017

47. Validation of image restoration methods on 3D-printed ultrasound phantoms

Author: Adrian Basarab, Krisztián Füzesi, Miklós Gyöngy, Denis Kouame, György Cserey, Pázmány Péter Catholic University, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Pázmány Péter Catholic University - PPCU (HUNGARY), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Subjects: Mean squared error, Computer science, Deconvolution, 02 engineering and technology, 01 natural sciences, Imaging phantom, Rendering (computer graphics), Image restoration, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Phantom manufacture, 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Computer vision, 14. Life underwater, 010301 acoustics, Image resolution, Ground truth, Scattering, business.industry, 3D printing, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract: National audience; Abstract:The resolution of ultrasound images is limited by the bandwidth of the imaging system and the features of the propagating medium. Using certain assumptions, image restoration can recover out-of-bandwidth data and improve resolution. Several resolution improvement methods have been reported in the literature. However, due to the lack of ground truth, their evaluation on experimental data remains an open issue. Indeed, to evaluate the performance of such methods, knowledge of the scattering function is necessary. Usually this is achieved with numerical simulations, since in traditional phantoms the exact distribution of scatterers is unknown. In the current work, based on a 3D-printed phantom, the feasibility of the evaluation of deconvolution is investigated. The deconvolution method used lp-norm-regularization terms with p=0.5 and p=2. Knowledge of the scattering function allows comparison of the deconvolved images with the ground truth. Thus, using the scattering function and the originally acquired B-mode image, performance of image restoration methods could be evaluated quantitatively through comparison of root mean square error and full width half maximum values. Preliminary results demonstrate the benefits of knowing the scattering function during experimental testing of image restoration methods. In summary, the current work shows the potential of an experimental method for evaluating the extent to which an image restoration method provides a faithful rendering of the underlying scattering structure.
Published: 2017

48. Missing data reconstruction and anomaly detection in crop development using agronomic indicators derived from multispectral satellite images

Author: Guillaume Rieu, Mohanad Albughdadi, Denis Kouame, Jean-Yves Tourneret, Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, TerraNIS, CoMputational imagINg anD viSion (IRIT-MINDS), Institut National Polytechnique (Toulouse) (Toulouse INP), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), TerraNIS (FRANCE), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Subjects: 2. Zero hunger, Mean shift, 010504 meteorology & atmospheric sciences, Computer science, Multispectral image, Agronomic indicators, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 02 engineering and technology, Vision par ordinateur et reconnaissance de formes, Anomaly detection, Missing data, 01 natural sciences, Traitement des images, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, KNN reconstruction, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, 020201 artificial intelligence & image processing, Mean-shift, Spot 5 satellite images, 0105 earth and related environmental sciences, Remote sensing
Abstract: International audience; This paper studies a new three-step procedure for detecting anomalies in crop development using temporal indicators derived from multispectral satellite images. These anomalies may result from seeding problems, heterogeneity, deficiency and stress. The first step estimates different biophysical and statistical parameters associated with these parameters from the observed images. In a second step, missing data that arise from the existence of clouds or limited coverage in the satellite image are reconstructed. Finally, the mean shift algorithm is used as an unsupervised classifier to detect anomalies in these reconstructed data. The proposed procedure is evaluated using agronomic indicators estimated from SPOT 5 Take 5 satellite images from the Beauce area in France.
Published: 2017

49. Enhancement of 250-MHz quantitative acoustic-microscopy data using a single-image super-resolution method

Author: Jonathan Mamou, Daniel Rohrbach, Ningning Zhao, Adrian Basarab, Jean-Yves Tourneret, Denis Kouame, Traitement et Compréhension d’Images (IRIT-TCI), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Toulouse III - Paul Sabatier (UT3), Lizzi Center for Biomedical Engineering, Riverside Research Institute, Signal et Communications (IRIT-SC), CoMputational imagINg anD viSion (IRIT-MINDS), Institut National Polytechnique (Toulouse) (Toulouse INP), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), and Riverside Research (USA)
Subjects: Materials science, Acoustics, Acoustic microscopy, Image processing, 010103 numerical & computational mathematics, 02 engineering and technology, 01 natural sciences, Optics, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, 0101 mathematics, Image resolution, Electrical impedance, business.industry, Acoustic properties, Resolution (electron density), Experimental data, Single image super-resolution, Total variation regularization, Total variation denoising, Son, Transducer, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, business, Quantitativimaging, Scanning acoustic microscopy
Abstract: International audience; Scanning acoustic microscopy (SAM) is a well-accepted imaging modality for forming quantitative, two-dimensional maps of acoustic properties of soft tissues at microscopic scales. The quantitative maps formed using our custom SAM system using a 250-MHz single-element transducer have a nominal resolution of 7 μm, which is insufficient for some investigations. To enhance spatial resolution, a SAM system operating at even higher frequencies could be designed, but associated costs and experimental difficulties are challenging. Therefore, the objective of this study is to evaluate the potential of super-resolution (SR) image processing to enhance the spatial resolution of quantitative maps in SAM. To the best of our knowledge, this is the first attempt at using post-processing, image-enhancement techniques in SAM. Results of realistic simulations and experimental data acquired from a standard resolution test pattern confirm the improved spatial resolution and the potential value of using SR in SAM.
Published: 2017

50. Enhanced ultrasound image reconstruction using a compressive blind deconvolution approach

Author: Zhouye Chen, Adrian Basarab, Denis Kouame, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), and Université Toulouse 1 Capitole - UT1 (FRANCE)
Subjects: Blind deconvolution, Point spread function, Alternating minimization, business.industry, Compressive sam-pling, Ultrasound, 02 engineering and technology, Iterative reconstruction, Son, 01 natural sciences, Imaging phantom, Matrix (mathematics), Compressed sensing, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Deconvolution, business, Ultrasound imaging, 010301 acoustics, Mathematics
Abstract: Compressive deconvolution, combining compressive sampling and image deconvolution, represents an interesting possibility to reconstruct enhanced ultrasound images from compressed measurements. The model of compressive deconvolution includes, in addition to the measurement matrix, a 2D convolution operator carrying the information on the system point spread function which is usually unkown in practice. In this paper, we propose a novel alternating minimization-based optimization scheme to invert the resulting linear model, to jointly reconstruct enhanced ultrasound images and estimate the point spread function. The performance of the method is evaluated on both Shepp-Logan phantom and simulated ultrasound data.
Published: 2017

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Publication Type

Journal

Database

Publisher

112 results on '"Denis Kouame"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources