Search

A first review of the InVivo-ONL project is presented. The aim of the project is to develop a non-linear endomicroscopic system dedicated in first intention to in vivo imaging of the lung extracellular matrix.

PMID:19709963; International audience; We present the Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizors for the modified Demons objective function can be efficiently approximated on the sphere using iterative smoothing. Based on one parameter subgroups of diffeomorphisms, the resulting registration is diffeomorphic and fast. The Spherical Demons algorithm can also be modified to register a given spherical image to a probabilistic atlas. We demonstrate two variants of the algorithm corresponding to warping the atlas or warping the subject. Registration of a cortical surface mesh to an atlas mesh, both with more than 160k nodes requires less than 5 minutes when warping the atlas and less than 3 minutes when warping the subject on a Xeon 3.2GHz single processor machine. This is comparable to the fastest non-diffeomorphic landmarkfree surface registration algorithms. Furthermore, the accuracy of our method compares favorably to the popular FreeSurfer registration algorithm. We validate the technique in two different applications that use registration to transfer segmentation labels onto a new image: (1) parcellation of in-vivo cortical surfaces and (2) Brodmann area localization in ex-vivo cortical surfaces.

Open peer-review journal. Open code / open data.; Insight Journal; International audience; This document describes an implementation for GPU and CPU of Young and Van Vliet's recursive Gaussian smoothing as an external module for the Insight Toolkit ITK, version 4.* www.itk.org. In the absence of an OpenCL-capable platform, the code will run the CPU implementation as an alternative to the existing Deriche recursive Gaussian smoothing filter in ITK.

International audience; Probe-based Confocal Laser Endomicroscopy (pCLE) provides physicians with real-time access to histological information during standard endoscopy procedures, through high-resolution cellular imaging of internal tissues. Earlier work on mosaicing has enhanced the potential of this imaging modality by meeting the need to get a complete representation of the imaged region. However, with approaches, the dynamic information, which may be of clinical interest, is lost. In this study, we propose a new mosaic construction algorithm for pCLE sequences based on a min-cut optimization and gradient-domain composition. Its main advantage is that the motion of some structures within the tissue such as blood cells in capillaries, is taken into account. This allows physicians to get both a sharper static representation and a dynamic representation of the imaged tissue. Results on 16 sequences acquired in vivo on six different organs demonstrate the clinical relevance of our approach.

International audience; pCLE enables microscopic imaging of biliary strictures, in vivo and in real time, during an ERCP procedure. Results of a multicentric study (Meining et al., GIE 2011) have shown that pCLE allows endoscopists to diferentiate benign from malignant strictures in real time with high sensitivity and NPV. A computer-aided diagnosis software called Smart Atlas has been developed to assist endoscopists with the interpretation of pCLE sequences. This study aims at evaluating the performance of this software for the diferentiation of benign and malignant strictures.

International audience; pCLE enables microscopic imaging of gastrointestinal mucosal lesions, in vivo and in real time, during an endoscopy procedure. Recent studies have demonstrated that pCLE enables accurate diagnosis of superfcial gastric neoplasia. In parallel, a computer-aided diagnosis software called Smart Atlas has been developed to assist endoscopists with the interpretation of pCLE sequences. This study aims at evaluating the performance of this software for the classifcation of gastric lesions into four pathological classes: healthy stomach, gastric intestinal metaplasia (GIM), dysplasia, and cancer.

International audience; The two classical steps of image or video classification are: image signature extraction and assignment of a class based on this image signature. The class assignment rule can be learned from a training set composed of sample images manually classified by experts. This is known as supervised statistical learning. The well-known Support Vector Machine (SVM) learning method was designed for two classes. Among the proposed extensions to multiclass (three classes or more), the one-versus-one and one-versus-all approaches are the most popular ones. This work presents an alternative approach to extending the original SVM method to multiclass. A tree of SVMs is built using a recursive learning strategy, achieving a linear worst-case complexity in terms of number of classes for classification. During learning, at each node of the tree, a bi-partition of the current set of classes is determined to optimally separate the current classification problem into two sub-problems. Rather than relying on an exhaustive search among all possible subsets of classes, the partition is obtained by building a graph representing the current problem and looking for a minimum cut of it. The proposed method is applied to classification of endomicroscopic videos and compared to classical multiclass approaches.

International audience; Content-based video retrieval has shown promising results to help physicians in their interpretation of medical videos in general and endomicroscopic ones in particular. Defining a relevant query for CBVR can however be a complex and time-consuming task for non-expert and even expert users. Indeed, uncut endomicroscopy videos may very well contain images corresponding to a variety of different tissue types. Using such uncut videos as queries may lead to drastic performance degradations for the system. In this study, we propose a semi-automated methodology that allows the physician to create meaningful and relevant queries in a simple and efficient manner. We believe that this will lead to more reproducible and more consistent results. The validation of our method is divided into two approaches. The first one is an indirect validation based on per video classification results with histopathological ground-truth. The second one is more direct and relies on perceived inter-video visual similarity ground-truth. We demonstrate that our proposed method significantly outperforms the approach with uncut videos and approaches the performance of a tedious manual query construction by an expert. Finally, we show that the similarity perceived between videos by experts is significantly correlated with the inter-video similarity distance computed by our retrieval system.

We present a method to perform video mosaicing for endomicroscopy with two major improvements compared to the state of the art. First, instead of using individual images directly, we start by creating sub-mosaics from short video sub-sequences using iconic registration. The sub-mosaics are then considered for registration. Second, groupwise estimation is performed between all sub-mosaics based on SIFT matching to infer globally consistent spatial transformations. Both improvements increase robustness of the reconstruction compared to a baseline mosaicing method.

Endomicroscopy allows in vivo and in situ imaging with cellular resolution. One limitation of endomicroscopy is the small field of view which can however be extended using mosaicing techniques. In this paper, we describe a methodological framework aiming to reconstruct a mosaic of endomicroscopic images acquired following a noisy robotized spiral trajectory. First, we infer the topology of the frames, that is the map of neighbors for every frame in the spiral. For this, we use a Viterbi algorithm considering every new acquired frame in the current branch of the spiral as an observation and the index of the best neighboring frame from the previous branch as the underlying state. Second, the estimated transformation between each spatial pair previously found is assessed. Mosaicing is performed based only on the pairs of frames for which the registration is considered successful. We tested our method on 3 spiral video sequences of endomicroscopic images each including more than 200 frames: a printed grid, an ex vivo tissue sample and an in vivo animal trial. Reconstruction results were statistically significantly improved compared to reconstruction where only registration between successive frames was used.

International audience; This work deals with label free multiphoton imaging of the human lung tissue extra-cellular matrix (ECM) through optical fibers. Two devices were developed, the first one using distal scanning associated to a double clad large mode area (LMA) air-silica microstructured fiber, the second one using proximal scanning of a miniature multicore image guide (30000 cores inside a 0.8 mm diameter). In both cases, the main issue has been efficient linear and nonlinear distortion pre-compensation of excitation pulses. By inserting before the delivery fiber a compact (10 cm × 10 cm footprint) grisms-based stretcher (a grating in close contact with a prism) made of readily available commercial components, we achieved as short as 35-femtosecond-duration pulses that were temporally compressed at the direct exit of a 2-meter-long fiber. Interestingly, this femtosecond pulse fiber delivery device is also wavelength tunable over more than 100 nm inside the Ti: Sapphire emission band. With the help of distal scan system, those unique features allowed us to record elastin (through two-photon fluorescence) and collagen (through second harmonic generation) fibered network images. These images were obtained ex-vivo with only 15 mW @ 80 MHz of IR radiation delivered to the alveoli or bronchus tissues. 3D imaging with 400-μm-penetration depth inside the tissue was possible working with a 2-meter-long LMA fiber. With the help of proximal scanning, the miniature image guide allowed us to perform endoscopic real time microimaging of the ECM ex vivo. © (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

International audience; AIM: To support probe-based confocal laser endomicroscopy (pCLE) diagnosis by designing a software for automated classification of colonic polyps. MATERIALS AND METHODS: Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients undergoing screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a Content-Based Image Retrieval (CBIR) technique followed by k-nearest neighbor classification. The performances of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists were compared with those of automated pCLE software classification. All evaluations were performed using leave-one-patient-out cross-validation to avoid bias. RESULTS: 135 colorectal lesions were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study finds no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There is very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing are: −0.073 to 0.073 for the accuracy, −0.068 to 0.089 for the sensitivity and −0.18 to 0.13 for the specificity. Besides, the classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist. CONCLUSION: The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.

Contains fulltext : 96888.pdf (Publisher’s version ) (Open Access) EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform for fair and meaningful comparison of registration algorithms which are applied to a database of intrapatient thoracic CT image pairs. Evaluation of nonrigid registration techniques is a nontrivial task. This is compounded by the fact that researchers typically test only on their own data, which varies widely. For this reason, reliable assessment and comparison of different registration algorithms has been virtually impossible in the past. In this work we present the results of the launch phase of EMPIRE10, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups. All algorithms are applied to the same set of 30 thoracic CT pairs. Algorithm settings and parameters are chosen by researchers expert in the configuration of their own method and the evaluation is independent, using the same criteria for all participants. All results are published on the EMPIRE10 website (http://empire10.isi.uu.nl). The challenge remains ongoing and open to new participants. Full results from 24 algorithms have been published at the time of writing. This paper details the organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms. The gain in knowledge and future work are discussed.

Traditional Content-Based Image Retrieval (CBIR) systems only deliver visual outputs that are not directly interpretable by the physicians. Our objective is to provide a system for endomicroscopy video retrieval which delivers both visual and semantic outputs that are consistent with each other. In a previous study, we developed an adapted bag-of-visual-words method for endomicroscopy retrieval that computes a visual signature for each video. In this study, we first leverage semantic ground-truth data to transform these visual signatures into semantic signatures that reflect how much the presence of each semantic concept is expressed by the visual words describing the videos. Using cross-validation, we demonstrate that our visual-word-based semantic signatures enable a recall performance which is significantly higher than those of several state-of-the-art methods in CBIR. In a second step, we propose to improve retrieval relevance by learning, from a perceived similarity ground truth, an adjusted similarity distance. Our distance learning method allows to improve, with statistical significance, the correlation with the perceived similarity. Our resulting retrieval system is efficient in providing both visual and semantic information that are correlated with each other and clinically interpretable by the endoscopists.

International audience

International audience; In this paper we present the first Content-Based Image Retrieval (CBIR) framework in the field of in vivo endomicroscopy, with applications ranging from training support to diagnosis support. We propose to adjust the standard Bag-of-Visual-Words method for the retrieval of endomicroscopic videos. Retrieval performance is evaluated both indirectly from a classification point-of-view, and directly with respect to a perceived similarity ground truth. The proposed method significantly outperforms, on two different endomicroscopy databases, several state-of-the-art methods in CBIR. With the aim of building a self-training simulator, we use retrieval results to estimate the interpretation difficulty experienced by the endoscopists. Finally, by incorporating clinical knowledge about perceived similarity and endomicroscopy semantics, we are able: 1) to learn an adequate visual similarity distance and 2) to build visual-word-based semantic signatures that extract, from low-level visual features, a higher-level clinical knowledge expressed in the endoscopist own language.

International audience; In vivo pathology from endomicroscopy videos can be a challenge for many physicians. To ease this task, we propose a content-based video retrieval method providing, given a query video, relevant similar videos from an expert-annotated database. Our main contribution consists in revisiting the Bag of Visual Words method by weighting the contributions of the dense local regions according to the registration results of mosaicing. We perform a leave-one-patient-out k-nearest neighbors classification and show a significantly better accuracy (e.g. around 94 % for 9 neighbors) when compared to using the video images independently. Less neighbors are needed to classify the queries and our signature summation technique reduces retrieval runtime.

International audience; The registration of thoracic images is a common but still challenging problem with critical clinical applications (e.g. radiotherapy and diagnosis). In the context of the EMPIRE10 challenge, we briefly introduce in this paper our registration method based on the di ffeomorphic demons algorithm. Although fully automatic and generic (applies to a large variety of images such as brain or thoracic CT scans), the proposed method appears to be a very e fficient registration method.

International audience; Learning medical image interpretation is an evolutive process that requires modular training systems, from non-expert to expert users. Our study aims at developing such a system for endomicroscopy diagnosis. It uses a difficulty predictor to try and shorten the physician learning curve. As the understanding of video diagnosis is driven by visual similarities, we propose a content-based video retrieval approach to estimate the level of interpretation difficulty. The performance of our retrieval method is compared with several state of the art methods, and its genericity is demonstrated with two different clinical databases, on the Barrett's Esophagus and on colonic polyps. From our retrieval results, we learn a difficulty predictor against a ground truth given by the percentage of false diagnoses among several physicians. Our experiments show that, although our datasets are not large enough to test for statistical significance, there is a noticeable relationship between our retrieval-based difficulty estimation and the difficulty experienced by the physicians.

Authors Manuscript received: 2010 May 4. 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part I, A natural requirement in pairwise image registration is that the resulting deformation is independent of the order of the images. This constraint is typically achieved via a symmetric cost function and has been shown to reduce the effects of local optima. Consequently, symmetric registration has been successfully applied to pairwise image registration as well as the spatial alignment of individual images with a template. However, recent work has shown that the relationship between an image and a template is fundamentally asymmetric. In this paper, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates., NAMIC (NIH NIBIB NAMIC U54-EB005149), NAC (NIH NCRR NAC P41- RR13218), mBIRN (NIH NCRR mBIRN U24-RR021382), NIH NINDS (R01-NS051826 Grant), National Science Foundation (U.S.) (CAREER Grant 0642971), NIBIB (R01 EB001550), NIBIB (R01EB006758), NCRR (R01 RR16594-01A1), NCRR (P41-RR14075), NINDS (R01 NS052585-01), Singapore. Agency for Science, Technology and Research

International audience; All fields of neuroscience that employ brain imaging need to communicate their results with reference to anatomical regions. In particular, comparative morphometry and group analysis of functional and physiological data require coregistration of brains to establish correspondences across brain structures. It is well established that linear registration of one brain to another is inadequate for aligning brain structures, so numerous algorithms have emerged to nonlinearly register brains to one another. This study is the largest evaluation of nonlinear deformation algorithms applied to brain image registration ever conducted. Fourteen algorithms from laboratories around the world are evaluated using 8 different error measures. More than 45,000 registrations between 80 manually labeled brains were performed by algorithms including: AIR, ANIMAL, ART, Diffeomorphic Demons, FNIRT, IRTK, JRD-fluid, ROMEO, SICLE, SyN, and four different SPM5 algorithms ("SPM2-type" and regular Normalization, Unified Segmentation, and the DARTEL Toolbox). All of these registrations were preceded by linear registration between the same image pairs using FLIRT. One of the most significant findings of this study is that the relative performances of the registration methods under comparison appear to be little affected by the choice of subject population, labeling protocol, and type of overlap measure. This is important because it suggests that the findings are generalizable to new subject populations that are labeled or evaluated using different labeling protocols. Furthermore, we ranked the 14 methods according to three completely independent analyses (permutation tests, one-way ANOVA tests, and indifference-zone ranking) and derived three almost identical top rankings of the methods. ART, SyN, IRTK, and SPM's DARTEL Toolbox gave the best results according to overlap and distance measures, with ART and SyN delivering the most consistently high accuracy across subjects and label sets. Updates will be published on the http://www.mindboggle.info/papers/ website.

International audience; In this paper, we propose the DT-REFinD algorithm for the diffeomorphic nonlinear registration of diffusion tensor images. Unlike scalar images, deforming tensor images requires choosing both a reorientation strategy and an interpolation scheme. Current diffusion tensor registration algorithms that use full tensor information face difficulties in computing the differential of the tensor reorientation strategy and consequently, these methods often approximate the gradient of the objective function. In the case of the finite-strain (FS) reorientation strategy, we borrow results from the pose estimation literature in computer vision to derive an analytical gradient of the registration objective function. By utilizing the closed-form gradient and the velocity field representation of one parameter subgroups of diffeomorphisms, the resulting registration algorithm is diffeomorphic and fast. We contrast the algorithm with a traditional FS alternative that ignores the reorientation in the gradient computation. We show that the exact gradient leads to significantly better registration at the cost of computation time. Independently of the choice of Euclidean or Log-Euclidean interpolation and sum of squared differences dissimilarity measure, the exact gradient achieves better alignment over an entire spectrum of deformation penalties. Alignment quality is assessed with a battery of metrics including tensor overlap, fractional anisotropy, inverse consistency and closeness to synthetic warps. The improvements persist even when a different reorientation scheme, preservation of principal directions, is used to apply the final deformations.

International audience; We propose an efficient non-parametric diffeomorphic image registration algorithm based on Thirion's demons algorithm. In the first part of this paper, we show that Thirion's demons algorithm can be seen as an optimization procedure on the entire space of displacement fields. We provide strong theoretical roots to the different variants of Thirion's demons algorithm. This analysis predicts a theoretical advantage for the symmetric forces variant of the demons algorithm. We show on controlled experiments that this advantage is confirmed in practice and yields a faster convergence. In the second part of this paper, we adapt the optimization procedure underlying the demons algorithm to a space of diffeomorphic transformations. In contrast to many diffeomorphic registration algorithms, our solution is computationally efficient since in practice it only replaces an addition of displacement fields by a few compositions. Our experiments show that in addition to being diffeomorphic, our algorithm provides results that are similar to the ones from the demons algorithm but with transformations that are much smoother and closer to the gold standard, available in controlled experiments, in terms of Jacobians.

International audience; Retinal pathologies, like ARMD or glaucoma, need to be early detected, requiring imaging instruments with resolution at a cellular scale. However, in vivo retinal cells studies and early diagnoses are severely limited by the lack of resolution on eye-fundus images from classical ophthalmologic instruments. We built a 2D retina imager using Adaptive Optics to improve lateral resolution. This imager is currently used in clinical environment. We are currently developing a time domain full-field optical coherence tomograph. The first step was to conceive the images reconstruction algorithms and validation was realized on non-biological samples. Ex vivo retina are currently being imaged. The final step will consist in coupling both setups to acquire high resolution retina cross-sections.

International audience; High resolution wide-field imaging of the human retina calls for a 3D deconvolution. In this communication, we report on a regularized 3D deconvolution method, developed in a Bayesian framework in view of retinal imaging, which is fully unsupervised, i.e., in which all the usual tuning parameters, a.k.a. "hyper-parameters", are estimated from the data. The hyper-parameters are the noise level and all the parameters of a suitably chosen model for the object's power spectral density (PSD). They are estimated by a maximum likelihood (ML) method prior to the deconvolution itself. This 3D deconvolution method takes into account the 3D nature of the imaging process, can take into account the non-homogeneous noise variance due to the mixture of photon and detector noises, and can enforce a positivity constraint on the recovered object. The performance of the ML hyper-parameter estimation and of the deconvolution are illustrated both on simulated 3D retinal images and on non-biological 3D experimental data.

International audience; Interpreting endomicroscopic images is still a significant challenge, especially since one single still image may not always contain enough information to make a robust diagnosis. To aid the physicians, we investigated some local feature-based retrieval methods that provide, given a query image, similar annotated images from a database of endomicroscopic images combined with high-level diagnosis represented as textual information. Local feature-based methods may be limited by the small field of view (FOV) of endomicroscopy and the fact that they do not take into account the spatial relationship between the local features, and the time relationship between successive images of the video sequences. To extract discriminative information over the entire image field, our proposed method collects local features in a dense manner instead of using a standard salient region detector. After the retrieval process, we introduce a verification step driven by the textual information in the database and in which spatial relationship between the local features is used. A spatial criterion is built from the co-occurence matrix of local features and used to remove outliers by thresholding on this criterion. To overcome the small-FOV problem and take advantage of the video sequence, we propose to combine image retrieval and mosaicing. Mosaicing essentially projects the temporal dimension onto a large field of view image. In this framework, videos, represented by mosaics, and single images can be retrieved with the same tools. With a leave-n-out cross-validation, our results show that taking into account the spatial relationship between local features and the temporal information of endomicroscopic videos by image mosaicing improves the retrieval accuracy.

International audience; no abstract

International audience; We describe here two parts of our future 3D fundus camera coupling Adaptive Optics and full-field Optical Coherence Tomography. The first part is an Adaptive Optics flood imager installed at the Quinze-Vingts Hospital, regularly used on healthy and pathological eyes. A posteriori image reconstruction is performed, increasing the final image quality and field of view. The instrument lateral resolution is better than 2 microns. The second part is a full-field Optical Coherence Tomograph, which has demonstrated capability of performing a simple kind of "4 phases" image reconstruction of non biological samples and ex situ retinas. Final aim is to couple both parts in order to achieve 3D high resolution mapping of in vivo retinas.

In the context of surgery simulation, this paper presents a generic and efficient solution to handle topological changes on deformable meshes under real-time constraints implemented in the SOFA [4] platform. The proposed design is based on a simulation tree gathering software components acting on a mesh. The mesh topology is described by a topological component which also provides algorithms for performing topological changes (cutting, refinement). An important aspect of the design is that mesh related data is not centralized in the mesh data structure but stored in each dedicated component. Furthermore, topological changes are handled in a transparent way for the user through a mechanism of propagation of topological events from the topological components toward other components. Finally, the previous concepts have been extended to provide multiple topologies for the same degrees of freedom. Examples of cataract surgery simulation based on this versatile design are shown.

International audience; We propose an algorithm for the diffeomorphic registration of diffusion tensor images (DTI). Previous DTI registration algorithms using full tensor information suffer from difficulties in computing the differential of the Finite Strain tensor reorientation strategy. We borrow results from computer vision to derive an analytical gradient of the objective function. By leveraging on the closed-formgradient and the one-parameter subgroups of diffeomorphisms, the resulting registration algorithm is diffeomorphic and fast. Registration of a pair of 128 × 128 × 60 diffusion tensor volumes takes 15 minutes. We contrast the algorithm with a classic alternative that does not take into account the reorientation in the gradient computation. We show with 40 pairwise DTI registrations that using the exact gradient achieves significantly better registration.

Classical confocal microscopy can be used to obtain high-resolution images of cells in tissue samples or cell cultures. Translation of this technology for in vivo applications can be achieved by using optical fibers and miniature optics. Ultimately, fibered confocal microscopy should enable clinicians and biologists to perform what can be referred to as an optical biopsy: a real-time histological examination of biological tissues in the living organism directly onto the region of interest.The main goal of this thesis is to move beyond current hardware limitations of these imaging devices by developing specific innovative image registration schemes. In particular, this manuscript is framed by the goal of providing, through video sequence mosaicing tools, wide field-of-view optical biopsies to the clinicians. This targeted application is seen as a pipeline that takes raw data as input and provides wide field-of-view image mosaics as output. We detail the critical building blocks of this pipeline, namely real-time image reconstruction, linear image registration and non-rigid registration, before presenting our mosaicing framework.The raw data that fibered confocal microscopy produces is difficult to use as it is modulated by a fiber optics bundle pattern and distorted by geometric artifacts. In this context, we show that real-time image reconstruction can be used as a preprocessing step to get readily interpretable video sequences. Since fibered confocal microscopy is a contact imaging modality, the combined movement of the imaged tissues and the flexible optical microprobe makes it sometimes difficult to get robust and accurate measurements of parameters of interest. To address this problem, we investigated efficient and robust registration of pairs of images. We show that registration tools recently developed in the field of vision-based robot control can outperform classical image registration solutions used in biomedical image analysis. The adequacy of these tools for linear image registration led us to revisit non-rigid registration. By casting the non-rigid registration problem as an optimization problem on a Lie group, we develop a fast non-parametric diffeomorphic image registration scheme. In addition to being diffeomorphic, our algorithm provides results that are similar to the ones from Thirion's demons algorithm but with transformations that are smoother and closer to the true ones.Finally, we use these image reconstruction and registration building blocks to propose a robust mosaicing algorithm that is able to recover a globally consistent alignment of the input frames, to compensate for the motion distortions and to capture the non-rigid deformations. Moreover, our mosaicing algorithm has recently been incorporated within a multicenter clinical trial. This trial illustrates the clinical value of our tools in the particular application of Barrett's esophagus surveillance., La microscopie confocale classique permet d'obtenir des images à haute résolution de cellules en culture ou dans un tissu biologique excisé. Cette technologie peut être adaptée aux applications in vivo grâce à l'utilisation de fibres optiques et d'optiques miniaturisées. A terme, la microscopie confocale fibrée devrait permettre aux médecins et biologistes de réaliser des biopsies optiques; c'est à dire un examen histologique, en temps réel, des tissus biologiques à l'intérieur d'un organisme vivant et directement au contact de la zone d'intérêt.Le but premier de cette thèse est de dépasser les limites matérielles de ces instruments d'imagerie en développant des outils de recalage d'images spécifiques et innovants. En particulier, le propos de ce manuscrit est cadré par l'objectif de proposer, au travers d'outils de création de mosaïques d'images, des biopsies optiques à grand champ aux médecins. Cette application est considérée, dans cette thèse, comme un système, ou un circuit, qui prendrait en entrée un flot de données brutes et délivrerait en sortie des mosaïques d'images à grand champ. Nous détaillons les éléments critiques de ce système, en particulier la reconstruction d'images en temps réel, le recalage linéaire d'images et le recalage non linéaire, avant de présenter la structure du système complet.Les données brutes produites par la microscopie confocale fibrée sont difficiles à interpréter parce qu'elle sont modulées par la structure en nid d'abeille du réseau de fibres optiques et parce qu'elle sont entachées d'artefacts géométriques. Dans ce contexte, nous montrons qu'une reconstruction en temps réel des images peut être utilisée en pré-traitement afin de produire des séquences vidéos directement interprétables. Comme la microscopie confocale fibrée est une imagerie qui se fait au contact des tissus, le mouvement relatif du tissu par rapport à la sonde optique implique qu'il est parfois difficile d'obtenir de manière robuste certaines mesures quantitatives d'intérêt. Nous avons donc attaqué le problème du recalage linéaire, efficace et robuste de paires d'images. Nous montrons que des outils récents provenant du domaine du contrôle robotique par la vision peuvent surpasser les solutions standards utilisées en analyse d'images biomédicales. L'adéquation de ces outils au problème du recalage linéaire d'images nous a amenés à revisiter le problème du recalage non-linéaire. En interprétant le recalage non-linéaire comme un problème d'optimisation sur un groupe de Lie, nous développons un algorithme rapide de recalage difféomorphe non-paramétrique d'images. En plus d'être difféomorphe, notre algorithme produit des résultats qui sont similaires à ceux de l'algorithme des démons de Thirion mais qui sont plus lisses et plus proche de la vérité.Finalement, nous obtenons une boîte à outils de reconstruction et de recalage d'images que nous utilisons pour proposer un algorithme robuste de création de mosaïques d'images qui permette de calculer un alignement globalement cohérent à partir de résultats locaux, de compenser les distorsions liées au mouvement et de retrouver les déformations non-rigides. Par ailleurs, notre algorithme de mosaïques d'images a récemment été incorporé dans un essai clinique multicentrique. Cet essai illustre l'intérêt clinique de nos outils dans le cadre spécifique de la surveillance de l'œsophage de Barrett.

Classical confocal microscopy can be used to obtain high-resolution images of cells in tissue samples or cell cultures. Translation of this technology for in vivo applications can be achieved by using optical fibers and miniature optics. Ultimately, fibered confocal microscopy should enable clinicians and biologists to perform what can be referred to as an optical biopsy: a real-time histological examination of biological tissues in the living organism directly onto the region of interest.The main goal of this thesis is to move beyond current hardware limitations of these imaging devices by developing specific innovative image registration schemes. In particular, this manuscript is framed by the goal of providing, through video sequence mosaicing tools, wide field-of-view optical biopsies to the clinicians. This targeted application is seen as a pipeline that takes raw data as input and provides wide field-of-view image mosaics as output. We detail the critical building blocks of this pipeline, namely real-time image reconstruction, linear image registration and non-rigid registration, before presenting our mosaicing framework.The raw data that fibered confocal microscopy produces is difficult to use as it is modulated by a fiber optics bundle pattern and distorted by geometric artifacts. In this context, we show that real-time image reconstruction can be used as a preprocessing step to get readily interpretable video sequences. Since fibered confocal microscopy is a contact imaging modality, the combined movement of the imaged tissues and the flexible optical microprobe makes it sometimes difficult to get robust and accurate measurements of parameters of interest. To address this problem, we investigated efficient and robust registration of pairs of images. We show that registration tools recently developed in the field of vision-based robot control can outperform classical image registration solutions used in biomedical image analysis. The adequacy of these tools for linear image registration led us to revisit non-rigid registration. By casting the non-rigid registration problem as an optimization problem on a Lie group, we develop a fast non-parametric diffeomorphic image registration scheme. In addition to being diffeomorphic, our algorithm provides results that are similar to the ones from Thirion's demons algorithm but with transformations that are smoother and closer to the true ones.Finally, we use these image reconstruction and registration building blocks to propose a robust mosaicing algorithm that is able to recover a globally consistent alignment of the input frames, to compensate for the motion distortions and to capture the non-rigid deformations. Moreover, our mosaicing algorithm has recently been incorporated within a multicenter clinical trial. This trial illustrates the clinical value of our tools in the particular application of Barrett's esophagus surveillance.; La microscopie confocale classique permet d'obtenir des images à haute résolution de cellules en culture ou dans un tissu biologique excisé. Cette technologie peut être adaptée aux applications in vivo grâce à l'utilisation de fibres optiques et d'optiques miniaturisées. A terme, la microscopie confocale fibrée devrait permettre aux médecins et biologistes de réaliser des biopsies optiques; c'est à dire un examen histologique, en temps réel, des tissus biologiques à l'intérieur d'un organisme vivant et directement au contact de la zone d'intérêt.Le but premier de cette thèse est de dépasser les limites matérielles de ces instruments d'imagerie en développant des outils de recalage d'images spécifiques et innovants. En particulier, le propos de ce manuscrit est cadré par l'objectif de proposer, au travers d'outils de création de mosaïques d'images, des biopsies optiques à grand champ aux médecins. Cette application est considérée, dans cette thèse, comme un système, ou un circuit, qui prendrait en entrée un flot de données brutes et délivrerait en sortie des mosaïques d'images à grand champ. Nous détaillons les éléments critiques de ce système, en particulier la reconstruction d'images en temps réel, le recalage linéaire d'images et le recalage non linéaire, avant de présenter la structure du système complet.Les données brutes produites par la microscopie confocale fibrée sont difficiles à interpréter parce qu'elle sont modulées par la structure en nid d'abeille du réseau de fibres optiques et parce qu'elle sont entachées d'artefacts géométriques. Dans ce contexte, nous montrons qu'une reconstruction en temps réel des images peut être utilisée en pré-traitement afin de produire des séquences vidéos directement interprétables. Comme la microscopie confocale fibrée est une imagerie qui se fait au contact des tissus, le mouvement relatif du tissu par rapport à la sonde optique implique qu'il est parfois difficile d'obtenir de manière robuste certaines mesures quantitatives d'intérêt. Nous avons donc attaqué le problème du recalage linéaire, efficace et robuste de paires d'images. Nous montrons que des outils récents provenant du domaine du contrôle robotique par la vision peuvent surpasser les solutions standards utilisées en analyse d'images biomédicales. L'adéquation de ces outils au problème du recalage linéaire d'images nous a amenés à revisiter le problème du recalage non-linéaire. En interprétant le recalage non-linéaire comme un problème d'optimisation sur un groupe de Lie, nous développons un algorithme rapide de recalage difféomorphe non-paramétrique d'images. En plus d'être difféomorphe, notre algorithme produit des résultats qui sont similaires à ceux de l'algorithme des démons de Thirion mais qui sont plus lisses et plus proche de la vérité.Finalement, nous obtenons une boîte à outils de reconstruction et de recalage d'images que nous utilisons pour proposer un algorithme robuste de création de mosaïques d'images qui permette de calculer un alignement globalement cohérent à partir de résultats locaux, de compenser les distorsions liées au mouvement et de retrouver les déformations non-rigides. Par ailleurs, notre algorithme de mosaïques d'images a récemment été incorporé dans un essai clinique multicentrique. Cet essai illustre l'intérêt clinique de nos outils dans le cadre spécifique de la surveillance de l'œsophage de Barrett.

pmid 18979814; International audience; Modern morphometric studies use non-linear image registration to compare anatomies and perform group analysis. Recently, log-Euclidean approaches have contributed to promote the use of such computational anatomy tools by permitting simple computations of statistics on a rather large class of invertible spatial transformations. In this work, we propose a non-linear registration algorithm perfectly fit for log-Euclidean statistics on diffeomorphisms. Our algorithm works completely in the log-domain, i.e. it uses a stationary velocity field. This implies that we guarantee the invertibility of the deformation and have access to the true inverse transformation. This also means that our output can be directly used for log-Euclidean statistics without relying on the heavy computation of the log of the spatial transformation. As it is often desirable, our algorithm is symmetric with respect to the order of the input images. Furthermore, we use an alternate optimization approach related to Thirion's demons algorithm to provide a fast non-linear registration algorithm. First results show that our algorithm outperforms both the demons algorithm and the recently proposed diffeomorphic demons algorithm in terms of accuracy of the transformation while remaining computationally efficient.

Confocal endomicroscopy provides tools for in vivo imaging of human cell architecture endoscopically. These technologies are a tough challenge since multiple trade-offs have to be overcome: resolution versus field of view, dynamic versus stability, contrast versus low laser power or low contrast agent doses. Many difficult clinical applications, such as lung, bile duct, urethral imaging and NOTES applications, need to optimize miniaturization, resolution, frame rate and contrast agent dose simultaneously. We propose one solution based on real-time video image processing to efficiently address these trade-offs. Dynamic imaging provides a flow of images that we process in real time. Images are aligned using efficientalgorithms specifically adapted to confocal devices. From the displacement that we find across the images, instantaneous velocities are computed and used to compensate for motion distortions. All images are stitched together onto the same reference space and displayed in real-time to reconstruct an image of the entire surface explored during the clinical procedure. This representation brings both stability and an increased field of view. Moreover, because a given area can be imaged by several frames, the contrast can be improved using temporal adaptive averaging. Such processing enhances the visualization of the video sequence, overcoming most classical trade-offs. The stability and increased field of view help the clinician better focus his attention on his practice which improves the patient benefit. Our tools are currently evaluated in a multicenter clinical trial to assess the improvement of the clinical practice.

International audience; no abstract

International audience; We propose a non-parametric diffeomorphic image registration algorithm based on Thirion's demons algorithm. The demons algorithm can be seen as an optimization procedure on the entire space of displacement fields. The main idea of our algorithm is to adapt this procedure to a space of diffeomorphic transformations. In contrast to many diffeomorphic registration algorithms, our solution is computationally efficient since in practice it only replaces an addition of free form deformations by a few compositions. Our experiments show that in addition to being diffeomorphic, our algorithm provides results that are similar to the ones from the demons algorithm but with transformations that are much smoother and closer to the true ones in terms of Jacobians.

International audience; As image registration becomes more and more central to many biomedical imaging applications, the efficiency of the algorithms becomes a key issue. Image registration is classically performed by optimizing a similarity criterion over a given spatial transformation space. Even if this problem is considered as almost solved for linear registration, we show in this paper that some tools that have recently been developed in the field of vision-based robot control can outperform classical solutions. The adequacy of these tools for linear image registration leads us to revisit non-linear registration and allows us to provide interesting theoretical roots to the different variants of Thirion's demons algorithm. This analysis predicts a theoretical advantage to the symmetric forces variant of the demons algorithm. We show that, on controlled experiments, this advantage is confirmed, and yields a faster convergence.

no abstract

PMID: 17767932; no abstract

This article provides an implementation of our non-parametric diffeomorphic image registration algorithm generalizing Thirion’s demons algorithm. Within the Insight Toolkit (ITK), the demons algorithm is implemented as part of the finite difference solver framework. We show that this framework can be extended to handle diffeomorphic transformations. The source code is composed of a set of reusable ITK filters and classes. In addition to an overview of our implementation, we provide a small example program that allows the user to compare the different variants of the demons algorithm.

International audience; In vivo and in situ confocal images are often distorted by motion artifacts and soft tissue deformations. To measure small amplitude phenomena on this type of images, we have to compensate for those artifacts. We present in this paper a Region Of Interest (ROI) tracking algorithm specialized for confocal imaging using a scanning device. Two different algorithms are presented: one based on the motion artifacts, and one based on affine registration. One typical application of this tool is developed: the blood velocity estimation inside a capillary on a moving organ. These first results show that the method permits accurate estimations of blood cell velocities even in presence of motion artifacts.

International audience; In vivo and in situ confocal images are often distorted by motion artifacts and soft tissue deformations. To measure small amplitude phenomena on this type of images, we have to compensate for those artifacts. We present in this paper a Region Of Interest (ROI) tracking algorithm specialized for confocal imaging using a scanning device. Two different algorithms are presented: one based on the motion artifacts, and one based on affine registration. One typical application of this tool is developed: the blood velocity estimation inside a capillary on a moving organ. These first results show that the method permits accurate estimations of blood cell velocities even in presence of motion artifacts.