Search

Unsupervised pixel-level defective region segmentation is an important task in image-based anomaly detection for various industrial applications. The state-of-the-art methods have their own advantages and limitations: matrix-decomposition-based methods are robust to noise, but lack complex background image modeling capability; representation-based methods are good at defective region localization, but lack accuracy in defective region shape contour extraction; reconstruction-based methods detected defective region match well with the ground truth defective region shape contour, but are noisy. To combine the best of both worlds, we present an unsupervised Patch AutoEncoder-based Deep Image Decomposition (PAEDID) method for defective region segmentation. In the training stage, we learn the common background as a deep image prior by a patch autoencoder network. In the inference stage, we formulate anomaly detection as an image decomposition problem with the deep image prior and sparsity regularizations. By adopting the proposed approach, the defective regions in the image can be accurately extracted in an unsupervised fashion. We demonstrate the effectiveness of the PAEDID method in simulation studies and an industrial dataset in the case study. [ABSTRACT FROM AUTHOR]

In the research of dynamic MRI imaging, we have utilized the minimax-concave (MC) function to replace the traditional nuclear norm, thereby significantly enhancing the model's fitting accuracy. The Total Variation (TV) duality technique is introduced to refine the model resolution further, better capturing underlying structures in MRI data. The splitting method is also employed to establish a comprehensive solution framework for the model. A high-efficiency algorithm, designed using the proximity operator, is developed to solve sub-problems within this framework, ensuring swift and accurate convergence. Numerical experiments on various dynamic MRI datasets and undersampling templates demonstrate that the new method outperforms traditional approaches in several key metrics, including CPU runtime, iteration count, and reconstruction performance. The new method reduces computational overhead, expedites the image reconstruction process, and significantly improves the quality of reconstructed images. [ABSTRACT FROM AUTHOR]

Background: In-situ micro-computed tomography (µCT) technology is an attractive approach to investigate the evolution process of damage inside ceramic matrix composites (CMCs) during high-temperature service. The evolution process is highly time-sensitive under temperature-induced loads, and fast scanning is very necessary for in-situ µCT tests. Objective: The objective of this work is to provide a fast scanning method for in situ µCT tests on CMCs with complex microstructures by the innovation of a reconstruction algorithm. Method: To overcome the severe degradation of the reconstructed image quality resulting from sparse CT scans, a deep-learning-based multi-domain sparse reconstruction method was proposed. Three sub-networks including the projection-domain, image-domain, and fusion network were constructed in the multi-domain method to make full use of the information from the projection and image domain. Results: The proposed deep-learning-based sparse reconstruction method provided satisfactory µCT images on C/SiC composites with acceptable quality. The scanning time was reduced by 6 times. All selected evaluation metrics of the proposed method are higher than those of other single-domain methods and traditional iterative method. The segmentation accuracy of the µCT images obtained by the proposed method can meet the subsequent quantitative analysis. An in-situ tensile test of CMCs is conducted to further evaluate the performance in the practical application of in-situ experiments. The results indicate that the weak and thin micro-cracks can still be effectively retained and recovered. A detailed workflow to implement the method generally is also provided. Conclusions: Based on the deep-learning-based multi-domain sparse reconstruction method, the process of in-situ µCT tests can be greatly accelerated with little loss of the reconstructed image quality. [ABSTRACT FROM AUTHOR]

With the development of image feature matching technology, feature matching algorithms based on deep learning have achieved excellent results, but in scenarios with low texture or extreme perspective changes, the matching accuracy is still difficult to guarantee. In this paper, a superresolution reconstruction method based on a Residual-ESPCN (efficient subpixel convolutional neural network) approach is proposed based on LoFTR (local feature matching with transformers). The superresolution method is used to improve the interpolation method used in ASFF (adaptive spatial feature fusion) to increase the image resolution, enhance the detailed information of the image, and make the extracted features richer. Then, ASFF is introduced into the local feature extraction module of LoFTR, which can alleviate the inconsistency problem of information transmission between different scale features of the feature pyramid and lessen the amount of information lost during transmission from low- to high-resolution levels. Moreover, to improve the adaptability of the algorithm to different scenarios, OTSU is introduced to adaptively calculate the threshold of feature matching. The experimental results show that in different indoor or outdoor scenarios, our proposed algorithm for matching features can effectively improve the adaptability of feature matching and can achieve good results in terms of the area under the curve (AUC), accuracy and recall. [ABSTRACT FROM AUTHOR]

Aiming at the problems of traditional image super-resolution reconstruction algorithms in the image reconstruction process, such as small receptive field, insufficient multi-scale feature extraction, and easy loss of image feature information, a super-resolution reconstruction algorithm of multi-scale dilated convolution network based on dilated convolution is proposed in this paper. First, the algorithm extracts features from the same input image through the dilated convolution kernels of different receptive fields to obtain feature maps with different scales; then, through the residual attention dense block, further obtain the features of the original low resolution images, local residual connections are added to fuse multi-scale feature information between multiple channels, and residual nested networks and jump connections are used at the same time to speed up deep network convergence and avoid network degradation problems. Finally, deep network extraction features, and it is fused with input features to increase the nonlinear expression ability of the network to enhance the superresolution reconstruction effect. Experimental results show that compared with Bicubic, SRCNN, ESPCN, VDSR, DRCN, LapSRN, MemNet, and DSRNet algorithms on the Set5, Set14, BSDS100, and Urban100 test sets, the proposed algorithm has improved peak signal-to-noise ratio and structural similarity, and reconstructed images. The visual effect is better. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) image reconstruction techniques have found extensive applications in fields such as medicine, education, and computer science, enabling high-precision 3D images to enhance work efficiency. However, traditional methods of 3D image reconstruction solely rely on acoustic information, resulting in limited accuracy. Therefore, a novel method based on virtual reality (VR) and multimodal deep learning is proposed for 3D image reconstruction. First, VR technology is employed to capture 3D image information, followed by de-noising and removal of redundant information. Second, a logarithmic transformation method is employed to enhance the details in the 3D image. Finally, a multimodal deep learning method is utilized to reconstruct the 3D image from the perspectives of imagery, sound, and video. Experimental results demonstrate that the proposed method achieves superior 3D image reconstruction with an accuracy of over 90%. The reconstruction process is efficient and exhibits low signal-to-noise ratio, while the average registration error is less than 0.04%. These findings highlight the practical value and potential applications of the proposed method. [ABSTRACT FROM AUTHOR]

Image super‐resolution (SR) reconstruction is a key technique for improving image quality and details. Conventional methods are frequently limited by interpolation, filtering, or statistical approaches; thus, they are unable to reconstruct high‐quality continuously enlarged images with detailed information. This study proposes an image SR reconstruction network model, called LALNet, based on implicit image functions and residual multilayered perceptron (RAMLP) with an attention mechanism. Through the implicit image function and RAMLP + attention, high‐quality SR reconstruction with continuous scale factors is achieved, and LALNets can run on embedded edge computing platforms. This method exhibits the following advantages: lightweight network structure reduces computing requirements, introduction of implicit image functions and RAMLP improves reconstruction quality, and attention mechanism suppresses artefacts and distortions. Experimental results show that LALNet outperforms traditional and other deep learning methods in terms of reconstruction performance and computational efficiency. This research provides new ideas and methods for the further development of the field of image SR reconstruction. [ABSTRACT FROM AUTHOR]

Machine learning-based image super-resolution (SR) has garnered increasing research interest in recent years. However, there are two issues that have not been adequately addressed. The first issue is that existing SR methods often overlook the importance of improving the quality of the training dataset, which is a crucial factor in determining SR performance, regardless of the training method employed. The second issue is that while some studies report high numerical metrics, the visual results remain unsatisfactory. To address the first problem, we propose a new image down-sampling method to obtain higher-quality training datasets. To tackle the second problem, we present a new image super-resolution model based on a large-size convolution kernel and a multi-path algorithm. Specifically, we use an adaptive large-size convolutional kernel to extract features from the image based on the size of the input image, and a residual network to generate a deeper model to retain more details of the original input image. Experimental results demonstrate that the proposed multilayer downsampling method (MDM) can significantly improve the visual quality compared to traditional downsampling methods. Moreover, our proposed method achieves the best peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values compared to several typical SR algorithms. Furthermore, subjective evaluation by human observers reveals that our method retains more details of the original image and produces smoother high-resolution images. Our proposed method effectively addresses the two aforementioned issues, which leads to improved SR performance in terms of both quantitative and qualitative measures. [ABSTRACT FROM AUTHOR]

Background: The beam‐hardening effect due to the polychromatic nature of the X‐ray spectra results in two main artifacts in CT images: cupping in homogeneous areas and dark bands between dense parts in heterogeneous samples. Post‐processing methods have been proposed in the literature to compensate for these artifacts, but these methods may introduce additional noise in low‐dose acquisitions. Iterative methods are an alternative to compensate noise and beam‐hardening artifacts simultaneously. However, they usually rely on the knowledge of the spectrum or the selection of empirical parameters. Purpose: We propose an iterative reconstruction method with beam hardening compensation for small animal scanners that is robust against low‐dose acquisitions and that does not require knowledge of the spectrum, overcoming the limitations of current beam‐hardening correction algorithms. Methods: The proposed method includes an empirical characterization of the beam‐hardening function based on a simple phantom in a polychromatic statistical reconstruction method. Evaluation was carried out on simulated data with different noise levels and step angles and on limited‐view rodent data acquired with the ARGUS/CT system. Results: Results in small animal studies showed a proper correction of the beam‐hardening artifacts in the whole sample, independently of the quantity of bone present on each slice. The proposed approach also reduced noise in the low‐dose acquisitions and reduced streaks in the limited‐view acquisitions. Conclusions: Using an empirical model for the beam‐hardening effect, obtained through calibration, in an iterative reconstruction method enables a robust correction of beam‐hardening artifacts in low‐dose small animal studies independently of the bone distribution. [ABSTRACT FROM AUTHOR]

This work proposes a novel Noor iterative scheme, called CT‐iteration, to approximate the fixed points in the new context of generalized nonexpansive mappings with property (E)$$ (E) $$. We establish the strong and weak convergence results in a uniformly convex Banach space. Additionally, numerical examples of the iterative technique are demonstrated using a signal recovery application in a compressed sensing situation. Furthermore, we show the use of the proposed method to generate polynomiographs. The proposed algorithm has been implemented and tested via numerical simulation in MATLAB. The simulation results show the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we aim to improve super-resolution (SR) imaging quality on 4K/8K images with a negligible increase in computational cost and alleviate the accuracy drop after quantization. Experiments have discovered two phenomena: (1) the re-parameterization (Rep) technique has no apparent advantages in regions with smooth textures, and (2) the accuracy drop after quantization compared with SR methods based on No-Rep because the structure information of the image will be weakened caused by the multi-branch fusion in Rep technique. Inspired by the above phenomenon, we innovatively combine texture classification and Rep techniques to propose a generic TARepSR framework (consisting of TA-Module and VarRepSR-Module) to adjust the branching of Rep blocks texture-awarely. Specifically, the TA-Module is a lightweight classification network to classify textures in different regions. An existing SR network using texture-aware Rep techniques can be used as the VarRepSR-Module to super-resolute images with higher imaging quality without additional computational costs. Moreover, we propose a TC loss to avoid over-fitting caused by an unbalanced degree of the tendency of classification results to classify different textures better. Experiments show that our TARepSR can not only improve the imaging quality of most existing methods (e.g., FSRCNN, CARN, EDSR, XLSR) on 4K/8K images with negligible increase in computational cost but also improve the accuracy after quantization compared with the state-of-the-art Rep methods. [ABSTRACT FROM AUTHOR]

In order to construct a numerical simulation model that can reflect the bedding structure of real shale samples, CT scanning and digital image processing were utilized to analyze the intricate internal structure of the shale. By integrating this information with RFPA3D finite element software, a 3D non-uniform numerical model that can accurately represent the shale bedding structure was built and simulated for direct tensile tests. The experimental findings demonstrated that shale possesses noticeable anisotropic properties with regard to tensile strength. Two distinct modes of damage were observed in shale specimens subjected to uniaxial tensile loading: tensile damage along the bedding plane and damage occurring perpendicular to the bedding plane. The spatial distribution characteristics of the acoustic emission points better reflect the damage pattern of the specimen, and the acoustic emission counting evolution characteristics are closely related to the damage process of the specimen. These research findings shed light on the fracture damage mechanism of shale formations, thereby contributing to a better understanding of the engineering stability evaluation for rock bodies. Furthermore, they offer a novel perspective for investigating the evolution of damage in rock particles. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) imaging plays a crucial role in various medical applications, but noise in projection data can significantly degrade image quality and hinder diagnosis accuracy. Iterative algorithms for tomographic image reconstruction outperform transform methods, especially in scenarios with severe noise in projections. In this paper, we propose a method to dynamically adjust two parameters included in the iterative rules during the reconstruction process. The algorithm, named the parameter-extended expectation-maximization based on power divergence (PXEM), aims to minimize the weighted extended power divergence between the measured and forward projections at each iteration. Our numerical and physical experiments showed that PXEM surpassed conventional methods such as maximum-likelihood expectation-maximization (MLEM), particularly in noisy scenarios. PXEM combines the noise suppression capabilities of power divergence-based expectation-maximization with static parameters at every iteration and the edge preservation properties of MLEM. The experimental results demonstrated significant improvements in image quality in metrics such as the structural similarity index measure and peak signal-to-noise ratio. PXEM improves CT image reconstruction quality under high noise conditions through enhanced optimization techniques. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel sparse Bayesian learning (SBL) method for image reconstruction. We integrate the generalized approximate message passing (GAMP) algorithm and Laplacian hierarchical priors (LHP) into a basic SBL model (called LHP-GAMP-SBL) to improve the reconstruction efficiency. In our SBL model, the GAMP structure is used to estimate the mean and variance without matrix inversion in the E-step, while LHP is used to update the hyperparameters in the M-step.The combination of these two structures further deepens the hierarchical structures of the model. The representation ability of the model is enhanced so that the reconstruction accuracy can be improved. Moreover, the introduction of LHP accelerates the convergence of GAMP, which shortens the reconstruction time of the model. Experimental results verify the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Objectives: Magnetic resonance imaging (MRI) is a commonly used tool in clinical medicine, but it suffers from the disadvantage of slow imaging speed. To address this, we propose a novel MRI reconstruction algorithm based on image decomposition to realize accurate image reconstruction with undersampled k‐space data. Methods: In our algorithm, the MR images to be recovered are split into cartoon and texture components utilizing image decomposition theory. Different sparse transform constraints are applied to each component based on their morphological structure characteristics. The total variation transform constraint is used for the smooth cartoon component, while the L0 norm constraint of tight frame redundant transform is used for the oscillatory texture component. Finally, an alternating iterative minimization approach is adopted to complete the reconstruction. Results: Numerous numerical experiments are conducted on several MR images and the results consistently show that, compared with the existing classical compressed sensing algorithm, our algorithm significantly improves the peak signal‐to‐noise ratio of the reconstructed images and preserves more image details. Conclusions: Our algorithm harnesses the sparse characteristics of different image components to reconstruct MR images accurately with highly undersampled data. It can greatly accelerate MRI speed and be extended to other imaging reconstruction fields. [ABSTRACT FROM AUTHOR]

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions The requirement for precise and effective delivery of the actual dose to the patient grows along with the complexity of breast cancer radiotherapy. Dosimetry during treatment has become a crucial component of guaranteeing the efficacy and security.To propose a dosimetry method during breast cancer radiotherapy based on body surface changes.A total of 29 left breast cancer radiotherapy cases were retroactively retrieved from an earlier database for analysis. Non‐rigid image registration and dose recalculation of the planning computed tomography (CT) referring to the Cone‐beam computed tomography were performed to obtain dose changes. The study used 3D point cloud feature extraction to characterize body surface changes. Based on the correlation proof, a mapping model is developed between body surface changes and dose changes using neural network framework. The MSE metrics, the Euclidean distances of feature points and the 3D gamma pass rate metric were used to assess the prediction accuracy.A strong correlation exist between body surface changes and dose changes (first canonical correlation coefficient = 0.950). For the dose deformation field and dose amplitude difference in the test set, the MSE of the predicted and actual values were 0.136 pixels and 0.229 cGy, respectively. After deforming the planning dose into a deformed one, the feature points’ Euclidean distance between it and the recalculated dose changes from 9.267 ± 1.879 mm to 0.456 ± 0.374 mm. The 3D gamma pass rate of 90% or higher for the 2 mm/2% criteria were achieved by 80.8% of all cases, with a minimum pass rate of 75.9% and a maximum pass rate of 99.6%. Pass rate for the 3 mm/2% criteria ranged from 87.8% to 99.8%, with 92.3% of the cases having a pass rate of 90% or higher.This study provides a dosimetry method that is non‐invasive, real‐time, and requires no additional dose for breast cancer radiotherapy. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Cardiac applications in radiation therapy are rapidly expanding including magnetic resonance guided radiation therapy (MRgRT) for real‐time gating for targeting and avoidance near the heart or treating ventricular tachycardia (VT).This work describes the development and implementation of a novel multi‐modality and magnetic resonance (MR)‐compatible cardiac phantom.The patient‐informed 3D model was derived from manual contouring of a contrast‐enhanced Coronary Computed Tomography Angiography scan, exported as a Stereolithography model, then post‐processed to simulate female heart with an average volume. The model was 3D‐printed using Elastic50A to provide MR contrast to water background. Two rigid acrylic modules containing cardiac structures were designed and assembled, retrofitting to an MR‐safe programmable motor to supply cardiac and respiratory motion in superior‐inferior directions. One module contained a cavity for an ion chamber (IC), and the other was equipped with multiple interchangeable cavities for plastic scintillation detectors (PSDs). Images were acquired on a 0.35 T MR‐linac for validation of phantom geometry, motion, and simulated online treatment planning and delivery. Three motion profiles were prescribed: patient‐derived cardiac (sine waveform, 4.3 mm peak‐to‐peak, 60 beats/min), respiratory (cos4 waveform, 30 mm peak‐to‐peak, 12 breaths/min), and a superposition of cardiac (sine waveform, 4 mm peak‐to‐peak, 70 beats/min) and respiratory (cos4 waveform, 24 mm peak‐to‐peak, 12 breaths/min). The amplitude of the motion profiles was evaluated from sagittal cine images at eight frames/s with a resolution of 2.4 mm × 2.4 mm. Gated dosimetry experiments were performed using the two module configurations for calculating dose relative to stationary. A CT‐based VT treatment plan was delivered twice under cone‐beam CT guidance and cumulative stationary doses to multi‐point PSDs were evaluated.No artifacts were observed on any images acquired during phantom operation. Phantom excursions measured 49.3 ± 25.8%/66.9 ± 14.0%, 97.0 ± 2.2%/96.4 ± 1.7%, and 90.4 ± 4.8%/89.3 ± 3.5% of prescription for cardiac, respiratory, and cardio‐respiratory motion profiles for the 2‐chamber (PSD) and 12‐substructure (IC) phantom modules respectively. In the gated experiments, the cumulative dose was <2% from expected using the IC module. Real‐time dose measured for the PSDs at 10 Hz acquisition rate demonstrated the ability to detect the dosimetric consequences of cardiac, respiratory, and cardio‐respiratory motion when sampling of different locations during a single delivery, and the stability of our phantom dosimetric results over repeated cycles for the high dose and high gradient regions. For the VT delivery, high dose PSD was <1% from expected (5–6 cGy deviation of 5.9 Gy/fraction) and high gradient/low dose regions had deviations <3.6% (6.3 cGy less than expected 1.73 Gy/fraction).A novel multi‐modality modular heart phantom was designed, constructed, and used for gated radiotherapy experiments on a 0.35 T MR‐linac. Our phantom was capable of mimicking cardiac, cardio‐respiratory, and respiratory motion while performing dosimetric evaluations of gated procedures using IC and PSD configurations. Time‐resolved PSDs with small sensitive volumes appear promising for low‐amplitude/high‐frequency motion and multi‐point data acquisition for advanced dosimetric capabilities. Illustrating VT planning and delivery further expands our phantom to address the unmet needs of cardiac applications in radiotherapy. [ABSTRACT FROM AUTHOR]

Pulmonary monitoring is crucial for the diagnosis and management of respiratory conditions, especially after the epidemic of coronavirus disease. Electrical impedance tomography (EIT) is an alternative non-radioactive tomographic imaging tool for monitoring pulmonary conditions. This review proffers the current EIT technical principles and applications on pulmonary monitoring, which gives a comprehensive summary of EIT applied on the chest and encourages its extensive usage to clinical physicians. The technical principles involving EIT instrumentations and image reconstruction algorithms are explained in detail, and the conditional selection is recommended based on clinical application scenarios. For applications, specifically, the monitoring of ventilation/perfusion (V/Q) is one of the most developed EIT applications. The matching correlation of V/Q could indicate many pulmonary diseases, e.g., the acute respiratory distress syndrome, pneumothorax, pulmonary embolism, and pulmonary edema. Several recently emerging applications like lung transplantation are also briefly introduced as supplementary applications that have potential and are about to be developed in the future. In addition, the limitations, disadvantages, and developing trends of EIT are discussed, indicating that EIT will still be in a long-term development stage before large-scale clinical applications. [ABSTRACT FROM AUTHOR]

Metal artifacts notoriously pose significant challenge in computed tomography (CT), leading to inaccuracies in image formation and interpretation. Artifact reduction tools have been designed to improve cone beam computed tomography (CBCT) image quality by reducing artifacts caused by certain high-density materials. Metal artifact reduction (MAR) tools are specific algorithms that are applied during image reconstruction to minimize or eliminate artifacts degrading CBCT images. The purpose of the study is to evaluate the effect of a MAR algorithm on image quality in CBCT performed for evaluating patients before transarterial radioembolization (TARE). We retrospectively included 40 consecutive patients (aged 65 ± 13 years; 23 males) who underwent 45 CBCT examinations (Allura FD 20, XperCT Roll protocol, Philips Healthcare, Best, The Netherlands) in the setting of evaluation for TARE between January 2017 and December 2018. Artifacts caused by coils, catheters, and surgical clips were scored subjectively by four readers on a 5-point scale (1 = artifacts affecting diagnostic information to 5 = no artifacts) using a side-by-side display of uncorrected and MAR-corrected images. In addition, readers scored tumor visibility and vessel discrimination. MAR-corrected images were assigned higher scores, indicating better image quality. The differences between the measurements with and without MAR were most impressive for coils with a mean improvement of 1.6 points (95%CI [1.5 1.8]) on the 5-point likert scale, followed by catheters 1.4 points (95%CI [1.3 1.5]) and clips 0.7 points (95%CI [0.3 1.1]). Improvements for other artifact sources were consistent but relatively small (below 0.25 points on average). Interrater agreement was good to perfect (Kendall's W coefficient = 0.68–0.95) and was higher for MAR-corrected images, indicating that MAR improves diagnostic accuracy. A metal artifact reduction algorithm can improve diagnostic and interventional accuracy of cone beam CT in patients undergoing radioembolization by reducing artifacts caused by diagnostic catheters and coils, lowering interference of metal artifacts with adjacent major structures, and improving tumor visibility. [ABSTRACT FROM AUTHOR]

Positron Emission Tomography (PET) image reconstruction remains a pivotal area in PET technology, critically influencing clinical diagnostic outcomes. Addressing the need for enhanced image quality, this study introduces a novel algorithm for PET image reconstruction. This algorithm integrates a penalty mechanism, morphological filtering, and the Maximum Likelihood Expectation Maximization (MLEM) algorithm, aiming to improve reconstructed image quality significantly. The operational process of the algorithm within each iteration encompasses two primary phases. Initially, image reconstruction is accomplished via the MLEM algorithm, followed by the application of a morphological filter to attenuate noise in the reconstructed image. Simulation experiments demonstrate that this algorithm effectively mitigates noise while preserving crucial details, such as image edges. Notably, this method presents the dual benefits of straightforward parameter configuration and ease of implementation. The results indicate a substantial enhancement in noise suppression and fine structure preservation in the reconstructed images, marking a significant advancement in PET image reconstruction techniques. [ABSTRACT FROM AUTHOR]

Ultrasound imaging has a history of several decades. With its non-invasive, low-cost advantages, this technology has been widely used in medicine and there have been many significant breakthroughs in ultrasound imaging. Even so, there are still some drawbacks. Therefore, some novel image reconstruction and image analysis algorithms have been proposed to solve these problems. Although these new solutions have some effects, many of them introduce some other side effects, such as high computational complexity in beamforming. At the same time, the usage requirements of medical ultrasound equipment are relatively high, and it is not very user- friendly for inexperienced beginners. As artificial intelligence technology advances, some researchers have initiated efforts to deploy deep learning to address challenges in ultrasound imaging, such as reducing computational complexity in adaptive beamforming and aiding novices in image acquisition. In this survey, we are about to explore the application of deep learning in medical ultrasound imaging, spanning from image reconstruction to clinical diagnosis. [ABSTRACT FROM AUTHOR]

Wavefront Coding (WFC) is an innovative technique aimed at extending the depth of focus (DOF) of optics imaging systems. In digital imaging systems, super-resolution digital reconstruction close to the diffraction limit of optical systems has always been a hot research topic. With the design of a point spread function (PSF) generated by a suitably phase mask, WFC could also be used in super-resolution image reconstruction. In this paper, we use a deep learning network combined with WFC as a general framework for images reconstruction, and verify its possibility and effectiveness. Considering the blur and additive noise simultaneously, we proposed three super-resolution image reconstruction procedures utilizing convolutional neural networks (CNN) based on mean square error (MSE) loss, conditional Generative Adversarial Networks (CGAN), and Swin Transformer Networks (SwinIR) based on mean absolute error (MAE) loss. We verified their effectiveness by simulation experiments. A comparison of experimental results shows that the SwinIR deep residual network structure based on MAE loss optimization criteria can generate more realistic super-resolution images with more details. In addition, we used a WFC camera to obtain a resolution test target and real scene images for experiments. Using the resolution test target, we demonstrated that the spatial resolution could be improved from 55.6 lp/mm to 124 lp/mm by the proposed super-resolution reconstruction procedure. The reconstruction results show that the proposed deep learning network model is superior to the traditional method in reconstructing high-frequency details and effectively suppressing noise, with the resolution approaching the diffraction limit. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Organ doses in spiral CT scans depend on the tube start angle.To determine the effective dose in single source CT (SSCT) and dual source CT (DSCT) scans as a function of tube start angle and spiral pitch value to identify the dose reduction potential by selecting the optimal start angle.Using Monte Carlo simulations, dose values for different tube positions with an angular increment of 10∘$10^\circ$ and a longitudinal increment of 4.5mm$4.5 \,\mathrm{m}\mathrm{m}$ were simulated over a range of 31.5cm$31.5 \,\mathrm{c}\mathrm{m}$ with collimations of 40mm$40\, \mathrm{mm}$, 60mm$60\, \mathrm{mm}$, and 80mm$80 \,\mathrm{m}\mathrm{m}$. The simulations were performed for the thorax region of six adult patients based on clinical CT data. From the resulting dose distributions, organ doses and effective dose were determined as a function of tube angle and longitudinal position. Using these per‐view dose data, the individual organ doses, as well as the total effective dose, were determined for spiral scans with and without tube current modulation (TCM) with pitch values ranging from 0.5 to 1.5 for SSCT and up to 3.0 for DSCT. The dose of the best and worst tube start angle in terms of dose was determined and compared to the mean dose over all tube start angles.With increasing pitch and collimation, the dose variations from the effective dose averaged over all start angles increase. While for a collimation of 40mm$40 \,\mathrm{m}\mathrm{m}$, the variations from the mean dose value stay below 5%$5 \%$ for SSCT, we find that for a spiral scan with a pitch of 3.0 for DSCT with TCM and collimation of 80mm$80 \,\mathrm{m}\mathrm{m}$, the dose for the best starting angle is on average 16%$16 \%$ lower than the mean value and 28%$28 \%$ lower than the maximum value.Variation of the tube start angle in spiral scans exhibits substantial differences in radiation dose especially for high pitch values and for high collimations. Therefore, we suggest to control the tube start angle to minimize patient risk. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Cone beam CT (CBCT) is widely utilized in clinics. However, the scatter artifact degrades the CBCT image quality, hampering the expansion of CBCT applications. Recently, beam‐blocker methods have been used for CBCT scatter correction and proved their high cost‐effectiveness.A rotating beam‐blocker (RBB) method for CBCT scatter correction was proposed to complete scatter correction and image reconstruction within a single scan in both full‐ and half‐fan scan scenarios.The RBB consisted of two open regions and two blocked regions, and was designed as a centrosymmetric structure. The open and blocked projections could be alternatively obtained within one single rotation. The open projections were corrected with the scatter signal calculated from the blocked projections, and then used to reconstruct the 3D image via the Feldkamp‐Davis‐Kress algorithm. The performance of the RBB method was evaluated on head and pelvis phantoms in scenarios with and without a bowtie filter. The images obtained from nine repeated scans in each scenario were used to calculate the evaluation metrics including the CT number error, spatial nonuniformity (SNU) and contrast‐to‐noise ratio (CNR).For the head phantom, the CT number error was decreased to <5 after scatter correction from >200 HU before correction when scanned without a bowtie filter, and to <4 from >160 HU when scanned with a full bowtie filter. For the pelvis phantom, the CT number error was reduced to <12 after scatter correction from >250 HU before correction when scanned without a bowtie filter, and to <10 from >190 HU when scanned with a half bowtie filter. After scatter correction, the uniformity and contrast were both improved, resulting in an SNU of >79% decrease and CNR of >2 times increase, respectively.High‐quality CBCT images could be obtained in a single scan after using the proposed RBB method for scatter correction, enabling more accurate image guidance for surgery and radiation therapy applications. With almost no time delay between the successive open and blocked projections, the RBB method could eliminate the motion‐induced anatomical mismatches between the corresponding open and blocked projections and could find particular usefulness in thoracic and abdominal imaging. [ABSTRACT FROM AUTHOR]

Early detection of lung cancer is necessary to prevent deaths caused by lung cancer. But, the identification of cancer in lungs using Computed Tomography (CT) scan based on some deep learning algorithms does not provide accurate results. A novel adaptive deep learning is developed with heuristic improvement. The proposed framework constitutes three sections as (a) Image acquisition, (b) Segmentation of Lung nodule, and (c) Classifying lung cancer. The raw CT images are congregated through standard data sources. It is then followed by nodule segmentation process, which is conducted by Adaptive Multi-Scale Dilated Trans-Unet3+. For increasing the segmentation accuracy, the parameters in this model is optimized by proposing Modified Transfer Operator-based Archimedes Optimization (MTO-AO). At the end, the segmented images are subjected to classification procedure, namely, Advanced Dilated Ensemble Convolutional Neural Networks (ADECNN), in which it is constructed with Inception, ResNet and MobileNet, where the hyper parameters is tuned by MTO-AO. From the three networks, the final result is estimated by high ranking-based classification. Hence, the performance is investigated using multiple measures and compared among different approaches. Thus, the findings of model demonstrate to prove the system’s efficiency of detecting cancer and help the patient to get the appropriate treatment. [ABSTRACT FROM AUTHOR]

Background: Multiplexed positron emission tomography (mPET) imaging can measure physiological and pathological information from different tracers simultaneously in a single scan. Separation of the multiplexed PET signals within a single PET scan is challenging due to the fact that each tracer gives rise to indistinguishable 511 keV photon pairs, and thus no unique energy information for differentiating the source of each photon pair. Methods: Recently, many applications of deep learning for mPET image separation have been concentrated on pure data-driven methods, e.g., training a neural network to separate mPET images into single-tracer dynamic/static images. These methods use over-parameterized networks with only a very weak inductive prior. In this work, we improve the inductive prior of the deep network by incorporating a general kinetic model based on spectral analysis. The model is incorporated, along with deep networks, into an unrolled image-space version of an iterative fully 4D PET reconstruction algorithm. Results: The performance of the proposed method was evaluated on a simulated brain image dataset for dual-tracer [ 18 F]FDG+[ 11 C]MET PET image separation. The results demonstrate that the proposed method can achieve separation performance comparable to that obtained with single-tracer imaging. In addition, the proposed method outperformed the model-based separation methods (the conventional voxel-wise multi-tracer compartment modeling method (v-MTCM) and the image-space dual-tracer version of the fully 4D PET image reconstruction algorithm (IS-F4D)), as well as a pure data-driven separation [using a convolutional encoder-decoder (CED)], with fewer training examples. Conclusions: This work proposes a kinetic model-informed unrolled deep learning method for mPET image separation. In simulation studies, the method proved able to outperform both the conventional v-MTCM method and a pure data-driven CED with less training data. [ABSTRACT FROM AUTHOR]

Aiming at solving the problem that the capability of direction of arrival method for estimation of nested arrays decreases sharply under unknown mutual coupling, an iterative weighted low‐rank matrix reconstruction algorithm is proposed here. First, the received data covariance matrix is extended, and a weighted low‐rank matrix recovery problem is formulated for joint estimations of the Toeplitz matrix and mutual coupling coefficients. Next, the direction of arrival from recovered Toeplitz matrix is retrieved by using the root multiple signal classification algorithm. Simulation results show that iterative weighted low‐rank matrix reconstruction algorithm can effectively avoid the influence of mutual coupling while solving the grid‐mismatch problem so that the accuracy and the resolution of estimation are improved. [ABSTRACT FROM AUTHOR]

Removing texture while preserving the main structure of an image is a challenging task. To address this, this paper propose an image smoothing method based on global gradient sparsity and local relative gradient constraints optimization. To reduce the interference of complex texture details, adopting a multi-directional difference constrained global gradient sparsity decomposition method, which provides a guidance image with weaker texture detail gradients. Meanwhile, using the luminance channel as a reference, edge-aware operator is constructed based on local gradient constraints. This operator weakens the gradients of repetitive and similar texture details, enabling it to obtain more accurate structural information for guiding global optimization of the image. By projecting multi-directional differences onto the horizontal and vertical directions, a mapping from multi-directional differences to bi-directional gradients is achieved. Additionally, to ensure the consistency of measurement results, a multi-directional gradient normalization method is designed. Through experiments, we demonstrate that our method exhibits significant advantages in preserving image edges compared to current advanced smoothing methods. [ABSTRACT FROM AUTHOR]

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections. This results in scan times of several days to acquire hundreds of hyperspectral projections, during which end users have minimal feedback. To address these challenges, a golden ratio scanning protocol combined with model-based image reconstruction algorithms have been proposed. This novel approach enables high quality real-time reconstructions from streaming experimental data, thus providing feedback to users, while requiring fewer yet a fixed number of projections compared to the filtered back projection method. In this paper, we propose a novel machine learning criterion that can terminate a streaming neutron tomography scan once sufficient information is obtained based on the current set of measurements. Our decision criterion uses a quality score which combines a reference-free image quality metric computed using a pre-trained deep neural network with a metric that measures differences between consecutive reconstructions. The results show that our method can reduce the measurement time by approximately a factor of five compared to a baseline method based on filtered back projection for the samples we studied while automatically terminating the scans. [ABSTRACT FROM AUTHOR]

The management and processing of synchrotron and neutron computed tomography data can be a complex, labor‐intensive and unstructured process. Users devote substantial time to both manually processing their data (i.e. organizing data/metadata, applying image filters etc.) and waiting for the computation of iterative alignment and reconstruction algorithms to finish. In this work, we present a solution to these problems: TomoPyUI, a user interface for the well known tomography data processing package TomoPy. This highly visual Python software package guides the user through the tomography processing pipeline from data import, preprocessing, alignment and finally to 3D volume reconstruction. The TomoPyUI systematic intermediate data and metadata storage system improves organization, and the inspection and manipulation tools (built within the application) help to avoid interrupted workflows. Notably, TomoPyUI operates entirely within a Jupyter environment. Herein, we provide a summary of these key features of TomoPyUI, along with an overview of the tomography processing pipeline, a discussion of the landscape of existing tomography processing software and the purpose of TomoPyUI, and a demonstration of its capabilities for real tomography data collected at SSRL beamline 6‐2c. [ABSTRACT FROM AUTHOR]

Background: Measurement of Computed Tomography (CT) beam width is required by accrediting and regulating bodies for routine physics evaluations due to its direct correlation to patient dose. Current methods for performing CT beam width measurement require special hardware, software, and/or consumable films. Today, most 100‐mm pencil chambers with a digital interface used to evaluate Computed Tomography Dose Index (CTDIvol) have a sufficiently high sampling rate to reconstruct a high‐resolution dose profile for any acquisition mode. Purpose: The goal of this study is to measure the CT beam width from the sampled dose profile under a single helical acquisition with the 100‐mm pencil chamber used for CTDIvol measurements. Methods: The dose profiles for different scanners were measured for helical scans with varying collimation settings using a 100‐mm pencil chamber placed at the isocenter and co‐moving with the patient table. The measured dose profiles from the 100‐mm pencil chamber were corrected for table attenuation by extracting a periodic correction function (PCF) to eliminate table interference. The corrected dose profiles were then deconvolved with the response function of the chamber to compute the beam profile. The beam width was defined by the full width half maximum (FWHM) of the resulting beam profile. Reference dose profiles were also measured using Gafchromic film for comparison. Results: The beam widths, estimated using the innovative deconvolution method from the 100‐mm pencil chamber, exhibit an average percentage difference of 1.6 ± 1.8 when compared with measurements obtained through Gafchromic film for beam width assessment. Conclusion: The proposed approach to deconvolve the pencil chamber response demonstrates the potential of obtaining the CT beam width at high accuracy without the need of special hardware, software, or consumable films. This technique can improve workflow for routine performance evaluation of CT systems. [ABSTRACT FROM AUTHOR]

Blind compressive sensing generates a reduced set of measurements of a signal without the knowledge of the sparsifying basis. In this context, the unique recovery and reconstruction of the underlying signal is a challenging problem. One of the properties of the Householder operator is to transform a non-sparse vector in a finite dimensional vector space to a sparse representation of the vector, preserving its ℓ 2 -norm. In this work, we present an algorithm that invokes the sparsifying property of the Householder transforms for the recovery and reconstruction of a signal from its reduced set of blind measurements. The algorithm is an iterative procedure using two objective functions. The first objective function is to estimate the sparse set of representing coefficients. The second objective function jointly estimates the unknown sparsifying transform and the unknown signal. Both the objective functions are entangled to ensure that the estimates meet the fidelity requirement with the available reduced set of measurements. An ℓ 1 -trend filtering is applied to minimize overfitting the estimate of the signal. The signal is uniquely recovered and reconstructed upto an acceptable lower error bound. [ABSTRACT FROM AUTHOR]

To improve image quality in highly accelerated parameter mapping by incorporating a linear constraint that relates consecutive images. In multi-echo T 1 or T 2 mapping, scan time is often shortened by acquiring undersampled but complementary measures of k-space at each TE or TI. However, residual undersampling artifacts from the individual images can then degrade the quality of the final parameter maps. In this work, a new reconstruction method, dubbed Constrained Alternating Minimization for Parameter mapping (CAMP), is introduced. This method simultaneously extracts T 2 or T 1 * maps in addition to an image for each TE or TI from accelerated datasets, leveraging the constraints of the decay to improve the reconstructed image quality. The model enforces exponential decay through a linear constraint, resulting in a biconvex objective function that lends itself to alternating minimization. The method was tested in four in vivo volunteer experiments and validated in phantom studies and healthy subjects, using T 2 and T 1 mapping, with accelerations of up to 12. CAMP is demonstrated for accelerated radial and Cartesian acquisitions in T 2 and T 1 mapping. The method is even applied to generate an entire T 2 weighted image series from a single TSE dataset, despite the blockwise k-space sampling at each echo time. Experimental undersampled phantom and in vivo results processed with CAMP exhibit reduced artifacts without introducing bias. For a wide array of applications, CAMP linearizes the model cost function without sacrificing model accuracy so that the well-conditioned and highly efficient reconstruction algorithm improves the image quality of accelerated parameter maps. [ABSTRACT FROM AUTHOR]

Depth estimation tries to obtain 3D scene geometry from low-dimensional data like 2D images. This is a vital operation in computer vision and any general solution must preserve all depth information of potential relevance to support higher-level tasks. For scenes with well-defined depth, this work shows that multi-view edges can encode all relevant information—that multi-view edges are complete. For this, we follow Elder's complementary work on the completeness of 2D edges for image reconstruction. We deploy an image-space geometric representation: an encoding of multi-view scene edges as constraints and a diffusion reconstruction method for inverting this code into depth maps. Due to inaccurate constraints, diffusion-based methods have previously underperformed against deep learning methods; however, we will reassess the value of diffusion-based methods and show their competitiveness without requiring training data. To begin, we work with structured light fields and epipolar plane images (EPIs). EPIs present high-gradient edges in the angular domain: with correct processing, EPIs provide depth constraints with accurate occlusion boundaries and view consistency. Then, we present a differentiable representation form that allows the constraints and the diffusion reconstruction to be optimized in an unsupervised way via a multi-view reconstruction loss. This is based around point splatting via radiative transport, and extends to unstructured multi-view images. We evaluate our reconstructions for accuracy, occlusion handling, view consistency, and sparsity to show that they retain the geometric information required for higher-level tasks. [ABSTRACT FROM AUTHOR]

Background: High-quality images with minimum radiation dose are considered a challenge in Computed Tomography (CT) scans. Objective: The current study aimed to assess the efficacy of the Iterative Reconstruction in Image Space (IRIS) algorithm combined with Automatic Tube Current Modulation (ATCM) compared to Filtered Back Projection (FBP) in brain CT scans. Material and Methods: In this cross-sectional study, 200 patients underwent to brain CT scan, and images were then reconstructed using both FBP and IRIS. The CT Number (CTN), noise, and Signal-to-Noise Ratio (SNR) were computed for different tissues from CT images. The performance of two algorithms under different exposure conditions was evaluated using a water phantom. Two experienced radiologists assessed the image quality. Volume CT Dose Index (CTDIvol) and Dose Length Product (DLP) were recorded for each scan. Results: FBP reconstruction exhibited higher noise and lower SNR compared to IRIS, both with and without ATCM. Noise levels significantly increased for FBP combined with ATCM. Subjective analysis showed higher performance for IRIS without ATCM compared to other approaches. The mean CTDIvol with and without ATCM was 20.04±3.33 and 36.37±4.65 mGy, respectively. In the phantom study, the noise with IRIS remained lower than that with FBP even with a 42% dose reduction. Conclusion: IRIS algorithm can preserve the image quality when radiation dose is significantly reduced by ATCM in brain CT scan. Implementation of IRIS combined with ATCM is recommended for brain CT examinations. [ABSTRACT FROM AUTHOR]

In order to improve the spatial resolution of brain magnetic resonance imaging (MRI) images, the super resolution (SR) reconstruction method based on deep convolutional neural network (CNN) has achieved remarkable results. Increasing network depth or width usually can expand the receptive field of the network to improve the quality of reconstruction, but it is difficult to train the network due to the large parameter quantity and huge computing requirements. Meanwhile, the network does not pay enough attention to the medium and high frequency features of the image, which affects the quality of reconstruction. To solve the above problems, this paper proposes a cascaded channels-space attention and encode-decode network for 3D-MRI image SR reconstruction. Firstly, feature extraction is carried out in the low resolution space, and the image features are extracted by the symmetric connected encoder-decoder with dilated convolution to alleviate the checkerboard artifacts. Secondly, a serial connected channel-space attention module is constructed to capture the interdependence between the feature channels by channel attention, and the spatial attention is increased to assign weight to information of different positions, effectively enhancing the network' s learning of medium and high frequency information. Finally, subpixel convolution is used to sample the feature map to the target image size and meanwhile reduce memory consumption. Experimental results on public Kirby21 and BraTS datasets show that the proposed method is superior in both quantitative peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and subjective visual quality when compared with traditional SR algorithms and mainstream CNN-based SR algorithms. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Setting up a complex CNN requires a powerful platform, several hours of run-time, and a lot of data for training. Here, we propose a generalised lightweight solution that exploits super-resolution and scalable vector graphics and uses a small-scale UNet as the baseline framework to segment different organs in MR and CT data. We selected the UNet since many researchers use it as the baseline, modify it in their proposal, and perform an ablation study to show the effectiveness of the proposed modification. First, we downsample the input 2D CT slices by bicubic interpolation. Using the architecture of the conventional UNet, we reduce the size of the network's input, and the number of layers and filters to construct a lightweight UNet. The network segments the low-resolution images and prepares the mask of an organ. Then, we upscale the boundary of the output mask by the Scalable Vector Graphics technique to obtain the final border. This design reduces the number of parameters and the run-time by a factor of two. We segmented several tissues to prove the stability of our method to the type of organ. The experiments proved the feasibility of setting up complex deep neural networks with conventional platforms. [ABSTRACT FROM AUTHOR]

Purpose: Quantitative T1 mapping has the potential to replace biopsy for noninvasive diagnosis and quantitative staging of chronic liver disease. Conventional T1 mapping methods are confounded by fat and B1+$$ {B}_1^{+} $$ inhomogeneities, resulting in unreliable T1 estimations. Furthermore, these methods trade off spatial resolution and volumetric coverage for shorter acquisitions with only a few images obtained within a breath‐hold. This work proposes a novel, volumetric (3D), free‐breathing T1 mapping method to account for multiple confounding factors in a single acquisition. Theory and Methods: Free‐breathing, confounder‐corrected T1 mapping was achieved through the combination of non‐Cartesian imaging, magnetization preparation, chemical shift encoding, and a variable flip angle acquisition. A subspace‐constrained, locally low‐rank image reconstruction algorithm was employed for image reconstruction. The accuracy of the proposed method was evaluated through numerical simulations and phantom experiments with a T1/proton density fat fraction phantom at 3.0 T. Further, the feasibility of the proposed method was investigated through contrast‐enhanced imaging in healthy volunteers, also at 3.0 T. Results: The method showed excellent agreement with reference measurements in phantoms across a wide range of T1 values (200 to 1000 ms, slope = 0.998 (95% confidence interval (CI) [0.963 to 1.035]), intercept = 27.1 ms (95% CI [0.4 54.6]), r2 = 0.996), and a high level of repeatability. In vivo imaging studies demonstrated moderate agreement (slope = 1.099 (95% CI [1.067 to 1.132]), intercept = −96.3 ms (95% CI [−82.1 to −110.5]), r2 = 0.981) compared to saturation recovery‐based T1 maps. Conclusion: The proposed method produces whole‐liver, confounder‐corrected T1 maps through simultaneous estimation of T1, proton density fat fraction, and B1+$$ {B}_1^{+} $$ in a single, free‐breathing acquisition and has excellent agreement with reference measurements in phantoms. [ABSTRACT FROM AUTHOR]

If an unknown finite set C ⊂ Z 2 is cut by lines parallel to given directions, then one may count the number of points of C that are intercepted by each line, that is, the projections of C in the given directions. The inverse problem consists in reconstructing the set C , interpreted as a binary image, from the knowledge of its projections. In general, this challenging combinatorial problem, also related to the tomographic reconstruction of an unknown homogeneous object by means of X-rays, is ill-posed, meaning that different binary images exist that match the available projections. Therefore, as a preliminary step, one can try to find conditions to be imposed on the considered directions in order to limit the number of allowed solutions. In this paper we address the above problems for sets C contained in a finite assigned lattice grid, and generalize some results known in literature. First, we describe special sets of lattice directions, called simple cycles, and focus on some of their properties. Then we prove that uniqueness of reconstruction for binary images is guaranteed if and only if the line sums are computed along suitable simple cycles having even cardinality. As a second item, we prove that the unique binary solution can be explicitly reconstructed from a real-valued solution having minimal Euclidean norm. This leads to an explicit reconstruction algorithm, tested on four different phantoms and compared with previous results, which points out a significant improvement of the corresponding performance. [ABSTRACT FROM AUTHOR]

Computing the proximal operator of the sparsity-promoting piece-wise exponential (PiE) penalty 1 − e − | x | / σ with a given shape parameter σ > 0 , which is treated as a popular nonconvex surrogate of ℓ 0 -norm, is fundamental in feature selection via support vector machines, image reconstruction, zero-one programming problems, compressed sensing, neural networks, etc. Due to the nonconvexity of PiE, for a long time, its proximal operator is frequently evaluated via an iteratively reweighted ℓ 1 algorithm, which substitutes PiE with its first-order approximation, however, the obtained solutions only are the critical point. Based on the exact characterization of the proximal operator of PiE, we explore how the iteratively reweighted ℓ 1 solution deviates from the true proximal operator in certain regions, which can be explicitly identified in terms of σ , the initial value and the regularization parameter in the definition of the proximal operator. Moreover, the initial value can be adaptively and simply chosen to ensure that the iteratively reweighted ℓ 1 solution belongs to the proximal operator of PiE. [ABSTRACT FROM AUTHOR]

Background: Although the importance of quantitative SPECT has increased tremendously due to newly developed therapeutic radiopharmaceuticals, there are still no accreditation programs to harmonize SPECT imaging. Work is currently underway to develop an accreditation for quantitative 177Lu SPECT/CT. The aim of this study is to verify whether the positioning of the spheres within the phantom has an influence on the recovery and thus needs to be considered in SPECT harmonization. In addition, the effects of these recovery coefficients on a potential partial volume correction as well as absorbed-dose estimates are investigated. Methods: Using a low-dose CT of a SPECT/CT acquisition, a computerized version of the NEMA body phantom was created using a semi-automatic threshold-based method. Based on the mass-density map, the detector orbit, and the sphere centers, realistic SPECT acquisitions of all possible 720 sphere configurations of both the PET and the SPECT versions of the NEMA Body Phantom were generated using Monte Carlo simulations. SPECT reconstructions with different numbers of updates were performed without (CASToR) and with resolution modeling (STIR). Recovery coefficients were calculated for all permutations, reconstruction methods, and phantoms, and their dependence on the sphere positioning was investigated. Finally, the simulation-based findings were validated using SPECT/CT acquisitions of six different sphere configurations. Results: Our analysis shows that sphere positioning has a significant impact on the recovery for both of the reconstruction methods and the phantom type. Although resolution modeling resulted in significantly higher recovery, the relative variation in recovery within the 720 permutations was even larger. When examining the extreme values of the recovery, reconstructions without resolution modeling were influenced primarily by the sphere position, while with resolution modeling the volume of the two adjacent spheres had a larger influence. The SPECT measurements confirmed these observations, and the recovery curves showed good overall agreement with the simulated data. Conclusion: Our study shows that sphere positioning has a significant impact on the recovery obtained in NEMA sphere phantom measurements and should therefore be considered in a future SPECT accreditation. Furthermore, the single-measurement method normally performed for PVC should be reconsidered to account for the position dependency. [ABSTRACT FROM AUTHOR]

BACKGROUND: Traditional lateral cephalometric radiographs always suffer from some problems, such as magnification distortion, left and right overlap inconsistency and so on, while the cone-beam CT can truly display the three-dimensional structure of the craniofacial region. Performing three-dimensional reconstruction of cone-beam CT and then transforming the cone-beam CT in the selected area into the two-dimensional image can make the overlap between the left and right sides consistent and reduce the influence of surrounding tissue structures. OBJECTIVE: To explore the consistency of quantitative analysis of cervical vertebral bone age between two kinds of cone-beam CT transformed twodimensional images with different integrated thicknesses and traditional lateral cephalometric radiographs. METHODS: The cone-beam CT and lateral cephalometric radiograph data of 118 adolescent orthodontic patients were collected. Firstly, the cone-beam CT image was reconstructed in 3D imaging software. After reconstruction, two types of cone-beam CT images with different integrated thicknesses were selected in the sagittal interface and transformed into two-dimensional images, which were named ICB-1 and ICB-2, respectively. The Zhibeiyun system was used to measure and calculate the angle between the concave base of the second cervical vertebra and the lower edge of the vertebral body (@2), the ratio of the third cervical spine to the posterior height (AH3/PH3), the ratio of height to width of the fourth cervical spine (H4/W4) in lateral cephalometric radiograph, ICB-1, ICB-2 and the cervical vertebral bone age. After an interval of two weeks, 20 adolescents were randomly selected to repeat the above measurements. The intraclass correlation coefficient (ICC) method was used to evaluate the repeatability of the three images in measuring cervical bone age. Paired t-test was used to analyze the consistency of cervical bone age measurements between the three images. The Kappa test was used to analyze the consistency of cervical vertebral bone age staging assessment between the three images. RESULTS AND CONCLUSION: (1) ICC of AH3/PH3 in the lateral cephalometric radiograph group was < 0.9, and the ICC of other measurement items in each group was > 0.9. (2) Paired t-test results showed that there were statistical differences in AH3/PH3 and H4/W4 between the ICB-1 group and lateral cephalometric radiograph group and between the ICB-1 group and ICB-2 group (P < 0.05), and there were no statistically significant differences in the other items between the three groups (P > 0.05). (3) The Kappa test results showed that the Kappa coefficients of the two groups were all more than 0.8 according to the staging of cervical vertebral bone age in three groups (P < 0.001). (4) It is indicated that the repeatability of ICB-1 and ICB-2 in the measurement of cervical vertebral bone age is better than that of lateral cephalometric radiographs. Lateral cephalometric radiographs, ICB-1 and ICB-2 have good consistency in the measurement of cervical vertebral bone age, but considering the integrity of cervical vertebra structure, ICB-2 is more suitable for quantitative analysis of cervical vertebral bone age than ICB-1. [ABSTRACT FROM AUTHOR]

Low-Dose computer tomography (LDCT) is an ideal alternative to reduce radiation risk in clinical applications. Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging. In this paper, we propose an unsupervised and training data-free learning reconstruction method for LDCT imaging that avoids the requirement for training data. The proposed method is a post-processing technique that aims to enhance the initial low-quality reconstruction results, and it reconstructs the high-quality images by neural work training that minimizes the ℓ1-norm distance between the CT measurements and their corresponding simulated sinogram data, as well as the total variation (TV) value of the reconstructed image. Moreover, the proposed method does not require to set the weights for both the data fidelity term and the plenty term. Experimental results on the AAPM challenge data and LoDoPab-CT data demonstrate that the proposed method is able to effectively suppress the noise and preserve the tiny structures. Also, these results demonstrate the rapid convergence and low computational cost of the proposed method. The source code is available at https://github.com/linfengyu77/IRLDCT. [ABSTRACT FROM AUTHOR]

Imaging parameters, frequencies and resulting patient organ doses in treatments of prostate cancer were assessed in Finnish radiotherapy centres. Based on a questionnaire to the clinics, Monte Carlo method was used to estimate organ doses in International Commission on Radiological Protection standard phantom for prostate, bladder, rectum and femoral head. The results show that doses from cone beam computed tomography imaging have reduced compared to earlier studies and are between 3.6 and 34.5 mGy per image for the above-mentioned organs and for normal sized patients. There still is room for further optimization of the patient exposure, as many centres use the default imaging parameters, and the length of the imaged region may not be optimal for the purpose. [ABSTRACT FROM AUTHOR]

Photoacoustic imaging (PAI) is an emerging imaging technique that offers real-time, non-invasive, and radiation-free measurements of optical tissue properties. However, image quality degradation due to factors such as non-ideal signal detection hampers its clinical applicability. To address this challenge, this paper proposes an algorithm for super-resolution reconstruction and segmentation based on deep learning. The proposed enhanced deep super-resolution minimalistic network (EDSR-M) not only mitigates the shortcomings of the original algorithm regarding computational complexity and parameter count but also employs residual learning and attention mechanisms to extract image features and enhance image details, thereby achieving high-quality reconstruction of PAI. DeepLabV3+ is used to segment the images before and after reconstruction to verify the network reconstruction performance. The experimental results demonstrate average improvements of 19.76% in peak-signal-to-noise ratio (PSNR) and 4.80% in structural similarity index (SSIM) for the reconstructed images compared to those of their pre-reconstructed counterparts. Additionally, mean accuracy, mean intersection and union ratio (IoU), and mean boundary F1 score (BFScore) for segmentation showed enhancements of 8.27%, 6.20%, and 6.28%, respectively. The proposed algorithm enhances the effect and texture features of PAI and makes the overall structure of the image restoration more complete. [ABSTRACT FROM AUTHOR]

Objective. Deep learning reconstruction (DLR) algorithms exhibit object-dependent resolution and noise performance. Thus, traditional geometric CT phantoms cannot fully capture the clinical imaging performance of DLR. This study uses a patient-derived 3D-printed PixelPrint lung phantom to evaluate a commercial DLR algorithm across a wide range of radiation dose levels. Method. The lung phantom used in this study is based on a patient chest CT scan containing ground glass opacities and was fabricated using PixelPrint 3D-printing technology. The phantom was placed inside two different size extension rings to mimic a small- and medium-sized patient and was scanned on a conventional CT scanner at exposures between 0.5 and 20 mGy. Each scan was reconstructed using filtered back projection (FBP), iterative reconstruction, and DLR at five levels of denoising. Image noise, contrast to noise ratio (CNR), root mean squared error, structural similarity index (SSIM), and multi-scale SSIM (MS SSIM) were calculated for each image. Results. DLR demonstrated superior performance compared to FBP and iterative reconstruction for all measured metrics in both phantom sizes, with better performance for more aggressive denoising levels. DLR was estimated to reduce dose by 25%–83% in the small phantom and by 50%–83% in the medium phantom without decreasing image quality for any of the metrics measured in this study. These dose reduction estimates are more conservative compared to the estimates obtained when only considering noise and CNR. Conclusion. DLR has the capability of producing diagnostic image quality at up to 83% lower radiation dose, which can improve the clinical utility and viability of lower dose CT scans. Furthermore, the PixelPrint phantom used in this study offers an improved testing environment with more realistic tissue structures compared to traditional CT phantoms, allowing for structure-based image quality evaluation beyond noise and contrast-based assessments. [ABSTRACT FROM AUTHOR]