Hypoxic Ischemic Encephalopathy (HIE) represents a brain dysfunction, affecting approximately 1 to 5 per 1000 full-term neonates. The precise delineation and segmentation of HIE-related lesions in neonatal brain Magnetic Resonance Images (MRI) are pivotal in advancing outcome predictions, identifying patients at high risk, elucidating neurological manifestations, and assessing treatment efficacies. Despite its importance, the development of algorithms for segmenting HIE lesions from MRI volumes has been impeded by data scarcity. Addressing this critical gap, we organized the first BONBID-HIE challenge with diffusion MRI data (Apparent Diffusion Coefficient (ADC) maps) for HIE lesion segmentation, in conjunction with the MICCAI 2023. Totally 14 algorithms were submitted, employing a gamut of cutting-edge automatic machine-learning-based segmentation algorithms. Our comprehensive analysis of HIE lesion segmentation and submitted algorithms facilitates an in-depth evaluation of the current technological zenith, outlines directions for future advancements, and highlights persistent hurdles. To foster ongoing research and benchmarking, the annotated HIE dataset, developed algorithm dockers, and unified evaluation codes are accessible through a dedicated online platform (https://bonbid-hie2023.grand-challenge.org).

Segmentation of the right ventricle (RV) in magnetic resonance imaging (MRI) sequences is critical for assessing RV function. However, manual segmentation involves processing hundreds of images per patient, making it a tedious and timeconsuming process. Recently, deep convolutional neural networks have emerged as an effective solution for automating RV segmentation in MRI sequences, substantially reducing manual workload. Accurate segmentation of the RV is crucial for reliable clinical applications. In this study, we demonstrate that transfer learning using a pre-trained segmentation model from the Medical Open Network for Artificial Intelligence (MONAI) Model Zoo significantly improves segmentation accuracy, as measured by the Dice similarity coefficient (DSC) and$\mathbf{9 5}^{\text {th }}$percentile Hausdorff distance (HD95) scores, compared to manual annotations from medical experts. Our approach increased DSC-based segmentation accuracy from 74.93 % (pre-trained MONAI Zoo model) and 83.15 % (same architecture trained on our data) to 84.91 % on 1,994 test images acquired from seven patients. Furthermore, it outperformed a state-of-the-art self-configuring network, nnU-Net, which achieved an accuracy of 81.98 % on the same dataset. This study demonstrates the effectiveness of transfer learning in improving segmentation accuracy for the proposed task.

Effective visualization of three-dimensional (3D) medical images is essential for planning medical procedures, as it directly impacts diagnostic precision and enhances patient understanding. High-quality 3D visualization enables physicians to make informed decisions, supports surgeons in planning complex procedures, and helps patients better understand their conditions and treatment options. However, commonly used headmounted display (HMD) devices such as the Meta Quest and Microsoft HoloLens often cause discomfort, eye strain, and communication challenges, and their complex setup can limit practical use in clinical settings. The recently developed, glassesfree Looking Glass Factory 16” Spatial Display presents a compelling alternative, capable of delivering high-quality holographic images without requiring HMDs, making it a promising solution for clinical visualization. This study investigates using the Looking Glass 16” Spatial Display to visualize 3D pediatric cardiac CT scans in DICOM format, demonstrating its potential to improve accessibility and usability in clinical imaging. Clinical DICOM images are converted into MetaImages (RAW images with MHD headers) using 3DSlicer software and rendered with a volume rendering algorithm to create detailed volumetric models. These 3D images are then displayed on the Looking Glass device through the Unity3D platform, with an NVIDIA GeForce RTX 4060 Ti graphics card optimizing frame rates, reducing latency, and supporting real-time image control on a personal computer (PC). Experimental evaluations confirm the feasibility of producing high-quality, real-time displays on the Looking Glass 16” Spatial Display, offering clinicians an intuitive and efficient interface. This research highlights the potential of the Looking Glass 16” Spatial Display to enhance 3D medical image visualization, particularly for cardiac CT applications. By providing a more precise, accessible imaging method, this technology could significantly improve clinical decision-making and deepen medical professionals understanding of complex anatomical data.

Echocardiography plays an important role in the assessment of cardiovascular diseases. The lack of ionizing radiation and portability make it one of the safest imaging modalities. Although two-dimensional echocardiography is widely used to obtain the motion of the heart structures in real-time, three-dimensional (3D) echocardiography allows for scanning of the heart in 3D with unlimited postprocessing geometries compared to 2D. However, the feasibility is limited because of speckle noise, poor quality, limited field of view and missing anatomical structures. The entire heart cannot be imaged in a single 3D echocardiography scan in most cases, and further improvements are needed to solve the problem. This study proposes a point-based rigid registration followed by B-spline non-rigid registration to align 4D echocardiography images obtained from different sonographic windows. The approach was tested on scans obtained from three volunteer participants. The accuracy of registration was visually and quantitatively assessed by delineating the left ventricle in each scan and computing the Dice score overlap metric and the Hausdorff distance mutual proximity measure between the first scan and the rest. The overall results indicate that the proposed registration approach improves the alignment of the images compared to the original scans.

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

Cardiac segmentation from magnetic resonance imaging (MRI) is one of the essential tasks to analyze the anatomy and function of the heart for the assessment and diagnosis of cardiac diseases. However, manual annotation is difficult and time consuming. This study proposes a novel end-to-end supervised cardiac MRI segmentation framework based on a diffeomorphic deformable registration that can segment the left ventricle from 2D and 3D images or volumes. In order to represent the actual cardiac deformation, the methodology parameterizes the transformation using radial and rotational components, computed using a deep learning approach The method was evaluated over three different data sets and showed significant improvements compared to exacting learning and non-learning based methods in terms of the Dice score and Hausdorff distance metrics.

The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

Multiview three-dimensional echocardiography (M3DE) fuses volumetric datasets acquired from complementary acoustic windows to expand field-of-view and allow for visualization of the entire heart. This is of great importance for cardiac chamber quantification. The M3DE also allows for image quality improvement through fusion of single views on overlapping regions. However, shape variations and increase in noise stemming from the nature of ultrasound physics make fusion a challenging task. This study proposes a novel machine learning-based fusion method to combine ultrasound views that are spatially apart, namely, apical and parasternal. Our method jointly uses: 1) an autoencoder framework to generate the fused image; and 2) a mutual information neural estimation network to maximize the mutual information between source and fused images. The experimental evaluations show promising results and the fused image generated by the proposed method improves the signal-to-noise ratio by up to 18.23 dB and the contrast-to-noise ratio by up to 21.76 dB compared to the state-of-art approaches.

Interactive dashboards process and present raw data in the form of visuals, graphs, and text along with various options for user interactions. The dashboards allow for extracting valuable information and showcase the data in an intuitive and easy to understand manner. As the world is battling with the COVID-19 pandemic, we developed an interactive data-driven dashboard to not only view the current trends, but to also display important analytics and projections for the upcoming week. Built using python modules Dash and Plotly for visualization, the proposed dashboard utilizes the data analytic capabilities of the Pandas python library to structure and organize the raw data efficiently. Our dashboard is lightweight and designed for optimal performance. It can update values dynamically and be loaded onto any web server. Moreover, our proposed solution performed the best when compared to three other COVID-19 solutions, in terms of performance and speed, page size, and the number of HTTP requests.

Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 well-performing methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download.

We present efficient graph cut algorithms for three problems: (1) finding a region in an image, so that the histogram (or distribution) of an image feature within the region most closely matches a given model; (2) co-segmentation of image pairs and (3) interactive image segmentation with a user-provided bounding box. Each algorithm seeks the optimum of a global cost function based on the Bhattacharyya measure, a convenient alternative to other matching measures such as the Kullback-Leibler divergence. Our functionals are not directly amenable to graph cut optimization as they contain non-linear functions of fractional terms, which make the ensuing optimization problems challenging. We first derive a family of parametric bounds of the Bhattacharyya measure by introducing an auxiliary labeling. Then, we show that these bounds are auxiliary functions of the Bhattacharyya measure, a result which allows us to solve each problem efficiently via graph cuts. We show that the proposed optimization procedures converge within very few graph cut iterations. Comprehensive and various experiments, including quantitative and comparative evaluations over two databases, demonstrate the advantages of the proposed algorithms over related works in regard to optimality, computational load, accuracy and flexibility.

Automating the detection and localization of segmental (regional) left ventricle (LV) abnormalities in magnetic resonance imaging (MRI) has recently sparked an impressive research effort, with promising performances and a breadth of techniques. However, despite such an effort, the problem is still acknowledged to be challenging, with much room for improvements in regard to accuracy. Furthermore, most of the existing techniques are labor intensive, requiring delineations of the endo- and/or epi-cardial boundaries in all frames of a cardiac sequence. The purpose of this study is to investigate a real-time machine-learning approach which uses some image features that can be easily computed, but that nevertheless correlate well with the segmental cardiac function. Starting from a minimum user input in only one frame in a subject dataset, we build for all the regional segments and all subsequent frames a set of statistical MRI features based on a measure of similarity between distributions. We demonstrate that, over a cardiac cycle, the statistical features are related to the proportion of blood within each segment. Therefore, they can characterize segmental contraction without the need for delineating the LV boundaries in all the frames. We first seek the optimal direction along which the proposed image features are most descriptive via a linear discriminant analysis. Then, using the results as inputs to a linear support vector machine classifier, we obtain an abnormality assessment of each of the standard cardiac segments in real-time. We report a comprehensive experimental evaluation of the proposed algorithm over 928 cardiac segments obtained from 58 subjects. Compared against ground-truth evaluations by experienced radiologists, the proposed algorithm performed competitively, with an overall classification accuracy of 86.09% and a kappa measure of 0.73.

This study investigates a convex relaxation approach to figure-ground separation with a global distribution matching prior evaluated by the Bhattacharyya measure. The problem amounts to finding a region that most closely matches a known model distribution. It has been previously addressed by curve evolution, which leads to suboptimal and computationally intensive algorithms, or by graph cuts, which result in metrication errors. Solving a sequence of convex subproblems, the proposed relaxation is based on a novel bound of the Bhattacharyya measure which yields an algorithm robust to initial conditions. Furthermore, we propose a novel flow configuration that accounts for labeling-function variations, unlike existing configurations. This leads to a new max-flow formulation which is dual to the convex relaxed subproblems we obtained. We further prove that such a formulation yields exact and global solutions to the original, nonconvex subproblems. A comprehensive experimental evaluation on the Microsoft GrabCut database demonstrates that our approach yields improvements in optimality and accuracy over related recent methods.

This study investigates an efficient algorithm for image segmentation with a global constraint based on the Bhattacharyya measure. The problem consists of finding a region consistent with an image distribution learned a priori. We derive an original upper bound of the Bhattacharyya measure by introducing an auxiliary labeling. From this upper bound, we reformulate the problem as an optimization of an auxiliary function by graph cuts. Then, we demonstrate that the proposed procedure converges and give a statistical interpretation of the upper bound. The algorithm requires very few iterations to converge, and finds nearly global optima. Quantitative evaluations and comparisons with state-of-the-art methods on the Microsoft GrabCut segmentation database demonstrated that the proposed algorithm brings improvements in regard to segmentation accuracy, computational efficiency, and optimality. We further demonstrate the flexibility of the algorithm in object tracking.

We present an original information theoretic measure of heart motion based on the Shannon's differential entropy (SDE), which allows heart wall motion abnormality detection. Based on functional images, which are subject to noise and segmentation inaccuracies, heart wall motion analysis is acknowledged as a difficult problem, and as such, incorporation of prior knowledge is crucial for improving accuracy. Given incomplete, noisy data and a dynamic model, the Kalman filter, a well-known recursive Bayesian filter, is devised in this study to the estimation of the left ventricular (LV) cavity points. However, due to similarity between the statistical information of normal and abnormal heart motions, detecting and classifying abnormality is a challenging problem, which we investigate with a global measure based on the SDE. We further derive two other possible information theoretic abnormality detection criteria, one is based on Rényi entropy and the other on Fisher information. The proposed methods analyze wall motion quantitatively by constructing distributions of the normalized radial distance estimates of the LV cavity. Using 269 x 20 segmented LV cavities of short-axis MRI obtained from 30 subjects, the experimental analysis demonstrates that the proposed SDE criterion can lead to a significant improvement over other features that are prevalent in the literature related to the LV cavity, namely, mean radial displacement and mean radial velocity.