Coarctation of the aorta (CoA) is a common congenital heart defect characterized by aortic narrowing. Prenatally, it has mild hemodynamic effects as right ventricular disproportion and ductus arteriosus (DA) dilation occur as adaptive mechanisms, but their impact on CoA hemodynamics remains poorly understood. To investigate this, we built a closed 0D computational model of fetal circulation and simulated different CoA cardiovascular remodeling patterns, including aortic isthmus (AoI) narrowing, ventricular disproportion, and DA dilation. Our results showed mild AoI narrowing (80% of reference diameter) required up to 1.7 right/left ventricular end-diastolic volume ratio and 115% DA dilation to maintain physiological pressures, wall shear stresses, and organ perfusion. In contrast, severe narrowing (20% of reference AoI diameter) required up to 5 right/left ventricular end-diastolic volume ratio and 125% DA dilation, highlighting the necessity of co-occurrence of prenatal ventricular disproportion and DA dilation to compensate for AoI narrowing. These physiological regions were validated with ultrasonographic measurements from 7 controls and 9 CoA patients. We compared blood pressures, velocities, and volumetric flow rates across different fetoplacental anatomical sites. AoI velocity showed a delayed retrograde flow peak and increased antegrade diastolic velocity with greater AoI narrowing, which may aid in diagnosing CoA. Minimal differences were observed in other velocities and pressures. Volumetric flow rates across varying degrees of AoI narrowing decreased in the AoI and mitral and aortic valves, remained stable in the middle cerebral and umbilical arteries, and increased in the DA and tricuspid and pulmonary valves. Therefore, we corroborated that in fetal CoA a redistribution of blood flow occurs to ensure perfusion of the brain and placenta, without a significant alteration in fetal hemodynamics (blood pressure and velocities) except for increased diastolic velocities in the AoI.

Segmentation is a critical step in analyzing the developing human fetal brain. There have been vast improvements in automatic segmentation methods in the past several years, and the Fetal Brain Tissue Annotation (FeTA) Challenge 2021 helped to establish an excellent standard of fetal brain segmentation. However, FeTA 2021 was a single center study, limiting real-world clinical applicability and acceptance. The multi-center FeTA Challenge 2022 focused on advancing the generalizability of fetal brain segmentation algorithms for magnetic resonance imaging (MRI). In FeTA 2022, the training dataset contained images and corresponding manually annotated multi-class labels from two imaging centers, and the testing data contained images from these two centers as well as two additional unseen centers. The multi-center data included different MR scanners, imaging parameters, and fetal brain super-resolution algorithms applied. 16 teams participated and 17 algorithms were evaluated. Here, the challenge results are presented, focusing on the generalizability of the submissions. Both in- and out-of-domain, the white matter and ventricles were segmented with the highest accuracy (Top Dice scores: 0.89, 0.87 respectively), while the most challenging structure remains the grey matter (Top Dice score: 0.75) due to anatomical complexity. The top 5 average Dices scores ranged from 0.81-0.82, the top 5 average percentile Hausdorff distance values ranged from 2.3-2.5mm, and the top 5 volumetric similarity scores ranged from 0.90-0.92. The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms.

This study presents a novel methodology for stratifying post-myocardial infarction patients at risk of ventricular arrhythmias using patient-specific 3D cardiac models derived from late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) images. The method integrates imaging and computational simulation with the fast electrophysiology solver, Arritmic3D, enabling rapid and accurate ventricular arrhythmias (VA) risk assessment in clinical timeframes. Applied to 51 patients, the solver generated thousands of personalized simulations exploring ranges of values for several parameters to evaluate arrhythmia inducibility and predict VA risk. Key findings include the identification of slow conduction channels (SCCs) within scar tissue as critical to reentrant arrhythmias and the localization of high-risk zones for potential intervention. The Arrhythmic Risk Score (ARRISK), developed from simulation results, demonstrated strong concordance with clinical outcomes and outperformed traditional imaging-based risk stratification. The methodology is fully automated, requiring minimal user intervention, and offers a promising tool for improving precision medicine in cardiac care by enhancing patient-specific arrhythmia risk assessment and guiding treatment strategies.

Left atrial appendage occlusion devices (LAAO) are a feasible alternative for non-valvular atrial fibrillation (AF) patients at high risk of thromboembolic stroke and contraindication to antithrombotic therapies. However, optimal LAAO device configurations (i.e., size, type, location) remain unstandardized due to the large anatomical variability of the left atrial appendage (LAA) morphology, leading to a 4-6% incidence of device-related thrombus (DRT). In-silico simulations have the potential to assess DRT risk and identify the key factors, such as suboptimal device positioning. This work presents fluid simulation results computed on 20 patient-specific left atrial geometries, analysing different commercially available LAAO occluders, including plug-type and pacifier-type devices. In addition, we explored two distinct device positions: 1) the real post-LAAO intervention configuration derived from follow-up imaging; and 2) one covering the pulmonary ridge if it was not achieved during the implantation (13 out of 20). In total, 33 different configurations were analysed. In-silico indices indicating high risk of DRT (e.g., low blood flow velocities and flow complexity around the device) were combined with particle deposition analysis based on a discrete phase model. The obtained results revealed that covering the pulmonary ridge with the LAAO device may be one of the key factors to prevent DRT, resulting in higher velocities and reduced flow recirculations (e.g., mean velocities of 0.183 ± 0.12 m/s and 0.236 ± 0.16 m/s for uncovered versus covered positions in DRT patients). Moreover, disk-based devices exhibited enhanced adaptability to various LAA morphologies and, generally, demonstrated a lower risk of abnormal events after LAAO implantation.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known decision support tool, owing to their interpretability, fundamental in safety-critical contexts such as medical diagnosis. However, learning DTs from uncertain data leads to poor generalization, and generating predictions for uncertain data hinders prediction accuracy. Several methods have suggested the potential of probabilistic decisions at the internal nodes in making DTs robust to uncertainty. Some approaches only employ probabilistic thresholds during evaluation. Others also consider the uncertainty in the learning phase, at the expense of increased computational complexity or reduced interpretability. The existing methods have not clarified the merit of a probabilistic approach in the distinct phases of DT learning, nor when the uncertainty is present in the training or the test data. We present a probabilistic DT approach that models measurement uncertainty as a noise distribution, independently realized: (1) when searching for the split thresholds, (2) when splitting the training instances, and (3) when generating predictions for unseen data. The soft training approaches (1, 2) achieved a regularizing effect, leading to significant reductions in DT size, while maintaining accuracy, for increased noise. Soft evaluation (3) showed no benefit in handling noise.

Two-dimensional representation of 3D anatomical structures is a simple and intuitive way for analysing patient information across populations and image modalities. It also allows convenient visualizations that can be included in clinical reports for a fast overview of the whole structure. While cardiac ventricles, especially the left ventricle, have an established standard representation (e.g. bull's eye plot), the 2D depiction of the left atrium (LA) is challenging due to its sub-structural complexity including the pulmonary veins (PV) and the left atrial appendage (LAA). Quasi-conformal flattening techniques, successfully applied to cardiac ventricles, require additional constraints in the case of the LA to place the PV and LAA in the same geometrical 2D location for different cases. Some registration-based methods have been proposed but 3D (or 2D) surface registration is time-consuming and prone to errors if the geometries are very different. We propose a novel atrial flattening methodology where a quasi-conformal 2D map of the LA is obtained quickly and without errors related to registration. In our approach, the LA is divided into 5 regions which are then mapped to their analogue two-dimensional regions. A dataset of 67 human left atria from magnetic resonance images (MRI) was studied to derive a population-based 2D LA template representing the averaged relative locations of the PVs and LAA. The clinical application of the proposed methodology is illustrated on different use cases including the integration of MRI and electroanatomical data.

Decision trees (DTs) are a widely used prediction tool, owing to their interpretability. Standard learning methods follow a locally-optimal approach that trades off prediction performance for computational efficiency. Such methods can however be far from optimal, and it may pay off to spend more computational resources to increase performance. Monte Carlo tree search (MCTS) is an approach to approximate optimal choices in exponentially large search spaces. Since exploring the space of all possible DTs is computationally intractable, we propose a DT learning approach based on MCTS. To bound the branching factor of MCTS, we limit the number of decisions at each level of the search tree, and introduce mechanisms to balance exploration, DT size and the statistical significance of the predictions. To mitigate the computational cost of our method, we employ a move pruning strategy that discards some branches of the search tree, leading to improved performance. The experiments show that our approach outperformed locally optimal search in 20 out of 31 datasets, with a reduction in DT size in most of the cases.

Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Automatic Cardiac Diagnosis Challenge" dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

The electrical activation of the heart is a complex physiological process that is essential for the understanding of several cardiac dysfunctions, such as ventricular tachycardia (VT). Nowadays, patient-specific activation times on ventricular chambers can be estimated from electro-anatomical maps, providing crucial information to clinicians for guiding cardiac radio-frequency ablation treatment. However, some relevant electrical pathways such as those of the Purkinje system are very difficult to interpret from these maps due to sparsity of data and the limited spatial resolution of the system. We present here a novel method to estimate these fast electrical pathways from the local activations maps (LATs) obtained from electro-anatomical maps. The location of Purkinje-myocardial junctions (PMJs) is estimated considering them as critical points of a distance map defined by the activation maps, and then minimal cost geodesic paths are computed on the ventricular surface between the detected junctions. Experiments to validate the proposed method have been carried out in simplified and realistic simulated data, showing good performance on recovering the main characteristics of simulated Purkinje networks (e.g. PMJs). A feasibility study with real cases of fascicular VT was also performed, showing promising results.

Intrauterine growth restriction (IUGR) due to placental insufficiency is associated with blood flow redistribution in order to maintain delivery of oxygenated blood to the brain. Given that, in the fetus the aortic isthmus (AoI) is a key arterial connection between the cerebral and placental circulations, quantifying AoI blood flow has been proposed to assess this brain sparing effect in clinical practice. While numerous clinical studies have studied this parameter, fundamental understanding of its determinant factors and its quantitative relation with other aspects of haemodynamic remodeling has been limited. Computational models of the cardiovascular circulation have been proposed for exactly this purpose since they allow both for studying the contributions from isolated parameters as well as estimating properties that cannot be directly assessed from clinical measurements. Therefore, a computational model of the fetal circulation was developed, including the key elements related to fetal blood redistribution and using measured cardiac outflow profiles to allow personalization. The model was first calibrated using patient-specific Doppler data from a healthy fetus. Next, in order to understand the contributions of the main parameters determining blood redistribution, AoI and middle cerebral artery (MCA) flow changes were studied by variation of cerebral and peripheral-placental resistances. Finally, to study how this affects an individual fetus, the model was fitted to three IUGR cases with different degrees of severity. In conclusion, the proposed computational model provides a good approximation to assess blood flow changes in the fetal circulation. The results support that while MCA flow is mainly determined by a fall in brain resistance, the AoI is influenced by a balance between increased peripheral-placental and decreased cerebral resistances. Personalizing the model allows for quantifying the balance between cerebral and peripheral-placental remodeling, thus providing potentially novel information to aid clinical follow up.

The aim of this paper is to develop a registration methodology in order to combine anatomical and functional information provided by thoracic/abdominal computed tomography (CT) and whole-body positron emission tomography (PET) images. The proposed procedure is based on the incorporation of prior anatomical information in an intensity-based nonrigid registration algorithm. This incorporation is achieved in an explicit way, initializing the intensity-based registration stage with the solution obtained by a nonrigid registration of corresponding anatomical structures. A segmentation algorithm based on a hierarchically ordered set of anatomy-specific rules is used to obtain anatomical structures in CT and emission PET scans. Nonrigid deformations are modeled in both registration stages by means of free-form deformations, the optimization of the control points being achieved by means of an original vector field-based approach instead of the classical gradient-based techniques, considerably reducing the computational time of the structure registration stage. We have applied the proposed methodology to 38 sets of images (33 provided by standalone machines and five by hybrid systems) and an assessment protocol has been developed to furnish a qualitative evaluation of the algorithm performance.

The main goal of this work is the generation of ground-truth data for the validation of atrophy measurement techniques, commonly used in the study of neurodegenerative diseases such as dementia. Several techniques have been used to measure atrophy in cross-sectional and longitudinal studies, but it is extremely difficult to compare their performance since they have been applied to different patient populations. Furthermore, assessment of performance based on phantom measurements or simple scaled images overestimates these techniques' ability to capture the complexity of neurodegeneration of the human brain. We propose a method for atrophy simulation in structural magnetic resonance (MR) images based on finite-element methods. The method produces cohorts of brain images with known change that is physically and clinically plausible, providing data for objective evaluation of atrophy measurement techniques. Atrophy is simulated in different tissue compartments or in different neuroanatomical structures with a phenomenological model. This model of diffuse global and regional atrophy is based on volumetric measurements such as the brain or the hippocampus, from patients with known disease and guided by clinical knowledge of the relative pathological involvement of regions and tissues. The consequent biomechanical readjustment of structures is modelled using conventional physics-based techniques based on biomechanical tissue properties and simulating plausible tissue deformations with finite-element methods. A thermoelastic model of tissue deformation is employed, controlling the rate of progression of atrophy by means of a set of thermal coefficients, each one corresponding to a different type of tissue. Tissue characterization is performed by means of the meshing of a labelled brain atlas, creating a reference volumetric mesh that will be introduced to a finite-element solver to create the simulated deformations. Preliminary work on the simulation of acquisition artefacts is also presented. Cross-sectional and longitudinal sets of simulated data are shown and a visual classification protocol has been used by experts to rate real and simulated scans according to their degree of atrophy. Results confirm the potential of the proposed methodology.

Measures of overlap of labelled regions of images, such as the Dice and Tanimoto coefficients, have been extensively used to evaluate image registration and segmentation algorithms. Modern studies can include multiple labels defined on multiple images yet most evaluation schemes report one overlap per labelled region, simply averaged over multiple images. In this paper, common overlap measures are generalized to measure the total overlap of ensembles of labels defined on multiple test images and account for fractional labels using fuzzy set theory. This framework allows a single "figure-of-merit" to be reported which summarises the results of a complex experiment by image pair, by label or overall. A complementary measure of error, the overlap distance, is defined which captures the spatial extent of the nonoverlapping part and is related to the Hausdorff distance computed on grey level images. The generalized overlap measures are validated on synthetic images for which the overlap can be computed analytically and used as similarity measures in nonrigid registration of three-dimensional magnetic resonance imaging (MRI) brain images. Finally, a pragmatic segmentation ground truth is constructed by registering a magnetic resonance atlas brain to 20 individual scans, and used with the overlap measures to evaluate publicly available brain segmentation algorithms.