Publications

dc.title: Towards contrast- and pathology-agnostic clinical fetal brain MRI segmentation using SynthSeg dc.contributor.author: Shang, Ziyao; Kaandorp, Misha; Payette, Kelly; Fernandez Garcia, Marina; Licandro, Roxane; Langs, Georg; Aviles Verdera, Jordina; Hutter, Jana; Menze, Bjoern; Kasprian, Gregor; Bach Cuadra, Meritxell; Jakab, Andras dc.description.abstract: Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines. Copyright © 2026 The Author(s). Published by Elsevier Inc. All rights reserved.

dc.title: Advances in automated fetal brain MRI segmentation and biometry: Insights from the FeTA 2024 challenge dc.contributor.author: Zalevskyi, Vladyslav; Sanchez, Thomas; Kaandorp, Misha; Roulet, Margaux; Fajardo-Rojas, Diego; Li, Liu; Hutter, Jana; Li, Hongwei Bran; Barkovich, Matthew J; Ji, Hui; Wilhelmi, Luca; Dändliker, Aline; Steger, Céline; Koob, Mériam; Gomez, Yvan; Jakovčić, Anton; Klaić, Melita; Adžić, Ana; Marković, Pavel; Grabarić, Gracia; Rados, Milan; Aviles Verdera, Jordina; Kasprian, Gregor; Dovjak, Gregor; Gaubert-Rachmühl, Raphael; Aschwanden, Maurice; Zeng, Qi; Karimi, Davood; Peruzzo, Denis; Ciceri, Tommaso; Longari, Giorgio; Hamadache, Rachika E; Bouzid, Amina; Lladó, Xavier; Chiarella, Simone; Martí-Juan, Gerard; González Ballester, Miguel Ángel; Castellaro, Marco; Pinamonti, Marco; Visani, Valentina; Cremese, Robin; Sam, Keïn; Gaudfernau, Fleur; Ahir, Param; Parikh, Mehul; Zenk, Maximilian; Baumgartner, Michael; Maier-Hein, Klaus; Tianhong, Li; Hong, Yang; Longfei, Zhao; Preloznik, Domen; Špiclin, Žiga; Won Choi, Jae; Li, Muyang; Fu, Jia; Wang, Guotai; Jiang, Jingwen; Tong, Lyuyang; Du, Bo; Gondova, Andrea; You, Sungmin; Im, Kiho; Qayyum, Abdul; Mazher, Moona; Niederer, Steven A; Jakab, Andras; Licandro, Roxane; Payette, Kelly; Bach Cuadra, Meritxell dc.description.abstract: Accurate fetal brain tissue segmentation and biometric measurement are essential for monitoring neurodevelopment and detecting abnormalities in utero. The Fetal Tissue Annotation (FeTA) Challenges have established robust multi-center benchmarks for evaluating state-of-the-art segmentation methods. This paper presents the results of the 2024 challenge edition, which introduced three key innovations. First, we introduced a topology-aware metric based on the Euler characteristic difference (ED) to overcome the performance plateau observed with traditional metrics like Dice or Hausdorff distance (HD), as the performance of the best models in segmentation surpassed the inter-rater variability. While the best teams reached similar scores in Dice (0.81-0.82) and HD95 (2.1-2.3 mm), ED provided greater discriminative power: the winning method achieved an ED of 20.9, representing roughly a 50% improvement over the second- and third-ranked teams despite comparable Dice scores. Second, we introduced a new 0.55T low-field MRI test set, which, when paired with high-quality super-resolution reconstruction, achieved the highest segmentation performance across all test cohorts (Dice=0.86, HD95=1.69, ED=6.26). This provides the first quantitative evidence that low-cost, low-field MRI can match or surpass high-field systems in automated fetal brain segmentation. Third, the new biometry estimation task exposed a clear performance gap: although the best model reached a mean average percentage error (MAPE) of 7.72%, most submissions failed to outperform a simple gestational-age-based linear regression model (MAPE=9.56%), and all remained above inter-rater variability with a MAPE of 5.38%. Finally, by analyzing the top-performing models from FeTA 2024 alongside those from previous challenge editions, we identify ensembles of 3D nnU-Net trained on both real and synthetic data with both image- and anatomy-level augmentations as the most effective approaches for fetal brain segmentation. Our quantitative analysis reveals that acquisition site, super-resolution strategy, and image quality are the primary sources of domain shift, informing recommendations to enhance the robustness and generalizability of automated fetal brain analysis methods. Copyright © 2026 The Author(s). Published by Elsevier B.V. All rights reserved.

dc.title: Towards trustworthy AI for the analysis of MRI biomarkers in multiple sclerosis dc.contributor.author: Molchanova, Nataliia dc.description.abstract: The rapid development and widespread adoption of artificial intelligence (AI) introduce new challenges, particularly when these methods are applied to high-risk domains. In response, the concept of Trustworthy AI has emerged, emphasizing the need for privacy, fairness, and transparency in critical applications. This thesis focuses specifically on the reliability of deep learning (DL) models to support the care of patients with multiple sclerosis (MS). The use of DL to automatically assess magnetic resonance imaging (MRI) for MS diagnosis and monitoring has been explored previously. These methods offer several advantages, including speed, cost-efficiency, and reproducibility, due to their deterministic nature and ability to produce results in near real-time. However, despite these benefits, such methods have not been widely adopted in clinical or research settings. The central hypothesis of this work is that the lack of transparency and trust in AI systems contributes significantly to their limited clinical integration. Recent developments, such as policy regulations, research initiatives, and professional guidelines, support this view. To address these concerns, the thesis involved close collaboration with medical professionals, engineers, and user experience designers to evaluate and improve the reliability of DL models. The work began with the development of DL methods for the segmentation of white matter and cortical lesions, two distinct MS biomarkers visible in MRI. Initial experiments revealed notable performance limitations, likely due to the ambiguity in lesion definitions and the limited availability of high-quality annotated data. This led to the first objective: uncertainty quantification (UQ) in DL models, addressing both aleatoric and epistemic sources. We examined how uncertainty relates to different types of model errors across multiple anatomical scales. The second objective focused on interpreting model behavior, specifically testing the hypothesis that uncertainty may convey complementary information beyond prediction error. The third objective was to assess the clinical alignment of the developed tools. This was achieved through continuous collaboration with medical experts, who provided both informal and formal feedback. Finally, the fourth aim addressed benchmarking: for both white matter and cortical lesions, we developed multi-center evaluation pipelines to assess DL or UQ performance using both in- and out-of-domain settings. Overall, this thesis identifies several technical and methodological approaches for improving the reliability of DL models in MS imaging. While the proposed approaches do not resolve all current limitations, they contribute to a better understanding of how DL systems can be aligned with clinical expectations. Realizing this potential will require sustained interdisciplinary collaboration and continued focus on trustworthiness, usability, and clinical integration.

dc.title: ConfLUNet: Multiple sclerosis lesion instance segmentation in presence of confluent lesions dc.contributor.author: Wynen, Maxence; Gordaliza, Pedro M; Istasse, Maxime; Stölting, Anna; Maggi, Pietro; Macq, Benoît; Bach Cuadra, Meritxell dc.description.abstract: Accurate lesion-level segmentation on MRI is critical for multiple sclerosis (MS) diagnosis, prognosis, and disease monitoring. However, current evaluation practices largely rely on semantic segmentation post-processed with connected components (CC), which cannot separate confluent lesions (aggregates of confluent lesion units, CLUs) due to reliance on spatial connectivity. To address this misalignment with clinical needs, we introduce formal definitions of CLUs and associated CLU-aware detection metrics, and include them in an exhaustive instance segmentation evaluation framework. Within this framework, we systematically evaluate CC and post-processing-based Automated Confluent Splitting (ACLS), the only existing methods for lesion instance segmentation in MS. Our analysis reveals that CC consistently underestimates CLU counts, while ACLS tends to oversplit lesions, leading to overestimated lesion counts and reduced precision. To overcome these limitations, we propose ConfLUNet, the first end-to-end instance segmentation framework for MS lesions. ConfLUNet jointly optimizes lesion detection and delineation from a single FLAIR image. Trained on 50 patients, ConfLUNet significantly outperforms CC and ACLS on the held-out test set (n = 13) in instance segmentation (Panoptic Quality: 42.0% vs. 37.5%/36.8%; p = 0.017/0.005) and lesion detection (F1: 67.3% vs. 61.6%/59.9%; p = 0.028/0.013). For CLU detection, ConfLUNet achieves the highest textF1^CLU (81.5%), improving recall over CC (+12.5%, p = 0.015) and precision over ACLS (+31.2%, p = 0.003). By combining rigorous definitions, new CLU-aware metrics, a reproducible evaluation framework, and the first dedicated end-to-end model, this work lays the foundation for lesion instance segmentation in MS. Copyright © 2025 The Authors. Published by Elsevier Ltd.. All rights reserved.

dc.title: Deep Learning for fODF Estimation in Infant Brains: Model Comparison, Ground-Truth Impact, and Domain Shift Mitigation dc.contributor.author: Lin, Rizhong; Kebiri, Hamza; Gholipour, Ali; Chen, Yufei; Thiran, Jean-Philippe; Karimi, Davood; Bach Cuadra, Meritxell dc.description.abstract: The accurate estimation of fiber orientation distribution functions (fODFs) in diffusion magnetic resonance imaging (MRI) is crucial for understanding early brain development and its potential disruptions. Although supervised deep learning (DL) models have shown promise in fODF estimation from neonatal diffusion MRI (dMRI) data, the out-of-domain (OOD) performance of these models remains largely unexplored, especially under diverse domain shift scenarios. This study evaluated the robustness of three state-of-the-art DL architectures: multilayer perceptron (MLP), transformer, and U-Net/convolutional neural network (CNN) on fODF predictions derived from dMRI data. Using 488 subjects from the developing Human Connectome Project (dHCP) and the Baby Connectome Project (BCP) datasets, we reconstructed reference fODFs from the full dMRI series using single-shell three-tissue constrained spherical deconvolution (SS3T-CSD) and multi-shell multi-tissue CSD (MSMT-CSD) to generate reference fODF reconstructions for model training, and systematically assessed the impact of age, scanner/protocol differences, and input dimensionality on model performance. Our findings reveal that U-Net consistently outperformed other models when fewer diffusion gradient directions were used, particularly with the SS3T-CSD-derived ground truth, which showed superior performance in capturing crossing fibers. However, as the number of input diffusion gradient directions increased, MLP and the transformer-based model exhibited steady gains in accuracy. Nevertheless, performance nearly plateaued from 28 to 45 input directions in all models. Age-related domain shifts showed asymmetric patterns, being less pronounced in late developmental stages (late neonates, and babies), with SS3T-CSD demonstrating greater robustness to variability compared to MSMT-CSD. To address inter-site domain shifts, we implemented two adaptation strategies: the Method of Moments (MoM) and fine-tuning. Both strategies achieved significant improvements ( p < 0.05 $$ p<0.05 $$ ) in over 95% of tested configurations, with fine-tuning consistently yielding superior results and U-Net benefiting the most from increased target subjects. This study represents the first systematic evaluation of OOD settings in DL applications to fODF estimation, providing critical insights into model robustness and adaptation strategies for diverse clinical and research applications. © 2025 The Author(s). Human Brain Mapping published by Wiley Periodicals LLC.

dc.title: Biometry and volumetry in multi-centric fetal brain magnetic resonance imaging: assessing the bias of super-resolution reconstruction dc.contributor.author: Sanchez, Thomas; Mihailov, Angeline; Koob, Mériam; Girard, Nadine; Manchon, Aurélie; Valenzuela, Ignacio; Gómez-Chiari, Marta; Martí Juan, Gerard; Pron, Alexandre; Eixarch, Elisenda; Piella, Gemma; Gonzalez Ballester, Miguel Angel; Camara, Oscar; Dunet, Vincent; Auzias, Guillaume; Bach Cuadra, Meritxell dc.description.abstract: Fetal brain MRI is increasingly used to complement ultrasound imaging. Images are processed using complex super-resolution reconstruction pipelines, which may bias biometric and volumetric measurements. To assess the consistency of 2-dimensional (D) biometric and 3-D volumetric measurements across three hospitals using three widely used super-resolution reconstruction pipelines. This retrospective multi-centric study used T2-weighted fetal brain MRI scans acquired at three hospitals between 2009 and 2023. MRIs from each subject were reconstructed with each super-resolution reconstruction method, and biometric measurements were performed by four experts. Automated 3-D volumetry was performed using a state-of-the-art segmentation method. A qualitative evaluation assessed the clinicians' likelihood of using super-resolution reconstructed volumes in their practice. Eighty-four healthy subjects were included. Biometric measurements revealed statistically significant changes that consistently remained below voxel width (0.8 mm; P<0.001). Automated 3-D volumetry revealed small systematic effects (<2.8%; P<0.001). The qualitative evaluation showed systematic differences between super-resolution reconstruction methods for the perception of white matter intensity (P=0.02) and sharpness of the image (P=0.01). Variations in 2-D and 3-D quantitative measurements did not show any large systematic bias when using different super-resolution reconstruction methods for clinical radiological assessment across centers, scanners, and raters. © 2025. The Author(s).

dc.title: A dataset of synthetic, maturation-informed magnetic resonance images of the human fetal brain. dc.contributor.author: Lajous, H.; Le Boeuf Fló, A.; Gordaliza, P.M.; Esteban, O.; Marques, F.; Dunet, V.; Koob, M.; Bach Cuadra, M. dc.description.abstract: Magnetic resonance imaging (MRI) is a powerful modality for investigating abnormal developmental patterns in utero. However, since it is not the first-line diagnostic tool in this sensitive population, data remain scarce and heterogeneous across scanners and hospitals. To address this, we present a novel dataset of synthetic images representative of real fetal brain MRI. Our dataset comprises 594 two-dimensional, low-resolution series of T ₂ -weighted images corresponding to 78 developing human fetal brains between 20.0 and 34.8 weeks of gestational age. Data are generated using a new version of the Fetal Brain MR Acquisition Numerical phantom (FaBiAN) to account for local white matter heterogeneities throughout maturation. Both healthy and pathological anatomies are simulated with standard clinical settings. Two independent radiologists qualitatively assessed the realism of the simulated images. A quantitative analysis confirms an enhanced fidelity compared to the original version of the software, with further validation through its applicability to fetal brain tissue segmentation. The cohort is publicly available to support the continuous endeavor of developing advanced post-processing methods as well as cutting-edge artificial intelligence models.

dc.title: Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results. dc.contributor.author: Payette, K.; Steger, C.; Licandro, R.; Dumast, P.; Li, H.B.; Barkovich, M.; Li, L.; Dannecker, M.; Chen, C.; Ouyang, C.; McConnell, N.; Miron, A.; Li, Y.; Uus, A.; Grigorescu, I.; Gilliland, P.R.; Siddiquee, MMR; Xu, D.; Myronenko, A.; Wang, H.; Huang, Z.; Ye, J.; Alenya, M.; Comte, V.; Camara, O.; Masson, J.B.; Nilsson, A.; Godard, C.; Mazher, M.; Qayyum, A.; Gao, Y.; Zhou, H.; Gao, S.; Fu, J.; Dong, G.; Wang, G.; Rieu, Z.; Yang, H.; Lee, M.; Plotka, S.; Grzeszczyk, M.K.; Sitek, A.; Daza, L.V.; Usma, S.; Arbelaez, P.; Lu, W.; Zhang, W.; Liang, J.; Valabregue, R.; Joshi, A.A.; Nayak, K.N.; Leahy, R.M.; Wilhelmi, L.; Dandliker, A.; Ji, H.; Gennari, A.G.; Jakovcic, A.; Klaic, M.; Adzic, A.; Markovic, P.; Grabaric, G.; Kasprian, G.; Dovjak, G.; Rados, M.; Vasung, L.; Cuadra, M.B.; Jakab, A. dc.description.abstract: 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.

dc.title: Assessment of fetal corpus callosum biometry by 3D super-resolution reconstructed T2-weighted magnetic resonance imaging dc.contributor.author: Lamon, Samuel dc.description.abstract: Le corps calleux (CC) est une structure cérébrale clé jouant un rôle fondamental dans l’intégration des fonctions cérébrales latéralisées. Chez les 0.3 à 0.7% des personnes venant au monde avec un corps calleux absent, que ce soit totalement ou partiellement, le développement neurologique est étrangement variable. L’évaluation prénatale du CC est essentielle et passe par une appréciation biométrique précise qui contribue à établir un pronostic et à anticiper les soins anté- et post-nataux. L’évaluation prénatale du CC s’appuie sur deux modalités d’imagerie complémentaires : l’échographie (US) qui est utilisée pour le dépistage et l’imagerie par résonance magnétique (IRM) pondérée T2 (T2WS) pour compléter le bilan. L’IRM foetale clinique présente néanmoins certaines limitations comme les artéfacts induits par les mouvements imprévisibles du fœtus et la résolution spatiale limite en dehors du plan d’acquisition. Afin de surmonter ces obstacles, une nouvelle technique - l'IRM super-résolution (SR) - a été développée. Elle repose sur des algorithmes de correction de mouvements et d’interpolation de données et permet d’obtenir un volume en 3D de meilleure résolution dans les trois orientations de l’espace. Bien que prometteuse, l'intégration de cette technique en clinique reste un défi. Une validation par rapport aux références actuelles, notamment à l’échographie, est nécessaire avant d’envisager son implémentation. Cette étude y contribue en évaluant la précision de la biométrie du CC en utilisant la SR, comparée à l’échographie et à l’IRM conventionnelle (T2WS). Pour ce faire, nous avons rétrospectivement sélectionné une population de 57 fœtus ayant bénéficié d’IRM cérébrales (et d’US) entre 2014 et 2021 au CHUV. La longueur du CC, la hauteur de ses 4 segments (rostrum, genou, corps et splenium) ainsi que son aire ont été mesurées par deux observateurs : Le premier, junior, supervisé directement pour la lecture des US et le deuxième - senior. L’analyse statistique a principalement porté sur une comparaison entre les modalités et entre les observateurs. Nos résultats montrent que la SR, grâce à son approche multiplanaire et à sa meilleure résolution spatiale isotropique à 1mm, présente un taux nettement plus faible de segments du CC non-visualisés par rapport à l'US et à la T2WS. Ces omissions concernaient principalement le segment rostral du CC. En termes de biométrie, les mesures de la longueur du CC (LCC) et des segment postérieurs et moyens étaient similaires entre les modalités d’image etudiées. Cependant, des différences ont été observées pour les segments antérieurs (rostrum et genou), qui restent difficiles à mesurer même en SR. Nous avançons plusieurs hypothèses pour expliquer cette difficulté persistante, comme la taille millimétrique du rostrum, se heurtant à l’effet du volume partiel et le rôle de l’environnement liquidien variable du cerveau foetal. L’étude a également validé des régression linéaires pour la LCC et introduit des valeurs normatives auparavant inexistantes pour les hauteurs des sous-segments du CC en T2WS et en SR. Bien que cette étude présente des résultats prometteurs, la portée de ses conclusions est réduite par sa nature rétrospective, son faible effectif, l’absence de données d’imagerie post-natale et de suivi clinique à long terme ainsi que par un intervalle toléré de 2 semaines entre les US et les IRM. En termes de perspectives, les recherches futures devraient inclure des cohortes plus importantes, notamment de patients avec agénésie partiel calleuse, et un suivi clinique prolongé. D’un point de vue ingénierie, des progrès vers l’automatisation complète du processus de reconstruction SR doivent être encouragés. En conclusion, cette étude montre que la SR permet une évaluation fiable et plus fréquemment possible de la longueur du CC et des hauteurs des segments postérieurs et moyens du CC, même si son utilisation ne peut pas encore être appliquée dans la pratique clinique courante. En cas de difficultés d'évaluation par US, la SR pourrait offrir une alternative précieuse. Des recherches supplémentaires sont cependant nécessaires pour valider cette technique et faciliter son intégration dans la pratique clinique courante. La SR pourrait ainsi devenir un outil essentiel pour mieux comprendre les anomalies du CC et leur impact sur le développement neurologique global. Soulignons pour le mot de la fin l’excellent exemple de collaboration entre cliniciens et ingénieurs que cette étude a représenté.

dc.title: Functional organization of the neonatal thalamus across development depicted by functional MRI dc.contributor.author: Kebiri, Hamza; Delavari, Farnaz; Van De Ville, Dimitri; Jorge, João; Cuadra, Meritxell Bach dc.description.abstract: The thalamus is a central component of the brain that is involved in a variety of functions, from sensory processing to high-order cognition. Its structure and function in the first weeks of extrauterine life, including its connections to different cortical and subcortical areas, have not yet been widely explored. Here, we used functional magnetic resonance imaging data of 588 newborns during natural sleep from the developing Human Connectome Project to study the functional organization of the thalamus from 37 to 44 post-conceptual weeks. We introduce KNIT: K-means for Nuclei in Infant Thalamus. The framework employs a highly granular vector space of 40 features, each corresponding to functional connectivity to a brain region, using k-means clustering and uncertainty quantification through bootstrapping to delineate thalamic units. Although the different clusters showed common patterns of increased connectivity to the superior temporal gyrus, the parietal, and the frontal cortex, implying an expected decrease in specialization at that age, they also show some specificity. That is, a pulvinar unit was identified, similar to the adult thalamus. Ventrolateral motor and medial salience units were also highlighted. The latter appeared around 41 weeks of age, while the former showed at least from 37 weeks, but had a decrease in relative volume through age, replaced mostly by a dominant dorsal thalamic unit. We also observed an increase in clustering robustness and in hemispheric bilateral symmetry with age, suggesting more specialized functional units. We also found a burst in global thalamic connectivity around 41 weeks. Finally, we demonstrate the benefits of this method in terms of granularity compared to the more conventional winner-takes-all approach. © 2025 The Authors. Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.