Repositorio Digital de la UPF
Publicación
Artículo científico (JournalArticle)
Advances in automated fetal brain MRI segmentation and biometry: insights from the FeTA 2024 challenge
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., This research was funded by the Swiss National Science Foundation (182602, 215641, IZKSZ3_218590), ERA-NET Neuron MULTI-FACT project (SNSF 31NE30 203977), UKRI FLF (MR/T018119/1), the Adaptive Brain Circuits in Development and Learning Project, University Research Priority Program of the University of Zürich; by the Vontobel Foundation; by the Anna Müller Grocholski Foundation and the Prof. Max Cloetta Foundation and DFG Heisenberg funding (502024488); we acknowledge the Leenaards and Jeantet Foundations as well as CIBM Center for Biomedical Imaging, a Swiss research center of excellence founded and supported by CHUV, UNIL, EPFL, UNIGE and HUG. Diego Fajardo-Rojas would like to acknowledge funding from the EPSRC Centre for Doctoral Training in Smart Medical Imaging (EP/S022104/1). Lyuyang Tong, Bo Du and Jingwen Jiang would like to acknowledge funding from the National Key Research and Development Program of China under Grants 2023YFC2705700, the National Natural Science Foundation of China under Grants 62,306,217 and 62225113, the Postdoctoral Fellowship Program of CPSF under Grant Number GZC20231987, the China Postdoctoral Science Foundation under Grant Number 2024T170686 and 2024M752471, the Major Program (JD) of Hubei Province (2023BAA017), the Innovative Research Group Project of Hubei Province under Grants 2024AFA017. Gerard Martí-Juan is supported by the project PCI2021-122044-2A, funded by the project ERA-NET NEURON Cofund2, by MCIN/AEI/10.13039/501100011033/ and by the European Union NextGenerationEU/PRTR. R. Hamadache holds an IFUdG PhD grant from the University of Girona. R. Hamadache and X. Lladó received support by the PID2023-146187OB-I00 from the Ministerio de Ciencia e Innovación, Spain. Kiho Im, A. Gondova, and S. You received support from the National Institute of Neurological Disorders and Stroke (R01NS114087) and National Institute of Biomedical Imaging and Bioengineering (R01EB031170) of the National Institutes of Health (NIH).