Advances in automated fetal brain MRI segmentation and biometry : insights from the FeTA 2024 challenge

Zalevskyi, Vladyslav (author), Sanchez, Thomas (author), Kaandorp, Misha (author), Roulet, Margaux (author), Fajardo-Rojas, Diego (author), Liu, Li (author), Hutter, Jana (author), Bran Li, Hongwei (author), Barkovich, Matthew J. (author), Ji, Hui (author), Preložnik, Domen (author), Špiclin, Žiga (author)

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 superresolution 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 gestationalage-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.

• Language: English
• Keywords: fetal brain, magnetic resonance imaging, low-field segmentation, topology, biometry, domain shift, challenge results
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: 22 str.
• Numbering: Vol. 109, art. 103941
• PID: 20.500.12556/RUL-178379
• UDC: 004.93:61
• ISSN on article: 1361-8415
• DOI: 10.1016/j.media.2026.103941
• COBISS.SI-ID: 265974787

Note

V objavljenem članku je navedenih veliko virov financiranja raziskave

• Publication date in RUL: 26.01.2026

Record is a part of a journal

• Title: Medical image analysis
• Shortened title: Med. image anal.
• Publisher: Oxford University Press
• ISSN: 1361-8415
• COBISS.SI-ID: 1238293

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: možgani ploda, magnetnoresonančno slikanje, segmentacija slik pri šibkem magnetnem polju, topologija, biometrija, premestitev domene, rezultati računskega izziva