Advances in Automated Fetal Brain MRI Segmentation and Biometry: Insights from the FeTA 2024 Challenge

2025-05-05

AI Summary

Accurate and robust automatic segmentation and biometric analysis of fetal brain MRI remain challenging due to domain shift and topological errors across multi-center, multi-field-strength settings—including pioneering 0.55T low-field data. Method: We propose a dual-task evaluation framework jointly modeling tissue segmentation and biometric prediction; introduce a topology-aware metric—Euler characteristic difference (ED)—to quantify structural connectivity deficits undetected by conventional metrics (e.g., Dice); and integrate super-resolution preprocessing with domain adaptation to enhance low-field performance. Results: Among 16 participating segmentation methods, the best achieved inter-rater variability comparable to expert human annotations, with superior performance on low-field data; ED effectively identified clinically significant topological errors; and none of the seven biometric prediction models outperformed gestational age–based baselines. This work advances the clinical reliability of automated fetal neuroimaging analysis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Accurate fetal brain tissue segmentation and biometric analysis are essential for studying brain development in utero. The FeTA Challenge 2024 advanced automated fetal brain MRI analysis by introducing biometry prediction as a new task alongside tissue segmentation. For the first time, our diverse multi-centric test set included data from a new low-field (0.55T) MRI dataset. Evaluation metrics were also expanded to include the topology-specific Euler characteristic difference (ED). Sixteen teams submitted segmentation methods, most of which performed consistently across both high- and low-field scans. However, longitudinal trends indicate that segmentation accuracy may be reaching a plateau, with results now approaching inter-rater variability. The ED metric uncovered topological differences that were missed by conventional metrics, while the low-field dataset achieved the highest segmentation scores, highlighting the potential of affordable imaging systems when paired with high-quality reconstruction. Seven teams participated in the biometry task, but most methods failed to outperform a simple baseline that predicted measurements based solely on gestational age, underscoring the challenge of extracting reliable biometric estimates from image data alone. Domain shift analysis identified image quality as the most significant factor affecting model generalization, with super-resolution pipelines also playing a substantial role. Other factors, such as gestational age, pathology, and acquisition site, had smaller, though still measurable, effects. Overall, FeTA 2024 offers a comprehensive benchmark for multi-class segmentation and biometry estimation in fetal brain MRI, underscoring the need for data-centric approaches, improved topological evaluation, and greater dataset diversity to enable clinically robust and generalizable AI tools.

Problem

• Advancing automated fetal brain MRI segmentation and biometry analysis
• Evaluating performance across high- and low-field MRI datasets
• Addressing domain shift and improving AI model generalization

Innovation

• Introduced biometry prediction alongside tissue segmentation
• Included low-field MRI dataset for diverse testing
• Used topology-specific Euler characteristic difference metric