Domain generalization in fetal brain MRI segmentation \\with multi-reconstruction augmentation

TL;DR

This paper introduces a data augmentation technique using multi-reconstruction in fetal brain MRI to enhance the generalization of segmentation models, addressing dataset scarcity and variability issues.

Contribution

The study proposes a novel multi-reconstruction augmentation method leveraging super-resolution MRI reconstructions to improve fetal brain segmentation generalization.

Findings

Significant improvement in segmentation accuracy across different datasets.

Enhanced model robustness to variability in fetal MRI data.

Effective augmentation strategy without additional tuning requirements.

Abstract

Quantitative analysis of in utero human brain development is crucial for abnormal characterization. Magnetic resonance image (MRI) segmentation is therefore an asset for quantitative analysis. However, the development of automated segmentation methods is hampered by the scarce availability of fetal brain MRI annotated datasets and the limited variability within these cohorts. In this context, we propose to leverage the power of fetal brain MRI super-resolution (SR) reconstruction methods to generate multiple reconstructions of a single subject with different parameters, thus as an efficient tuning-free data augmentation strategy. Overall, the latter significantly improves the generalization of segmentation methods over SR pipelines.