Exploring Test Time Adaptation for Subcortical Segmentation of the Fetal Brain in 3D Ultrasound
This work addresses the challenge of adapting pretrained models for fetal brain monitoring in ultrasound, which is incremental as it builds on existing test time adaptation techniques with a specific anatomical prior.
The paper tackles the problem of performance degradation in automated subcortical segmentation of fetal brain 3D ultrasound images due to domain shifts, and proposes a novel test time adaptation method that incorporates a normative atlas to improve results, demonstrating enhancements over existing methods.
Monitoring the growth of subcortical regions of the fetal brain in ultrasound (US) images can help identify the presence of abnormal development. Manually segmenting these regions is a challenging task, but recent work has shown that it can be automated using deep learning. However, applying pretrained models to unseen freehand US volumes often leads to a degradation of performance due to the vast differences in acquisition and alignment. In this work, we first demonstrate that test time adaptation (TTA) can be used to improve model performance in the presence of both real and simulated domain shifts. We further propose a novel TTA method by incorporating a normative atlas as a prior for anatomy. In the presence of various types of domain shifts, we benchmark the performance of different TTA methods and demonstrate the improvements brought by our proposed approach, which may further facilitate automated monitoring of fetal brain development. Our code is available at https://github.com/joshuaomolegan/TTA-for-3D-Fetal-Subcortical-Segmentation.