Synthetic magnetic resonance images for domain adaptation: Application to fetal brain tissue segmentation
This work addresses the challenge of domain adaptation for fetal brain tissue segmentation, offering an incremental improvement by leveraging synthetic data to enhance model robustness.
The paper tackled the problem of limited annotated fetal brain MRI data for training segmentation algorithms by using a numerical phantom to generate synthetic images, which significantly improved segmentation accuracy in multiple brain tissues.
The quantitative assessment of the developing human brain in utero is crucial to fully understand neurodevelopment. Thus, automated multi-tissue fetal brain segmentation algorithms are being developed, which in turn require annotated data to be trained. However, the available annotated fetal brain datasets are limited in number and heterogeneity, hampering domain adaptation strategies for robust segmentation. In this context, we use FaBiAN, a Fetal Brain magnetic resonance Acquisition Numerical phantom, to simulate various realistic magnetic resonance images of the fetal brain along with its class labels. We demonstrate that these multiple synthetic annotated data, generated at no cost and further reconstructed using the target super-resolution technique, can be successfully used for domain adaptation of a deep learning method that segments seven brain tissues. Overall, the accuracy of the segmentation is significantly enhanced, especially in the cortical gray matter, the white matter, the cerebellum, the deep gray matter and the brain stem.