Disentanglement enables cross-domain Hippocampus Segmentation
This work addresses domain adaptation for medical imaging, specifically hippocampus segmentation, which is critical for diagnosing neuropsychiatric disorders, but it appears incremental as it builds on existing GAN and UNet methods.
The paper tackles the problem of limited labeled data and domain differences in hippocampus segmentation from MRI scans by disentangling images into content and domain components, enabling domain transfer and improving segmentation quality on unseen domains by 6-13%.
Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic resonance imaging (MRI) scans is critical for the diagnosis and treatment of neuropsychatric disorders. Domain differences in contrast or shape can significantly affect segmentation. We address this issue by disentangling a T1-weighted MRI image into its content and domain. This separation enables us to perform a domain transfer and thus convert data from new sources into the training domain. This step thus simplifies the segmentation problem, resulting in higher quality segmentations. We achieve the disentanglement with the proposed novel methodology 'Content Domain Disentanglement GAN', and we propose to retrain the UNet on the transformed outputs to deal with GAN-specific artefacts. With these changes, we are able to improve performance on unseen domains by 6-13% and outperform state-of-the-art domain transfer methods.