7T to 3T domain adaptation in white matter lesion segmentation on T2-weighted (T2-w) FLAIR images using deep learning
Jinghang Li, Eduardo de Oliveira Diniz, Taylor Forry, Tamer Ibrahim, Howard Jay Aizenstein, Minjie Wu · Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2024
In this work, we explored the domain adaptation problem in deep learning segmentation. Specifically, we applied the residual U-net [1] on 3T and 7T Fluid Attenuated Inverse Recovery (FLAIR) images to delineate the white matter hyperintensity (WMH) in a 2D fashion. We leveraged learning without forgetting [2] to regulate the network’s learning in the new domain to preserve the model’s performance on the old domain while still achieving satisfying results on the new domain images.