Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation

arXiv:2404.08951v1 Announce Type: cross
Abstract: Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS). In this scenario, we handle data from multiple medical centers, with limited annotations available for a single domain and …

arxiv cs.cv cs.lg domain domains image intermediate medical mixed segmentation semi-supervised type