Exploring Cycle Consistency Learning in Interactive Volume Segmentation

arXiv:2303.06493v2 Announce Type: replace
Abstract: Automatic medical volume segmentation often lacks clinical accuracy, necessitating further refinement. In this work, we interactively approach medical volume segmentation via two decoupled modules: interaction-to-segmentation and segmentation propagation. Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices. The user may repeat this process multiple times until a sufficiently high volume segmentation quality is achieved. However, due to the …

abstract accuracy arxiv clinical cs.cv interactive medical modules propagation segmentation slice type via work