Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realism Constraints
A stable semi-supervised virtual staining framework that jointly exploits both limited paired data and abundant unpaired source images is proposed, which suppress structural and appearance drift, stabilize semi-supervised stain translation, and promote the preservation of diagnostically relevant information.
Baoshun Wang, Weiping Lin, Lin-Wu Wang et al.
· 0 citations