Superpixel-Guided Graph-Attention Boundary GAN for Adaptive Feature Refinement in Scribble-Supervised Medical Image Segmentation

Fully supervised medical image segmentation still relies on labor-intensive, pixel-level annotations, which limits scale across cohorts and imaging settings. Scribble supervision reduces this burden, yet many CNN-based methods struggle under sparse labels due to weak global context and poor boundary...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Mansoor Hayat, Supavadee Aramvith
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IEEE 2025-01-01
Σειρά:	IEEE Access
Θέματα:	Scribble supervision weakly supervised medical segmentation superpixel-guided graph attention generative adversarial networks adaptive feature refinement
Διαθέσιμο Online:	https://ieeexplore.ieee.org/document/11251168/
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!