.png){kind=icon}
.png){kind=icon}
Return
Prioritized scanning: Combining spatial information multiple instance learning for computational pathology
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113151.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose PSMIL, a spatially enhanced MIL framework for WSI classification. • Spatial branch models local tissue context via 2D positions and SSM. • Cross-spatial branch captures global dependencies with significance scoring. • PSMIL achieves up to 5.26% ACC gain on 5 datasets across 3 tasks.