Cellpose-SAM Beats Inter-Expert Disagreement in Cell Segmentation

HHMI Janelia researchers released Cellpose-SAM, a SAM-based cell segmentation model that reduces error to 0.163, below the 25% disagreement rate between expert annotators, approaching the theoretical limit.

2026-11-10 ~ 2026-11-10 · 2 related posts

• Cellpose-SAM hits 0.163 error rate, beating expert disagreement in cellular segmentation — RichardsonDx · 2026-11-10
• Cellpose-SAM hits 0.163 error rate, beating human annotator disagreement on cell segmentation — RichardsonDx · 2026-11-10