Fig. 3From: An artificial intelligence model for the pathological diagnosis of invasion depth and histologic grade in bladder cancerExamples of manual annotation and automatic tissue segmentation. a Manual annotation by pathologists. b Heatmaps generated by the PAIDM. c Masks predicted by the PAIDM. PAIDM  pathological artificial intelligence diagnostic model, HGMI  high-grade muscle invasion, HGNMI  high-grade non-muscle invasion, LGNMI  low-grade non-muscle invasion, IA illegible area, NIA  normal interstitial area, NA  noise areaBack to article page