Fig. 4From: An artificial intelligence model for the pathological diagnosis of invasion depth and histologic grade in bladder cancerPerformance of the PAIDM in two validation sets. a ROC curves for patch-level diagnostic performance in validation set 1. b ROC curves for WSI-level classification performance in validation set 2. PAIDM  pathological artificial intelligence diagnostic model, ROC  receiver operating characteristic, WSI  whole slide image, AUC  area under the curve, HGMI  high-grade muscle invasion, HGNMI  high-grade non-muscle invasion, LGNMI  low-grade non-muscle invasionBack to article page