Machine Learning Based Classification from Whole-Slide Histopathological Images Enables Reliable and Interpretable Diagnosis of Inverted Urothelial Papilloma

Abstract

Inverted urothelial papilloma (IUP) is a benign neoplasm of the urinary tract that accounts for less than 1% of urothelial tumors. It is diagnostically challenging for pathologists to distinguish histological features of IUP from other subtypes of non-invasive urothelial carcinoma, such as inverted Ta urothelial carcinoma (UCInv) and low-grade Ta urothelial carcinoma (UCLG). Using a machine learning approach, we analyzed the H&E-stained whole-slide histopathological images of 64 IUP (the largest cohort to date), 69 UCInv, and 92 UCLG samples, and propose a reliable, reproducible, and interpretable machine learning pipeline to classify IUP from other non-invasive urothelial carcinomas. The results showed that our method could achieve area under the ROC of 0.913 and 0.920 for classifying IUP from UCInv and UCLG, respectively, which is superior to competing methods, including deep learning-based methods. Testing of the classification models on an external validation dataset confirmed that our model can effectively identify IUP with high accuracy. Our results suggest that the proposed machine learning pipeline can robustly and accurately capture histopathological differences between IUP and other urothelial carcinoma subtypes, which can be extended to identify other rare cancer subtypes with limited samples and has the potential to expand the clinician’s armamentarium for accurate diagnosis.