The current study detects different morphologies related to prostate pathology using deep learning models; these models were evaluated on 2,121 hematoxylin and eosin (H&E) stain histology images captured using bright field microscopy, which spanned a variety of image qualities, origins (whole slide, tissue micro array, whole mount, Internet), scanning machines, timestamps, H&E staining protocols, and institutions. For case usage, these models were applied for the annotation tasks in clinician-oriented pathology reports for prostatectomy specimens. The true positive rate (TPR) for slides with prostate cancer was 99.7% by a false positive rate of 0.785%. The F1-scores of Gleason patterns reported in pathology reports ranged from 0.795 to 1.0 at the case level. TPR was 93.6% for the cribriform morphology and 72.6% for the ductal morphology. The correlation between the ground truth and the prediction for the relative tumor volume was 0.987 n. Our models cover the major components of prostate pathology and successfully accomplish the annotation tasks.
@article{arxiv.1910.04918,
title = {Deep Learning for Prostate Pathology},
author = {Okyaz Eminaga and Yuri Tolkach and Christian Kunder and Mahmood Abbas and Ryan Han and Rosalie Nolley and Axel Semjonow and Martin Boegemann and Sebastian Huss and Andreas Loening and Robert West and Geoffrey Sonn and Richard Fan and Olaf Bettendorf and James Brook and Daniel Rubin},
journal= {arXiv preprint arXiv:1910.04918},
year = {2019}
}