Deep Learning for Prostate Pathology

TL;DR

This study develops and evaluates deep learning models for detecting and annotating prostate pathology features in diverse histology images, achieving high accuracy and robustness across different data sources and staining protocols.

Contribution

The paper introduces a comprehensive deep learning approach that effectively detects multiple prostate pathology morphologies across varied image qualities and sources, aiding clinical annotation tasks.

Findings

True positive rate for prostate cancer slides was 99.7%.

F1-scores for Gleason patterns ranged from 0.795 to 1.0.

Correlation of 0.987 between predicted and true tumor volume.

Abstract

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.