Path R-CNN for Prostate Cancer Diagnosis and Gleason Grading of Histological Images

TLDR

Prostate cancer is the most common and second most deadly cancer in U.S. men, and Gleason grading of histological images is critical for risk assessment and treatment planning, with multi‑task models offering complementary contextual information that improves performance. The study introduces a region‑based convolutional neural network framework that jointly predicts epithelial cells and Gleason grades using dedicated network heads. The framework employs a region‑based CNN with separate epithelial and grading heads to perform multi‑task prediction.

Abstract

Prostate cancer is the most common and second most deadly form of cancer in men in the United States. The classification of prostate cancers based on Gleason grading using histological images is important in risk assessment and treatment planning for patients. Here, we demonstrate a new region-based convolutional neural network framework for multi-task prediction using an epithelial network head and a grading network head. Compared with a single-task model, our multi-task model can provide complementary contextual information, which contributes to better performance. Our model is achieved a state-of-the-art performance in epithelial cells detection and Gleason grading tasks simultaneously. Using fivefold cross-validation, our model is achieved an epithelial cells detection accuracy of 99.07% with an average area under the curve of 0.998. As for Gleason grading, our model is obtained a mean intersection over union of 79.56% and an overall pixel accuracy of 89.40%.