Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Network

TL;DR

This paper presents a CNN-based method for automated prostate cancer grading using whole slide histopathology images, incorporating novel data augmentation, distribution correction, and a specialized loss function to improve accuracy and match expert-level performance.

Contribution

It introduces a comprehensive CNN framework with innovative data augmentation, distribution correction, and a new loss function for accurate prostate cancer grading from WSIs.

Findings

Achieved a quadratic-weighted kappa coefficient of 0.8885.

Demonstrated superior performance over existing methods.

Validated effectiveness of PBIR, DC, and QWMSE in improving accuracy.

Abstract

The Gleason grading system using histological images is the most powerful diagnostic and prognostic predictor of prostate cancer. The current standard inspection is evaluating Gleason H&E-stained histopathology images by pathologists. However, it is complicated, time-consuming, and subject to observers. Deep learning (DL) based-methods that automatically learn image features and achieve higher generalization ability have attracted significant attention. However, challenges remain especially using DL to train the whole slide image (WSI), a predominant clinical source in the current diagnostic setting, containing billions of pixels, morphological heterogeneity, and artifacts. Hence, we proposed a convolutional neural network (CNN)-based automatic classification method for accurate grading of PCa using whole slide histopathology images. In this paper, a data augmentation method named Patch-Based Image Reconstruction (PBIR) was proposed to reduce the high resolution and increase the diversity of WSIs. In addition, a distribution correction (DC) module was developed to enhance the adaption of pretrained model to the target dataset by adjusting the data distribution. Besides, a Quadratic Weighted Mean Square Error (QWMSE) function was presented to reduce the misdiagnosis caused by equal Euclidean distances. Our experiments indicated the combination of PBIR, DC, and QWMSE function was necessary for achieving superior expert-level performance, leading to the best results (0.8885 quadratic-weighted kappa coefficient).