Automated Gleason Grading and Gleason Pattern Region Segmentation Based on Deep Learning for Pathological Images of Prostate Cancer

Yuchun Li,Jing Chen,Wenlong Feng,Gang Wang,Haixia Xu,Mengxing Huang,Yu Zhang

doi:10.1109/access.2020.3005180

Abstract

Prostate cancer is the second-deadliest cancer in men in the United States, seriously affecting people's life and health. The Gleason grading system is one of the most reliable methods to quantify the invasiveness of prostate cancer, which is of great significance for risk assessment and treatment planning for patients. However, the task of automating Gleason grading is difficult because of the complexity of pathological images of prostate cancer. This paper presents an automated Gleason grading and Gleason pattern region segmentation method based on deep learning for pathological images of prostate cancer. An architecture combining the atrous spatial pyramid pooling and the multiscale standard convolution is proposed for the segmentation of the Gleason pattern region to get accurate Gleason grading. In addition, the postprocessing procedure based on conditional random fields is applied to the prediction. The quantitative experiments on 1211 prostate cancer tissue microarrays demonstrate that our results have a high correlation with the manual segmentations. The mean intersection over union and the overall pixel accuracy for the Gleason pattern region are 77.29% and 89.51%, respectively. Furthermore, the results of the automatic Gleason grading were comparable to the results of experienced pathologists. The inter-annotator agreements between the model and the pathologists, quantified via Cohen's quadratic kappa statistic, was 0.77 on average. Our study shows that the method of combining different deep neural network architectures is suitable for more objective and reproducible Gleason grading of prostate cancer.

Highlights

Prostate cancer is the second-deadliest cancer in men in the U.S, seriously affecting people’s life and health [1]
We propose a novel method for automatic Gleason grading and Gleason pattern region segmentation of images with prostate cancer pathologies based on a convolutional neural network (CNN)
An architecture that combines the atrous spatial pyramid pooling (ASPP) from Deeplab-V3 [14] and the multiscale standard convolution inspired by a multiscale parallel branch convolutional neural network (MPB-CNN) [15] is proposed for the segmentation of the Gleason pattern region to get accurate Gleason grading

Summary

Introduction

Prostate cancer is the second-deadliest cancer in men in the U.S, seriously affecting people’s life and health [1]. Prostate cancer mainly refers to a malignant tumor of an epithelial tissue that occurs in the prostate. Pathologists take out a small amount of prostate tissue using ultrasound-guided prostate biopsy technology [2]. By a series of advanced methods such as those using microscope, histochemistry, and immunofluorescence, they observe and analyze the pathology. The associate editor coordinating the review of this manuscript and approving it for publication was Andrea F.

Methods

Findings

Discussion

Conclusion