Weakly-supervised deep learning model for prostate cancer diagnosis and Gleason grading of histopathology images

Prostate cancer is the most common cancer in men worldwide and the second leading cause of cancer death in the United States. One of the prognostic features in prostate cancer is the Gleason grading of histopathology images. The Gleason grade is assigned based on tumor architecture on Hematoxylin and Eosin (H&E) stained whole slide images (WSI) by the pathologists. This process is time-consuming and has known interobserver variability. In the past few years, deep learning algorithms have been used to analyze histopathology images, delivering promising results for grading prostate cancer. However, most of the algorithms rely on fully annotated datasets which are expensive to generate. To address this limitation, we propose a novel weakly -supervised algorithm for prostate cancer grade classification. Our algorithm comprises three key steps. Firstly, we employ the Multiple Instance Learning (MIL) algorithm, based on Transformers, to extract discriminative areas within the histopathology images. This approach effectively identifies regions containing crucial information for accurate classification. Secondly, we construct a graph representation of the image by connecting the discriminative patches. This graph captures the intricate relationships between patches, facilitating the analysis of contextual information. Lastly, we develop a Graph Convolutional Neural Network (GCN) using a gated attention mechanism to classify the image into its respective Gleason grade. The performance of our algorithm is extensively evaluated using publicly available datasets, including TCGA-PRAD, PANDA, and Gleason 2019 challenge datasets, alongside rigorous cross -validation on an independent dataset. Our results consistently demonstrate that the proposed model surpasses existing methods in Gleason grading, as evidenced by superior accuracy, F1 score, and Cohen -Kappa scores. By leveraging weakly -supervised learning and graph -based analysis, our algorithm presents a promising solution to improve the efficiency and accuracy of prostate cancer grading, ultimately aiding in patient prognosis and treatment decisions. The code for our algorithm is available at https://github.com/NabaviLab/Prostate-Cancer.