A Weakly Supervised Deep Learning Model and Human-Machine Fusion for Accurate Grading of Renal Cell Carcinoma from Histopathology Slides

Simple Summary Renal cell carcinoma causes over 179,000 deaths per year worldwide, and the Fuhrman grading (FG) system is crucial for diagnosing this deadly cancer. However, visual histopathological assessment is influenced by inter-observer variability and irreproducibility. In this study, we trained a deep learning model named SSL-CLAM using whole slide histopathology images to objectively diagnose the FG status of patients with clear cell renal cell carcinoma (ccRCC). We demonstrated that the SSL-CLAM model successfully diagnosed five FG states of ccRCC (Grade-0, 1, 2, 3, and 4) and validated the results in two independent cohorts. The attention heatmap of the SSL-CLAM model visualized high attention regions, and we found that cell nuclear size, contour, and cellular pleomorphism were critical morphologies that align with the existing FG criteria. In summary, a human-machine collaborative diagnostic model may assist pathologists in making diagnostic decisions, and further prospective clinical trials are needed to confirm its efficacy. (1) Background: The Fuhrman grading (FG) system is widely used in the management of clear cell renal cell carcinoma (ccRCC). However, it is affected by observer variability and irreproducibility in clinical practice. We aimed to use a deep learning multi-class model called SSL-CLAM to assist in diagnosing the FG status of ccRCC patients using digitized whole slide images (WSIs). (2) Methods: We recruited 504 eligible ccRCC patients from The Cancer Genome Atlas (TCGA) cohort and obtained 708 hematoxylin and eosin-stained WSIs for the development and internal validation of the SSL-CLAM model. Additionally, we obtained 445 WSIs from 188 ccRCC eligible patients in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort as an independent external validation set. A human-machine fusion approach was used to validate the added value of the SSL-CLAM model for pathologists. (3) Results: The SSL-CLAM model successfully diagnosed the five FG statuses (Grade-0, 1, 2, 3, and 4) of ccRCC, and achieved AUCs of 0.917 and 0.887 on the internal and external validation sets, respectively, outperforming a junior pathologist. For the normal/tumor classification (Grade-0, Grade-1/2/3/4) task, the SSL-CLAM model yielded AUCs close to 1 on both the internal and external validation sets. The SSL-CLAM model achieved a better performance for the two-tiered FG (Grade-0, Grade-1/2, and Grade-3/4) task, with AUCs of 0.936 and 0.915 on the internal and external validation sets, respectively. The human-machine diagnostic performance was superior to that of the SSL-CLAM model, showing promising prospects. In addition, the high-attention regions of the SSL-CLAM model showed that with an increasing FG status, the cell nuclei in the tumor region become larger, with irregular contours and increased cellular pleomorphism. (4) Conclusions: Our findings support the feasibility of using deep learning and human-machine fusion methods for FG classification on WSIs from ccRCC patients, which may assist pathologists in making diagnostic decisions.