Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer
This could improve accuracy in prostate cancer prognosis and treatment decisions, especially in settings lacking specialist expertise, though it is an incremental application of deep learning to a known bottleneck.
The researchers tackled the problem of poor reproducibility in Gleason scoring for prostate cancer by developing a deep learning system that achieved a diagnostic accuracy of 0.70, significantly higher than the 0.61 mean accuracy of general pathologists.
For prostate cancer patients, the Gleason score is one of the most important prognostic factors, potentially determining treatment independent of the stage. However, Gleason scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility. Here we present a deep learning system (DLS) for Gleason scoring whole-slide images of prostatectomies. Our system was developed using 112 million pathologist-annotated image patches from 1,226 slides, and evaluated on an independent validation dataset of 331 slides, where the reference standard was established by genitourinary specialist pathologists. On the validation dataset, the mean accuracy among 29 general pathologists was 0.61. The DLS achieved a significantly higher diagnostic accuracy of 0.70 (p=0.002) and trended towards better patient risk stratification in correlations to clinical follow-up data. Our approach could improve the accuracy of Gleason scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. The DLS also goes beyond the current Gleason system to more finely characterize and quantitate tumor morphology, providing opportunities for refinement of the Gleason system itself.