Automated Gleason grading of prostate cancer tissue microarrays via deep learning

• Published in: Scientific reports Vol. 8; no. 1; pp. 12054 - 11
• Main Authors: Arvaniti, Eirini, Fricker, Kim S., Moret, Michael, Rupp, Niels, Hermanns, Thomas, Fankhauser, Christian, Wey, Norbert, Wild, Peter J., Rüschoff, Jan H., Claassen, Manfred
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 13-08-2018; Nature Publishing Group
• Subjects: 13/105; 13/51; 631/114/1305; 631/67/589/466; 692/700/139/422; 692/700/1421; Automation; Cohort Studies; Data processing; Deep Learning; Feasibility Studies; Humanities and Social Sciences; Humans; Male; Middle Aged; Models, Biological; multidisciplinary; Neoplasm Grading; Pathology; Prognosis; Prostate - pathology; Prostate cancer; Prostatic Neoplasms - mortality; Prostatic Neoplasms - pathology; Reproducibility of Results; Science; Survival Analysis; Tissue Array Analysis - methods
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-018-30535-1

The Gleason grading system remains the most powerful prognostic predictor for patients with prostate cancer since the 1960s. Its application requires highly-trained pathologists, is tedious and yet suffers from limited inter-pathologist reproducibility, especially for the intermediate Gleason score 7. Automated annotation procedures constitute a viable solution to remedy these limitations. In this study, we present a deep learning approach for automated Gleason grading of prostate cancer tissue microarrays with Hematoxylin and Eosin (H&E) staining. Our system was trained using detailed Gleason annotations on a discovery cohort of 641 patients and was then evaluated on an independent test cohort of 245 patients annotated by two pathologists. On the test cohort, the inter-annotator agreements between the model and each pathologist, quantified via Cohen’s quadratic kappa statistic, were 0.75 and 0.71 respectively, comparable with the inter-pathologist agreement (kappa = 0.71). Furthermore, the model’s Gleason score assignments achieved pathology expert-level stratification of patients into prognostically distinct groups, on the basis of disease-specific survival data available for the test cohort. Overall, our study shows promising results regarding the applicability of deep learning-based solutions towards more objective and reproducible prostate cancer grading, especially for cases with heterogeneous Gleason patterns.