Artificial intelligence for Gleason grading of prostate biopsies -- current status and next steps

Kimmo Kartasalo
Wouter Bulten
Brett Delahunt
Cameron Chen
Hans Pinckaers
Henrik Olsson
Xiaoyi Ji
Nita Mulliqi
Hemamali Samaratunga
Toyonori Tsuzuki
Johan Lindberg
Mattias Rantalainen
Carolina Wählby
Geert Litjens
Pekka Ruusuvuori
Lars Egevad
Martin Eklund
European Urology Focus (2021)

Abstract

Gleason grading of prostate biopsies is critical to the clinical management of men with prostate cancer. However, the challenge with high inter-pathologist variability leads to risks for under- and overtreatment. Artificial intelligence (AI) systems have shown promise to assist pathologists in performing Gleason grading, which could help address this problem. In this mini-review, we highlight studies reporting on the development of AI systems for Gleason grading and discuss remaining steps needed for widespread clinical implementation, as well as ongoing and future developments.