Artificial Intelligence for Diagnosis and Gleason Grading of Prostate Cancer in Biopsies—Current Status and Next Steps

• Published in: European urology focus Vol. 7; no. 4; pp. 687 - 691
• Main Authors: Kartasalo, Kimmo, Bulten, Wouter, Delahunt, Brett, Chen, Po-Hsuan Cameron, Pinckaers, Hans, Olsson, Henrik, Ji, Xiaoyi, Mulliqi, Nita, Samaratunga, Hemamali, Tsuzuki, Toyonori, Lindberg, Johan, Rantalainen, Mattias, Wählby, Carolina, Litjens, Geert, Ruusuvuori, Pekka, Egevad, Lars, Eklund, Martin
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.07.2021
• Subjects: Artificial Intelligence; Bioinformatik och systembiologi (metodutveckling under 10203); Biologi (Medicinska tillämpningar under 3 och lantbruksvetenskapliga under 4); Biopsy; Cancer och onkologi; Gleason grading; Histopathology; Humans; Image Interpretation, Computer-Assisted; Klinisk medicin; Male; Medicin och hälsovetenskap; Naturvetenskap; Neoplasm Grading; Prostate cancer; Prostatic Neoplasms - pathology; Urologi och njurmedicin; Uropathology; Uropathology; Histopathology; Gleason grading; Prostate cancer; Artificial intelligence
• ISSN: 2405-4569; 2405-4569
• DOI: 10.1016/j.euf.2021.07.002

Diagnosis and Gleason grading of prostate cancer in biopsies are critical for the clinical management of men with prostate cancer. Despite this, the high grading variability among pathologists leads to the potential for under- and overtreatment. Artificial intelligence (AI) systems have shown promise in assisting pathologists to perform Gleason grading, which could help address this problem. In this mini-review, we highlight studies reporting on the development of AI systems for cancer detection and Gleason grading, and discuss the progress needed for widespread clinical implementation, as well as anticipated future developments. This mini-review summarizes the evidence relating to the validation of artificial intelligence (AI)-assisted cancer detection and Gleason grading of prostate cancer in biopsies, and highlights the remaining steps required prior to its widespread clinical implementation. We found that, although there is strong evidence to show that AI is able to perform Gleason grading on par with experienced uropathologists, more work is needed to ensure the accuracy of results from AI systems in diverse settings across different patient populations, digitization platforms, and pathology laboratories. Artificial intelligence (AI) systems have shown promise in assisting pathologists to perform cancer detection and Gleason grading in prostate biopsies. We highlight studies reporting on the development of these AI systems, and discuss the progress needed for clinical implementation as well as anticipated future developments.