TY - JOUR
T1 - A systematic review and meta-analysis of artificial intelligence diagnostic accuracy in prostate cancer histology identification and grading
AU - Young Academic Urologists (YAU) Working Group in Uro-technology of the European Association of Urology
AU - Morozov, Andrey
AU - Taratkin, Mark
AU - Bazarkin, Andrey
AU - Rivas, Juan Gomez
AU - Puliatti, Stefano
AU - Checcucci, Enrico
AU - Belenchon, Ines Rivero
AU - Kowalewski, Karl Friedrich
AU - Shpikina, Anastasia
AU - Singla, Nirmish
AU - Teoh, Jeremy Y.C.
AU - Kozlov, Vasiliy
AU - Rodler, Severin
AU - Piazza, Pietro
AU - Fajkovic, Harun
AU - Yakimov, Maxim
AU - Abreu, Andre Luis
AU - Cacciamani, Giovanni E.
AU - Enikeev, Dmitry
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Nature Limited.
PY - 2023/12
Y1 - 2023/12
N2 - Background: Artificial intelligence (AI) is a promising tool in pathology, including cancer diagnosis, subtyping, grading, and prognostic prediction. Methods: The aim of the study is to assess AI application in prostate cancer (PCa) histology. We carried out a systematic literature search in 3 databases. Primary outcome was AI accuracy in differentiating between PCa and benign hyperplasia. Secondary outcomes were AI accuracy in determining Gleason grade and agreement among AI and pathologists. Results: Our final sample consists of 24 studies conducted from 2007 to 2021. They aggregate data from roughly 8000 cases of prostate biopsy and 458 cases of radical prostatectomy (RP). Sensitivity for PCa diagnostic exceeded 90% and ranged from 87% to 100%, and specificity varied from 68% to 99%. Overall accuracy ranged from 83.7% to 98.3% with AUC reaching 0.99. The meta-analysis using the Mantel-Haenszel method showed pooled sensitivity of 0.96 with I2 = 80.7% and pooled specificity of 0.95 with I2 = 86.1%. Pooled positive likehood ratio was 15.3 with I2 = 87.3% and negative – was 0.04 with I2 = 78.6%. SROC (symmetric receiver operating characteristics) curve represents AUC = 0.99. For grading the accuracy of AI was lower: sensitivity for Gleason grading ranged from 77% to 87%, and specificity from 82% to 90%. Conclusions: The accuracy of AI for PCa identification and grading is comparable to expert pathologists. This is a promising approach which has several possible clinical applications resulting in expedite and optimize pathology reports. AI introduction into common practice may be limited by difficult and time-consuming convolutional neural network training and tuning.
AB - Background: Artificial intelligence (AI) is a promising tool in pathology, including cancer diagnosis, subtyping, grading, and prognostic prediction. Methods: The aim of the study is to assess AI application in prostate cancer (PCa) histology. We carried out a systematic literature search in 3 databases. Primary outcome was AI accuracy in differentiating between PCa and benign hyperplasia. Secondary outcomes were AI accuracy in determining Gleason grade and agreement among AI and pathologists. Results: Our final sample consists of 24 studies conducted from 2007 to 2021. They aggregate data from roughly 8000 cases of prostate biopsy and 458 cases of radical prostatectomy (RP). Sensitivity for PCa diagnostic exceeded 90% and ranged from 87% to 100%, and specificity varied from 68% to 99%. Overall accuracy ranged from 83.7% to 98.3% with AUC reaching 0.99. The meta-analysis using the Mantel-Haenszel method showed pooled sensitivity of 0.96 with I2 = 80.7% and pooled specificity of 0.95 with I2 = 86.1%. Pooled positive likehood ratio was 15.3 with I2 = 87.3% and negative – was 0.04 with I2 = 78.6%. SROC (symmetric receiver operating characteristics) curve represents AUC = 0.99. For grading the accuracy of AI was lower: sensitivity for Gleason grading ranged from 77% to 87%, and specificity from 82% to 90%. Conclusions: The accuracy of AI for PCa identification and grading is comparable to expert pathologists. This is a promising approach which has several possible clinical applications resulting in expedite and optimize pathology reports. AI introduction into common practice may be limited by difficult and time-consuming convolutional neural network training and tuning.
UR - http://www.scopus.com/inward/record.url?scp=85153734267&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153734267&partnerID=8YFLogxK
U2 - 10.1038/s41391-023-00673-3
DO - 10.1038/s41391-023-00673-3
M3 - Review article
C2 - 37185992
AN - SCOPUS:85153734267
SN - 1365-7852
VL - 26
SP - 681
EP - 692
JO - Prostate Cancer and Prostatic Diseases
JF - Prostate Cancer and Prostatic Diseases
IS - 4
ER -