Artificial Intelligence and Radiologists at Prostate Cancer Detection in MRI — The PI-CAI Challenge

Anindo Saha, Joeran Bosma, Jasper Twilt, Bram van Ginneken, Derya Yakar, Mattijs Elschot, Jeroen Veltman, Jurgen Fütterer, Maarten de Rooij, henkjan huisman

Keywords: prostate cancer, artificial intelligence, magnetic resonance imaging, radiologists, computer-aided detection and diagnosis

TL;DR: International comparative study, investigating AI models that were independently developed, trained and externally tested using a large multi-center cohort of 10,207 patient exams, in comparison to 50+ international radiologists.

Abstract: We hypothesized that state-of-the-art AI models, trained using thousands of patient cases, are non-inferior to radiologists at clinically significant prostate cancer diagnosis using MRI. To test the same, we designed an international comparative study titled the PI-CAI challenge, where we investigated AI models that were independently developed, trained and externally tested using a large multi-center cohort of 10,207 patient exams. Preliminary results indicate that when trained on 1,500 cases only, such models already achieve diagnostic performance comparable to that of radiologists reported in literature.