Scaling Artificial Intelligence for Prostate Cancer Detection on MRI towards Population-Based Screening and Primary Diagnosis in a Global, Multiethnic Population (Study Protocol)

2025-08-04

AI Summary

Prostate cancer MRI screening and initial diagnosis require robust, equitable AI tools across diverse global populations. Method: We developed and externally validated PI-CAI-2B, a deep learning model strictly aligned with PI-RADS criteria, trained and validated on an intercontinental, multicenter, multiethnic cohort. It is the first study to systematically test diagnostic interchangeability and assess performance disparities across image quality, age, and racial subgroups. Contribution/Results: Primary endpoints were agreement rates between AI and clinical assessments at PI-RADS ≥3 (initial diagnosis) and ≥4 (screening), evaluated against a ±0.05 equivalence margin; secondary endpoint was AUROC. PI-CAI-2B demonstrated high generalizability and clinical deployability across heterogeneous real-world settings, achieving statistically equivalent diagnostic performance to radiologists. The model significantly advances fairness and scalability of AI-assisted prostate cancer detection, establishing a new benchmark for equitable, globally applicable prostate MRI interpretation.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

In this intercontinental, confirmatory study, we include a retrospective cohort of 22,481 MRI examinations (21,288 patients; 46 cities in 22 countries) to train and externally validate the PI-CAI-2B model, i.e., an efficient, next-generation iteration of the state-of-the-art AI system that was developed for detecting Gleason grade group $geq$2 prostate cancer on MRI during the PI-CAI study. Of these examinations, 20,471 cases (19,278 patients; 26 cities in 14 countries) from two EU Horizon projects (ProCAncer-I, COMFORT) and 12 independent centers based in Europe, North America, Asia and Africa, are used for training and internal testing. Additionally, 2010 cases (2010 patients; 20 external cities in 12 countries) from population-based screening (STHLM3-MRI, IP1-PROSTAGRAM trials) and primary diagnostic settings (PRIME trial) based in Europe, North and South Americas, Asia and Australia, are used for external testing. Primary endpoint is the proportion of AI-based assessments in agreement with the standard of care diagnoses (i.e., clinical assessments made by expert uropathologists on histopathology, if available, or at least two expert urogenital radiologists in consensus; with access to patient history and peer consultation) in the detection of Gleason grade group $geq$2 prostate cancer within the external testing cohorts. Our statistical analysis plan is prespecified with a hypothesis of diagnostic interchangeability to the standard of care at the PI-RADS $geq$3 (primary diagnosis) or $geq$4 (screening) cut-off, considering an absolute margin of 0.05 and reader estimates derived from the PI-CAI observer study (62 radiologists reading 400 cases). Secondary measures comprise the area under the receiver operating characteristic curve (AUROC) of the AI system stratified by imaging quality, patient age and patient ethnicity to identify underlying biases (if any).

Problem

• Develop AI for prostate cancer detection in diverse populations
• Validate AI model accuracy against standard clinical diagnoses
• Assess diagnostic performance across ethnicities and imaging quality

Innovation

• AI model trained on multiethnic global MRI data
• External validation in diverse screening settings
• Diagnostic interchangeability with standard care