# mpMRI-Based Risk Estimation to Optimize Prostate Cancer Patient Selection for Active Surveillance

## TL;DR

This study uses AI and MRI to better identify prostate cancer patients suitable for active surveillance, improving risk assessment and reducing unnecessary treatments.

## Contribution

An AI-based risk assessment platform using MRI-derived features to improve active surveillance patient selection for prostate cancer.

## Key findings

- The model achieved an AUC of 0.84 in predicting prostate cancer progression within 12 months.
- The model increased negative predictive value by 18.5% compared to standard-of-care methods in an independent test set.

## Abstract

Prostate cancer is the second leading cause of cancer-related deaths in the United States; however, approximately half of newly diagnosed patients present with low-risk, indolent disease. Active surveillance (AS) offers an alternative to immediate treatment by closely monitoring patients through serial blood biomarkers, multiparametric MRI, and repeat biopsies. In a prospective AS trial with annual follow-up for disease progression, this study evaluated the added prognostic value of quantitative MRI features automatically extracted from AI-identified, cancer-suspicious regions. A prediction model trained on 163 patients achieved an ROC-AUC of 0.84 in distinguishing between individuals with high risk of rapid progressions and those with stable disease, demonstrating the potential of AI-derived imaging biomarkers to improve risk stratification and patient selection for active surveillance.

Background/Objectives: Active surveillance (AS) has emerged as a safe alternative to primary therapy for low- and select intermediate-risk prostate cancer (PCa), but optimal patient selection and surveillance strategies remain challenging due to limited risk stratification tools enabling early detection of lesions with high potential for histopathological progression. This study presents an integrated method for predicting prostate cancer progression within 12 months, aiming to improve AS patient selection by categorizing patients into two risk groups: rapid progressors who would benefit from immediate treatment and slow progressors suitable for AS. Methods: The risk assessment platform combines convolutional neural networks for automatic segmentation of prostate and suspicious-for-cancer lesions on multiparametric MRI (mpMRI) with logistic regression to estimate progression risk. The networks were trained on annotated lesions from radical prostatectomy specimen mapped to mpMRI. The prediction model incorporated pre-biopsy clinical variables (age, PSA, PI-RADS) and MRI-derived intratumoral radiomic features from 163 participants of a prospective clinical trial, using histopathological progression within 12 months as endpoint. Results: The clinical-radiomics model achieved an AUC of 0.84 in distinguishing rapid from slow progressors, using non-invasive monitoring techniques. In an independent test set, the model significantly improved AS patient selection, increasing negative predictive value by 18.5% compared to current standard-of-care (p < 0.001). Conclusions: The risk assessment platform shows promise for use during annual follow-up visits to reliably differentiate suitable AS candidates with stable disease from PCa patients who are likely to experience early progression.