Radiomics As a Tool for Predicting Biochemical Recurrence After Total Prostatectomy: A Systematic Review and Meta‐Analysis Publisher Pubmed



Kiani I ; Toutounchian S ; Broomand Lomer N ; Tabari A
Source: International Urology and Nephrology Published:2026

Abstract

Purpose: Biochemical recurrence (BCR) following radical prostatectomy (RP) remains a significant concern in prostate cancer (PCa) management, as it is associated with an increased risk of metastasis and disease progression. While conventional clinical and pathological prognostic factors are helpful in determining the prognosis, their accuracy remains suboptimal. Radiomics has been shown to be a promising tool for improving risk stratification and outcome prediction in PCa patients post-RP. This systematic review and meta-analysis aims to evaluate the prognostic value of radiomics-based models in predicting BCR after RP. Methods: This study was conducted following PRISMA guidelines. A comprehensive literature search was performed across PubMed, Scopus, Web of Science, and Embase up to April 2025. Eligible studies included original research articles that evaluated radiomics models for predicting BCR in PCa patients post-RP. Data extraction and quality assessment were conducted independently by two reviewers using the METhodological RadiomICs Score (METRICS). Results: A total of 16 studies encompassing 3,634 patients met the inclusion criteria. The pooled sensitivity and specificity for radiomics-based models in predicting BCR in the validation subgroup were 0.82 (95% CI: 0.74–0.88) and 0.80 (95% CI: 0.67–0.88), respectively. The overall hazard ratio (HR) for BCR prediction in the radiomics models was 4.61 (95% CI: 3.06–6.96). Subgroup analyses indicated that models integrating radiomics with clinical variables outperformed those relying solely on imaging-derived features. Conclusion: Radiomics-based models show strong potential in predicting BCR after RP, with potential clinical utility in personalizing patient management. Moving forward, future research should focus on integrating radiomics with other omics data to develop more informative models. © The Author(s), under exclusive licence to Springer Nature B.V. 2026.