Radiomics as a tool for predicting biochemical recurrence after total prostatectomy: a systematic review and...

Area of Science:

• Oncology
• Medical Imaging
• Data Science

Background:

• Biochemical recurrence (BCR) after radical prostatectomy (RP) for prostate cancer (PCa) is a significant concern, linked to metastasis and progression.
• Current prognostic factors have suboptimal accuracy in predicting BCR.
• Radiomics offers a novel approach to enhance risk stratification and outcome prediction in PCa patients post-RP.

Purpose of the Study:

• To systematically review and meta-analyze the prognostic value of radiomics-based models for predicting BCR after RP.
• To evaluate the performance of radiomics in identifying patients at higher risk of recurrence.

Main Methods:

• Adherence to PRISMA guidelines for systematic review and meta-analysis.
• Comprehensive literature search across major databases (PubMed, Scopus, Web of Science, Embase) up to April 2025.
• Data extraction and quality assessment using the METhodological RadiomICs Score (METRICS) by two independent reviewers.

Main Results:

• 16 studies with 3,634 patients met the inclusion criteria.
• Pooled sensitivity and specificity for radiomics models in BCR prediction were 0.82 and 0.80, respectively.
• Radiomics models demonstrated a significant hazard ratio (HR) of 4.61 for BCR prediction; models combining radiomics with clinical variables showed superior performance.

Conclusions:

• Radiomics-based models exhibit strong potential for predicting BCR post-RP, offering clinical utility for personalized treatment strategies.
• Future research should explore integrating radiomics with other omics data to develop more robust predictive models.