JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Predicting pathogenic DNA damage repair gene mutations in prostate cancer patients: a multi-center magnetic resonance imaging radiomics study

  • 0Department of Radiology, West China Hospital, Sichuan University, Chengdu, China.
Quantitative Imaging in Medicine and Surgery +

|

July 29, 2025

|

July 29, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed an MRI radiomics model to predict pathogenic DNA damage repair gene (pDDRg) mutations in prostate cancer (PCa) patients, potentially reducing unnecessary genetic testing costs. The model showed strong predictive performance in validation cohorts.

Area Of Science

  • Radiology
  • Oncology
  • Genetics

Background

  • Genetic testing for pathogenic DNA damage repair gene (pDDRg) mutations offers clinical benefits for prostate cancer (PCa) patients.
  • High costs associated with genetic testing present a barrier to its widespread clinical application in PCa management.
  • There is a need for cost-effective methods to identify PCa patients likely to harbor pDDRg mutations before genetic testing.

Purpose Of The Study

  • To develop and validate a magnetic resonance imaging (MRI)-based radiomics model for predicting pDDRg mutations in PCa patients.
  • To assess the model's ability to identify patients who would benefit from genetic testing, thereby reducing healthcare costs.

Main Methods

  • A cohort of 225 PCa patients with pre-biopsy multiparametric MRI and genetic testing data was analyzed.
  • Radiomics features were extracted from T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) MRI sequences using the LASSO algorithm.
  • Model performance was validated internally and externally using receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

Main Results

  • A total of 48 out of 225 patients (21.3%) had positive pDDRg mutations.
  • The developed MRI radiomics model, utilizing 13 features from T2WI and ADC sequences, achieved AUC values of 0.824 (internal) and 0.836 (external validation).
  • The model demonstrated a potential to reduce unnecessary genetic testing by approximately 25%.

Conclusions

  • The MRI radiomics-based predictive model shows promise as a pre-testing tool for identifying PCa patients with pDDRg mutations.
  • This approach could help optimize the use of genetic testing and reduce associated costs.
  • Further prospective studies are recommended to validate the model's clinical utility before widespread adoption.

Keywords: