Sign in Subscribe
Genetic research

Combining MRI Radiomics and Clinical Data Improves Prostate Cancer Prognosis

Strategic Insights

— 1 min read

Research has shown that combining pre-treatment MRI-derived radiomic features with clinical data improves the accuracy of predicting biochemical recurrence-free survival (BCRFS) after prostate radiotherapy. This retrospective cohort analysis included patients with biopsy-proven prostate cancer who received radiotherapy between 2007 and 2013 at two cancer centers in the UK. The study found that adding radiomic features to a clinical model improves BCRFS prediction accuracy, while adding hypoxia gene signature scores does not.

Key Takeaways:

  • The study analyzed 178 patients with biopsy-proven prostate cancer who received radiotherapy between 2007 and 2013 at two cancer centers in the UK.
  • The clinical-only model performance had a C-index score of 0.69 [0.64-0.7], indicating moderate accuracy in predicting BCRFS.
  • The combined clinical-radiomics model had a higher C-index score of 0.70 [0.66-0.73], indicating improved accuracy in predicting BCRFS.
  • The addition of radiomic features to clinical variables alone improved model performance (p = 0.027), while adding hypoxia gene signature scores did not (p = 0.625).
  • The selected features of the combined clinical-radiomics model included age, ISUP grade, tumor stage, and wavelet-derived grey level co-occurrence matrix (GLCM) radiomic features.

Statistics:

  • 178 patients were included in the study.
  • The clinical-only model had a C-index score of 0.69 [0.64-0.7].
  • The combined clinical-radiomics model had a C-index score of 0.70 [0.66-0.73].
  • The addition of radiomic features to clinical variables alone improved model performance by 2.7-fold (p = 0.027).
  • The addition of hypoxia gene signature scores did not improve model accuracy (p = 0.625).

Sources:

  • Combining MRI radiomics, hypoxia gene signature score and clinical variables for prediction of biochemical recurrence-free survival after radiotherapy in prostate cancer. La radiologia medica, 2025.
  • NewsRx. University of Leeds Reports Findings in Prostate Cancer (Combining MRI radiomics, hypoxia gene signature score and clinical variables for prediction of biochemical recurrence-free survival after radiotherapy in prostate cancer). Chemicals & Chemistry. July 18, 2025; p 4329.

Read more