MRI radiomics ensemble model predicts aggressive cervical cancer with LVSI

An interpretable ensemble learning model using intratumoral & peritumoral MR-radiomics predicted high-grade cervical cancer with LVSI (HGVI), AUC 0.858 (95% CI 0.762-0.932) in the test set. SHAP analysis showed ADC_peritumoral_3mm as a top contributor.

• Retrospective study of 242 cervical cancer patients; training/test split of 169/73.
• The ensemble model (ENMLR) achieved test AUC 0.858, accuracy 0.7260, and improved clinical net benefit across a 10–90% threshold range.
• RCS analysis found a significant nonlinear relationship between ADC intratumoral radiomics scores and HGVI double positivity.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.