A clinical-radiomics model based on MRI sub-regions of gluteus maximus for recurrence prediction in high-grade serous ovarian cancer.
Combined clinical-radiomics model predicts ovarian cancer recurrence with AUC 0.817
A clinical-radiomics model based on MRI sub-regions of gluteus maximus for recurrence prediction in high-grade serous ovarian cancer.
To evaluate the predictive value of MRI sub-regional radiomics of the gluteus maximus for recurrence in high-grade serous ovarian cancer (high-grade serous ovarian cancer) and compare its performance with conventional radiomics and deep learning (deep learning) models.
A multi-center retrospective cohort of 531 patients with high-grade serous ovarian cancer was analyzed.
higher scores mean better prediction of recurrence, 1.0 is perfect
Neoadjuvant chemotherapy (neoadjuvant chemotherapy) and poly ADP-ribose polymerase (poly ADP-ribose polymerase) inhibitor treatment were identified as independent predictors of high-grade serous ovarian cancer recurrence (P < 0.05).
The U-Net segmentation achieved Dice Similarity Coefficient ranging from 0.726 to 0.903 across cohorts.
The sub-regional radiomics model demonstrated superior performance compared to clinical, conventional radiomics, and deep learning models, achieving AUCs of 0.774 (training), 0.774 (internal validation), 0.717 (external test A), 0.704 (external test B), and 0.717 (external test C).
The T2WI-based sub-regional radiomics model of the gluteus maximus effectively predicts recurrence in high-grade serous ovarian cancer patients.
The combined model, which integrates sub-regional radiomics features with clinical factors, generally improves predictive accuracy and provides a promising decision-support tool for post-treatment assessment of recurrence risk.