Predicting recurrence risk in endometrial cancer: a multisequence MRI intratumoral and peritumoral radiomics nomogram approach DOI Creative Commons
Jie Li, Di Ma,

Xiuting Chen

et al.

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: May 6, 2025

To assess the predictive value of a nomogram model incorporating clinical factors and multisequence MRI intratumoral peritumoral radiomics features for estimating recurrence risk in endometrial cancer (EC) patients. This retrospective study included 184 patients with EC. The samples were randomly divided into training set test according to 7:3 ratio, extracted from diffusion-weighted imaging (DWI) T2-weighted (T2WI) sequences. Optimal selected using f-classification function, minimum redundancy maximum relevance (mRMR) method, least absolute shrinkage selection operator (Lasso). Nine machine learning classifiers employed construct (RM1). best-performing then used develop 2 mm (RM2) 4 (RM3). scores (Rad-score) top-performing combined create (FM). performance FM was evaluated receiver operating characteristic (ROC) curve analysis, calibration assessment, decision analysis (DCA), impact (CIC), DeLong test. Feature importance SHapley Additive exPlanations (SHAP) methodology. logistic regression classifier (LR) showed optimal efficacy, RM2 demonstrated best diagnostic performance. results indicated that EC A integrating regions effectively predicts

Language: Английский

Predicting recurrence risk in endometrial cancer: a multisequence MRI intratumoral and peritumoral radiomics nomogram approach DOI Creative Commons
Jie Li, Di Ma,

Xiuting Chen

et al.

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: May 6, 2025

To assess the predictive value of a nomogram model incorporating clinical factors and multisequence MRI intratumoral peritumoral radiomics features for estimating recurrence risk in endometrial cancer (EC) patients. This retrospective study included 184 patients with EC. The samples were randomly divided into training set test according to 7:3 ratio, extracted from diffusion-weighted imaging (DWI) T2-weighted (T2WI) sequences. Optimal selected using f-classification function, minimum redundancy maximum relevance (mRMR) method, least absolute shrinkage selection operator (Lasso). Nine machine learning classifiers employed construct (RM1). best-performing then used develop 2 mm (RM2) 4 (RM3). scores (Rad-score) top-performing combined create (FM). performance FM was evaluated receiver operating characteristic (ROC) curve analysis, calibration assessment, decision analysis (DCA), impact (CIC), DeLong test. Feature importance SHapley Additive exPlanations (SHAP) methodology. logistic regression classifier (LR) showed optimal efficacy, RM2 demonstrated best diagnostic performance. results indicated that EC A integrating regions effectively predicts

Language: Английский

Citations

0