Progression-Free Survival Prediction for Locally Advanced Cervical Cancer After Chemoradiotherapy With MRI-based...

Area of Science:

• Oncology
• Radiology
• Medical Imaging

Background:

• Locally advanced cervical cancer (LACC) patients often experience disease progression after chemoradiotherapy (CRT).
• Current clinical variables are insufficient for accurately predicting treatment response in LACC.
• There is a need for improved prognostic tools to guide personalized management strategies.

Purpose of the Study:

• To develop and validate a radiomics-based model to predict progression-free survival (PFS) in LACC patients undergoing CRT.
• To evaluate the performance of a combined radiomics-clinical model compared to clinical variables alone.

Main Methods:

• Radiomics features were extracted from pre-treatment MR T2-weighted images (T2WI) of 105 LACC patients.
• A Cox proportional hazard model and feature selection methods identified optimal predictors.
• A radiomics-clinical combined model was developed and validated using nested 5-fold cross-validation.

Main Results:

• Radiomics features from MR T2WI significantly predicted PFS in LACC patients post-CRT.
• The combined radiomics-clinical model demonstrated superior performance (C-index 0.748) compared to clinical variables alone (C-index 0.655).
• The model effectively stratified patients into high- and low-risk groups for disease progression (P < 0.001).

Conclusions:

• An MR T2WI-based radiomics and clinical combined model offers enhanced prognostic capability for predicting PFS in LACC patients treated with CRT.
• This radiomics approach shows promise as an imaging biomarker for personalized treatment strategies in LACC.
• The findings support the integration of MR T2WI radiomics into clinical decision-making for LACC management.