A T2-weighted MRI-based radiomic signature for disease-free survival in locally advanced cervical cancer following chemoradiation: An international, multicentre study
View abstract on PubMed
Summary
This summary is machine-generated.A new MRI-based radiomic signature shows promise as a prognostic biomarker for disease-free survival (DFS) in locally advanced cervical cancer patients treated with chemoradiation, aiding in personalized treatment strategies.
Area Of Science
- Oncology
- Radiology
- Medical Imaging
Background
- Locally advanced cervical cancer (LACC) requires effective prognostic biomarkers for treatment stratification.
- Current prognostic models may not fully capture the complexity of treatment response and survival outcomes.
Purpose Of The Study
- To develop and validate a T2-weighted magnetic resonance imaging (MRI)-based radiomic signature.
- To assess the signature's association with disease-free survival (DFS) in LACC patients treated with chemoradiation.
Main Methods
- Radiomic features were extracted from MRI scans of 132 patients (training) and 199 patients (validation) using PyRadiomics.
- A prognostic model for DFS was developed using a minimal redundancy maximum relevancy feature selection method.
- Univariate and multivariable Cox regression analyses were performed to evaluate the radiomic signature's prognostic value.
Main Results
- The radiomic signature was prognostic for DFS in both training (HR 5.54, p=0.002; HR 3.59, p=0.04) and validation cohorts (HR 2.22, p=0.003; HR 1.84, p=0.04).
- The signature remained independently associated with DFS after adjusting for stage and tumor volume.
- Significant differences in 4-year DFS rates were observed between patients with high and low radiomic signature scores (e.g., 48.2% vs 87.9% in the training cohort).
Conclusions
- An MRI-based radiomic signature serves as a valuable prognostic biomarker for DFS in LACC patients.
- This signature can potentially guide treatment decisions and improve patient outcomes in chemoradiation therapy.

