A Dual-phase Enhanced CT-based Nomogram for Predicting the Response to Neoadjuvant Chemotherapy in Locally Advanced...

Area of Science:

• Oncology
• Radiology
• Medical Imaging

Background:

• Early prediction of neoadjuvant chemotherapy (NAC) response is crucial for optimizing treatment in locally advanced gastric cancer (LAGC).
• Dual-phase contrast-enhanced CT (CECT) offers rich imaging data for potential predictive biomarkers.
• Current prediction methods may lack the precision needed for individualized treatment planning.

Purpose of the Study:

• To develop and validate a radiomics nomogram for predicting NAC response in LAGC patients.
• To integrate radiomics features from dual-phase CECT with clinicopathological characteristics.
• To assess the nomogram's predictive performance and clinical utility compared to existing models.

Main Methods:

• Retrospective analysis of 143 LAGC patients.
• Extraction of radiomics features from arterial (AP) and venous (VP) phase CECT images.
• Development of AP, VP, and combined AP_VP radiomics models, and a nomogram integrating radiomics with clinical factors.
• Evaluation using ROC curves, DCA, calibration curves, NRI, and IDI.

Main Results:

• The combined AP_VP radiomics model showed good performance (AUC 0.810 training, 0.745 validation).
• The nomogram integrating radiomics and clinicopathological data achieved high AUCs (0.845 training, 0.829 validation).
• The nomogram significantly outperformed the clinical model (p < 0.05), demonstrating superior predictive accuracy.

Conclusions:

• A nomogram combining dual-phase CECT radiomics and clinicopathological data effectively predicts NAC response in LAGC.
• This tool can assist clinicians in making informed, individualized treatment decisions for LAGC patients.
• The nomogram offers enhanced predictive performance, potentially improving treatment outcomes.