Predictive Potential of Contrast-Enhanced MRI-Based Delta-Radiomics for Chemoradiation Responsiveness in...

Area of Science:

• Radiology
• Oncology
• Medical Imaging Analysis

Background:

• Delta-radiomics analyzes feature variations across different time-points.
• Predicting therapeutic response to chemoradiotherapy (CRT) in muscle-invasive bladder cancer (MIBC) is crucial for treatment planning.
• Contrast-enhanced (CE) and non-contrast-enhanced (NE) T1-weighted images (WI) offer distinct information for analysis.

Purpose of the Study:

• To assess the utility of delta-radiomics feature analysis in predicting CRT response in MIBC patients.
• To compare the predictive performance of delta-radiomics models with traditional radiomics models using CE-T1WI alone.

Main Methods:

• Retrospective review of 43 non-metastatic MIBC patients undergoing cystectomy after induction CRT.
• Texture analysis of pre-therapeutic 1.5-T MRI using LIFEx software.
• Construction of predictive models using 112 delta-radiomics features and machine learning algorithms, including Extreme Gradient Boosting.

Main Results:

• 21 patients (49%) achieved pathological complete response (pCR).
• The best delta-radiomics model achieved an AUC of 0.85 (95% CI: 0.75-0.95) using four signal intensity-based features.
• Delta-radiomics significantly outperformed the best CE-T1WI radiomics model (AUC: 0.63, 95% CI: 0.50-0.75).

Conclusions:

• Delta-radiomics applied to pre-therapeutic CE- and NE-MRI shows promising predictive ability for CRT responsiveness in MIBC.
• This approach can potentially guide treatment decisions before therapy initiation.
• Further validation is warranted to integrate this technique into clinical practice.