Deep Learning Model based on multi-parametric MRI for Accurate Prediction of D-TACE Efficacy in Hepatocellular Carcinoma

Motivation: HCC presents a significant treatment challenge due to varying patient responses to D-TACE. Current prediction methods often lack precision and rely on subjective assessments, limiting their effectiveness in personalized treatment planning Goal(s): This study aimed to develop an accurate, automated prediction model for D-TACE efficacy by integrating multi-parametric MRI to enhance treatment outcome prediction Approach: Using a deep learning framework, multi-parametric MRI features —arterial phase , diffusion-weighted imaging, and T2-weighted imaging —were combined to create a fusion model, capturing comprehensive tumor characteristics to improve predictive performance Results: The fusion model achieved an AUC score of 0.829, outperforming single-sequence models and enhancing clinical decision-making for HCC patients Impact: This model provides a non-invasive, reliable tool for predicting D-TACE outcomes, potentially transforming personalized treatment planning for HCC. Enhanced prediction accuracy can improve patient outcomes and optimize healthcare resources by tailoring treatment to individual needs