Meeting Banner
Abstract #1392

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

Yuchi Tian1, Zihan Xi2,3, Dongcheng Ren4, and Xiaoyun Liang1
1Institute of Research and Clinical Innovations,Neusoft Medical Systems Co., Ltd, Shanghai, China, 2Baoding No.1 Center Hospital, Baoding, China, 3Zhejiang Cancer Hospital, Hangzhou, China, 4School of Mechanical Engineering, Hebei University of Technology, Tianjin, China

Synopsis

Keywords: Diagnosis/Prediction, Diagnosis/Prediction

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

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords