Meeting Banner
Abstract #5096

AI-Derived MRI Biomarkers Using Vision Transformer for Predicting Combination Immunotherapy Outcomes in Liver Cancer

Guangbo Yu1, Aydin Eresen2, Zigeng Zhang2, Qiaoming Hou2, Farideh Amirrad3, Sha Webster3, Surya Nauli3, Vahid Yaghmai2, and Zhuoli Zhang2
1Department of Biomedical Engineering, University of California, Irvine, Irvine, CA, United States, 2Department of Radiological Sciences, University of California, Irvine, Irvine, CA, United States, 3Chapman University, Irvine, CA, United States

Synopsis

Keywords: Diagnosis/Prediction, Machine Learning/Artificial Intelligence

Motivation: Predicting liver cancer treatment outcomes, especially for combination therapies, is challenging due to the limited sensitivity of conventional MRI. This study uses a Vision Transformer model to enhance response specificity.

Goal(s): To develop and validate an MRI-based classification model that accurately differentiates outcomes across control, single (NK or Sorafenib), and combination (NK + Sorafenib) treatments in an HCC rat model.

Approach: Multi-parametric MRI data from a Buffalo rat model with liver-implanted McA-RH7777 cells were analyzed using a ViT model to classify treatment outcomes.

Results: The model achieved an accuracy of 79.4%, sensitivity of 78.1%, specificity of 79.5%, and an AUROC of 90.1%

Impact: This study showcases the potential of ViT-based MRI analysis in distinguishing HCC treatment outcomes, enabling more precise combination therapy selection and advancing personalized care for improved patient outcomes.

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