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

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.