Deep learning fusion of CT and MRI achieves high accuracy for HCC grading across centers

A cross-modal deep learning model combining CT and MRI achieved AUCs 0.754 and 0.790 in external validation for hepatocellular carcinoma grading, surpassing unimodal approaches (AUC 0.53-0.745).

• CMIF fused CT anatomical detail with MRI functional features using self-supervised DINOv2.
• External validation AUCs of 0.754 and 0.790 vs. 0.53-0.745 for baseline methods.
• Retrospective study of 270 patients from four centers, with internal and external validation.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.