Hepatobiliary Phase Synthesis Using Multi-Task Learning GAN: Application to Liver Fibrosis Classification

Motivation: Hepatobiliary phase (HBP) has important clinical diagnostic value for liver diseases, but its long acquisition time can pose issues with scanning resources and patient cooperation. Goal(s): Our goal was to design a generative model for HBP synthesis based on early phases in hepatobiliary-specific contrast-enhanced MRI. Approach: We proposed a multi-task learning deep learning model and evaluated its performance on a multi-center dataset. Results: The proposed model exhibited superior HBP synthesis performance compared to the classic Pix2Pix model. The synthetic HBP was comparable to the real HBP, and significantly outperformed early phases in subsequent liver fibrosis grading tasks. Impact: The proposed approach has the potential to accurately synthesize HBP, which is expected to be extended to clinical practice for rapid acquisition of HBP in hepatobiliary-specific contrast-enhanced MRI, thereby significantly reducing scanning time and alleviating clinical stress.