Triple-Phase Sequential Fusion Network for Hepatobiliary Phase Liver MRI Synthesis

TL;DR

This paper introduces TriPF-Net, a novel neural network that synthesizes hepatobiliary phase MRI images from multiple dynamic contrast-enhanced sequences, improving efficiency and robustness in liver imaging.

Contribution

The study presents a new triple-phase fusion network that adaptively integrates multi-phase MRI data for accurate HBP synthesis, even with missing sequences.

Findings

TriPF-Net outperforms conventional methods in MAE, PSNR, and SSIM metrics.

The model demonstrates robust performance across datasets from two different centers.

Clinical variables further enhance the physiological accuracy of synthesized images.

Abstract

Gadoxetate disodium-enhanced MRI is essential for the detection and characterization of hepatocellular carcinoma. However, acquisition of the hepatobiliary phase (HBP) requires a prolonged post-contrast delay, which reduces workflow efficiency and increases the risk of motion artifacts. In this study, we propose a Triple-Phase Sequential Fusion Network (TriPF-Net) to synthesize HBP images by leveraging the sequential information from pre-HBP sequences: while T1-weighted imaging serves as the indispensable baseline, the model adaptively integrates arterial-phase (AP) and venous-phase (VP) features when available. By modeling the tissue-specific contrast uptake and excretion dynamics across these three phases, TriPF-Net ensures robust HBP synthesis even under the stochastic absence of one or both dynamic contrast-enhanced sequences. The framework comprises an Enhanced Region-Guided Encoder and a Dynamic Feature Unification Module, optimized with a Region-Guided Sequential Fusion Loss to maintain physiological consistency. In addition, clinical variables, including age, sex, total bilirubin, and albumin, are incorporated to enhance physiological consistency. Compared with conventional methods, TriPF-Net achieved superior performance on datasets from two centers. On the internal dataset, the model achieved an MAE of 10.65, a PSNR of 23.27, and an SSIM of 0.76. On the external validation dataset, the corresponding values were 12.41, 23.11, and 0.78, respectively. This flexible solution enhances clinical workflow and lesion depiction, potentially eliminating the need for delayed HBP acquisition in HCC imaging.