HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models

2025/04/25 by Jens Hooge, Hooge, Jens, Gerard Sanroma‐Guell +15
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Hepatocellular Carcinoma Treatment and Prognosis #Image and Video Processing (eess.IV) #MRI in cancer diagnosis #Medical Image Segmentation Techniques #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2504.18405

openalex publication_date 2025/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a crucial role in the detection and characterization of focal liver lesions, with the hepatobiliary phase (HBP) providing essential diagnostic information. However, acquiring HBP images requires prolonged scan times, which may compromise patient comfort and scanner throughput. In this study, we propose a deep learning based approach for synthesizing HBP images from earlier contrast phases (precontrast and transitional) and compare three generative models: a perceptual U-Net, a perceptual GAN (pGAN), and a denoising diffusion probabilistic model (DDPM). We curated a multi-site DCE-MRI dataset from diverse clinical settings and introduced a contrast evolution score (CES) to assess training data quality, enhancing model performance. Quantitative evaluation using pixel-wise and perceptual metrics, combined with qualitative assessment through blinded radiologist reviews, showed that pGAN achieved the best quantitative performance but introduced heterogeneous contrast in out-of-distribution cases. In contrast, the U-Net produced consistent liver enhancement with fewer artifacts, while DDPM underperformed due to limited preservation of fine structural details. These findings demonstrate the feasibility of synthetic HBP image generation as a means to reduce scan time without compromising diagnostic utility, highlighting the clinical potential of deep learning for dynamic contrast enhancement in liver MRI. A project demo is available at: https://jhooge.github.io/hepatogen

Citations

• Soft Masked Mamba Diffusion Model for CT to MRI Conversion
• Similarity-aware Syncretic Latent Diffusion Model for Medical Image Translation with Representation Learning
• Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Synthesis of Contrast-Enhanced Breast MRI Using Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanism
• DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
• CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
• Using Machine Learning to Reduce the Need for Contrast Agents in Breast MRI through Synthetic Images
• Diffusion Models for Contrast Harmonization of Magnetic Resonance Images
• Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRI
• Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models
• Unsupervised Medical Image Translation with Adversarial Diffusion Models
• A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion
• Diffusion Models for Implicit Image Segmentation Ensembles
• Breaking the Dilemma of Medical Image-to-image Translation
• Generative Adversarial Networks
• Diffusion Models Beat GANs on Image Synthesis
• Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery
• A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agents
• Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
• Generative Modeling by Estimating Gradients of the Data Distribution
• Residual Flows for Invertible Generative Modeling
• DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis
• Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network
• Deep CT to MR Synthesis using Paired and Unpaired Data
• Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size
• Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Computational Radiomics System to Decode the Radiographic Phenotype
• Deep MR to CT Synthesis using Unpaired Data
• Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
• Density estimation using Real NVP
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• Deep multi-scale video prediction beyond mean square error
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• N4ITK: Improved N3 Bias Correction
• Image quality assessment: from error visibility to structural similarity

Related

• T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis
• CT Data Curation for Liver Patients: Phase Recognition in Dynamic Contrast-Enhanced CT
• The 1st Solution for CARE Liver Task Challenge 2025: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation
• A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI
• AAD-DCE: An Aggregated Multimodal Attention Mechanism for Early and Late Dynamic Contrast Enhanced Prostate MRI Synthesis