Deep learning and generative models are advancing rapidly, with synthetic data increasingly being integrated into training pipelines for downstream analysis tasks. However, in medical imaging, their adoption remains constrained by the scarcity of reliable annotated datasets. To address this limitation, we propose 3D-LLDM, a label-guided 3D latent diffusion model that generates high-quality synthetic magnetic resonance (MR) volumes with corresponding anatomical segmentation masks. Our approach uses hepatobiliary phase MR images enhanced with the Gd-EOB-DTPA contrast agent to derive structural masks for the liver, portal vein, hepatic vein, and hepatocellular carcinoma, which then guide volumetric synthesis through a ControlNet-based architecture. Trained on 720 real clinical hepatobiliary phase MR scans from Samsung Medical Center, 3D-LLDM achieves a Fr\'echet Inception Distance (FID) of 28.31, improving over GANs by 70.9% and over state-of-the-art diffusion baselines by 26.7%. When used for data augmentation, the synthetic volumes improve hepatocellular carcinoma segmentation by up to 11.153% Dice score across five CNN architectures.
@article{arxiv.2603.23845,
title = {3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation},
author = {Kyeonghun Kim and Jaehyeok Bae and Youngung Han and Joo Young Bae and Seoyoung Ju and Junsu Lim and Gyeongmin Kim and Nam-Joon Kim and Woo Kyoung Jeong and Ken Ying-Kai Liao and Won Jae Lee and Pa Hong and Hyuk-Jae Lee},
journal= {arXiv preprint arXiv:2603.23845},
year = {2026}
}
Comments
Accepted to ISBI 2026 (Oral). Camera-ready version