3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917360931176448 |
|---|---|
| author | Kim, Kyeonghun Bae, Jaehyeok Han, Youngung Bae, Joo Young Ju, Seoyoung Lim, Junsu Kim, Gyeongmin Kim, Nam-Joon Jeong, Woo Kyoung Liao, Ken Ying-Kai Lee, Won Jae Hong, Pa Lee, Hyuk-Jae |
| author_facet | Kim, Kyeonghun Bae, Jaehyeok Han, Youngung Bae, Joo Young Ju, Seoyoung Lim, Junsu Kim, Gyeongmin Kim, Nam-Joon Jeong, Woo Kyoung Liao, Ken Ying-Kai Lee, Won Jae Hong, Pa Lee, Hyuk-Jae |
| contents | 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 Fréchet 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23845 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation Kim, Kyeonghun Bae, Jaehyeok Han, Youngung Bae, Joo Young Ju, Seoyoung Lim, Junsu Kim, Gyeongmin Kim, Nam-Joon Jeong, Woo Kyoung Liao, Ken Ying-Kai Lee, Won Jae Hong, Pa Lee, Hyuk-Jae Computer Vision and Pattern Recognition 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 Fréchet 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. |
| title | 3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.23845 |