用标签引导生成高分辨率肝脏MRI，提升癌症分割效果
3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation
- 基于控制网架构，用解剖标签指导3D扩散模型生成真实MR图像
- 生成图像FID达28.31，优于生成对抗网络70.9%以上
- 合成数据可提升肝癌分割性能，最高增益11.153%的骰子分数
深度学习与生成模型快速发展，合成数据正被引入下游分析任务训练流程。然而在医学影像领域，其应用受限于高质量标注数据集稀缺。为此，我们提出3D-LLDM——一种标签引导的3D潜在扩散模型，可生成带有对应解剖分割掩码的高质量合成磁共振（MR）体数据。该方法利用含Gd-EOB-DTPA对比剂的肝胆期MR图像，提取肝脏、门静脉、肝静脉及肝细胞癌的结构掩码，并通过基于ControlNet的架构引导三维体数据合成。模型在三星医疗中心720例真实临床肝胆期MR扫描上训练，实现28.31的弗雷切特初始距离（FID），相比GAN提升70.9%，较当前最优扩散基线提升26.7%。用于数据增强时，合成数据可使五种CNN架构的肝细胞癌分割Dice分数最高提升11.153%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。