基于多编码器潜在扩散模型的放射学报告条件三维CT生成
Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model
AI总结：
Report2CT提出一种以完整放射学报告为条件、融合三个医学文本编码器的三维潜在扩散模型，在20000个CT体数据上训练，实现高保真胸部CT生成，并在MICCAI 2025 VLM3D挑战赛中取得最优性能。
摘要：
文本到图像的潜在扩散模型近期推动了医学图像合成的发展，但在三维CT生成方面的应用仍然有限。现有方法依赖简化的提示文本，忽略了完整放射学报告中的丰富语义细节，从而降低了文本与图像的对齐程度和临床保真度。我们提出Report2CT，这是一个以放射学报告为条件的潜在扩散框架，能够直接从自由文本放射学报告中合成三维胸部CT体数据，并利用多个文本编码器同时纳入“发现”和“印象”部分。Report2CT集成了三个预训练的医学文本编码器（BiomedVLP CXR BERT、MedEmbed和ClinicalBERT），以捕捉细致的临床上下文。放射学报告和体素间距信息共同条件化一个三维潜在扩散模型，该模型在来自CT RATE数据集的20000个CT体数据上训练。模型性能使用Frechet Inception Distance（FID）评估真实与合成分布相似性，并使用基于CLIP的指标评估语义对齐，同时与GenerateCT模型进行了额外的定性和定量比较。Report2CT生成了解剖结构一致的CT体数据，具有出色的视觉质量和文本图像对齐能力。多编码器条件化提高了CLIP分数，表明自由文本放射学报告中的细粒度临床细节得到了更强的保留。无分类器引导进一步增强了对齐，仅在FID上产生轻微折衷。我们在MICCAI 2025的VLM3D挑战赛“文本条件CT生成”赛道中排名第一，并在所有评估指标上取得了最先进的性能。通过利用完整放射学报告和多编码器文本条件化，Report2CT推进了三维CT合成，生成了临床忠实且高质量的合成数据。
英文摘要：
Text to image latent diffusion models have recently advanced medical image synthesis, but applications to 3D CT generation remain limited. Existing approaches rely on simplified prompts, neglecting the rich semantic detail in full radiology reports, which reduces text image alignment and clinical fidelity. We propose Report2CT, a radiology report conditional latent diffusion framework for synthesizing 3D chest CT volumes directly from free text radiology reports, incorporating both findings and impression sections using multiple text encoder. Report2CT integrates three pretrained medical text encoders (BiomedVLP CXR BERT, MedEmbed, and ClinicalBERT) to capture nuanced clinical context. Radiology reports and voxel spacing information condition a 3D latent diffusion model trained on 20000 CT volumes from the CT RATE dataset. Model performance was evaluated using Frechet Inception Distance (FID) for real synthetic distributional similarity and CLIP based metrics for semantic alignment, with additional qualitative and quantitative comparisons against GenerateCT model. Report2CT generated anatomically consistent CT volumes with excellent visual quality and text image alignment. Multi encoder conditioning improved CLIP scores, indicating stronger preservation of fine grained clinical details in the free text radiology reports. Classifier free guidance further enhanced alignment with only a minor trade off in FID. We ranked first in the VLM3D Challenge at MICCAI 2025 on Text Conditional CT Generation and achieved state of the art performance across all evaluation metrics. By leveraging complete radiology reports and multi encoder text conditioning, Report2CT advances 3D CT synthesis, producing clinically faithful and high quality synthetic data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
