用扩散模型根据病灶和扫描方式生成脑MRI，提升数据量且保护隐私。
Diffusion Models for conditional MRI generation
- 基于病理和扫描模态条件生成脑MRI，采用潜在扩散模型。
- 生成图像与真实图像分布相近，FID低至23.1，MS-SSIM达0.93。
- 可生成训练未见的组合，适合医学数据增强与隐私保护研究。
本文提出一种潜在扩散模型（LDM），用于生成脑部磁共振成像（MRI），根据病理状态（健康、胶质母细胞瘤、硬化、痴呆）和扫描模态（T1w、T1ce、T2w、Flair、PD）进行条件生成。通过弗雷歇起始距离（FID）和多尺度结构相似性指数（MS-SSIM）评估生成图像质量，结果表明生成图像在视觉保真度与多样性之间取得平衡，分布接近真实数据。模型还展现出外推能力，能生成训练数据中未出现的模态-病理组合。该方法有助于扩充临床数据集，缓解类别不平衡问题，并在不泄露患者隐私的前提下评估医学AI模型，推动放射科诊断工具的发展。
原文摘要 · Abstract (English)
In this article, we present a Latent Diffusion Model (LDM) for the generation of brain Magnetic Resonance Imaging (MRI), conditioning its generation based on pathology (Healthy, Glioblastoma, Sclerosis, Dementia) and acquisition modality (T1w, T1ce, T2w, Flair, PD). To evaluate the quality of the generated images, the Fréchet Inception Distance (FID) and Multi-Scale Structural Similarity Index (MS-SSIM) metrics were employed. The results indicate that the model generates images with a distribution similar to real ones, maintaining a balance between visual fidelity and diversity. Additionally, the model demonstrates extrapolation capability, enabling the generation of configurations that were not present in the training data. The results validate the potential of the model to increase in the number of samples in clinical datasets, balancing underrepresented classes, and evaluating AI models in medicine, contributing to the development of diagnostic tools in radiology without compromising patient privacy.
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。