用大模型生成逼真胸片，微调能显著提升效果。
Exploring Foundation Models for Synthetic Medical Imaging: A Study on Chest X-Rays and Fine-Tuning Techniques
- 基于预训练扩散模型，通过微调生成胸部X光图像。
- 微调后图像在医学专家评估中更真实，生成质量明显提升。
- 适合医疗数据稀缺场景下的合成数据研究者使用。
机器学习已显著推动医疗进步，但在疾病预防与诊疗识别中，患者数据因隐私和监管限制难以获取。生成合成且逼真的医疗数据为突破此瓶颈提供了可能，近期研究显示微调基础模型可有效实现这一目标。本文探索基础模型生成逼真医学图像（特别是胸部X光片）的潜力，并评估其性能随微调的提升情况。我们采用潜空间扩散模型，以预训练基础模型为基础，通过多种配置进行微调。此外，我们邀请医学专业人士对各训练模型生成的图像进行真实性评估，以验证生成质量。结果表明，经微调后的模型生成的图像在视觉逼真度和临床可用性上均有显著改善。
原文摘要 · Abstract (English)
Machine learning has significantly advanced healthcare by aiding in disease prevention and treatment identification. However, accessing patient data can be challenging due to privacy concerns and strict regulations. Generating synthetic, realistic data offers a potential solution for overcoming these limitations, and recent studies suggest that fine-tuning foundation models can produce such data effectively. In this study, we explore the potential of foundation models for generating realistic medical images, particularly chest x-rays, and assess how their performance improves with fine-tuning. We propose using a Latent Diffusion Model, starting with a pre-trained foundation model and refining it through various configurations. Additionally, we performed experiments with input from a medical professional to assess the realism of the images produced by each trained model.
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。