解耦稳定扩散潜空间中用于因子化医学图像生成的语言引导轨迹遍历
Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation
AI总结：
首次探讨微调预训练视觉-语言基础模型在医学图像潜空间解耦中的能力，设计框架通过Stable Diffusion潜空间轨迹遍历识别与操纵关键属性，实现因子化医学图像的精确生成与插值。
摘要：
文本到图像扩散模型已展现出从自然语言提示生成逼真图像的卓越能力。这些高分辨率、语言引导的合成图像对于疾病可解释性或探索因果关系至关重要。然而，它们在医学成像等专业领域解耦和控制潜在变异因子的潜力仍未被充分探索。在本研究中，我们首次探讨了预训练视觉-语言基础模型在医学图像数据集上微调后，执行潜空间解耦以实现因子化医学图像生成与插值的能力。通过对胸部X光和皮肤数据集的广泛实验，我们表明微调后的语言引导Stable Diffusion本质上学会了因子化图像生成的关键属性，例如患者的解剖结构或疾病诊断特征。我们设计了一个框架，通过生成模型的潜空间轨迹遍历来识别、隔离和操纵关键属性，从而实现对医学图像合成的精确控制。
英文摘要：
Text-to-image diffusion models have demonstrated a remarkable ability to generate photorealistic images from natural language prompts. These high-resolution, language-guided synthesized images are essential for the explainability of disease or exploring causal relationships. However, their potential for disentangling and controlling latent factors of variation in specialized domains like medical imaging remains under-explored. In this work, we present the first investigation of the power of pre-trained vision-language foundation models, once fine-tuned on medical image datasets, to perform latent disentanglement for factorized medical image generation and interpolation. Through extensive experiments on chest X-ray and skin datasets, we illustrate that fine-tuned, language-guided Stable Diffusion inherently learns to factorize key attributes for image generation, such as the patient's anatomical structures or disease diagnostic features. We devise a framework to identify, isolate, and manipulate key attributes through latent space trajectory traversal of generative models, facilitating precise control over medical image synthesis.
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。
