当前位置: X-MOL 学术Nat. Biomed. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Synthetic chest X-ray images from text prompts
Nature Biomedical Engineering ( IF 26.8 ) Pub Date : 2024-10-07 , DOI: 10.1038/s41551-024-01261-z
Daniel Truhn, Jakob Nikolas Kather

A latent diffusion model pre-trained on pairs of natural images and text descriptors can be adapted to generate realistic chest radiographs that are controlled by free-form medical text prompts.

中文翻译:


来自文本提示的合成胸部 X 线图像



在自然图像和文本描述符对上预先训练的潜在扩散模型可以适应,以生成由自由格式的医学文本提示控制的逼真胸片。
更新日期:2024-10-07
down
wechat
bug