@inproceedings{390e9d67e46f430cb114583765ff7941,
title = "Generation of visualized medical rehabilitation exercise prescriptions with diffusion models",
abstract = "Visualization of medical rehabilitation exercise prescriptions is to provide a more intuitive and understandable way of conveying medical guidance through visual means. Currently, the generation of visualized medical rehabilitation exercise prescriptions is largely based on the manual use of software for hand drawing. However, not only does this production method exhibit the drawbacks of complexity and high labor costs, but it also suffers from low production efficiency. In this study, we present four novel methods that aim to harness the potential of existing Stable Diffusion to generate visualized medical rehabilitation exercise prescription outputs, as well as to exemplify the generation of visualized rehabilitation exercise prescriptions for frozen shoulders. Experimental results demonstrate that our approaches achieve high-quality and more precise visualized rehabilitation exercise prescriptions.",
keywords = "Diffusion Models, Medical Prescription, Visualization",
author = "Juewen Ni and Peng Du and Qihan Hu and Zhenghui Xu and Hao Zeng and Hao Xie and Youbing Zhao and Gengling Wang and Songjin Yang and Jian Song and Shengyou Lin",
note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on AI-generated Content, AIGC 2023 ; Conference date: 25-08-2023 Through 26-08-2023",
year = "2023",
month = nov,
day = "2",
language = "English",
isbn = "9789819975860",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "237--247",
editor = "Feng Zhao and Duoqian Miao",
booktitle = "AI-generated Content - 1st International Conference, AIGC 2023, Revised Selected Papers",
address = "Germany",
}