Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15084 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909400041521152 |
|---|---|
| author | Polamreddy, Lakshmikar R. Roy, Kalyan Yueh, Sheng-Han Mahato, Deepshikha Kuppili, Shilpa Li, Jialu Zhang, Youshan |
| author_facet | Polamreddy, Lakshmikar R. Roy, Kalyan Yueh, Sheng-Han Mahato, Deepshikha Kuppili, Shilpa Li, Jialu Zhang, Youshan |
| contents | The scarcity of accessible medical image data poses a significant obstacle in effectively training deep learning models for medical diagnosis, as hospitals refrain from sharing their data due to privacy concerns. In response, we gathered a diverse dataset named MedImgs, which comprises over 250,127 images spanning 61 disease types and 159 classes of both humans and animals from open-source repositories. We propose a Leapfrog Latent Consistency Model (LLCM) that is distilled from a retrained diffusion model based on the collected MedImgs dataset, which enables our model to generate real-time high-resolution images. We formulate the reverse diffusion process as a probability flow ordinary differential equation (PF-ODE) and solve it in latent space using the Leapfrog algorithm. This formulation enables rapid sampling without necessitating additional iterations. Our model demonstrates state-of-the-art performance in generating medical images. Furthermore, our model can be fine-tuned with any custom medical image datasets, facilitating the generation of a vast array of images. Our experimental results outperform those of existing models on unseen dog cardiac X-ray images. Source code is available at https://github.com/lskdsjy/LeapfrogLCM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15084 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation Polamreddy, Lakshmikar R. Roy, Kalyan Yueh, Sheng-Han Mahato, Deepshikha Kuppili, Shilpa Li, Jialu Zhang, Youshan Image and Video Processing Computer Vision and Pattern Recognition Machine Learning The scarcity of accessible medical image data poses a significant obstacle in effectively training deep learning models for medical diagnosis, as hospitals refrain from sharing their data due to privacy concerns. In response, we gathered a diverse dataset named MedImgs, which comprises over 250,127 images spanning 61 disease types and 159 classes of both humans and animals from open-source repositories. We propose a Leapfrog Latent Consistency Model (LLCM) that is distilled from a retrained diffusion model based on the collected MedImgs dataset, which enables our model to generate real-time high-resolution images. We formulate the reverse diffusion process as a probability flow ordinary differential equation (PF-ODE) and solve it in latent space using the Leapfrog algorithm. This formulation enables rapid sampling without necessitating additional iterations. Our model demonstrates state-of-the-art performance in generating medical images. Furthermore, our model can be fine-tuned with any custom medical image datasets, facilitating the generation of a vast array of images. Our experimental results outperform those of existing models on unseen dog cardiac X-ray images. Source code is available at https://github.com/lskdsjy/LeapfrogLCM. |
| title | Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.15084 |