Saved in:
Bibliographic Details
Main Authors: Polamreddy, Lakshmikar R., Roy, Kalyan, Yueh, Sheng-Han, Mahato, Deepshikha, Kuppili, Shilpa, Li, Jialu, Zhang, Youshan
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