Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation

TL;DR

The paper introduces LLCM, a novel diffusion-based model for real-time high-resolution medical image generation, trained on a large diverse dataset, and capable of fine-tuning for various medical imaging tasks.

Contribution

We propose LLCM, a leapfrog latent diffusion model that accelerates medical image generation using PF-ODE in latent space, with state-of-the-art results and fine-tuning capabilities.

Findings

State-of-the-art performance in medical image generation.

Fast sampling enabled by PF-ODE in latent space.

Effective fine-tuning on custom datasets.

Abstract

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.