Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation
This addresses the problem of limited medical image data for training deep learning models in healthcare, enabling broader access for diagnosis, though it appears incremental as it builds on existing diffusion and consistency model frameworks.
The authors tackled the scarcity of medical image data by proposing the Leapfrog Latent Consistency Model (LLCM), which generates high-resolution medical images in real-time, achieving state-of-the-art performance on a dataset of over 250,000 images and outperforming existing models on unseen dog cardiac X-ray images.
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.