By Dave DeFusco
In artificial intelligence and healthcare, there’s a big problem that doesn’t get enough attention: a drought of good data. Deep learning—the kind of AI that powers everything from voice assistants to diagnostic imaging—needs massive amounts of data to work well but in healthcare, getting access to that kind of data is easier said than done.
Hospitals and medical centers often can’t—or won’t—share patient images like X-rays, MRIs or CT scans. Privacy concerns and strict regulations mean that many AI researchers simply don’t have enough high-quality, varied medical images to train their models. And without those datasets, it’s nearly impossible to build AI that can diagnose diseases across a broad spectrum of people and conditions.
A team of researchers from the Katz School's Department of Graduate Computer Science and Engineering has taken on this challenge with a powerful combination of creativity and cutting-edge computing. They’ve created a new dataset and AI tool that could dramatically change how medical images are made and used in the future—without compromising patient privacy.
“Since hospitals wouldn’t share enough data, we decided to build our own. We collected over 250,000 medical images from open-source databases—everything from brain scans to lung X-rays to animal images—and called the collection MedImgs,” said Lakshmikar Polamreddy, a lead author of the study, Katz School Ph.D. student in mathematics and 2023 graduate of the M.S. in Artificial Intelligence.
Polamreddy was joined in the research by current students in the M.S. Artificial Intelligence: Sheng-Han Yueh, Deepshikha Mahato, Shilpa Kuppili, Jialu Li and Kalyan Roy.
This new dataset includes 61 disease types and 159 total categories of images from both humans and animals. That variety is important, because AI models learn better when they see more examples, especially of rarer conditions. With the dataset ready, the researchers developed a new image generator called the Leapfrog Latent Consistency Model (LLCM). This model is built on top of a powerful class of AI called diffusion models, which are known for creating incredibly realistic images—think art, photos or even deepfakes.
But while traditional diffusion models are powerful, they’re also slow and computationally expensive. Creating just one high-resolution image can take dozens or even hundreds of steps. For medical applications where time, cost and efficiency matter, that’s a problem. That’s where the “leapfrog” idea comes in.
In the world of physics and math, leapfrog algorithms help solve complex equations quickly by jumping over unnecessary steps—hence the name. The team applied this method in a clever way: by solving a mathematical model of the image generation process in a more direct and efficient way, skipping the usual back-and-forth that diffusion models go through. Instead of taking 20, 50 or 100 steps to generate an image, the LLCM can create high-quality 512×512-pixel images in as few as one to four steps.
“That’s a huge improvement,” said Roy. "It means doctors, researchers and AI developers could someday generate medical images almost instantly to test new ideas, train algorithms or even simulate rare diseases for study—all without needing real patient data.”
To see how well their model worked, the researchers compared it to some of the biggest names in image generation: Stable Diffusion, Dreambooth and a previous model called Latent Consistency Model (LCM). They used a common measure of image quality called the Fréchet Inception Distance. Lower scores mean more realistic, higher-quality images. The LLCM blew away the competition, especially at earlier steps, showing that it could generate great images faster than the others. LLCM’s images looked much more like real medical scans, even with fewer steps.
To see if their model could handle totally new types of images, the researchers tested it on an unseen dataset of dog cardiac X-rays. It performed exceptionally well, even outshining the best AI models currently available. That’s important because it shows that LLCM isn’t just memorizing images—it’s learning to generalize, to synthesize realistic images it hasn’t seen before.
“One of the coolest things about LLCM is that it can be fine-tuned,” said Dr. Youshan Zhang, senior author of the study and assistant professor of artificial intelligence and computer science. “That means hospitals, labs or even veterinary clinics could customize it with their own small sets of medical images and generate thousands of realistic versions in just a few clicks. That would be a game changer for training diagnostic tools—especially in places where patient data is limited or inconsistent.”
