{"id":236,"date":"2025-08-01T08:36:59","date_gmt":"2025-08-01T15:36:59","guid":{"rendered":"https:\/\/scienceblog.com\/neuroedge\/?p=236"},"modified":"2025-08-01T08:36:59","modified_gmt":"2025-08-01T15:36:59","slug":"new-ai-learns-to-read-scans-with-just-a-few-examples","status":"publish","type":"post","link":"https:\/\/scienceblog.com\/neuroedge\/2025\/08\/01\/new-ai-learns-to-read-scans-with-just-a-few-examples\/","title":{"rendered":"New AI Learns to Read Scans With Just a Few Examples"},"content":{"rendered":"

A team of researchers at the University of California San Diego has developed a new artificial intelligence tool that can learn to read medical images using only a fraction of the data typically required. The system, called GenSeg, dramatically cuts down the amount of expert-labeled scans needed to train diagnostic models, reducing data demands by up to 20 times. The breakthrough could help bring powerful imaging tools to hospitals and clinics with fewer resources, where annotated datasets are often scarce.<\/p>\n

Learning From Just a Handful of Examples<\/h2>\n

Medical image segmentation, where each pixel in a scan is labeled as healthy or diseased tissue, is a cornerstone of many diagnostic tasks. Traditionally, training AI to perform segmentation has required thousands of pixel-by-pixel annotated images. But creating these datasets is expensive and time-consuming, often requiring highly trained specialists.<\/p>\n

“Creating such datasets demands expert labor, time and cost,” said Li Zhang, lead author and PhD student in electrical and computer engineering at UC San Diego. “For many medical conditions, that level of data simply does not exist.”<\/p>\n

GenSeg changes the game. It can learn from as few as 40 labeled images and still match or outperform standard methods trained on hundreds. The key is how it learns. GenSeg doesn’t just consume data, it generates it, smartly.<\/p>\n

How It Works<\/h2>\n

GenSeg operates in stages. First, it learns how to generate realistic images from expert-labeled segmentation masks. Then it creates synthetic image-mask pairs to supplement the small real-world dataset. These combined examples are used to train a segmentation model. Through a feedback loop, the system tweaks its image generation based on how well the model performs.<\/p>\n

“The segmentation performance itself guides the data generation process,” Zhang explained. “This ensures that the synthetic data are not just realistic, but also specifically tailored to improve the model’s segmentation capabilities.”<\/p>\n

What It Can Do<\/h2>\n

GenSeg was tested on 19 datasets across a wide range of imaging types and medical conditions. It learned to identify:<\/p>\n