Segmentation Tool Lets Medical Professionals ‘Teach’ Computers to Correctly Annotate Medical Images

Jacobs School of Medicine and Biomedical Sciences researchers have developed a tool that lets medical professionals analyze images without having to rely on engineering expertise to interpret medical images. “We have created an automatic, human-in-the-loop segmentation tool for pathologists and radiologists,” said Pinaki Sarder, PhD, associate professor of pathology and anatomical sciences. “With our system, you don't have to know any machine learning. Now medical professionals can do structure annotation by themselves.”