Researchers at Ben-Gurion University of the Negev have developed a tool called DISCOVER, which helps explain how AI makes decisions in medical imaging. DISCOVER works by breaking down images into important parts that are clinically meaningful, making it easier to understand the AI’s reasoning. This is especially useful in medicine, where understanding how decisions are made is very important.
In partnership with Israeli startup AIVF, the team tested this tool on images from IVF embryo scans, MRI scans of Alzheimer’s patients, and other standard photos. DISCOVER uses generative AI to create synthetic images that highlight the key features that the AI used to make its decisions, helping to improve diagnostic accuracy in clinical settings.
This technology shows how AI can find important medical details that human experts might miss, potentially advancing areas like fertility treatments and disease diagnosis. The research, led by PhD student Oded Rotem and guided by Prof. Assaf Zaritsky, was recently published in Nature Communications and supported by the Rosetrees Trust and the Israeli Council for Higher Education.
Source: themedialine
