Gastrointestinal stromal tumors are tumors of the digestive tract that grow underneath the mucus layer covering our organs. Because they are deep inside the tissue, these ’submucosal tumors‘ are difficult to detect and diagnose, even with a biopsy. Now, researchers have developed a novel minimally invasive and accurate method using infrared imaging and machine learning to distinguish between normal tissue and tumor areas. This technique has a strong potential for widespread clinical use.