A Duke University researcher is launching a U.S. study that will investigate how best to treat early breast cancer.
The study, called Comparison of Operative to Medical Endocrine Therapy (COMET), will focus on ductal carcinoma in situ (DCIS). Dr. E. Shelley Hwang, chief of breast surgery at Duke Cancer Institute, will lead the study through a cooperative group, the Alliance for Clinical Trials in Oncology. The effort will be funded by a $13.4 million, five-year award from the Patient-Centered Outcomes Research Institute (PCORI).
DCIS is diagnosed annually in 60,000 U.S. women, and it's usually treated the same way as advanced breast cancers, with surgery and radiation therapy, according to a statement released by Duke. But physicians and researchers are concerned about whether these treatments are necessary, since DCIS does not tend to grow rapidly or spread in the majority of women.
The study will include 900 patients diagnosed with low-risk DCIS from 100 cancer centers throughout the U.S.; enrollment will begin later this year. Participants will be randomized to receive either the current standard of care -- surgery and radiation therapy -- or careful monitoring with mammograms and physical exams every six months.













![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)





