The ECOG-ACRIN Cancer Research Group is now recruiting medical facilities in preparation for the launch of the Tomosynthesis Mammography Imaging Screening Trial (TMIST) in mid-2017.
With the goal of providing a modern basis for the continued use of mammography for breast cancer screening, TMIST will enroll 165,000 asymptomatic women in the U.S. and Canada between the ages of 45 and 74. The trial will compare the incidence of advanced cancers in those screened for four years with digital breast tomosynthesis and those screened with standard digital mammography, according to the group. The U.S. National Cancer Institute (NCI) has approved TMIST for funding.
TMIST will require nearly 100 sites, with each enrolling about four to five women per day to reach the trial's patient accrual goal in about three years. To participate in TMIST, a medical facility must be:
- Located in the U.S. or Canada
- Able to provide both imaging methods in the same location
- A member of a research group in the NCI National Clinical Trials Network (NCTN), either directly or through the NCI Community Oncology Research Program (NCORP)
Those who are interested in participating can attend one of two TMIST informational sessions at the upcoming RSNA 2016 meeting in Chicago. One TMIST satellite session will be held Monday, November 28, from 1:30 p.m. to 2:30 p.m. in Room W470A at McCormick Place, while the second session will be held on Wednesday, November 30, from 11 a.m. to 12 p.m. in Room W192B. Preregistration is not required.












![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)





