Dear Advanced Visualization Insider,
For many full-field digital mammography (FFDM) users, the results of the Digital Mammographic Imaging Screening Trial (DMIST) just reaffirmed what they already thought.
But did the trial results underestimate the impact of FFDM? It may have, owing to DMIST's necessary use of the technology available at the time. FFDM technology was just beginning to hit the market when the trial began, and image quality and processing are much better now, according to an article by contributing writer Cynthia E. Keen.
As an Advanced Visualization Insider subscriber, you have access to this Insider Exclusive article before it is published for the rest of our AuntMinnie.com members. To find out about more reactions to DMIST, click here.
Do you have a topic you'd like to see covered, or are you interested in submitting an article to AuntMinnie.com? Please feel free to drop me a line.
![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&dpr=2&fit=crop&h=167&q=70&w=250)
