The Mammography Matters newsletter will no longer be published in a free, hard-copy format starting with the spring 2000 issue, but can be accessed at the Web site for the Center for Devices and Radiological Health. Produced by the Food and Drug Administration, Mammography Matters offers up-to-date information on the Mammography Quality Standards Act, as well as other new developments in the breast cancer care community.
Paper copies of the newsletter will now cost $48 for a one-year subscription. For more information, contact the National Technical Information Service at 800-363-2068 and request an order form for publication SUB9945.
Mammography Matters also has a new editor: Founder Carole Sierka retired in December 1999. Evelyn Wandell, the newsletter's production manager, took over the position with the winter 2000 issue.
The FDA's Mammography Program Web site recently underwent changes to render it more user-friendly. The Policy Guidance Help System is a multidocument, regularly updated search engine focusing on implementation of the MQSA. In addition, the site will offer access to a PowerPoint slide presentation and speech on the MQSA final regulations that can be downloaded for public use.
By AuntMinnie.com staff writersApril 6, 2000
Copyright © 2000 AuntMinnie.com
![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=100&q=70&w=100)
![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)
