Women receiving hormone replacement therapy (HRT) are no likelier to need a follow-up mammogram than women not taking the hormones, according to researchers at Massachusetts General Hospital in Boston. Previous studies have inferred that hormone replacement therapy can increase breast density, thus making it necessary for further screening, according to the American Roentgen Ray Society in Leesburg, VA. The MGH study indicates that HRT rarely complicates the interpretation of screening mammograms.
A team of 10 MGH radiologists reviewed the cases of 25,297 patients who had routine screenings between May 1995 and September 1997. In the cases studied, 6,504 of the women had been using HRT at the time of their mammograms.
Comparing the women on HRT and those not on the therapy, the results showed that only 7.4% of women on HRT needed follow-up imaging, the same as for women not on HRT. Less than 1% of the recalls for women on HRT were related to the use of the hormone therapy. The MGH investigators will present their results at the annual ARRS meeting, to be held on May 7-12 in Washington, DC.
By AuntMinnie.com staff writersMay 1, 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)
