Computer-aided detection developer R2 Technology of Sunnyvale said the results of a paper published in the August issue of Radiology indicate that its technology boosted breast cancer detection by 7.4% in an academic medical setting.
The prospective study was conducted at Stanford University Hospital in Stanford, CA, and examined 8,682 women who received routine screening mammograms over a period of 18 months. Each mammogram was interpreted by a radiologist, followed by re-evaluation of the mammogram by R2's ImageChecker CAD system.
The 7.4% increase in cancer detection was significant because it indicates that even highly trained radiologists can benefit from CAD, according to the company. There was an increase in the recall rate that was similar to the increase in the cancer detection rate.
By AuntMinnie.com staff writers
July 25, 2005
Related Reading
R2 adds pulmonary artery patency exam tool, June 16, 2005
R2 updates mammo CAD, June 3, 2005
R2 debuts ImageChecker 2.0 for CT, May 17, 2005
R2 adds to executive lineup, May 13, 2005
iCAD, R2 in patent dispute, April 28, 2005
Copyright © 2005 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&dpr=2&fit=crop&h=167&q=70&w=250)
