Dear AuntMinnie Member,
The growing use of mammography computer-aided detection software is creating a mountain of documentation in the form of printouts and digital files that indicate areas on mammograms that could have cancer. Since these documents are used only as reference materials by breast imaging specialists, they can be discarded after the interpretation takes place, right?
Not so fast. How to properly handle CAD markings is becoming a thorny legal issue, and is the subject of a new article by contributing writer Cynthia Keen in our Advanced Visualization Digital Community.
Some mammography experts are recommending that sites save their CAD documentation and include them as part of the patient's medical record. Saving CAD markings could help protect a mammography practice in a malpractice case, and CAD documents have already been used in the successful defense of a lawsuit against an Ohio practice.
Read all about it by clicking here, or go to our Advanced Visualization Digital Community at av.auntminie.com for all the latest news on advanced visualization technologies.
In other news, our thoughts go out to the victims of Hurricane Katrina in the southeastern U.S. The disaster has already wreaked an awful toll, but operators of MRI scanners that have been without power for several days may face an additional risk of their magnets quenching if power is not restored. Read about how to deal with the situation by clicking here.
If you haven't already done so, you can make a donation to help with hurricane relief efforts by visiting the American Red Cross, at www.redcross.org.
![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)
