Artificial Intelligence for Breast Cancer Diagnosis: Sensitive But Not Specific

Artificial Intelligence for Breast Cancer Diagnosis

Researchers at the University of Washington and the University of California at Los Angeles (UCLA) have developed a machine-learning system that confirms breast cancer diagnoses made by radiologists, a recent paper in JAMA Network Open reports. Skilled diagnosticians differ in their interpretation of radiographic images of different forms of cancer. Concordance among physicians, in recent research…

Read More

Current Breast Cancer Screening Guidelines Including for At-Risk Women

Mature female doctor assisting young patient undergoing mammogram

The American College of Radiology updated their guidelines for mammographic screenings recently. The ACR strongly supports early screening with particular detail to at-risk women. The ARC Commission on Breast Imaging evaluated numerous studies regarding effective methods for screening women at higher risk for breast cancer. The evaluation utilized the American College of Radiology’s Appropriateness Criteria®…

Read More

Medical Excellence Doesn’t Mean You Never Have to Say “I’m Sorry”

I'm sorry on a blue background

Every radiologist worries about missing a diagnosis or giving a false-positive reading, but diagnostic errors are not a rare event in radiology. The multi-facility RADPEER study found peer disagreement in 0.8 percent of “non-difficult” cases and in 2.9 percent of “difficult” cases. One study has found that up to 54 percent of results of mammography are…

Read More