AI Breast Cancer Screening Is Equally Effective As Human Readers
Researchers in the UK evaluated the effectiveness of a commercially available artificial intelligence (AI) algorithm with human readers of screening mammography using a standardized assessment. The Radiological Society of North America (RSNA) journal Radiology published the outcomes of their research. Not all breast cancers are found during mammogram screening. The needless use of imaging and biopsy in women who do not have breast cancer can be brought on by false-positive interpretations. One alternative is to have two readers evaluate each mammogram in order to increase the sensitivity and specificity of screening mammography. The researchers found that twice reading lowers recall rates while increasing breast cancer detection rates by 6 to 15%. In times of reader shortages, this technique is labor-intensive and challenging to implement. To evaluate the performance of human readers and AI, Prof. Chen and her study team employed test sets from the Personal Performance in Mammo...