Radiologists, Al Read Screenings Differently.

• Position: BREAST CANCER

Radiologists and artificial intelligence systems yield significant differences in breast-cancer screenings, a team of researchers has found. Its work, which appears in the journal Nature Scientific Reports, reveals the potential value of using both human and Al methods in making medical diagnoses.

"While Al may offer benefits in health care, its decisionmaking is still poorly understood." explains lead author Taro Maki-no, a doctoral candidate in New York University's Center for Data Science. "Our findings take an important step in better comprehending how Al yields medical assessments and, with it, offer a way forward in enhancing cancer detection."

The analysis centered on a specific Al tool: deep neural networks (DNNs), which are layers of computing elements ("neurons") simulated on a computer. A network of such neurons can be trained to "learn" by building many layers and configuring how calculations are performed based on data input--a process called "deep learning."

The scientists compared breast-cancer screenings read by radiologists with those analyzed by DNNs and found that DNNs and radiologists diverged...