Deep-learning model accurately assesses mammographic breast density

A deep-learning (DL) algorithm was able to assess mammographic breast density at the level of an experienced mammographer, according to a study published in Radiology.

Researchers from the Massachusetts General Hospital and Harvard Medical School trained the DL algorithm to assess Breast Imaging Reporting and Data System (BI-RADS) breast imaging based on the original interpretation by a radiologist, and used 41,479 digital screening mammograms in the process.

The DL algorithm was then implemented into routine clinical practice and categorized 10,763 consecutive mammograms as either dense or non-dense breasts, the study said. Eight radiologists reviewed the DL model’s categorizations and agreed with 94 percent of its assessments.

The researchers said the DL model showed “good agreement” with radiologists in the test and reader study sets, and “very good agreement” with radiologists in the clinical implementation set.

“Given the high level of agreement between the deep learning algorithm and experienced mammographers, this algorithm has the potential to standardize and automate routine breast density assessment,” the study said.

Based on the results, the researchers said the DL model can help providers give more accurate information to patients.

“Our DL model provides efficient and reliable density assessments, both at the patient level and at the population level, and it is designed to be widely available, simple to use and cost effective. It can be used to measure breast density in a diverse set of patients, without limitations based on prior surgery or other breast interventions,” the study concluded.

“Our tool can potentially address concerns for current breast density legislation, and it can help providers supply more accurate information to patients and help health systems optimize the use of supplemental screening resources.”