'New AI algorithm measures breast density accurately'

A newly developed artificial intelligence (AI) algorithm measures breast density as accurately as an experienced mammographer, according to a study.

Breast density can mask cancers on mammography and is an independent risk factor for the disease, according to the study published in the journal Radiology.

Despite its importance, breast density assessment is an imperfect science, and research has shown much discrepancy among radiologists in making density determinations.

"We are dependent on human qualitative assessment of breast density, and that approach has significant flaws. We need a more accurate tool," said Constance D Lehman from Massachusetts General Hospital (MGH) in the US.

The researchers used tens of thousands of high-quality digital mammograms, an X-ray picture of the breast, to train and test the algorithm before implementing it in routine clinical practice.

 

Eight radiologists then reviewed 10,763 mammograms that the model had determined were either dense or non-dense tissue.

The interpreting radiologist accepted the algorithm's assessment in 10,149 of the mammograms, or 94 per cent.

Lehman noted that the 94 per cent agreement rate between the radiologists and the algorithm does not necessarily mean the machine was wrong in six per cent of the cases.

Reader variability could affect the disagreement because radiologists visually assess breast density, which is subjective and qualitative.

"The deep learning algorithm processes all our screening mammograms and provides density, which is either accepted or rejected by the radiologists," Lehman said.

"The results show that the algorithm worked remarkably well. But what's more important is that it is being used every day to measure breast density in mammograms at a major hospital," said Regina Barzilay, a professor at the Massachusetts Institute of Technology in the US.

The system has been in continuous operation at MGH since January and has processed approximately 16,000 images, Barzilay said.

Lehman attributed the successful clinical implementation of the AI model to two components: the availability of high-quality, annotated data evaluated by expert radiologists, and the collaborative efforts of experienced, accomplished medical and computer science professionals.