The future of breast cancer screening and risk-reducing strategies is being shaped by artificial intelligence (AI), according to a review article published by Cell Press on December 12 in the journal Trends in Cancer.
"We discuss recent advances in AI-assisted breast cancer risk prediction, what this means for the future of breast cancer screening and prevention, and the key research needed to progress mammographic features from research into clinical practice," says senior study author Erik Thompson of the Queensland University of Technology in Brisbane, Australia.
Breast tissue that appears white on a mammogram is radiologically dense, while breast tissue that appears dark is considered non-dense. It is widely accepted that women with higher mammographic density for their age and body-mass index have a greater risk of breast cancer. In addition, higher density makes breast cancer harder to detect by mammography, known as the "masking effect."
Advocacy movements across the world are demanding that women be notified of their mammographic density, with policy changes in the U.S., Canada, and Australia. Mammographic density is guiding the use of supplemental imaging technologies in some places, with ultrasound and magnetic resonance imaging (MRI) providing increased cancer detection rates in clinical studies of women with extremely dense breasts. Yet scientists and clinicians continue to struggle with the complexity arising from the masking effect, the breast cancer risk associated with mammographic density, and how to optimally implement changes in clinical practice.
To predict a future breast cancer diagnosis, advanced computational approaches such as deep learning are now being used to analyze mammographic images. In particular, AI methods are uncovering mammographic features that have potential to be stronger predictors of breast cancer risk than any other known risk factor. These features might explain a large proportion of the association between mammographic density and breast cancer risk. The discovery of the risk-predicting AI-generated mammographic features is providing new opportunities to identify women at most risk of developing breast cancer in the future and separating them from those women most at risk of having a breast cancer missed due to the masking effect.
"A woman with mammographic features associated with a high risk of breast cancer detection could benefit from more frequent screening or risk-reducing medication," Thompson says. "On the other hand, a longer interval between screens could be provided to a woman with a low chance of breast cancer diagnosis in the next five years. Additionally, a woman with high mammographic density without high-risk mammographic features might benefit from supplementary imaging such as MRI or ultrasound."
Research suggests that some AI-generated mammographic features are indicative of early malignancy that is undetectable by radiologist-read mammography, while others may be benign conditions associated with an increased risk of breast cancer. The identity of AI-generated mammographic features that are not identified as cancer or a benign condition remains unclear.
"Critically, we need to identify the pathobiology associated with mammographic features and the underlying mechanisms that link them with breast cancer oncogenesis," Thompson says. "This will be essential in establishing their relevance to short- and long-term breast cancer risk, as well as future efforts to reduce that risk."
