Reviewed by Lexie CornerDec 13 2024
A review article published by Cell Press in Trends in Cancer discusses how artificial intelligence (AI) is influencing the future of breast cancer screening and risk-reduction techniques.
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.
Erik Thompson, Study Senior Author and Professor, Queensland University of Technology
Breast tissue that appears white on mammograms is considered radiologically dense, while tissue that appears dark is less dense. It is well known that women with higher mammographic density, relative to their age and body mass index, are more likely to develop breast cancer. In addition, increased density can make breast cancer harder to detect via mammography, a phenomenon referred to as the "masking effect."
Advocacy movements worldwide are calling for regulatory changes in the United States, Canada, and Australia to inform women about their mammographic density. In some regions, the use of supplemental imaging methods is based on mammographic density. For women with exceptionally dense breasts, clinical studies have shown that magnetic resonance imaging (MRI) and ultrasound can improve cancer detection rates.
However, the complexity of the masking effect, the relationship between mammographic density and breast cancer risk, and the best approaches for implementing clinical changes continue to present challenges for both researchers and practitioners.
Increasingly, mammographic images are being analyzed using advanced computational technologies, such as deep learning, to predict future breast cancer diagnoses. AI approaches, in particular, are identifying mammographic features that may serve as stronger indicators of breast cancer risk than any known risk factor to date.
These characteristics may help explain much of the link between mammographic density and breast cancer risk. The discovery of AI-generated mammographic features that predict risk opens up new possibilities for identifying women most at risk of developing breast cancer in the future and distinguishing them from those who might have their cancer overlooked due to the masking effect.
Thompson added, “A woman with mammographic features associated with a high risk of breast cancer detection could benefit from more frequent screening or risk-reducing medication. 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 traits indicate early malignancies that might not be detected by radiologists, while others are linked to benign conditions that carry an increased risk of breast cancer. However, the identity of AI-generated mammographic features that are neither cancerous nor benign remains unclear.
“Critically, we need to identify the pathobiology associated with mammographic features and the underlying mechanisms that link them with breast cancer oncogenesis. 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,” Thompson concluded.
Journal Reference:
Ingman, W. V., et. al. (2024) Artificial intelligence improves mammography-based breast cancer risk prediction. Trends in Cancer. doi.org/10.1016/j.trecan.2024.10.007