Summary: A Trends in Cancer study reveals how AI is advancing breast cancer screening by identifying mammographic features that improve risk prediction, guide personalized care, and uncover links to cancer development.
Key Takeaways
- AI’s Potential in Risk Prediction: AI is uncovering mammographic features that enhance breast cancer risk prediction, outperforming traditional methods and bridging the gap between mammographic density and breast cancer risk.
- Personalized Screening: AI can guide individualized care by identifying high-risk women who may benefit from more frequent screenings or preventive measures, while low-risk women could have extended intervals between screenings.
- Need for Further Research: Understanding the biological mechanisms behind AI-identified mammographic features is crucial to refining risk prediction and developing effective strategies for prevention and treatment.
———————————————————————————————————————————————————
AI is transforming breast cancer screening and prevention, according to a review published in Trends in Cancer. The study highlights advances in AI-assisted breast cancer risk prediction and its potential to reshape clinical practice.
“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 author Erik Thompson, PhD, of Queensland University of Technology in Brisbane, Australia.
Mammographic Density
Mammographic density, characterized by white areas on a mammogram, is a known breast cancer risk factor. Women with higher density face increased risk and the challenge of the “masking effect,” where dense tissue obscures cancer detection. Advocacy movements worldwide are pushing for mandatory mammographic density notifications, influencing policy in the U.S., Canada, and Australia.
AI is revolutionizing this field by identifying new mammographic features that may better predict breast cancer risk than current methods. These features could bridge the gap between mammographic density and breast cancer risk, enabling more personalized care.
“A woman with mammographic features associated with high risk could benefit from more frequent screening or risk-reducing medication,” says Thompson. “Conversely, low-risk women might have longer intervals between screens, while those with high density but low risk may benefit from supplemental imaging like MRI or ultrasound.”
Refining Risk Prediction
Emerging evidence suggests AI can detect early malignancies and benign conditions linked to increased risk, often missed by traditional radiology. However, some AI-identified features remain unexplained.
“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 for refining breast cancer risk prediction and developing effective prevention strategies.”