A study led by Andreas D. Lauritzen, Ph.D., from the University of Copenhagen, indicates that combining artificial intelligence (AI) systems can significantly improve the assessment of short-term and long-term breast cancer risks.
The study was recently published in the journal Radiology and emphasizes the importance of AI tools in earlier cancer detection and relieving the healthcare system’s workload.
The Problem: One-size-fits-all approaches Are Insufficient
Current breast cancer screening often relies on a one-size-fits-all approach that might not accurately represent a woman’s lifetime risk of developing breast cancer.
According to Dr. Lauritzen, “About one in 10 women develop breast cancer throughout their lifetime,” highlighting the need for more accurate risk assessment tools.
The Solution: AI Models Tailored for Short-Term and Long-Term Risks
The researchers employed a combination of diagnostic AI models, which are adept at spotting suspicious lesions in mammograms, and texture AI models, which can identify breast density—a known factor for long-term risk of developing breast cancer.
For the study, Dr. Lauritzen and his team used Transpara, a commercially available diagnostic AI tool, and a texture model they developed.
They trained these models on a Dutch dataset containing over 39,000 exams and integrated them using a three-layer neural network.
Key Findings: Improved Risk Assessment
The team tested their combined model on a group of more than 119,000 women, aged on average 59, who participated in a breast cancer screening program in the Capital Region of Denmark.
The results showed significant improvements in risk assessment compared to using either the diagnostic or texture models alone.
- Women identified as having the top 10% highest risk accounted for 44.1% of interval cancers and 33.7% of long-term cancers.
Implications: Faster and More Accurate Screenings
Dr. Lauritzen emphasized that using AI in this way will not only lead to earlier cancer detection but will also help alleviate the strain on the healthcare system due to a shortage of specialized breast radiologists.
“Current clinical risk models require multiple tests such as blood work, genetic testing, mammogram, and filling out extensive questionnaires, increasing the workload in the screening clinic.
Our model can assess risk within seconds from screening, without introducing overhead,” he said.
Conclusion
The study introduces a transformative way of assessing breast cancer risk using AI, potentially leading to earlier detection and more effective treatments.
This development has significant implications for women’s health and could revolutionize the existing protocols for breast cancer screening.
If you care about breast cancer, please read studies about a major cause of deadly breast cancer, and common blood pressure drugs may increase the death risk of breast cancer.
For more information about cancer, please see recent studies that new cancer treatment could reawaken the immune system, and results showing vitamin D can cut cancer death risk.
Follow us on Twitter for more articles about this topic.
Copyright © 2023 Knowridge Science Report. All rights reserved.
