Two groundbreaking artificial intelligence technologies are showing remarkable promise in the early detection of breast cancer, potentially transforming screening protocols and improving patient outcomes.
AI System Tracks Subtle Changes in Mammograms Over Time
Researchers at Washington University School of Medicine in St. Louis have developed an artificial intelligence system that can identify women at higher risk for developing breast cancer by analyzing changes in breast tissue across sequential mammograms.
The AI technology detects subtle differences in mammograms that are typically invisible to the human eye, including changes in density, texture, calcification, and asymmetry within breast tissue. According to lead researcher Shu (Joy) Jiang, an associate professor of surgery at Washington University, "Our new method is able to detect subtle changes over time in repeated mammogram images that are not visible to the eye."
In a study published December 5 in JCO Clinical Cancer Informatics, the researchers demonstrated that their AI system identified high-risk women 2.3 times more accurately than standard screening methods. The team trained the AI on mammograms from more than 100,000 women who received breast cancer screening at Siteman Cancer Center between 2008 and 2012, with follow-up through 2020. Nearly 500 of these women subsequently developed breast cancer.
When tested on a separate cohort of over 18,000 women from Emory University in Atlanta, the results were striking: women classified as high-risk by the AI were 21 times more likely to be diagnosed with breast cancer within five years compared to those in the lowest risk group. Approximately 53 out of every 1,000 women in the high-risk group developed breast cancer, versus fewer than 3 per 1,000 in the low-risk group.
"We are seeking ways to improve early detection, since that increases the chances of successful treatment," said senior researcher Dr. Graham Colditz, associate director of the Siteman Cancer Center at Barnes-Jewish Hospital. "This improved prediction of risk also may help research surrounding prevention, so that we can find better ways for women who fall into the high-risk category to lower their five-year risk of developing breast cancer."
The research team is currently testing the AI in women of diverse racial and ethnic backgrounds to ensure equitable accuracy across populations. A patent is pending for the technology.
Laser Analysis Combined with AI Shows Promise for Earliest Stage Detection
Meanwhile, researchers at the University of Edinburgh in Scotland have developed a different approach that combines AI with advanced laser technology to detect very early-stage breast cancers through blood analysis.
The technique, detailed in the Journal of Biophotonics, uses Raman spectroscopy to subject blood plasma to laser beam analysis. A spectrometer then analyzes how the laser light interacts with the blood, detecting tiny shifts in chemical composition that may indicate the presence of cancer. Artificial intelligence algorithms help interpret these subtle changes quickly and accurately.
In a small study involving 24 blood samples—12 from breast cancer patients and 12 from healthy individuals—the technology demonstrated 98% effectiveness in identifying stage 1a breast cancers, the earliest stage of the disease. Additionally, the approach was 90% effective in differentiating between the four major subtypes of breast cancer.
Lead study author Andy Downes, a senior lecturer in engineering at the University of Edinburgh, emphasized the potential life-saving implications of this technology. "Most deaths from cancer occur following a late-stage diagnosis after symptoms become apparent, so a future screening test for multiple cancer types could find these at a stage where they can be far more easily treated," Downes noted.
While the findings are preliminary and based on a small sample size, the researchers believe this approach could eventually be applied to other cancer types. "Early diagnosis is key to long-term survival, and we finally have the technology required," Downes said. "We just need to apply it to other cancer types and build up a database, before this can be used as a multi-cancer test."
Clinical Implications and Future Directions
Both technologies address a critical need in breast cancer screening. Early-stage breast cancers are notoriously difficult to detect with conventional mammography, and identifying high-risk patients remains challenging despite decades of research.
The Washington University AI system could potentially be integrated into existing mammography screening programs, providing an additional layer of risk assessment without requiring new equipment or patient procedures. This approach leverages the wealth of historical mammogram data already available for many patients.
The Edinburgh approach, while requiring additional validation in larger studies, offers the tantalizing possibility of a blood-based screening test that could detect breast cancer at its earliest, most treatable stage. The ability to also identify specific cancer subtypes could help clinicians tailor treatment approaches more precisely.
As these technologies continue to be refined and validated, they represent significant steps toward more effective breast cancer screening and risk assessment. The integration of artificial intelligence into cancer detection workflows appears increasingly likely to become a standard component of future screening protocols, potentially saving thousands of lives through earlier intervention.
