By Dr. Jonathan Nash

New advances in artificial intelligence (AI) have potential to transform breast cancer screening and make the greatest impact when integrated across the entire screening pathway, not only during image interpretation. Along this pathway, two critical stages at which AI can dramatically improve outcomes are when women are invited to schedule their screening mammogram, especially considering screening backlogs exacerbated by COVID-19, as well as during the image acquisition and audit process.

At the 2021 European Society of Breast Imaging (EUSOBI) Annual Scientific Meeting in October, Kheiron Medical Technologies, an applied science company focused on supporting breast cancer screening with machine-learning, presented a virtual workshop session covering this topic, titled “Showcasing the future of breast cancer screening: Applications of AI across the screening pathway.” The session featured presentations from leading experts, including renowned statistician Stephen Duffy, Professor of Cancer Screening, Barts and the London School of Medicine and Dentistry, Queen Mary University of London; Professor Ruud Pijnappel of the LRCB, the Dutch Expert Center for Breast Screening; and Dr. Randy Hicks of U.S.-based Regional Medical Imaging.

The panel was moderated by Mary Beth Chalk, patient advocacy advisor at Kheiron who is also a breast cancer survivor. She shared her experience and the life-changing importance of correct breast positioning and what artificial intelligence would have meant to her breast screening.

Professor Duffy shared how the UK Breast Screening Programme is tackling the challenges of breast screening backlogs. Over the past 18-months, Covid-19 has exacerbated existing backlogs due to radiologist shortages and demanding workloads. As a result, there is more urgency than ever to ensure that millions of unscreened women around the world are not overlooked, especially those at greatest risk.

Based on initial internal research, Kheiron’s AI-enabled invitation tool RSViP has been shown to flag higher risk women for screening. Earlier screening can contribute directly to significantly earlier detection rates, which in turn can lead to improved survivorship and a lower cost of care.

To address the potential for AI integration during image acquisition and audit, Professor Pijnappel and Dr. Hicks discussed the importance of well-positioned, properly exposed mammograms. They shared lessons learned and the value they believe AI solutions such as Kheiron’s Mia IQ can bring to the acquisition of mammography images. Mia IQ is powered by artificial intelligence and machine learning to assess the image quality of mammograms and train radiographers to achieve proper breast positioning during mammography.

Despite the success of the Mammography Quality Standards Act (MQSA) in improving and standardizing the quality of mammographic imaging, improper breast positioning remains the most common reason for technical failure under American College of Radiology clinical image quality review. Evidence suggests that technical issues are responsible for delays in diagnosing 22% of screen-detected cancers and 35% of interval breast cancers.

In addressing the different stages of the breast screening pathway where AI can play a significant role in improving cancer detection and patient outcomes, the workshop underscored the potential for new solutions to make a positive impact on the future of breast screening. By adopting new AI-enabled technologies, breast radiologists and their teams will have the opportunity to give every woman, everywhere a better fighting chance against breast cancer.

About the author: Dr. Jonathan Nash is the medical director at Kheiron Medical Technologies.

Business Affairs Homepage