Four things to know:
1. SwRI engineers and UT Health pathologists trained a computer algorithm previously used for automotive, robotics and defense applications to identify cancer cells.
2. UT Health pathologists first worked with the SwRI engineers to teach them how to recognize breast cancer tumor cells. From there, the SwRI engineers trained the algorithm to identify characteristics that distinguish cancerous cells from normal cells in cell images.
3. The algorithm won the BreastPathQ: Cancer Cellularity Challenge, a competition conducted by the American Association of Physicists in Medicine, the National Cancer Institute and the International Society for Optics and Photonics.
During the challenge, the algorithm matched the findings of human pathologists at the highest rate compared to 100 other competing submissions.
4. “Artificial intelligence and machine learning approaches to medical image analysis will provide pathologists with a powerful tool to more rapidly identify and quantify important image features,” Bradley Brimhall, MD, UT Health pathologist and challenge participant, said in a news release. “In doing so, additional diagnostic and prognostic information will be available for providers to guide cancer treatment.”
More articles on clinical leadership and infection control:
Why some hospitals are offering essential oils to surgery patients
Viewpoint: Why patient advocacy groups should consider CRISPR’s potential
Ebola clinical trial expands to Congo’s outbreak hot spots
