New Machine Learning System Aids Pathologists in Cancer Diagnoses

Researchers from the University of Washington (Seattle, WA, USA) and University of California (Los Angeles, CA; USA) have developed an artificial intelligence (AI) system that could help pathologists read biopsies more accurately, and lead to better detection and diagnosis of breast cancer. The new algorithm can interpret images of breast tissue biopsies to diagnose breast cancer nearly as accurately, or even better than an experienced pathologist, depending upon the task.

In 2015, a study by the UW School of Medicine found that pathologists often disagreed on the interpretation of breast biopsies, which are performed on millions of women each year. The study revealed that diagnostic errors occurred for about one out of every six women who had a non-invasive type of breast cancer called “ductal carcinoma in situ.” Additionally, incorrect diagnoses were given in about half of the biopsy cases with abnormal cells that are associated with a higher risk for breast cancer — a condition called breast atypia.

The researchers reasoned that AI could provide more accurate readings consistently as it uses a large dataset that makes it possible for the machine learning system to recognize patterns associated with cancer that are difficult for doctors to see. After studying the strategies used by pathologists during breast biopsy interpretations, the team developed image analysis methods to address these challenges. The researchers fed 240 breast biopsy images into a computer, training it to recognize patterns associated with several types of breast lesions, ranging from noncancerous and atypia to ductal carcinoma in situ and invasive breast cancer. The correct diagnoses were determined by a consensus among three expert pathologists.

The researchers then tested the system by comparing its readings with independent diagnoses made by 87 practicing US pathologists who interpreted the same cases. The algorithm came close to performing as well as the human doctors in differentiating cancer from non-cancer. However, the algorithm outperformed doctors when differentiating ductal carcinoma in situ from atypia, correctly diagnosing pre-invasive breast cancer biopsies about 89% of the time, as compared to 70% for pathologists. The researchers have already begun working on training the system to diagnose skin cancer.

“These results are very encouraging,” said the study’s co-author Dr. Joann Elmore, a professor of medicine at the David Geffen School of Medicine at UCLA, who was previously a professor of internal medicine at the UW School of Medicine. “There is low accuracy among practicing pathologists in the U.S. when it comes to the diagnosis of atypia and ductal carcinoma in situ, and the computer-based automated approach shows great promise.”

Related Links:
University of Washington
University of California