Google’s AI algorithm for detecting breast cancer put to the test in 2 new studies

An artificial intelligence (AI) algorithm developed by Google can help detect metastatic breast cancers with significant accuracy and improve pathologist performance, according to two new studies published in the Archives of Pathology and Laboratory Medicine and the American Journal of Surgical Pathology.

The algorithm—known as LYmph Node Assistant (LYNA)—was shown to be accurate back in 2017, but Google’s researchers still wanted to learn more about its capabilities.

“For patient safety, these algorithms must be tested in a variety of settings to understand their strengths and weaknesses,” Google AI’s Martin Stumpe and Craig Mermel wrote in a recent blog post. “Furthermore, the actual benefits to pathologists using these algorithms had not been previously explored and must be assessed to determine whether or not an algorithm actually improves efficiency or diagnostic accuracy.”

In the Archives of Pathology and Laboratory Medicine study, the authors applied LYNA to pathology samples from two different datasets. The algorithm “was able to correctly distinguish a slide with metastatic cancer from a slide without cancer 99 percent of the time," according to the authors.

In the American Journal of Surgical Pathology study, six board-certified pathologists reviewed lymph nodes with and without help from LYNA. The pathologists reported that using LYNA made detecting small metastases “easier.”

“While encouraging, the bench-to-bedside journey to help doctors and patients with these types of technologies is a long one,” Stumpe and Mermel wrote. “These studies have important limitations, such as limited dataset sizes and a simulated diagnostic workflow which examined only a single lymph node slide for every patient instead of the multiple slides that are common for a complete clinical case. Further work will be needed to assess the impact of LYNA on real clinical workflows and patient outcomes.”