First Approved AI Pathology Program: Helps Detect Prostate Cancer


The United States Food and Drug Administration (FDA) has cleared artificial intelligence (AI) software to help pathologists detect prostate cancer.

The program, called Paige Prostate, is the first AI system approved in pathology.

“We really believe this product can make a huge difference,” said Paige CEO Leo Grady, PhD. Medscape Medical News.

The program has been approved as an adjunct to the pathologist review, not a replacement.

Grady explained that “for a second opinion today you send someone else a glass slide or do another stain that’s really expensive or you do another molecular test.”

With Paige Prostate, pathologists digitally scan and download biopsy slides to their computer, then import them into the program, which is a cloud-based service accessible through a web browser.

The software compares the tissue models to a large database of tissue models collected at Memorial Sloan Kettering Cancer Center, which Paige established as a company in 2018 from her work on scanning and applying l AI to pathology slides.

The program looks for patterns that have already been diagnosed as cancer. When it finds such patterns, it highlights them so that pathologists can grasp them, so that they “don’t miss a thing” and have “a lot more confidence in their diagnosis without having to send it in for further consultation. “Grady said.

Shortly after the agency announced the marketing authorization on September 21, Acting FDA Commissioner Janet Woodcock, MD, tweeted that she is “still excited to see potentially life-saving advancements in medical device technology, such as the use of artificial intelligence to help identify prostate cancer.”

FDA approval was based on a study in which 16 pathologists examined 527 digitally scanned prostate biopsy slides; 171 of the specimens were cancerous and 356 were benign. The pathologist did two assessments, one with and one without program assistance.

The software improved cancer detection on individual slide images by an average of 7.3% compared to unassisted reads. There was no impact on the reading of benign slides.

The FDA has said the risk of false negatives and false positives with the program is mitigated by its use as an adjunct and by pathologists’ consideration of the patient’s history, additional lab studies, and other clinical information.

Grady said the price was per slide but did not provide numbers.

Mr. Alexander Otto is a medical assistant and holds a master’s degree in medical science. He is an award-winning medical journalist who worked for several major news organizations before joining Medscape. He is an MIT Knight Fellow in Science Journalism. Email: [email protected]

For more news, follow Medscape on Facebook, Twitter, Instagram and YouTube.


About Hector Hedgepeth

Check Also

Why We Order Redux Lab Tests

George D. Lundberg, MD In 2022, doctors have a wide range of clinical laboratory tests …

Leave a Reply

Your email address will not be published.