First AI Pathology Program Approved: Helps Detect Prostate Cancer

The US Food and Drug Administration (FDA) has authorized marketing of artificial intelligence (AI) software to help pathologists detect prostate cancer.

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

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

The program was approved as an adjunct to pathologist review, not a replacement.

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

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

The software compares the tissue patterns against a large database of tissue patterns collected at the Memorial Sloan Kettering Cancer Center, which spun out Paige as a company in 2018 from its work on digitizing and applying AI to pathology slides.

The program looks for patterns that have been previously diagnosed as cancer. When it finds such patterns, it highlights them for the pathologists to key in on, so they “don’t miss anything” and have “a lot more confidence in their diagnosis without having to send it out for additional consultation,” Grady said.

Shortly after the agency announced the market authorization on September 21, the FDA’s acting commissioner, Janet Woodcock, MD, tweeted that she’s “always pleased to see potentially life-saving advancements in medical device technology, such as using artificial intelligence to help identify prostate cancer.”

The 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 made two assessments, one with and one without the program’s help.

The software improved detection of cancer on individual slide images by 7.3% on average in comparison with unassisted reads. There was no impact on the read of benign slides.

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

Grady said pricing is per slide but didn’t provide figures.

M. Alexander Otto is a physician assistant with a master’s degree in medical science. He is an award-winning medical journalist who worked for several major news outlets before joining Medscape. He is an MIT Knight Science Journalism fellow. Email: [email protected].

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

Source: Read Full Article