Paige Prostate software has the potential to detect an area of interest on the prostate biopsy image with the highest likelihood of harbouring cancer

FDA device

The US FDA’s Centre for Devices and Radiological Health. (Credit: The U.S. Food and Drug Administration)

Paige.AI has secured an approval from the US Food and Drug Administration (FDA) for its artificial intelligence (AI) based software that helps in the detection of prostate cancer.

Paige Prostate software has been designed for medical professionals examining body tissues (pathologists) to detect areas, which are suspicious for cancer as an adjunct to the review of digitally-scanned slide images from prostate biopsies.

The software will help detect an area of interest on the prostate biopsy image with the highest likelihood of harbouring cancer, thereby enabling pathologists to further review the area of concern that was not detected in the initial review.

The US FDA’s Centre for Devices and Radiological Health invitro diagnostics and radiological health office director Dr Tim Stenzel said: “Pathologists examine biopsies of tissue suspected for diseases, such as prostate cancer, every day. Identifying areas of concern on the biopsy image can help pathologists make a diagnosis that informs the appropriate treatment.

“The authorisation of this AI-based software can help increase the number of identified prostate biopsy samples with cancerous tissue, which can ultimately save lives.”

Paige Prostate is developed for use with slide images, which have been digitised using a scanner. Later, the digitised slide image is visualised using a slide image viewer.

The data from a clinical study has been assessed by the regulator where 16 pathologists examined 527 slide images of prostate biopsies, which were digitised using a scanner.

Each pathologist completed two assessments for each slide image, of which one without Paige Prostate’s assistance and one with Paige Prostate’s assistance.

According to the FDA, the study found that Paige Prostate enhanced detection of cancer on individual slide images by 7.3% on average when compared to pathologists’ unassisted reads for whole slide images of individual biopsies.

The clinical study did not assess the impact on final patient diagnosis, which is generally based on multiple biopsies.