First digital AI pathology approved for prostate cancer

Source: Free-Photos / Pixabay

Artificial Intelligence (AI) machine learning is rapidly transforming healthcare by powering new diagnostic tools for clinicians and healthcare professionals. In a landmark move this week, the United States Food and Drug Administration (FDA) cleared the marketing of an AI machine learning software called Paige Prostate, the first approved AI-based software that identifies the prostate cancer to help pathologists.

The FDA De Novo pre-market review process is for new types of low to moderate risk devices. With FDA approval from De Novo, the new device is cleared for sale in accordance with regulatory controls.

“Authorizing this AI-based software may help increase the number of prostate biopsy samples identified with cancerous tissue, which may ultimately save lives,” said Tim Stenzel, MD, Ph. D., director of the Office of In Vitro Diagnostics and Radiological Health at the FDA’s Center for Devices and Radiological Health in a statement.

Prostate cancer is one of the most common cancers in American men, second only to skin cancer. According to the American Cancer Society (ACS), about 1 in 8 men in the United States will be diagnosed with prostate cancer in their lifetime. In addition, the ACS estimates that by 2021, prostate cancer will cause more than 34,000 deaths with more than 248,000 new cases in the United States. According to the ACS, about 1 in 41 American men will die of prostate cancer. It is the second leading cause of cancer death in American men after lung cancer.

“Pathologists examine daily biopsies of tissue suspected of disease, such as prostate cancer. Identifying areas of concern in the biopsy image can help pathologists make a diagnosis that informs appropriate treatment, ”said Stenzel.

According to the FDA statement, the study used data from 16 pathologists reviewing 527 scanned prostate biopsy slide images that were scanned. Of the slides, 356 were benign and 171 were cancerous. Each of the slides was evaluated twice by pathologists, once with the help of Paige Prostate and once without.

The clinical study submitted to the FDA showed that pathologists using Paige Prostate increased performance by more than seven percentage points in accuracy, from 89.5% to 96.8% for cancer detection. In addition, the clinical study showed that non-specialist pathologists were as precise as prostate specialists who did not use the software.

With this new FDA approval, AI-based software is making significant progress in shaping the future of assistive tools for disease detection.

Copyright © 2021 Cami Rosso All rights reserved.

Source link

About Hector Hedgepeth

Hector Hedgepeth

Check Also

Diadem presents data at 22nd International Alzheimer’s Drug Discovery Conference, emphasizing that his blood biomarker test is 84% ​​concordant with amyloid brain imaging

Further analysis of clinical validation data shows that Diadem’s AlzoSure® prediction is highly concordant with …

Leave a Reply

Your email address will not be published. Required fields are marked *