Proscia touts study showing digital pathology software detected melanoma

Shortly after Paige obtained FDA clearance for her algorithm to flag potentially cancerous lesions, another digital pathology startup touts the results of a study claiming its deep learning technology can detect melanoma. with a high degree of precision.

Philadelphia-based Proscia shared the results of a prospective study testing its DermAI software on skin biopsies from two different labs. He found that his AI detected melanoma in situ and invasive melanoma with a sensitivity of 93% and a specificity of 91%.

Proscia has not yet published the results of the prospective study, but it hopes to move towards using its software in a clinical setting. Currently, DermAI is for research use only.

In an emailed statement, Proscia vice president of research and development Julianna Ianni wrote that the company was eager to bring DermAI into mainstream practice.

“We are taking the necessary steps to do this, including conducting ongoing validation studies,” she wrote.

For the prospective study, AI was performed on 1422 skin biopsies which were scanned to create full slide images. The software would work, and then a pathologist would review a case, with the option to sort or prioritize cases based on the AI ​​classification.

For example, if the AI ​​identifies a potential case of melanoma, the pathologist could urgently examine it before other cases, wrote Dr. Kiran Motaparthi, director of dermatopathology at the University of Florida, who helped to lead the study.

The biopsies from the two labs were not organized and anonymized, to “make sure the data we used was representative of what these labs would encounter in day-to-day operations,” he wrote.

Motaparthi noted that there were variations in patient demographics, diagnoses and how any diagnosis would appear, as well as how biopsies are prepared and stained. However, Proscia did not share details on patient demographics for the study.

It builds on a previous retrospective study conducted by Proscia, where it trained the system on more than 7,600 images from one lab and tested it on just over 5,000 from two other labs.

Proscia has scheduled additional testing to see if its AI can deliver results faster for melanoma patients and if it can make the diagnosis more consistent. It could also benefit from Paige’s de novo clearance, which has opened a new avenue for other digital pathology companies seeking the FDA green light for their solutions.

Last year, Proscia raised $ 23 million, with the aim of obtaining regulatory approval for more of its products. Its software for scanning, storing and analyzing tissue biopsies has been CE marked in Europe. It also made it available in the United States, under the temporary leadership of the FDA, to allow pathologists to use these devices to remotely examine scanned slides, thereby minimizing their exposure to Covid-19.

Photo credit: Proscia

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.