The software could improve the confidence, quality and speed of pathology.
Digital pathology continues to be a focus in healthcare, as Proscia this week announced the release of DermAI, which leverages deep learning to pre-screen and classify skin biopsies.
Proscia claims the software can automatically classify hundreds of variants of skin diseases into pre-diagnostic categories to improve the confidence, quality and speed of pathology. Using artificial intelligence (AI), the software could help reduce costly errors and improve laboratory quality and efficiency — all as the number of pathologists declines.
“DermAI allows oft-overburdened practices to accelerate pathology workflows and improve quality,” David West, CEO of Proscia, said in a statement to Inside Digital Health™. “This week’s release signals the first step in bringing AI to the center of diagnostic medicine, alleviating the economic challenges of laboratory medicine and enabling a new paradigm of precision care.”
Proscia can accelerate the rollout of additional disease-specific AI-based modules, according to the company.
In the meantime, DermAI is slated to help pathologists balance their workload and case prioritization.
Proscia said the software could enable the lab to sort, triage and prioritize cases. It also could optimize how cases are distributed to various dermatopathologists in a lab by subject matter, by order of cases to examine or to create continuity. That would enable pathologists to focus on high-impact cases.
The AI software also analyzes a lab’s full caseload and interprets each case as an automated second layer of review. It could allow a dermatopathology lab to provide additional insight into the work it delivers.
DermAI was trained and tested using patient biopsies from academic and commercial dermatology laboratories. A multi-site study validated the performance of the software using more than 20,000 patient biopsy slides.
Proscia will submit the software to gain U.S. Food and Drug Administration approval for DermAI to be used in clinical diagnosis.
“The true promise of digital pathology lies in deep learning, which will transform the practice of pathology for the first time since the introduction of the microscope,” said Thomas Olsen, M.D., founder of Dermatopathology Laboratory of Central States. “It’s exciting to have been part of moving AI-enabled digital pathology beyond academic efforts and into real-world practice applications.”
Get the best insights in digital health directly to your inbox.
AI Directs Catheters to Target to Treat A-Fib
FDA Clears Aidoc's AI Solution for Triage of Cervical Spine Fractures