Proscia Launches AI-Powered Digital Pathology Solution for Dermatopathology
In many industries, there is standard 80/20 rule, which dictates that 80 percent of your time will be spent on 20 percent of your work. The remaining 80 percent of your work takes only 20 percent of your time. In medicine in general – and in pathology in particular – this rule would more accurately be described as being the 90/10 rule. Perhaps nine out of every ten cases are easier and more straightforward and can be performed with little additional workup or delay. But 10 percent are cases that require deeper thought and additional lab work and might be the ones you want to “sleep on.” Proscia’s announcement today of the release of DermAI takes that challenge head-on.
Proscia’s DermAI uses deep learning to read and automatically classify hundreds of variants of skin diseases into pre-diagnostic categories to improve the confidence, quality, and speed of dermatopathology. It’s a computational pathology approach that’s practical in nature, and takes a stab at the 90-10 challenge that dermatopathologists face in their interpretation of the 90% of cases that are straightforward (like those that are basaloid or squamous in nature), and the 10% (including those melanocytic cases) that are more challenging. By triaging the “simple” from the “complex” and highlighting the “routine” from the “needs workup,” this technology offers a workflow-oriented solution that aims to solve real problems in pathology.
Since its inception, most approaches to digital pathology have treated all cases as equal. This is highlighted by the industry’s fixation on obtaining approval for primary diagnosis on whole slide image viewers, a functionality and claim that does little to add value to the pathologist’s highly-variable workday. The two standalone applications of digital pathology that focus on unique value-adds for the pathologist have been teleconsultation and image analysis. I, for one, am excited that digital pathology has started to move beyond these applications, with technology like DermAI that’s another value-add for digital pathology and computational medicine.
Validated and implemented at leading academic and commercial laboratories, “DermAI” improves the efficiency and precision of diagnostic medicine
PHILADELPHIA (June 19, 2019) – Proscia, a leading provider of digital pathology software, today released DermAI™, the first in its series of AI applications that advance the practice of pathology. A module on Proscia’s Concentriq™ platformDermAI leverages deep learning to pre-screen and classify skin biopsies to help reduce costly errors and improve laboratory quality and efficiency as the number of medical professionals entering the field of pathology continues to decline.*
The standard of care for diagnosing the 25 million skin biopsies taken in the US every year has been based on a pathologist’s interpretation of patterns in tissue using a microscope. This 150-year-old manual and subjective practice cannot keep pace with the increasing demand for pathology diagnosis or deliver critical data in the promise of precision treatment. Proscia’s DermAI uses deep learning to read and automatically classify hundreds of variants of skin diseases into pre-diagnostic categories to improve the confidence, quality, and speed of pathology.
“DermAI demonstrates a high level of accuracy in categorizing common diagnoses,” said Dr. Kiran Motaparthi, from the Department of Dermatology at University of Florida College of Medicine. “As a dermatopathologist who seeks to prioritize and focus time on challenging cases, this is exciting technology.”
Proscia trialed and tested the DermAI algorithm using patient biopsies from leading academic and commercial derm laboratories including Cockerell Dermatopathology, Dermatopathology Laboratory of Central States, University of Florida, and Thomas Jefferson University Hospital. This multi-site study successfully validated the performance of DermAI using over 20,000 patient biopsy slides. Proscia intends to submit DermAI to the FDA for review to use in clinical diagnosis.*
“To date, attempts to apply AI to pathology have been engineered in isolated development environments using toy datasets. The challenge in fulfilling the promise of deep learning in diagnostic medicine is bringing to market a solution that can perform in the real world where we face tremendous variability among labs, systems, and specimen. Proscia is the first to deliver on this promise,” explained David West, CEO of Proscia. “We could not be more delighted to be celebrating this industry milestone. Now, with our first proven solution in market, we are able to scale out much of our IP to accelerate the roll-out of additional disease-specific AI-based modules.”
Capabilities central to the DermAI offering include:
- Intelligent workload balancing and case prioritization – enables the lab to sort, triage, and otherwise prioritize cases. It optimizes how cases are distributed to the various dermatopathologists in a lab – by subject matter expertise, by order of cases to examine, or even to create continuity so investigators maximize their focus on high-impact cases.
- Automated QA and 100% AI re-review – analyzes a lab’s entire caseload, providing an AI-based interpretation for every case. Running in the background before or after pathologist review, DermAI provides an automated second layer of quality review across the lab.
- Enhanced technical component reporting – technical component (labwork) and professional component (pathologist work) are billable services offered by anatomic pathology labs. DermAI allows a dermatopathology lab to provide additional insight into the labwork it delivers. This added value may guide when to let the lab handle the professional component and when to perform it in-house.
The flexible nature of the DermAI software allows laboratories to take advantage of multiple use cases in a variety of configurations based on their current workflows, preference of the pathologist, and the needs of their clients. It also seamlessly integrates with most laboratory information system (LIS) platforms, making DermAI easy to fit into existing lab processes.
Dr. Thomas G. Olsen, founder of Dermatopathology Laboratory of Central States and an investigator in the validation study, collaborated with Proscia on the design and clinical requirements for DermAI. “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,” commented Dr. Olsen. “It’s exciting to have been part of moving AI-enabled digital pathology beyond academic efforts and into real-world practice applications.”
To learn more about DermAI, please join our demonstration webinar on Wednesday, June 26 at 12pm EDT.
Related resources
- Overview: DermAI
- Blog: Proscia DermAI Helps Dermpath Labs Increase Efficiency, Improve Quality, and Achieve Better Business Outcomes
- Overview: Proscia Concentriq Digital Pathology Platform
About Proscia
Proscia is a software company that is changing the way the world practices pathology to transform cancer research and diagnosis. With the company’s Concentriq digital pathology platform and pipeline of AI algorithms, laboratories are leveraging new kinds of data to improve patient outcomes and accelerate discoveries. Proscia’s team of technologists, scientists, and pathologists is bringing a fresh approach to an outdated industry, helping the world to keep pace with the increasing demand for pathology services and fulfill the promise of precision care. For more information, visit proscia.com.
*Proscia’s products are for research use only.
Source: Proscia