What you should know:
– Proscia®, a provider of digital and computational pathology solutions, has released the results of a study of a new artificial intelligence (AI) that predicts diagnostic agreement for melanoma, the deadliest form of prostate cancer. skin.
– The results, which were presented at the European Conference on Computer Vision (ECCV) 2022, highlight the potential of the technology to improve the diagnostic accuracy of melanoma and other diseases with poor pathologist concordance.
Findings illustrate technology’s promise to reduce misdiagnosis rate for deadliest form of skin cancer
Proscia is a software company accelerating the digital transformation of pathology to change the way we understand diseases like cancer. Its Concentriq digital pathology platform and powerful AI applications are advancing the 150-year-old research and diagnostic standard into a data-driven discipline, unlocking new insights that accelerate discovery, improve patient outcomes and deliver on the promise of precision care.
Conducted at the University of Florida and Thomas Jefferson University, Proscia’s retrospective study “Using whole-slide image representations from self-supervised contrastive learning for melanoma concordance regression” has demonstrated AI performance on 1,412 whole-slide images of skin biopsies. Each image was evaluated by three to five dermatopathologists to establish a concordance rate. The R2 the correlation between technology predictions and dermatopathologist agreement rates was 0.51.
In addition to this study, Proscia plans to conduct additional research illustrating the potential benefits of AI in helping pathologists diagnose melanoma, including:
– Reduce the rate of diagnostic errors for difficult cases. Melanoma often presents as benign mimics, causing pathologists to disagree on its diagnosis 40% of the time. Since cases are often assessed by a single pathologist, AI that predicts concordance with multiple experts could help improve diagnostic accuracy by serving as a second set of eyes.
– Accelerate turnaround times for critical results. More than 15 million skin biopsies are performed each year in the United States, each of which can show one of hundreds of diagnoses. AI that predicts diagnostic concordance could flag cases that are likely to be difficult, leading to efficiencies by suggesting additional tests to provide more complete insight before pathologist review.
– Reduce costs and patient distress. The frequent overdiagnosis of melanoma not only imposes additional costs on healthcare systems, but also leads patients to pay for unnecessary treatment and face the stress of believing they have a life-threatening disease. Increased diagnostic accuracy could help eliminate these burdens.
“Melanoma can be very difficult to diagnose,” said Dr. Kiran Motaparthi, director of dermatopathology and clinical associate professor of dermatology at the University of Florida. “Proscia’s technology signals an exciting advance as pathologists increasingly turn to AI to deliver on their commitment to excellence in patient care.”
Proscia’s research also indicates that the same AI could be extended to other diagnoses that demonstrate low pathologist agreement. This includes breast cancer staging as well as the Gleason staging of prostate cancer, which is used to assess the aggressiveness of the disease. Both often play an important role in informing treatment decisions.
“With this study, we’ve laid the foundation for a new use case for AI in pathology that could have a dramatic impact on patient outcomes,” said Sean Grullon, senior AI scientist at Proscia and author. principal of the study. “Our technology relies on self-supervised learning to recognize incredibly subtle patterns, demonstrating the power of one of the most advanced approaches in AI.”