AI Breakthrough in Melanoma Detection

Proscia recently released study results on new technology that uses artificial intelligence (AI) to automictically detect melanoma with a high degree of accuracy.¹ These findings may demonstrate the ability of AI to deliver faster diagnoses of melanoma which can improve patient outcomes and lab economics in the routine practice of pathology. 

The trial was conducted at Thomas Jefferson University and the University of Florida, where the AI was used on an uncurated set of 1,422 sequential skin biopsies. The technology correctly identified invasive melanoma and melanoma in situ with a sensitivity of 93% and a specificity of 91%, according to the press release. 

It also classified basal cell carcinoma (BCC) and squamous cell carcinoma (SCC) with an AUC of .97 and .95, respectively, accounting for a combined 97% of all skin cancers. This study validated the results of a multi-site retrospective study of 12,784 images, which will be presented during the Computational Challenges in Digital Pathology Workshop at the 2021 International Conference on Computer Vision.²

“The performance of Proscia’s technology in detecting melanoma and other malignant skin diseases is impressive,” said Kiran Motaparthi, MD, FAAD, director of dermatopathology and clinical associate professor of dermatology at the University of Florida. “This is an exciting development as pathologists increasingly look to unlock new sources of value from artificial intelligence.”

Proscia is also conducting research to demonstrate the potential benefits of AI in dermatology, such as¹:

• Delivering faster results to patients. If AI can automatically identify melanoma, it can show the pathologist a high-risk case and then lead to earlier diagnosis. This will help prioritize cases and begin treatment sooner. 
• Consistency in the diagnosis of difficult melanoma cases. Melanoma can be challenging to diagnose and lead to interobserver variability among pathologists.3 The ability of AI to distinguish melanoma from other skin issues could serve as an adjunctive aid to the pathologist to increase diagnostic accuracy and improve patient outcomes.
• Optimizing laboratory productivity to enhance profitability. More than 15 million skin biopsies are taken annually in the United States.4 AI that classifies and distinguishes melanoma and non-melanoma skin cancer could enable laboratories to optimize case distribution among specialists and non-specialists. This may result in efficiency gains that make it possible to process more case volume and partially overcome the impact of declining reimbursements.

“Proscia’s technology represents a significant advancement in our work on skin pathology,” said Julianna Ianni, PhD, Proscia vice president of AI research and development. “Our AI not only identifies melanoma, a difficult diagnosis, but also accounts for the high degree of variation in disease to push the boundaries of deep learning in medicine. In doing so, it holds great promise to help pathologists deliver faster, more consistent diagnoses and improve patient outcomes.”

The AI validated in the study expands upon the technology that powers Proscia’s DermAI application. Available on the Concentriq digital pathology platform, DermAI provides an AI-based classification for every skin case to drive efficiency and quality gains, the press release explained. The application’s performance was tested in a pathology study, and continues to be validated and deployed as part of Proscia’s ongoing work in AI.

The company is also collaborating with academic and commercial laboratories, including LabPON, Johns Hopkins School of Medicine, Unilabs, University Medical Center Utrecht, and University of California, San Francisco, to accelerate the adoption of AI in pathology.

To learn more about Proscia’s prospective study, watch the webinar, “Automated Detection of Melanoma and Non-Melanoma Skin Cancer with Artificial Intelligence: Prospective Study & Real-World Impact,” on November 9, 2021.

References:

1. Proscia announces artificial intelligence breakthrough in melanoma detection. Proscia. Press release. Published October 5, 2021. Accessed October 14, 2021. https://proscia.com/proscia-announces-artificial-intelligence-breakthrough-in-melanoma-detection/

2. Sankarapandian, S. Kohn, S., Spurrier, V., et al. A Pathology Deep Learning System Capable of Triage of Melanoma Specimens Utilizing Dermatopathologist Consensus as Ground Truth. To be presented at CDPath Workshop at ICCV 2021. https://arxiv.org/abs/2109.07554.

3. Elmore, J. G., Barnhill, R. L., Elder, D. E., et al. (2017). Pathologists’ diagnosis of invasive melanoma and melanocytic proliferations: observer accuracy and reproducibility study. BMJ (Clinical research ed.), 357, j2813. doi:10.1136/bmj.j2813

4. Klipp, J. (2019). The U.S. Anatomic Pathology Market: Forecast & Trends 2019-2021. Laboratory Economics. Poughkeepsie, NY.