Proscia, a provider of digital and computational pathology solutions has released results on new technology that utilizes artificial intelligence (AI) to help automatically detect melanoma, the deadliest skin cancer form with a high level of accuracy.
The study was conducted at the Thomas Jefferson University and the University of Florida to demonstrate how AI can perform in reality on an uncurated set of 1422 sequential skin biopsies. The technology accurately identified melanoma in situ and invasive melanoma with a specificity of 91% and sensitivity of 93%. It also helps in the classification of basal cell carcinoma and squamous cell carcinoma with an AUC of .97 and .95 respectively which accounts for a combined 97% of all skin cancers.
Director of Dermatopathology, Dr. Kiran Motaparthi said that: The performance of Proscia technology in the detection of melanoma and other malignant skin diseases is impressive. This development is exciting to pathologists as they look forward to other valuable uses of artificial intelligence.
Additionally, Proscia is conducting more research to show the potential benefits of AI in dermatopathology which includes:
Delivering quick results to patients. AI that can identify melanoma automatically, alerts pathologists to be aware of the high-risk cases, flagging them for diagnosing early. The more the skin biopsies volume increase, the more detection can be of help to make sure that patients that have the most clinically impactful diagnoses are prioritized so they can start treatment sooner.
Driving consistency in diagnosing challenging melanoma cases. Melanoma is one of the most difficult diseases to diagnose which leads to interobserver variability among pathologists. AI has the ability to differentiate melanoma from benign mimickers which could be an aid to the pathologists increasing the accuracy of diagnosis and enhancing outcomes of patients.
Optimizing laboratory productivity to improve profitability. Over 15 million skin biopsies are taken yearly in the US, each of which may show hundreds of diagnoses. AI that distinguishes and classifies melanoma and non-melanoma skin cancer can assist laboratories in optimizing case distribution among non-specialists and specialists which results in gains in efficiency making it possible to process more case volume and partially overcome the impact of declining reimbursements.
Proscia’s vice president of AI Research & Development, Julianna Ianni, Ph.D. said: “Proscia’s technology represents a significant advancement in our work on skin pathology. 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.”
