Results of a prospective study just released demonstrate that an artificial intelligence (AI) technology solution from Proscia can automatically detect melanoma with a high degree of accuracy.
Conducted at Thomas Jefferson University in Philadelphia and the University of Florida, the study assessed the the real-world performance of Proscia’s technology 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%. It also classified basal cell carcinoma and squamous cell carcinoma 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.
New to digital pathology? Learn how whole slide imaging is changing the industry here.