Skip to main content

Proscia, UCSF Collaborate on AI-Based Pathology for Cancer Diagnosis

NEW YORK – Proscia said on Monday that it is partnering with the University of California, San Francisco with the aim of introducing artificial intelligence into the practice of pathology.

Beginning with prostate cancer, the collaboration will aim to validate the clinical efficacy of computational pathology applications for several high-impact pathology subspecialties, Proscia said.

As one of the early adopters of digital pathology for primary diagnosis, UCSF has amassed volumes of diverse, high-quality digitized data, the Philadelphia-based company said. The data is being used initially to ensure that Proscia’s computational pathology application for prostate cancer accurately accounts for the variability that exists across a wide range of diagnoses, methods of biopsy and tissue preparation, tissue staining procedures, and digital scanning processes.

Proscia said that beyond prostate cancer, the partners anticipate expanding their work to include similar solutions that advance the practice of pathology for cancer subspecialties making up most pathology cases. As digital pathology continues to gain traction, these deep learning-enabled applications will help drive its adoption by unlocking new diagnostic information that furthers discovery and improves patient outcomes, Proscia said.

Financial and other terms of the collaboration were not disclosed.

In December 2019, Proscia announced a data collaboration with Johns Hopkins School of Medicine. Last week, the firm released the results of a large AI validation study in pathology conducted in collaboration with Dermatopathology Laboratory of Central States, University of Florida, and Thomas Jefferson University Hospital, in support of the June 2019 release of its DermAI application for dermatopathology.