This episode of Digital Pathology Today™ our guest is Beatrice Knudsen, MD, PhD, Professor of Pathology; Medical Director of Digital and Computational Pathology, ARUP Laboratories; University of Utah.

The digital transformation in pathology is well underway but what kind of opportunities does this present to us? We've heard all the buzz words such as machine learning artificial intelligence and heard all the hype about enhanced workflows and making pathologists’ lives easier. What is the future practice of pathology going to look like?

Dr. Knudsen has built a program that integrates histopathology, multiplex tissue staining, digital image analysis, as well as computational pathology. She is applying this approach to close the gap between laboratory research and clinical care and to develop novel algorithms for diagnosis, prognosis and the treatment of patients.

Throughout her scientific career, Dr. Beatrice Knudsen has embraced multi-disciplinary research and have been fortunate to collaborate with the most talented basic scientists, epidemiologists and biostatisticians at the Fred Hutchinson Cancer Research Center in Seattle, Cedars-Sinai Medical Center in Los Angeles and now at the University of Utah – ARUP as Medical Director of Digital and Computational Pathology. Over the last 10 years, she built a program that integrates histopathology, multiplex tissue staining, digital image analysis and computational pathology for biomarker development. Advances in machine learning and high-performance computing permit the extraction of quantitative data from images of cancer tissues form patients and mouse models and to use images as molecular datasets. She is applying this approach to close the gap between laboratory research and clinical care and to develop novel algorithms for diagnosis, prognostication, and treatment of cancer patients.

After training in extracellular matrix biology, serine protease enzymology and receptor tyrosine kinases at Weill Cornel Medical School and Rockefeller University, Dr. Knudsen’s independent research focused primarily on mechanisms that drive prostate cancer metastasis. In addition, her training and board certification in anatomic pathology allowed to integrate mechanistic, laboratory research and digital pathology to move her research into the recently emerging area of computational pathology. She established pipelines for data generation from tissues stained on 5+5-plex antibody staining platforms (PLEXODY) that are fully automated and clinical grade. In addition, using machine learning and deep learning algorithms, my team developed methods to quantify cellular differentiation and chromosomal instability in regular pathology slides from prostate needle biopsies. Together, these methods can be used to convert tissue sections into high dimensional molecular data sets by enumerating the organization of tissue architecture, nuclear morphology, and subcellular protein expression.

At the University of Utah, her goal is to expand clinical, research and educational applications for digital and computational pathology. I was recruited by the department of pathology to establish an infrastructure for digital pathology sign-out, a shared resource for tissue staining and image analysis and to build a multidisciplinary program which integrates diagnostic and molecular pathology with basic and translational cancer research at the Huntsman Cancer Center and computer vision the Institute of Scientific Computing and Imaging.