Status Update On Digital Pathology And AI Algorithm Usage In An Academic Anatomical Pathology Practice: A 6-Year Report Card

The Ohio State University Wexner Medical Center (OSUWMC) was the first and is to date one of very few academic medical centers to implement digital pathology (DP) for clinical use with a fully automated end-to-end pathology workflow solution within the US. Since 2016, our pathology department, in conjunction with OSUWMC and James Cancer Hospital, has invested in a variety of DP tools and platforms, and has scanned retrospective oncology cases, mostly for research and archival purposes. In 2017, FDA approved the first DP system for primary diagnosis. Shortly after, we validated this system for clinical diagnostic purposes in accordance with the College of American Pathologists guideline.

Clinical service
In March 2018, we started to use DP for primary diagnosis. In 2019, we built our new histology laboratory with six scanners installed adjacent to staining machines to streamline our workflow. As of March 2023, we have scanned and archived approximately 3.2 million slides from about 300,000 clinical cases, which use four-petabyte storage. Currently, we are scanning 2,500 slides each day and adding one petabyte each year. The usage of DP is robust with 50-60 faculty, staff, and resident users daily. Besides primary diagnosis, other clinical applications using DP have been also established at OSUWMC including 1) Presenting pathology at multidiscipline tumor conferences; 2) Establishing a DP consultation portal to make OSU pathology subspecialty expertise accessible worldwide; and 3) Validating and implementing artificial intelligence (AI) applications for clinical use to improve accuracy and efficiency, and guide treatment.

Education
DP platform has been used for a variety of educational activity, such as signing out with trainees, conducting digital slide exams and unknown didactics. DP enabled our pathologists to provide uninterrupted trainee education during COVID-19 when many were social distancing. A first in class DP Master’s program will be offered at OSU in collaboration with department of Computer Science and Engineering. This program will leverage our state-of-the art and unique expertise in DP combined with the availability of already existing tools and DP image repository to generate a master’s program which will attract students from across the world.

Research
DP has benefited our research activities in many ways. By collaborating with faculty from department of Computer Science and Engineering, we have developed AI algorithms based on DP images to guide clinical decisions. We also plan to build a Center of Pathology AI by recruiting new faculty with expertise in pathology AI development and computer science to establish AI research laboratories with full access to the above-mentioned large-scale multimodal pathology database. We are also building comprehensive a deidentified and secure data warehouse equipped with clinicopathologic information, genomic information, DP images and AI analysis tools for researchers and clinicians to explore and compile data. Additionally, we are conducting clinical trials of DP systems and AI algorithms in partnership with vendors.

In summary, this presentation will provide the attendees with a perspectives of a more mature user group of pathologists and their next journey into the AI-driven pathology diagnostics.

Objectives:

1. To learn the experience in implementing digital pathology and artificial intelligence for clinical practice from a fully-digitized academic center
2. To gain knowledge of benefits and challenges of digital pathology and artificial intelligence in pathology

Presented by:

Zaibo Li, MD, PhD, MBA

Professor

The Ohio State University Wexner Medical Center

Zaibo Li, MD, Ph.D, MBA is a Professor, Director of Cytopathology and Cytopathology Fellowship Program, Associate Director of Digital and Computational Pathology at The Ohio State University Wexner Medical Center. He also holds an Endowed University Pathology Services Anatomic Pathology Professorship. Dr. Li is board certified in Anatomic/Clinical Pathology and Cytopathology. His academic interests are cytopathology, breast, gynecological pathology, and digital pathology. He completed his residency in AP/CP and a fellowship in Cytopathology at UPMC, and then completed a second fellowship in Breast/Gynecologic Pathology at Magee-Womens Hospital of UPMC in Pittsburgh, PA. Dr. Li has published more than 150 scientific articles and many book chapters. He is currently served as section or associate editor/editorial board for several Pathology Journals and also served in multiple national society committees. He has presented lectures on national/international pathology conferences and teaching courses.