IEEE Southern Minnesota Section

Pathology data, primarily consisting of slides and diagnostic reports, inherently contain knowledge pivotal for advancing data-driven biomedical research and clinical practice. However, the hidden and fragmented nature of this knowledge across various data modalities not only hinders its computational utilization but also impedes the effective integration of AI technologies in the domain of pathology. To systematically organize pathology knowledge for computational use, we propose PathoGraph, a representation method capable of comprehensively and structurally capturing multi-scale disease characteristics alongside pathologists’ expertise in a graph-based format. Furthermore, by leveraging existing pathology image recognition techniques, we achieved large-scale automated construction of PathoGraph, applied it to enhance the performance of downstream deep learning models, and presented two illustrative use cases that highlight its clinical potential. Collectively, we believe our efforts lay a critical foundation for constructing pathology knowledge graphs, thereby advancing AI-driven pathology practice. Agenda: 6:30 - 7:00 Social half hour to grab food and drink 7:00 - 8:00 Technical talk Room: Mann Hall, Bldg: Medical Sciences Building, 300 3rd Ave SW, Rochester, Minnesota, United States, 55902, Virtual: https://events.vtools.ieee.org/m/472672