March Talk: AI-Driven Pathology- Converting Knowledge to Graph Representations (HYBRID)
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.
Date and Time
Location
Hosts
Registration
- Date: 17 Mar 2025
- Time: 11:30 PM UTC to 12:45 AM UTC
-
Add Event to Calendar
- 300 3rd Ave SW
- Rochester, Minnesota
- United States 55902
- Building: Medical Sciences Building
- Room Number: Mann Hall
- Starts 03 March 2025 06:00 AM UTC
- Ends 17 March 2025 07:00 PM UTC
- No Admission Charge
Agenda
6:30 - 7:00 Social half hour to grab food and drink
7:00 - 8:00 Technical talk