Knowledge Graphs (KGs) are structured representations of knowledge that capture entities, their attributes, and the relationships between them. They are widely used in various applications, including search engines, recommendation systems, and natural language processing tasks.
I’d like to explore radiology report information extraction using knowledge graphs. There are two aspects of this domain that seem potentially interesting:
Extracting structured information from unstructured radiology reports to populate a knowledge graph.
Using knowledge graphs to enhance retrieval-augmented generation (RAG) for radiology-related tasks.