Ontology-Based Concept Distillation for Radiology Report Retrieval and Labeling
By: Felix Nützel, Mischa Dombrowski, Bernhard Kainz
Potential Business Impact:
Helps doctors find rare diseases in X-rays.
Retrieval-augmented learning based on radiology reports has emerged as a promising direction to improve performance on long-tail medical imaging tasks, such as rare disease detection in chest X-rays. Most existing methods rely on comparing high-dimensional text embeddings from models like CLIP or CXR-BERT, which are often difficult to interpret, computationally expensive, and not well-aligned with the structured nature of medical knowledge. We propose a novel, ontology-driven alternative for comparing radiology report texts based on clinically grounded concepts from the Unified Medical Language System (UMLS). Our method extracts standardised medical entities from free-text reports using an enhanced pipeline built on RadGraph-XL and SapBERT. These entities are linked to UMLS concepts (CUIs), enabling a transparent, interpretable set-based representation of each report. We then define a task-adaptive similarity measure based on a modified and weighted version of the Tversky Index that accounts for synonymy, negation, and hierarchical relationships between medical entities. This allows efficient and semantically meaningful similarity comparisons between reports. We demonstrate that our approach outperforms state-of-the-art embedding-based retrieval methods in a radiograph classification task on MIMIC-CXR, particularly in long-tail settings. Additionally, we use our pipeline to generate ontology-backed disease labels for MIMIC-CXR, offering a valuable new resource for downstream learning tasks. Our work provides more explainable, reliable, and task-specific retrieval strategies in clinical AI systems, especially when interpretability and domain knowledge integration are essential. Our code is available at https://github.com/Felix-012/ontology-concept-distillation
Similar Papers
Automated Radiology Report Generation Based on Topic-Keyword Semantic Guidance
Multimedia
Helps doctors write X-ray reports faster.
RadIR: A Scalable Framework for Multi-Grained Medical Image Retrieval via Radiology Report Mining
CV and Pattern Recognition
Finds matching medical scans using doctor's notes.
CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings
Computation and Language
Helps doctors write accurate patient reports faster.