RadSEM is a constrained LLM-assisted metric that rewrites radiology reports into atomic finding sentences, applies contradiction-constrained many-to-many matching, and computes an abnormal-focused weighted F1 score.
Chest ImaGenome Dataset.PhysioNet, July 2021
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
STAR3 is a multimodal spatio-temporal attentive retrieval system for radiology reports that aligns anatomical regions with clinical context and longitudinal changes, showing gains over prior retrieval methods on MIMIC-CXR.
citing papers explorer
-
RadSEM: A Finding-by-Finding Metric for Clinical Consistency in Radiology Reports
RadSEM is a constrained LLM-assisted metric that rewrites radiology reports into atomic finding sentences, applies contradiction-constrained many-to-many matching, and computes an abnormal-focused weighted F1 score.
-
Spatio-Temporal and Clinical Conditioning for Fine-Grained Radiology Report Retrieval
STAR3 is a multimodal spatio-temporal attentive retrieval system for radiology reports that aligns anatomical regions with clinical context and longitudinal changes, showing gains over prior retrieval methods on MIMIC-CXR.