RadGraph-XL: Radiology Entity and Relation Extraction
Entity and relation extraction from radiology reports. Annotators identify clinical entities (Anatomy, Observation, Medical Device, Procedure, Descriptor) and label relations between them (located_at, suggestive_of, modify, part_of).
Fichier de configurationconfig.yaml
# RadGraph-XL: Radiology Entity and Relation Extraction
# Based on Khanna et al., Findings ACL 2024
# Paper: https://aclanthology.org/2024.findings-acl.765/
# Dataset: https://physionet.org/content/radgraph-xl/
#
# RadGraph-XL provides expert annotations of radiology reports with clinical
# entities and relations. This enables automated extraction of structured
# information from free-text radiology reports.
#
# Entity Types:
# - Anatomy: Body parts, organs, anatomical structures
# (e.g., lungs, heart, mediastinum, pleural space)
# - Observation: Clinical findings, conditions, abnormalities
# (e.g., opacity, effusion, consolidation, pneumothorax)
# - Medical Device: Tubes, lines, implants, equipment
# (e.g., endotracheal tube, central line, pacemaker)
# - Procedure: Medical procedures, interventions
# (e.g., intubation, thoracentesis, CABG)
# - Descriptor: Modifiers describing size, severity, change
# (e.g., bilateral, small, stable, worsening, new)
#
# Relation Types:
# - located_at: Observation/device is located at an anatomy
# - suggestive_of: Observation suggests a condition
# - modify: Descriptor modifies an entity
# - part_of: Anatomy is part of another anatomy
#
# Annotation Guidelines:
# 1. Read the radiology report sentence in context
# 2. Identify all clinical entities and assign types
# 3. For each entity pair, determine the relation type
# 4. Anatomy-observation pairs typically use located_at
# 5. Descriptor-entity pairs typically use modify
# 6. Consider negation and uncertainty in observations
annotation_task_name: "RadGraph-XL: Radiology Relation Extraction"
task_dir: "."
data_files:
- sample-data.json
item_properties:
id_key: "id"
text_key: "text"
output_annotation_dir: "annotation_output/"
output_annotation_format: "json"
annotation_schemes:
# Step 1: Identify clinical entities
- annotation_type: span
name: clinical_entities
description: "Highlight all clinical entities in the radiology report"
labels:
- "Anatomy"
- "Observation"
- "Medical Device"
- "Procedure"
- "Descriptor"
label_colors:
"Anatomy": "#3b82f6"
"Observation": "#ef4444"
"Medical Device": "#22c55e"
"Procedure": "#f59e0b"
"Descriptor": "#8b5cf6"
keyboard_shortcuts:
"Anatomy": "1"
"Observation": "2"
"Medical Device": "3"
"Procedure": "4"
"Descriptor": "5"
tooltips:
"Anatomy": "Body parts, organs, anatomical structures (e.g., lungs, heart, mediastinum, pleural space)"
"Observation": "Clinical findings, conditions, abnormalities (e.g., opacity, effusion, consolidation, pneumothorax)"
"Medical Device": "Tubes, lines, implants, equipment (e.g., endotracheal tube, central line, pacemaker)"
"Procedure": "Medical procedures or interventions (e.g., intubation, thoracentesis, sternotomy)"
"Descriptor": "Modifiers describing size, severity, or change (e.g., bilateral, small, stable, worsening)"
allow_overlapping: false
# Step 2: Link entities with clinical relation types
- annotation_type: span_link
name: clinical_relations
description: "Draw relations between clinical entities"
labels:
- "located_at"
- "suggestive_of"
- "modify"
- "part_of"
tooltips:
"located_at": "Observation or device is located at an anatomical structure (e.g., opacity located_at right lung)"
"suggestive_of": "Observation suggests or indicates a clinical condition (e.g., air-fluid level suggestive_of abscess)"
"modify": "Descriptor modifies another entity (e.g., bilateral modify effusion; small modify opacity)"
"part_of": "Anatomical structure is part of another structure (e.g., right lobe part_of liver)"
html_layout: |
<div style="margin-bottom: 10px; padding: 8px; background: #f0f4f8; border-radius: 4px;">
<strong>Report Section:</strong> {{report_section}}
</div>
<div style="font-size: 16px; line-height: 1.6; font-family: 'Courier New', monospace;">
{{text}}
</div>
allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false
Données d'exemplesample-data.json
[
{
"id": "radgraph_001",
"text": "There is a small bilateral pleural effusion, greater on the right than the left, with associated compressive atelectasis at the lung bases.",
"report_section": "Findings"
},
{
"id": "radgraph_002",
"text": "The endotracheal tube is in satisfactory position with the tip approximately 4 cm above the carina. A right internal jugular central venous catheter terminates in the superior vena cava.",
"report_section": "Findings"
}
]
// ... and 8 more itemsObtenir ce design
Clone or download from the repository
Démarrage rapide :
git clone https://github.com/davidjurgens/potato-showcase.git cd potato-showcase/text/relation-extraction/radgraph-radiology-relations potato start config.yaml
Détails
Types d'annotation
Domaine
Cas d'utilisation
Étiquettes
Vous avez trouvé un problème ou souhaitez améliorer ce design ?
Ouvrir un ticketDesigns associés
CrossRE: Cross-Domain Relation Extraction
Cross-domain relation extraction across 6 domains (news, politics, science, music, literature, AI). Annotators identify entities and label 17 relation types between entity pairs, enabling study of domain transfer in relation extraction.
Event Coreference and Relations (MAVEN-ERE)
Unified event relation extraction covering coreference, temporal, causal, and subevent relations. Annotators identify event mentions and link them with typed relations (coreference, temporal_before/after/overlap, causal, subevent). Based on the MAVEN-ERE dataset which provides large-scale, unified annotations for four types of event relations.
Legal Event Coreference (LegalCore)
Event coreference resolution in legal documents including court opinions, contracts, and statutes. Annotators identify legal event mentions such as actions, states, obligations, and violations, then link coreferent events that refer to the same real-world event. Based on the LegalCore dataset for domain-specific event coreference in the legal domain.