Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Brain Imaging

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A large dataset of brain imaging linked to health systems data: curation and access to a whole system national cohort from NHS Scotland.

GigaScience·2026

Same author

Ethnicity and Heart Failure Outcomes in England: Role of Specialist Care in a Universal Health System.

Journal of the American College of Cardiology·2026

Same author

Natural language processing for geriatric syndromes: a systematic review of methods, applications, and challenges.

BMC medical informatics and decision making·2026

Same author

Clinically reported covert cerebrovascular disease and risk of neurological disease: a whole-population cohort of 367 988 people using natural language processing.

Journal of neurology, neurosurgery, and psychiatry·2026

Same author

Perihematomal Edema and Functional Outcome After Intracerebral Hemorrhage: A Meta-Analysis of Individual Participant Data.

Stroke·2026

Same author

Detecting Adverse Drug Events in Social Media: A Brief Literature Review.

SN computer science·2026

Same journal

Immune biomarkers, profiles, and responses: a vaccine ontology perspective.

Journal of biomedical semantics·2026

Same journal

A pragmatist approach to bridging tables and ontologies through LinkML and punning.

Journal of biomedical semantics·2026

Same journal

FAIR in practice: minimum metadata schema for bioinformatics analytics by machines.

Journal of biomedical semantics·2026

Same journal

Prenatal monitoring in primary health care: a design science research-based approach to FHIR interoperability.

Journal of biomedical semantics·2026

Same journal

From narrative evidence to computable knowledge: a decision-relevant corpus for medicinal herb-disease relationships.

Journal of biomedical semantics·2026

Same journal

BERTopic-driven term extraction from biomedical texts toward ontology population: evaluating vaccine ontology with Plotkin's vaccines corpus.

Journal of biomedical semantics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 4, 2026

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Text mining brain imaging reports.

Beatrice Alex^1,2,3, Claire Grover^4,5, Richard Tobin⁴

¹School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, Edinburgh, UK. balex@ed.ac.uk.

Journal of Biomedical Semantics

|November 13, 2019

Summary

This summary is machine-generated.

This study introduces the Edinburgh Information Extraction for Radiology reports (EdIE-R) system, a text mining tool that accurately classifies stroke information in radiology reports. High accuracy in extracting data from electronic health records aids population health monitoring and research.

Keywords:

Electronic healthcare records Neuroimaging reports Stroke classification Text mining

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

Related Experiment Videos

Last Updated: Jan 4, 2026

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

Area of Science:

Medical Informatics
Natural Language Processing
Radiology

Background:

Advancements in text mining and Electronic Healthcare Records (EHR) enable structured data extraction from unstructured clinical text.
Radiology reports, particularly for CT and MRI brain scans, contain valuable information about stroke and other observations.

Purpose of the Study:

To develop and evaluate a text mining system, Edinburgh Information Extraction for Radiology reports (EdIE-R), for classifying stroke-related information in radiology reports.
To identify entities, negation, and relations within reports to determine report-level labels (phenotypes).

Main Methods:

The EdIE-R system was developed and tested on 1168 radiology reports from the Edinburgh Stroke Study (ESS).
Manual annotations for entities, negation, relations, and labels were created iteratively with domain expert feedback.
The rule-based EdIE-R system was tuned based on these annotations.

Main Results:

High inter-annotator agreement (IAA) was achieved: 96.96% for entities, 96.46% for negation, 95.84% for relations, and 94.02% for labels.
The EdIE-R system demonstrated high performance on a blind test set, with scores above 94% for entities, negation, relations, and labels.

Conclusions:

Automated analysis of EHR data at high accuracy facilitates population health monitoring, audits, and epidemiological studies.
The EdIE-R system shows promise for extracting critical clinical information from radiology reports.
The manually annotated ESS corpus will be made available for research purposes.