Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Differential Impact of Low Voltage Area Radiofrequency Ablation on Recurrence of Atrial Fibrillation Versus Atrial Tachycardia in Patients With Persistent Atrial Fibrillation.

Circulation. Arrhythmia and electrophysiology·2026
Same author

Win Ratio Analysis of an Extensive Ablation Strategy in Patients With Persistent Atrial Fibrillation: Insights From the EARNEST-PVI Randomized Trial.

Circulation. Arrhythmia and electrophysiology·2026
Same author

Are β-Blockers Necessary for Patients with Heart Failure with Preserved Ejection Fraction? : PurSuit-HFpEF Registry.

European journal of heart failure·2026
Same author

Win ratio analysis of low-voltage area ablation in persistent atrial fibrillation: sub-analysis of SUPPRESS-AF.

European heart journal open·2026
Same author

ILD-Slider: A Parameter-Efficient Model for Identifying Progressive Fibrosing Interstitial Lung Disease from Chest CT Slices.

Journal of imaging·2025
Same author

Left Atrial Volumetric/Mechanical Coupling Index in Heart Failure With Preserved Ejection Fraction.

Journal of the American Heart Association·2025

Related Experiment Video

Updated: Jul 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Extracting Clinical Information From Japanese Radiology Reports Using a 2-Stage Deep Learning Approach: Algorithm

Kento Sugimoto1, Shoya Wada1,2, Shozo Konishi1

  • 1Department of Medical Informatics, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan.

JMIR Medical Informatics
|November 22, 2023
PubMed
Summary

A new two-stage deep learning system effectively extracts clinical information from free-text radiology reports, converting them into a structured format for better data reuse. This advanced system achieves high accuracy in entity and relation extraction from computed tomography (CT) reports.

Keywords:
NLPdeep learningfree textinformation extractionmachine learningnamed entity recognitionnatural language processingradiologyradiology reportrelation extractionreportreportsunstructured

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K

Related Experiment Videos

Last Updated: Jul 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Natural Language Processing for Healthcare
  • Radiology Informatics

Background:

  • Radiology reports are predominantly unstructured free text, hindering efficient data retrieval and secondary use.
  • The lack of structured data in radiology reports presents a significant challenge for clinical information extraction and analysis.
  • Developing methods to structure radiology report data is crucial for advancing medical research and improving patient care.

Purpose of the Study:

  • To develop and evaluate a two-stage deep learning system for extracting clinical information from free-text radiology reports.
  • To convert unstructured radiology report data into a structured format, enabling secondary use and analysis.
  • To assess the accuracy and comprehensiveness of a deep learning system in processing Japanese computed tomography (CT) reports.

Main Methods:

  • A two-stage deep learning system comprising entity extraction and relation extraction modules was developed.
  • State-of-the-art deep learning models were employed for both entity and relation extraction tasks.
  • The system was trained and validated on 1040 in-house Japanese CT reports annotated by medical experts.

Main Results:

  • The best-performing models achieved microaveraged F1-scores of 96.1% for entity extraction and 97.4% for relation extraction.
  • The overall two-stage system pipeline demonstrated a microaveraged F1-score of 91.9% for structured data conversion.
  • The system achieved 96.2% coverage of clinical information within the evaluated radiology reports.

Conclusions:

  • The developed two-stage deep learning system accurately and comprehensively extracts clinical information from free-text radiology reports.
  • The system shows significant promise for transforming unstructured radiology data into a usable structured format.
  • This approach facilitates the secondary use of radiology reports, potentially improving clinical research and data-driven healthcare insights.