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

Anatomically Localized Detection of Six Acute Abdominal Emergencies on CT Using Multi-window Deep Learning: Development and Validation.

Journal of imaging informatics in medicine·2026
Same author

Prospective quantitative analysis of hyperparameter and input optimization in GPT-5: comparative contribution to radiologist performance in abdominal radiology.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Diagnostic performance of contrast-enhanced spectral mammography in the evaluation of suspicious microcalcifications without associated mass.

Acta radiologica (Stockholm, Sweden : 1987)·2025
Same author

MammosighTR: Nationwide Breast Cancer Screening Mammogram Dataset with BI-RADS Annotations for Artificial Intelligence Applications.

Radiology. Artificial intelligence·2025
Same author

Assessment of Neovascularization in de Quervain's Disease With Superb Microvascular Imaging.

Journal of clinical ultrasound : JCU·2025
Same author

Systematic review of artificial intelligence competitions in radiology: a focus on design, evaluation, and trends.

Diagnostic and interventional radiology (Ankara, Turkey)·2025

Related Experiment Video

Updated: May 24, 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

2.6K

Deep learning for named entity recognition in Turkish radiology reports.

Abubakar Ahmad Abdullahi1, Murat Can Ganiz1, Ural Koç2

  • 1Marmara University Faculty of Engineering, Department of Computer Engineering, İstanbul, Türkiye.

Diagnostic and Interventional Radiology (Ankara, Turkey)
|February 28, 2025
PubMed
Summary
This summary is machine-generated.

This study developed a deep learning framework for named entity recognition (NER) in Turkish radiology reports. The BioBERTurk model achieved an 80.1 F1 score, enhancing clinical insights and patient care.

Keywords:
Named entity recognitionTurkishcomputed tomographyidirectional encoder representations from transformersradiology reportsthorax

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
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

1.3K

Related Experiment Videos

Last Updated: May 24, 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

2.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
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

1.3K

Area of Science:

  • Natural Language Processing
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Radiology reports contain critical patient information.
  • Efficient information extraction from these reports is challenging, especially in diverse languages like Turkish.
  • Named Entity Recognition (NER) is key to automating this extraction process.

Purpose of the Study:

  • To develop and evaluate a deep learning framework for Named Entity Recognition (NER) in Turkish radiology reports.
  • To enhance the accuracy and efficiency of information extraction from medical texts.
  • To improve clinical decision-making through better data insights.

Main Methods:

  • Utilized a synthetic dataset of 1,056 Turkish radiology reports.
  • Employed the DYGIE++ model with four Bidirectional Encoder Representations from Transformers (BERT) models: BERTurk, BioBERTurk, PubMedBERT, and XLM-RoBERTa.
  • Incorporated adaptive span enumeration and span graph propagation for enhanced entity recognition and coreference resolution.

Main Results:

  • Achieved an F1 score of 80.1 for the NER task.
  • The BioBERTurk model, pre-trained on relevant Turkish biomedical and radiology data, demonstrated superior performance among the tested BERT models.
  • Detailed analysis of precision, recall, and F1 scores for each label was provided.

Conclusions:

  • The developed deep learning framework effectively handles the complexities of Turkish radiology reports.
  • The findings highlight the potential of BioBERTurk for medical NER tasks in Turkish.
  • This approach offers clinicians more precise insights, streamlining diagnostics and expediting patient treatment decisions.