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

Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

5.6K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.6K
Computed Tomography01:10

Computed Tomography

4.5K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.5K

You might also read

Related Articles

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

Sort by
Same author

Towards clinically interpretable machine learning in emergency surgery: feature importance and insights across clinical time points in abdominal pain cases.

Langenbeck's archives of surgery·2026
Same author

Opportunistic CT Fatty Muscle Fraction for Outcome Prediction in Patients Undergoing Transcatheter Mitral Valve Edge-to-Edge Repair.

Circulation. Cardiovascular imaging·2026
Same author

Photon counting detector CT contrast agent-reduced transcatheter aortic valve reconstruction planning: a comparative study.

European radiology·2026
Same author

Tackling the global health research financing emergency to sustain national health research ecosystems.

Lancet (London, England)·2026
Same author

Optical See-Through and Video See-Through Head-Mounted Displays for Percutaneous Biopsies: A Comparative Phantom Study.

Cardiovascular and interventional radiology·2026
Same author

Deep learning improves image quality in motion-robust and sedation-free pediatric brain MRI.

European radiology·2026

Related Experiment Video

Updated: Jul 11, 2025

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

Development of image-based decision support systems utilizing information extracted from radiological free-text

Sebastian Nowak1, Helen Schneider2, Yannik C Layer3

  • 1Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Bonn, Germany. sebastian.nowak@ukbonn.de.

European Radiology
|November 7, 2023
PubMed
Summary

Transformer models can automatically annotate radiology reports, improving the development of AI-powered diagnostic systems. This approach unlocks large datasets for on-site artificial intelligence (AI) development, overcoming manual annotation limitations.

Keywords:
Deep learningIntensive care unitsRadiologyThorax

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.6K

Related Experiment Videos

Last Updated: Jul 11, 2025

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
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.6K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Natural Language Processing in Healthcare
  • Radiology and Diagnostic Systems

Background:

  • Developing AI-based diagnostic decision support systems (DDSS) often requires large, accurately annotated datasets.
  • Manual annotation of radiological images and reports is time-consuming and resource-intensive.
  • Transformer models offer a potential solution for automating the annotation process.

Purpose of the Study:

  • To evaluate the effectiveness of transformer-based report annotation for on-site development of image-based DDSS.
  • To compare the performance of DDSS models trained with different annotation strategies (gold labels, silver labels, combined).
  • To assess the impact of annotation effort on model performance.

Main Methods:

  • Utilized 88,353 chest X-rays from 19,581 intensive care unit (ICU) patients.
  • Generated 'gold labels' through manual assessment of radiologist reports and 'silver labels' using transformer models.
  • Trained image-based models using gold labels only (M_G), silver then gold (M_S/G), and silver plus gold (M_S+G) labels.

Main Results:

  • Transformer-based silver labels significantly improved performance (AUC) compared to gold labels alone.
  • The M_S/G approach showed superior results, especially with larger datasets (e.g., 14,580 images).
  • Combined silver and gold labels (M_S+G) were beneficial with fewer gold labels (N=500).

Conclusions:

  • Transformer-based annotation holds significant potential for leveraging free-text reports to develop image-based DDSS.
  • On-site DDSS development can benefit from sophisticated annotation pipelines beyond single reports.
  • This approach facilitates AI application in clinical practice by simplifying data access.