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

Computed Tomography01:10

Computed Tomography

4.7K
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...
4.7K
Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

325
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
325
Radiological Investigation II: MRI and Ventilation Perfusion Scan01:30

Radiological Investigation II: MRI and Ventilation Perfusion Scan

177
Description
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
177
Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

375
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
375
Positron Emission Tomography01:29

Positron Emission Tomography

4.4K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.4K
X-ray Imaging01:24

X-ray Imaging

5.7K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
5.7K

You might also read

Related Articles

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

Sort by
Same author

Quantitative MRI of the liver: Evaluation of extracellular volume fraction and other quantitative parameters in comparison to MR elastography for the assessment of hepatopathy.

Magnetic resonance imaging·2020
Same author

Correction to: Is liver lesion characterisation by simplified IVIM DWI also feasible at 3.0 T?

European radiology·2019
Same author

Is liver lesion characterisation by simplified IVIM DWI also feasible at 3.0 T?

European radiology·2019
Same author

Accurate IVIM model-based liver lesion characterisation can be achieved with only three b-value DWI.

European radiology·2018
Same author

Joint adolescent-adult early phase clinical trials to improve access to new drugs for adolescents with cancer: proposals from the multi-stakeholder platform-ACCELERATE.

Annals of oncology : official journal of the European Society for Medical Oncology·2018
Same author

Comparison of magnetic resonance feature tracking with harmonic phase imaging analysis (CSPAMM) for assessment of global and regional diastolic function.

European journal of radiology·2014
Same journal

ESR Essentials: uterine cancers-practice recommendations by the European Society of Urogenital Radiology.

European radiology·2026
Same journal

Adjunctive quantification for more reproducible amyloid PET interpretation.

European radiology·2026
Same journal

APEX-NET: automated pancreatic evaluation network using early non-contrast CT.

European radiology·2026
Same journal

Temporal bone remodeling after venous stenting for pulsatile tinnitus: isolated dehiscence versus diverticulum.

European radiology·2026
Same journal

Do hepatic and biliary functional data from gadoxetate-enhanced MRI add value in predicting outcomes in primary sclerosing cholangitis (PSC)?

European radiology·2026
Same journal

Cardiovascular risk factors and carotid plaque components in a multi-ethnic cohort using 3 Tesla MRI: the HELIUS study.

European radiology·2026
See all related articles

Related Experiment Video

Updated: Aug 7, 2025

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering
09:43

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering

Published on: November 22, 2019

6.3K

Transformer-based structuring of free-text radiology report databases.

S Nowak1, D Biesner2, Y C Layer3

  • 1Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany. sebastian.nowak@ukbonn.de.

European Radiology
|March 11, 2023
PubMed
Summary
This summary is machine-generated.

Custom pre-training of transformer models on-site, combined with manual annotation, efficiently structures free-text radiology reports for data-driven medicine. This approach unlocks valuable data even with limited annotation resources.

Keywords:
Deep learningIntensive care unitsNatural language processingRadiologyThorax

More Related Videos

Generation of Comprehensive Thoracic Oncology Database - Tool for Translational Research
11:18

Generation of Comprehensive Thoracic Oncology Database - Tool for Translational Research

Published on: January 22, 2011

16.1K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

140

Related Experiment Videos

Last Updated: Aug 7, 2025

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering
09:43

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering

Published on: November 22, 2019

6.3K
Generation of Comprehensive Thoracic Oncology Database - Tool for Translational Research
11:18

Generation of Comprehensive Thoracic Oncology Database - Tool for Translational Research

Published on: January 22, 2011

16.1K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

140

Area of Science:

  • Natural Language Processing (NLP) in medical informatics
  • Machine learning applications in radiology
  • Data structuring for clinical databases

Background:

  • Free-text radiology reports represent a rich data source for clinical insights.
  • Retrospective structuring of these databases is crucial for data-driven medicine.
  • On-site development of NLP methods offers a tailored solution for clinics.

Purpose of the Study:

  • To investigate optimal labeling and pre-training strategies for on-site transformer-based structuring of free-text radiology report databases.
  • To compare the performance of on-site custom pre-trained models versus publicly available models.
  • To evaluate the impact of varying amounts of manual (gold) and rule-based (silver) labels on model performance.

Main Methods:

  • Utilized 93,368 German chest X-ray reports from intensive care unit (ICU) patients.
  • Compared two labeling strategies: rule-based 'silver labels' and manually annotated 'gold labels'.
  • Evaluated an on-site pre-trained transformer model (Tmlm) against a medically pre-trained model (Tmed), fine-tuning with different label combinations and quantities.

Main Results:

  • The custom on-site pre-trained model fine-tuned on gold labels (Tmlm,gold) achieved high performance (95.5% MAF1).
  • Tmlm,gold significantly outperformed models trained solely on silver labels.
  • With sufficient gold labels (≥2000), hybrid training (silver then gold) did not significantly improve performance over gold-label-only training for the custom model.

Conclusions:

  • On-site custom pre-training of transformer models, coupled with targeted manual annotation, is an effective strategy for unlocking radiology report databases.
  • This approach facilitates data-driven medicine by enabling retrospective data structuring with efficient use of annotation resources.
  • The findings provide practical insights for clinics aiming to develop in-house NLP solutions for their specific data needs.