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

Traumatic Brain Injury l: Introduction01:28

Traumatic Brain Injury l: Introduction

39
DefinitionTraumatic brain injury, or TBI, is a disturbance of normal brain function induced by an external mechanical force, such as a direct blow to the head or a penetrating injury. It can affect both brain structure and function, producing a wide range of clinical outcomes. TBI is a heterogeneous condition, meaning its effects may differ based on the type, location, and severity of the injury.Basis of ClassificationTBI is classified based on severity, injury mechanism, or pathophysiology. In...
39

You might also read

Related Articles

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

Sort by
Same author

Retargeted serine integrases for one-step, precise integration of large DNA sequences in human cells.

Nature biotechnology·2026
Same author

Effect of [<sup>68</sup>Ga]Ga-PSMA-11 PET-CT in the diagnosis of prostate cancer in men with equivocal or clinically high-risk non-suspicious findings on multiparametric MRI (PRIMARY2): a multicentre, non-inferiority, phase 3, randomised controlled trial.

The Lancet. Oncology·2026
Same author

EMBC Special Issue: Modeling Early Oxygenation Trajectory in PARDS from High-Frequency Mechanical Ventilation Signals Using Deep Sequence Architectures.

IEEE transactions on bio-medical engineering·2026
Same author

Unmasking the unexpected: a rare case of rheumatic heart disease.

Cardiology in the young·2026
Same author

The Performance of Prognostic Measures for Survival in Spinal Metastatic Disease in Light of Modern Advancements in Medical and Surgical Management.

Spine·2026
Same author

A 2-Year Analysis of Peer Tutoring in Dental Education: Enhancing Student Learning and Developing a Faculty Pathway.

Journal of dental education·2026

Related Experiment Video

Updated: May 6, 2026

Stereotactic Atlas-Guided Laser Capture Microdissection of Brain Regions Affected by Traumatic Injury
09:29

Stereotactic Atlas-Guided Laser Capture Microdissection of Brain Regions Affected by Traumatic Injury

Published on: September 11, 2017

9.7K

Leveraging Language Models for Automated Label Generation in Traumatic Brain Injury Radiology Reports.

Lingrui Cai1, Craig Williamson2, Andrew Nguyen2

  • 1Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA.

Research Square
|December 11, 2025
PubMed
Summary

Automated natural language processing (NLP) frameworks extract critical findings from head CT scans, improving traumatic brain injury (TBI) diagnosis. This technology enables faster, more consistent radiology report interpretation for better neurotrauma care.

Keywords:
Clinical Decision SupportDomain AdaptationNature Language ProcessingRadiology ReportSemi-supervised LearningTraumatic Brain Injury

More Related Videos

Semi-quantitative Assessment Using [18F]FDG Tracer in Patients with Severe Brain Injury
09:58

Semi-quantitative Assessment Using [18F]FDG Tracer in Patients with Severe Brain Injury

Published on: November 9, 2018

7.9K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

986

Related Experiment Videos

Last Updated: May 6, 2026

Stereotactic Atlas-Guided Laser Capture Microdissection of Brain Regions Affected by Traumatic Injury
09:29

Stereotactic Atlas-Guided Laser Capture Microdissection of Brain Regions Affected by Traumatic Injury

Published on: September 11, 2017

9.7K
Semi-quantitative Assessment Using [18F]FDG Tracer in Patients with Severe Brain Injury
09:58

Semi-quantitative Assessment Using [18F]FDG Tracer in Patients with Severe Brain Injury

Published on: November 9, 2018

7.9K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

986

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Timely interpretation of head CT scans is crucial for managing traumatic brain injury (TBI).
  • Delays in radiology reporting can impede urgent clinical decisions.
  • Current methods for analyzing radiology reports are often manual and time-consuming.

Purpose of the Study:

  • To develop and evaluate natural language processing (NLP) frameworks for automatically converting free-text head CT radiology reports into structured, machine-readable findings.
  • To improve the accuracy and efficiency of clinical finding and location extraction from radiology reports.
  • To enable faster and more consistent interpretation of radiology reports for improved neurotrauma care.

Main Methods:

  • Utilized 4,038 de-identified head CT reports, with 444 expert-annotated samples.
  • Compared various NLP strategies, including lexicon-weighted domain-adaptive pretraining and location-aware cascade models.
  • Employed semi-supervised learning using unlabeled reports to assess performance gains.

Main Results:

  • A lexicon-weighted domain-adaptive pretraining approach achieved a weighted F1-score of 0.92 across five-fold cross-validation.
  • A location-aware cascade model enhanced the recognition of anatomical sites, improving transparency and clinical relevance.
  • Semi-supervised learning provided moderate performance improvements over standard supervised models.

Conclusions:

  • Domain-specific adaptation and structured modeling in NLP can reliably extract critical findings from radiology text.
  • These NLP frameworks facilitate faster, more consistent interpretation of radiology reports.
  • Automated report generation can shorten reporting turnaround times and support data-driven neurotrauma care.