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

Emergency radiology of severe acute injury in extreme alpine summer sports: a pictorial essay.

Emergency radiology·2026
Same author

Quadrato Motor Training in Parkinson's Disease: Resting-State fMRI Changes and Exploratory Whole-Brain Radiomics.

Bioengineering (Basel, Switzerland)·2026
Same author

Emergency radiology demand in a touristic region: residence status as a driver of imaging use.

Emergency radiology·2026
Same author

Evaluating head CT referral quality and appropriateness in an Italian emergency department: a monocentric retrospective study.

Insights into imaging·2025
Same author

Inter-reader reliability of MRI and CT Node Reporting and Data System 1.0 (Node-RADS) for mesorectal lymph nodes in rectal cancer.

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

ESR Essentials: gadolinium-wise MRI-practice recommendations by the European Society for Magnetic Resonance in Medicine and Biology.

European radiology·2024

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

Multi-Branch CNN-LSTM Fusion Network-Driven System With BERT Semantic Evaluator for Radiology Reporting in Emergency

Selene Tomassini1, Damiano Duranti1, Abdallah Zeggada1

  • 1Department of Information Engineering and Computer ScienceUniversity of Trento Trento 38121 Italy.

IEEE Journal of Translational Engineering in Health and Medicine
|March 4, 2025
PubMed
Summary

This study introduces an AI system for automatic radiology reporting of head CT scans in emergency rooms. The AI enhances diagnostic accuracy by analyzing brain anomalies, improving clinical decision-making for critical conditions.

Keywords:
Clinical and Translational Impact Statement—Our system improves clinical decision making by automating radiology reporting for emergency head CTs, enhancing diagnostic accuracy, reducing cognitive biases, and providing timely support for integration in hectic clinical settings.Convolutional neural networkemergency roomhead computed tomographylanguage modellong short-term memoryradiology reporting

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

348
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

451

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
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

348
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

451

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Emergency departments face high patient volumes requiring head CT scans.
  • Accurate and timely diagnosis of pathologies like ischemic or hemorrhagic stroke is critical.
  • Existing AI solutions do not offer structured reporting for head CT in emergency settings.

Purpose of the Study:

  • To develop an automated radiology reporting system for head CT scans.
  • To enhance diagnostic efficacy and clinical decision-making in emergency settings.
  • To analyze brain anomalies directly from head CT data using AI.

Main Methods:

  • A multi-branch CNN-LSTM fusion network was developed for report generation.
  • Head CT scans were preprocessed, selecting representative slices using PCA.
  • A pretrained VGG16 model processed slices, with LSTMs predicting captions combined via BERT semantic evaluation.

Main Results:

  • The system demonstrated effectiveness and stability in generating radiology reports.
  • Postprocessing refined the syntax of the automatically generated descriptions.
  • The AI system analyzes brain anomalies for improved diagnostic support.

Conclusions:

  • The developed AI system shows promise for automated radiology reporting in emergency settings.
  • Further work is needed to enhance the evaluation of clinical relevance.
  • Future research includes transitioning to 3D analysis and exploring vision-language models.