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

Imaging Studies for Cardiovascular System V: CT01:28

Imaging Studies for Cardiovascular System V: CT

71
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
71

You might also read

Related Articles

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

Sort by
Same author

The role of the globus pallidus subregions in the schizophrenia spectrum continuum.

Molecular psychiatry·2026
Same author

Early Pancreatic Cancer: Clinical Implications, Workup, and Imaging Findings with Histopathologic Correlation for Personalized Surveillance.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026
Same author

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026
Same author

Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT.

Abdominal radiology (New York)·2026
Same author

Effect of adding metronidazole to meropenem on clinical efficacy in complicated intra-abdominal infections: a retrospective study.

BMC infectious diseases·2026
Same author

Evaluation of super-resolution deep learning reconstruction on three-dimensional constructive interference in steady state for enhanced visualization of vestibular schwannomas.

Radiological physics and technology·2026

Related Experiment Video

Updated: Sep 18, 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

8.4K

Fine-tuned large language model for classifying CT-guided interventional radiology reports.

Koichiro Yasaka1, Naoaki Nishimura1, Takahiro Fukushima1

  • 1Department of Radiology, The University of Tokyo Hospital, Tokyo, Japan.

Acta Radiologica (Stockholm, Sweden : 1987)
|June 24, 2025
PubMed
Summary

A new large language model accurately classifies computed tomography (CT)-guided interventional radiology reports. This AI model significantly outperforms human readers in speed and accuracy for categorizing procedures.

Keywords:
Computed tomography-guided interventional radiologyartificial intelligencedeep learninglarge language modelobserver performance

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.3K
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

693

Related Experiment Videos

Last Updated: Sep 18, 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

8.4K
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.3K
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

693

Area of Science:

  • Artificial Intelligence in Radiology
  • Natural Language Processing for Medical Reports
  • Interventional Radiology Workflow Optimization

Background:

  • Manual data curation of radiology reports is time-consuming and prone to errors due to natural language complexities.
  • Automating the classification of computed tomography (CT)-guided interventional radiology reports is crucial for efficient data management.
  • Existing methods require significant manual effort, highlighting the need for advanced computational approaches.

Purpose of the Study:

  • To develop and evaluate a fine-tuned large language model (LLM) for classifying CT-guided interventional radiology reports.
  • To categorize reports into specific technique groups: drainage, soft tissue biopsy, lung biopsy, and bone biopsy.
  • To compare the LLM's classification performance and efficiency against human readers.

Main Methods:

  • A retrospective dataset of 1505 CT-guided interventional radiology reports (August 2008 - November 2024) was curated.
  • Reports were manually classified into four categories to establish a reference standard.
  • A bi-directional encoder representation from transformers (BERT) model was fine-tuned on the training data and optimized using the validation set.

Main Results:

  • The fine-tuned LLM achieved a high accuracy of 0.979 on the independent test dataset.
  • The model's accuracy was significantly superior to that of two human readers (0.922-0.940, P ≤ 0.012).
  • The LLM classified reports 49.8 to 53.5 times faster than human readers, demonstrating remarkable efficiency.

Conclusions:

  • A fine-tuned LLM can accurately and efficiently classify CT-guided interventional radiology reports into distinct technique categories.
  • The developed AI model offers a significant improvement over manual classification by human readers in both accuracy and speed.
  • This technology has the potential to streamline radiology workflows and enhance data analysis in interventional radiology.