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

8.0K
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...
8.0K
Imaging Studies for Cardiovascular System V: CT01:28

Imaging Studies for Cardiovascular System V: CT

279
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...
279

You might also read

Related Articles

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

Sort by
Same author

Hierarchical Mixture-of-Experts Framework for Whole-Brain Imaging and Whole-Genome Analysis of Multiple Cognitive Functions.

IEEE journal of biomedical and health informatics·2026
Same author

Personalized eye protection for head CT organ-based tube current modulation: A deep learning approach to derive 3D eyeball models from a single-view topogram.

Journal of applied clinical medical physics·2026
Same author

KGT: Knowledge-guided graph transformer for neurodegenerative disease diagnosis and brain age prediction with MRI.

Medical image analysis·2026
Same author

Automatic Detection of Multiple Artifacts in Computed Tomography Images by Self-Attention Guided Vision Transformer.

Journal of imaging informatics in medicine·2026
Same author

Validation of the Caprini risk assessment model and efficacy of perioperative nutritional support + preventive nursing in reducing DVT among high-risk older adults undergoing hip fracture surgery: a two-phase study.

Frontiers in medicine·2026
Same author

An Integrated Risk Prediction Model for Gout Using Clinical Data, Ultrasound Features, and Deep Learning: A Retrospective Multicenter Study.

Journal of inflammation research·2026

Related Experiment Video

Updated: Jan 14, 2026

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

4.2K

Personalized CT Protocol Recommendation via Large Language Model: Enabling Fully Automated CT Scanning Workflows.

Xiaolin Meng1,2, Yefen Wu3, Xin Dou4

  • 1School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China. xiaolin.meng@sjtu.edu.cn.

Journal of Imaging Informatics in Medicine
|October 16, 2025
PubMed
Summary

A new Large Language Model Retrieval-Augmented Generation (LLM-RAG) framework automates CT protocol selection, improving radiology workflow efficiency. This AI system provides personalized, accurate recommendations without retraining, accelerating imaging automation.

Keywords:
Computed tomographyLarge language modelProtocol recommendationRetrieval-augmented generationWorkflow automation

More Related Videos

Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.6K
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

1.0K

Related Experiment Videos

Last Updated: Jan 14, 2026

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

4.2K
Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.6K
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

1.0K

Area of Science:

  • Medical Imaging Informatics
  • Artificial Intelligence in Radiology
  • Clinical Workflow Optimization

Background:

  • Manual computed tomography (CT) protocol selection is a significant bottleneck in radiology.
  • This manual process is time-consuming and prone to errors, hindering full automation of scanning pipelines.

Purpose of the Study:

  • To develop and evaluate a Large Language Model Retrieval-Augmented Generation (LLM-RAG) framework for personalized CT protocol recommendations.
  • To overcome limitations in current CT protocol selection processes and enhance radiology workflow automation.

Main Methods:

  • Constructed a protocol knowledge base using historical examination records.
  • Utilized LLM-RAG for institutionally tailored, precision CT protocol recommendations.
  • Evaluated performance of Qwen and DeepSeek models at various scales, analyzing scaling laws and GPU memory requirements.

Main Results:

  • The LLM-RAG framework achieved high performance (min: 88.60% precision, 89.34% recall, 88.08% F1, 96.09% accuracy).
  • Task-specific parity was observed between Qwen and DeepSeek models at equivalent scales.
  • Larger models demonstrated improved accuracy, with linear GPU memory-cost scaling identified as a deployment constraint.

Conclusions:

  • The developed LLM-RAG framework offers clinically viable accuracy for CT protocol recommendation without requiring model retraining.
  • This approach significantly streamlines scanning operations and accelerates the automation of imaging workflows.
  • The study defines clinical deployment constraints based on model scale and GPU memory usage.