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

Positron Emission Tomography01:29

Positron Emission Tomography

3.9K
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...
3.9K

You might also read

Related Articles

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

Sort by
Same author

Evaluating ChatGPT 4.0 as a Tool for Nuclear Medicine Board Preparation.

Cureus·2025
Same author

Ventriculoperitoneal Shunt-Associated Cerebrospinal Fluid Pseudocyst Presenting as Abdominal Distension and Pain in an Adult Female Patient: A Case Report.

Cureus·2025
Same author

Layer by Layer: Assessing AI Diagnostic Accuracy With Incremental Case Information in Neuroradiology.

Cureus·2025
Same author

Vacuoles, E1 Enzyme, X-linked, Autoinflammatory, Somatic (VEXAS) Syndrome With Multisystem Involvement: Imaging and Genetic Insights From a Case Report.

Cureus·2025
Same author

A Case of Tip Appendicitis: The Role of CT Scan.

Cureus·2025
Same author

Lipomatous Dural Metaplasia Associated With Chronic Ventricular Shunting: A Report of Two Cases.

Cureus·2025

Related Experiment Video

Updated: May 8, 2025

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

458

ChatGPT-4 Turbo and Meta's LLaMA 3.1: A Relative Analysis of Answering Radiology Text-Based Questions.

Mohammed Abdul Sami1, Mohammed Abdul Samad2, Keyur Parekh1

  • 1Department of Diagnostic Radiology and Nuclear Medicine, Rush University Medical Center, Chicago, USA.

Cureus
|December 25, 2024
PubMed
Summary

GPT-4 Turbo demonstrated superior accuracy in answering pediatric radiology questions compared to LLaMA 3.1. This AI model shows promise for specialized medical education applications.

Keywords:
ai in medical educationchatgptlarge language models (llms)llamapediatric radiology

More Related Videos

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

8.1K
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

2.8K

Related Experiment Videos

Last Updated: May 8, 2025

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

458
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

8.1K
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

2.8K

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Education Technology
  • Radiology Informatics

Background:

  • Artificial intelligence (AI) models are increasingly being explored for their utility in specialized medical fields.
  • Evaluating the accuracy of large language models (LLMs) in answering domain-specific questions is crucial for their safe and effective implementation.
  • Pediatric radiology presents a unique set of challenges due to the specialized knowledge required.

Purpose of the Study:

  • To compare the accuracy of OpenAI's GPT-4 Turbo and Meta's LLaMA 3.1 in answering a standardized set of pediatric radiology questions.
  • To assess the overall performance and subsection-specific accuracy of each AI model.

Main Methods:

  • A set of 79 text-based pediatric radiology questions was curated from a larger dataset.
  • Questions covered seven subsections, excluding image-based queries to focus on text interpretation.
  • Both GPT-4 Turbo and LLaMA 3.1 were independently evaluated on the same question set, with accuracy calculated for overall and subsection performance.

Main Results:

  • GPT-4 Turbo achieved an overall accuracy of 88.6%, significantly outperforming LLaMA 3.1's 77.2%.
  • GPT-4 Turbo exhibited higher accuracy across most subsections, with perfect scores in chest and cardiac radiology.
  • LLaMA 3.1's highest accuracy was in musculoskeletal radiology (86.7%), while its lowest was in chest radiology (50.0%).

Conclusions:

  • GPT-4 Turbo demonstrated superior and consistent performance in answering pediatric radiology questions compared to LLaMA 3.1.
  • The findings suggest GPT-4 Turbo's potential for accurate responses in specialized medical education contexts.
  • Further research is warranted to explore AI model performance in other medical domains.