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 II: Positron Emission Tomography and Scintigraphy01:25

Imaging Studies II: Positron Emission Tomography and Scintigraphy

Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
Positron Emission Tomography01:29

Positron Emission Tomography

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 being...

You might also read

Related Articles

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

Sort by
Same author

Exploring the Influence of Leadership Identity on Radiologists' Leadership in German University Hospitals: A Nationwide Analysis.

Journal of healthcare leadership·2026
Same author

CT Radiomics Models Did Not Outperform Experts in Predicting [<sup>68</sup>Ga]Ga-PSMA-PET Positivity in Prostate Cancer Lymph Node Staging.

Current oncology (Toronto, Ont.)·2026
Same author

Reperfusion-Dependent Outcomes After Endovascular Thrombectomy Stratified by NIHSS-ASPECTS Clinical-Core Mismatch.

Annals of clinical and translational neurology·2026
Same author

Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Intracranial haemorrhage without early clinical deterioration after mechanical thrombectomy: rethinking the "asymptomatic" label.

European stroke journal·2026
Same author

Comparing performance of seven fine-tuned open-source large language models in summarizing and predicting outcome-relevant information from mechanical thrombectomy reports in patients with acute ischemic stroke.

European radiology·2025

Related Experiment Video

Updated: Jun 28, 2026

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

Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of

Semil Eminovic1, Robin Schmidt1, Bogdan Levita1

  • 1Department of Radiology, Charité - Universitätsmedizin Berlin, Augustenburger Platz 1, Berlin, 13353, Germany.

JMIR AI
|June 26, 2026
PubMed
Summary

DeepSeek-R1 demonstrated superior performance compared to ChatGPT-o1 in a radiology education context, excelling across all evaluated metrics. This suggests open-source large language models (LLMs) show promise for supporting radiology resident training.

Keywords:
artificial intelligencedeep learningeducationlarge language modelsmedicineradiology

Related Experiment Videos

Last Updated: Jun 28, 2026

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

Area of Science:

  • Artificial Intelligence in Medical Education
  • Radiology Training Technologies
  • Large Language Model (LLM) Applications

Background:

  • Radiology trainees need effective resources for learning complex imaging and diagnostic skills.
  • Large language models (LLMs) offer potential benefits for medical education, including personalized learning and diagnostic support.
  • Limited research exists on comparing LLMs for radiology education and clinical support across different subspecialties and experience levels.

Purpose of the Study:

  • To evaluate and compare the response quality of DeepSeek-R1 and ChatGPT-o1 as tools for radiology residency training.
  • To assess LLM performance across clinical and didactic dimensions, including text- and image-based responses.

Main Methods:

  • 27 radiology questions across 9 subspecialties were answered by both LLMs.
  • ChatGPT-o1 also responded to 6 image-based questions.
  • 7 radiology residents rated responses on factual accuracy, clinical practicality, and didactic value using a 5-point Likert scale.

Main Results:

  • DeepSeek-R1 significantly outperformed ChatGPT-o1 across all rating dimensions (4.51 vs 3.73, P<.001).
  • ChatGPT-o1's image-based responses were rated significantly lower than text-based responses (P=.007), especially in factual accuracy (P<.001).
  • Junior residents rated ChatGPT-o1 higher overall than senior residents (P=.02).

Conclusions:

  • DeepSeek-R1 and ChatGPT-o1 show potential for radiology education, with DeepSeek-R1 demonstrating superior performance.
  • Open-source models like DeepSeek-R1 are valuable for educational use in radiology.
  • Further research is needed to explore LLM integration into radiology training and their real-world impact.