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 Experiment Video

Updated: Jul 4, 2026

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Radiologist-Large Language Model Collaboration in Dermatologic Ultrasound Reporting: Evaluating the Clinical Utility

İstem Şanal Çamur1, Eren Çamur2

  • 1Department of Dermatology, Ankara Bilkent City Hospital, Ankara, Türkiye.

Studies in Health Technology and Informatics
|July 3, 2026
PubMed
Summary

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

A Comparative Study: Can Large Language Models be a Supportive Tool in the Diagnosis and Treatment of Scabies?

Indian journal of dermatology·2026
Same author

Quantitative Assessment of Liver Function Using the Liver Enhancement Ratio on Gadoxetic Acid-Enhanced Magnetic Resonance Imaging in Chronic Liver Disease.

The Turkish journal of gastroenterology : the official journal of Turkish Society of Gastroenterology·2026
Same author

Evaluating Reasoning Effect for LLMs: Prompt Sensitivity and Text-Image Based Performance in Musculoskeletal Radiology.

Studies in health technology and informatics·2026
Same author

Elastography-Based Modeling of Breast Non-Mass Lesions: Comparative Diagnostic Performance of Qualitative and Quantitative Metrics.

Ultrasound quarterly·2026
Same author

Bridging dermatology and imaging: Interpreting nail ultrasound in pediatric psoriasis.

Clinical imaging·2026
Same author

Reply: Evaluating the reference accuracy of large language models in radiology: a comparative study across subspecialties.

Diagnostic and interventional radiology (Ankara, Turkey)·2026

Large language models (LLMs) show potential in medical imaging. Combining LLM insights with radiologist reports significantly improved diagnostic accuracy and recommendations in dermatologic ultrasound.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Dermatology

Background:

  • Large language models (LLMs) are being explored for medical image interpretation, but their independent reliability is unproven.
  • Dermatologic ultrasound is a key imaging modality in dermatology, requiring accurate interpretation for diagnosis and management.

Purpose of the Study:

  • To evaluate the clinical utility of radiology reports generated by a large language model (LLM) under different reporting conditions.
  • To compare the diagnostic accuracy, recommendation appropriateness, and readability of LLM-generated reports against radiologist reports in dermatologic ultrasound.

Main Methods:

  • Analysis of 202 dermatologic ultrasound images from a public dataset.
  • Generation of radiology reports under three conditions: radiologist-only, LLM-only (image-based), and combined LLM-radiologist report.
Keywords:
Large language modelsdermatologic ultrasoundhealth informaticsreporting

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Related Experiment Videos

Last Updated: Jul 4, 2026

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

  • Evaluation of reports for diagnostic accuracy, next-step recommendation accuracy, and readability.

    • Main Results:

    • Diagnostic accuracy was highest in the combined LLM-radiologist report condition (83.2%), significantly outperforming radiologist-only (55.4%) and LLM-only (26.2%) reports (p<0.001).
    • Next-step recommendation accuracy followed a similar trend, with the combined condition (77.7%) superior to radiologist-only (38.6%) and LLM-only (59.9%) reports (p<0.001).
    • Report readability was also highest when LLM outputs were integrated with radiologist reports.

    Conclusions:

    • Integrating large language models with radiologist reports enhances diagnostic accuracy and clinical decision support in dermatologic ultrasound.
    • LLMs hold promise for augmenting, rather than replacing, the role of radiologists in medical imaging interpretation.
    • Combined LLM-radiologist reporting shows potential to improve clinical communication and patient care pathways.