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

4.2K
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...
4.2K
Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

93
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
93
Imaging Studies II: Positron Emission Tomography and Scintigraphy01:25

Imaging Studies II: Positron Emission Tomography and Scintigraphy

122
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
122

You might also read

Related Articles

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

Sort by
Same author

Increased expression of autophagy-related proteins in keratocystic odontogenic tumours: its possible association with growth potential.

The British journal of oral & maxillofacial surgery·2014
Same author

The sabotage of the bacterial transcription machinery by a small bacteriophage protein.

Bacteriophage·2014
Same author

In vivo and in vitro evidence of the sex-dependent pharmacokinetics and disposition of G004, a potential hypoglycemic agent, in rats.

European journal of drug metabolism and pharmacokinetics·2014
Same author

Inositol pyrophosphates mediate the effects of aging on bone marrow mesenchymal stem cells by inhibiting Akt signaling.

Stem cell research & therapy·2014
Same author

Sequential release of autophagy inhibitor and chemotherapeutic drug with polymeric delivery system for oral squamous cell carcinoma therapy.

Molecular pharmaceutics·2014
Same author

Proteomic analysis of differentially expressed skin proteins in iRhom2(Uncv) mice.

BMB reports·2014

Related Experiment Video

Updated: Jul 6, 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

8.3K

Zero-shot information extraction from radiological reports using ChatGPT.

Danqing Hu1, Bing Liu2, Xiaofeng Zhu1

  • 1Zhejiang Lab, Hangzhou, 311121, Zhejiang, China.

International Journal of Medical Informatics
|December 29, 2023
PubMed
Summary
This summary is machine-generated.

Large language models like ChatGPT can extract information from radiological reports without prior training. Incorporating medical knowledge into prompts improves some extraction tasks but may hinder others.

Keywords:
Information extractionLarge language modelLung cancerQuestion answeringRadiological report

More Related Videos

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

588
Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera
06:28

Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera

Published on: January 30, 2020

12.6K

Related Experiment Videos

Last Updated: Jul 6, 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

8.3K
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

588
Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera
06:28

Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera

Published on: January 30, 2020

12.6K

Area of Science:

  • Natural Language Processing
  • Artificial Intelligence in Medicine
  • Radiology Informatics

Background:

  • Electronic health records contain vast amounts of unstructured text data.
  • Information extraction from clinical text is crucial for structured data generation.
  • Annotated data for traditional information extraction methods presents a significant bottleneck.

Purpose of the Study:

  • To evaluate ChatGPT's zero-shot information extraction capabilities from radiological reports.
  • To assess the impact of incorporating prior medical knowledge into prompts for enhanced accuracy.
  • To analyze the consistency of information extraction results.

Main Methods:

  • Designing prompt templates for extracting specific information from CT reports.
  • Utilizing ChatGPT to process CT reports based on designed prompts.
  • Developing a post-processing module for structured data output.
  • Integrating prior medical knowledge into prompt templates to mitigate errors.

Main Results:

  • ChatGPT demonstrated competitive performance in extracting tumor location and dimensions from CT reports.
  • Adding medical knowledge to prompts significantly improved extraction of tumor spiculations and lobulations.
  • Performance gains were not observed for tumor density or lymph node status extraction with added medical knowledge.

Conclusions:

  • ChatGPT shows promise for zero-shot information extraction in radiological reporting.
  • Prior medical knowledge integration can enhance specific extraction tasks but may negatively impact others.
  • Further research is needed to optimize prompt engineering for complex clinical data extraction.