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

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

1.8K
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
1.8K
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

699
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
699

You might also read

Related Articles

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

Sort by
Same author

Bridging the gap from clinical to home ECG: quantifying and overcoming accuracy loss in AI-enabled single-lead ECG models.

NPJ digital medicine·2026
Same author

Deep learning analysis of 12-lead electrocardiograms for bloodstream infection prediction: a multi-center validation study.

BMC medical informatics and decision making·2026
Same author

Medical students' knowledge and attitudes towards integrative care with traditional Chinese medicine in Taiwan during the COVID-19 pandemic.

Medicine·2026
Same author

Deep Learning-Based Electrocardiogram Analysis for Pulmonary Embolism Diagnosis: A Systematic Review and Meta-Analysis.

Acta Cardiologica Sinica·2026
Same author

Measuring AI literacy in medical students: scale development and validation within a self-determination theory framework.

Medical education online·2026
Same author

Artificial Intelligence-Enabled Electrocardiography in Practice: A State-of-the-Art Review.

Korean circulation journal·2026

Related Experiment Video

Updated: May 3, 2026

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

8.6K

A Pretraining Approach for Small-sample Training Employing Radiographs (PASTER): a Multimodal Transformer Trained by

Kai-Chieh Chen1, Matthew Kuo2, Chun-Ho Lee3

  • 1Graduate Institute of Life Sciences, College of Biomedical Sciences, National Defense Medical University, Taipei, Taiwan, R.O.C.

Journal of Medical Systems
|September 29, 2025
PubMed
Summary
This summary is machine-generated.

This study shows a new AI model can interpret chest X-rays effectively with limited data. The multimodal Transformer model achieves high accuracy, reducing the need for large, expert-annotated datasets in medical imaging.

Keywords:
Chest radiographDeep learningFew-shot predictionFoundation modelMultimodal learningSmall sample trainingTransformer

Related Experiment Videos

Last Updated: May 3, 2026

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

8.6K

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Radiology

Background:

  • Deep convolutional neural networks (DCNNs) require large annotated datasets for chest X-ray (CXR) interpretation.
  • Clinical data collection is challenging due to limited resources, privacy, and patient variability.

Purpose of the Study:

  • To evaluate a multimodal Transformer pretrained on free-text reports and CXRs for limited-data settings.
  • To assess the model's effectiveness in reducing sample size requirements for AI advancements in CXR interpretation.

Main Methods:

  • Applied a multimodal Transformer pretrained on over 1 million CXRs and associated radiologist reports.
  • Evaluated a linear model trained on embeddings from the pretrained model.
  • Tested the approach on subsets with structured echocardiographic reports and external validation sets (CheXpert, ChestX-ray14).

Main Results:

  • The linear model achieved AUCs of 0.907 (internal) and 0.903 (external) using limited data (128 cases, 384 controls).
  • Performance was comparable to DenseNet trained on the entire dataset (AUCs 0.908 and 0.903).
  • Demonstrated excellent small sample learning capabilities on external validation sets.

Conclusions:

  • The multimodal Transformer model effectively interprets CXRs in limited-data scenarios.
  • This approach significantly reduces the sample size needed for developing AI in CXR interpretation.
  • The model shows promise for broader applications in medical imaging analysis with limited annotated data.