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

X-ray Imaging01:24

X-ray Imaging

6.8K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
6.8K
Vision01:24

Vision

55.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
55.2K
Computed Tomography01:10

Computed Tomography

6.0K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.0K

You might also read

Related Articles

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

Sort by
Same author

Meaningful Thresholds for Change in Quantitative CT-Derived Fibrosis Extent in Idiopathic Pulmonary Fibrosis.

American journal of respiratory and critical care medicine·2026
Same author

Vertebral body sliding osteotomy as a less invasive alternative to 540° surgery for cervical myelopathy with rigid kyphosis.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

Susceptibility of Large Language Models to User-Driven Factors in Medical Queries.

Journal of healthcare informatics research·2026
Same author

CT quantification of interstitial lung abnormalities: a prospective comparison between supine and prone positions.

European radiology·2026
Same author

Comparison of Hook Fixation and Vertebroplasty for Prevention of Proximal Junctional Failure: A Retrospective Cohort Study.

Global spine journal·2026
Same author

InfoColon: A dataset for consecutive informative frames in Colonoscopy.

Scientific data·2026

Related Experiment Video

Updated: Sep 5, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

489

Self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation.

Sangjoon Park1, Gwanghyun Kim1, Yujin Oh1

  • 1Department of Bio and Brain Engineering, KAIST, Daejeon, Korea.

Nature Communications
|July 5, 2022
PubMed
Summary

This study introduces DISTL, a novel framework for improving deep learning models using unlabeled chest X-rays. DISTL enhances diagnostic accuracy for conditions like tuberculosis and COVID-19, even outperforming fully supervised methods.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

840

Related Experiment Videos

Last Updated: Sep 5, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

489
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

840

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Computer-aided diagnosis

Background:

  • Deep learning models require extensive annotated data for high performance in medical diagnosis.
  • Unlabeled chest X-rays, abundant in clinical settings, are often underutilized due to annotation costs, particularly in underserved regions.
  • Existing computer-aided diagnosis systems face challenges in robustness and generalizability with limited labeled data.

Purpose of the Study:

  • To develop a framework that leverages unlabeled chest X-ray data to enhance the performance of deep learning models.
  • To improve the robustness and clinical applicability of vision transformer models in medical image analysis.
  • To address the data scarcity issue in developing diagnostic AI by utilizing self-supervision and self-training.

Main Methods:

  • A novel framework named DISTL (distillation for self-supervision and self-train learning) was developed, inspired by radiologist learning processes.
  • DISTL employs knowledge distillation to simultaneously enhance self-supervision and self-training capabilities of vision transformers.
  • The framework was validated externally across three hospitals for diagnosing tuberculosis, pneumothorax, and COVID-19.

Main Results:

  • DISTL demonstrated progressively improved diagnostic performance with increasing amounts of unlabeled data.
  • The model trained with DISTL outperformed fully supervised models trained with the same quantity of labeled data.
  • The resulting model exhibited robustness against various real-world nuisances, indicating enhanced clinical applicability.

Conclusions:

  • The DISTL framework effectively utilizes unlabeled chest X-ray data to boost the performance of deep learning diagnostic systems.
  • DISTL offers a promising solution for developing robust and accurate AI-powered diagnostic tools, especially in resource-limited settings.
  • The approach shows significant potential for improving the clinical utility of computer-aided diagnosis systems by overcoming data annotation barriers.