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

330
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...
330
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

230
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...
230
Imaging Studies for Cardiovascular System V: CT01:28

Imaging Studies for Cardiovascular System V: CT

57
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
57

You might also read

Related Articles

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

Sort by
Same author

Olive Leaf Extract Suppresses Sebogenesis and Inflammation via AKT/ERK and SREBP-1/PPAR-γ Signaling in Human Sebocytes.

Current issues in molecular biology·2026
Same author

Corrigendum to "Heavy metal-induced proteomic profiles associated with disease risk in environmentally vulnerable populations" [J Hazard Mater 511 (2026) 142267].

Journal of hazardous materials·2026
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

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

European radiology·2026
Same author

Heavy metal-induced proteomic profiles associated with disease risk in environmentally vulnerable populations.

Journal of hazardous materials·2026
Same author

Heterogeneous Kidney Patterns in Diabetic Patients Following SGLT2 Inhibitor Use.

Journal of Korean medical science·2026

Related Experiment Video

Updated: Aug 12, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

CheSS: Chest X-Ray Pre-trained Model via Self-supervised Contrastive Learning.

Kyungjin Cho1,2, Ki Duk Kim2, Yujin Nam1,2

  • 1Department of Biomedical Engineering, Asan Medical Center, College of Medicine, Asan Medical Institute of Convergence Science and Technology, University of Ulsan, Seoul, Republic of Korea.

Journal of Digital Imaging
|January 26, 2023
PubMed
Summary

A new self-supervised learning model, CheSS, trained on millions of chest X-rays, significantly improves performance on various medical imaging tasks. This publicly available model addresses data limitations and biases in deep learning for chest radiography analysis.

Keywords:
Bone suppressionChest X-rayClassificationContrastive learningPretrained weightSelf-supervised learning

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

169
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

Related Experiment Videos

Last Updated: Aug 12, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

169
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

Area of Science:

  • Medical Imaging
  • Deep Learning
  • Computer Vision

Background:

  • Deep learning model training on medical images requires extensive manual labeling, which is costly and time-consuming.
  • Medical image datasets, labels, and models often lack public accessibility and suffer from biases and imbalances.

Purpose of the Study:

  • To propose a publicly accessible, pre-trained deep learning model for chest radiographs (CXRs) using self-supervised contrastive learning.
  • To evaluate the transferability and effectiveness of the proposed model (CheSS) across diverse downstream tasks.

Main Methods:

  • Developed CheSS (chest X-ray pre-trained model via self-supervised contrastive learning) using a 4.8-million CXR dataset.
  • Employed self-supervised learning with a contrastive learning approach for model pre-training.
  • Validated CheSS on classification tasks (internal dataset, CheXpert), bone suppression, and nodule generation.

Main Results:

  • Achieved a 28.5% accuracy increase in 6-class disease classification compared to a model trained from scratch.
  • Improved mean ROC AUC by 1.3% on the full CheXpert dataset and 11.4% using only 1% of data.
  • Enhanced bone suppression (PSNR: 34.99 to 37.77, SSIM: 0.976 to 0.977) and nodule generation (FID: 24.06 to 17.07).

Conclusions:

  • The CheSS model demonstrates significant transferability and effectiveness across multiple medical imaging tasks.
  • CheSS weights offer a valuable resource to mitigate challenges of data imbalance, shortage, and inaccessibility in medical imaging research.
  • The pre-trained CheSS model is publicly available to facilitate further research and development in AI for chest radiography.