Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 21, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized ¹²⁹Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Graph guided multiscale cross attention for multilabel chest X ray classification.

Guokun Shi¹, Zijian Wang², Yucheng Shi¹

¹School of Medicine and Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, P.R. China.

Scientific Reports

|May 19, 2026

Summary

This summary is machine-generated.

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

Functional connectivity changes in patients with absence epilepsy studied using resting-state functional MRI.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2012

Same author

Quantitative analysis of mitral valve morphology in mitral valve prolapse with real-time 3-dimensional echocardiography: importance of annular saddle shape in the pathogenesis of mitral regurgitation.

Circulation·2012

Same author

Interval cancers in nasopharyngeal carcinoma screening: comparing two screening intervals after a negative initial screening result.

Journal of medical screening·2012

Same author

Two Epstein-Barr virus-related serologic antibody tests in nasopharyngeal carcinoma screening: results from the initial phase of a cluster randomized controlled trial in Southern China.

American journal of epidemiology·2012

Same author

MALT1 small molecule inhibitors specifically suppress ABC-DLBCL in vitro and in vivo.

Cancer cell·2012

Same author

Extraction and characterization of extracellular polymeric substances in biofilm and sludge via completely autotrophic nitrogen removal over nitrite system.

Applied biochemistry and biotechnology·2012

This study introduces a novel visual-semantic framework for multi-label chest X-ray classification. The approach effectively fuses diverse visual data and uses graph-guided reasoning to improve diagnostic accuracy for thoracic abnormalities.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Multi-label classification of chest X-rays (CXRs) is complex due to variations in abnormality scale, visual prominence, and distribution.
Disease labels in CXRs often have clinically significant interdependencies that are difficult to model.

Purpose of the Study:

To develop an advanced visual-semantic framework for image-level multi-label CXR classification.
To integrate heterogeneous visual representations and employ graph-guided label reasoning for enhanced diagnostic performance.

Main Methods:

A visual encoder combining Vision Transformer (ViT) and DenseNet-121 branches was utilized.
A multi-scale bidirectional dual cross-attention fusion (DCAF) module integrated these visual representations.

More Related Videos

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Published on: September 22, 2023

Related Experiment Videos

Last Updated: May 21, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized ¹²⁹Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Published on: September 22, 2023

A graph convolutional network (GCN) approach modeled label dependencies using co-occurrence statistics and GloVe embeddings.

Main Results:

The framework achieved a Mean AUC of 0.849 on the ChestX-ray14 dataset and 0.815 on the CheXpert dataset.
Qualitative Grad-CAM visualizations indicated that the model's activations aligned with visually suspicious regions.

Conclusions:

The proposed method demonstrates the benefits of cross-representation visual fusion for CXR analysis.
Graph-guided label-query decoding significantly improves multi-label classification accuracy in chest radiography.