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

Related Concept Videos

Chest Physiotherapy

Chest Physiotherapy

Chest Physiotherapy (CPT) is a therapeutic technique used in respiratory care to improve ventilation, clear bronchial secretions, and enhance the efficiency of respiratory muscles. This therapy includes three primary procedures: postural drainage, percussion, and vibration. It can be performed on spontaneously breathing patients and those who are intubated and mechanically ventilated.
Purpose
CPT is primarily used for patients with excessive bronchial secretions who have difficulty clearing...

You might also read

Related Articles

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

Sort by

Same author

A dynamic machine learning model for predicting organ transplant success to optimize donor organ utilization and reduce costs.

Clinical transplantation and research·2026

Same author

Female reproductive toxicity induced by nitrate in drinking water and the comparative ameliorative effects of ascorbic acid, curcumin and their combination.

Journal of environmental science and health. Part. B, Pesticides, food contaminants, and agricultural wastes·2026

Same author

Acute appendicitis complicated by portomesenteric venous thrombosis: A diagnostic and therapeutic challenge - A case report.

Journal of family medicine and primary care·2026

Same author

Bis-thiosemicarbazone functions as a selective chemosensor with the lowest LOD for Hg ions in water-rich medium: implications for on-site detection and logic gate experiments.

RSC advances·2026

Same author

Cytokine Gene Polymorphisms in Primary Glaucoma: Insights into Inflammatory Pathways and Future Directions.

Molecular neurobiology·2026

Same author

The Readability of Patient-Reported Measures in Early Psychosis.

Schizophrenia bulletin·2026

Search research articles

Related Experiment Video

Updated: Aug 22, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

CheXPrune: sparse chest X-ray report generation model using multi-attention and one-shot global pruning.

Navdeep Kaur^1,2, Ajay Mittal¹

¹UIET, Panjab University, Sector 25, Chandigarh, 160025 India.

Journal of Ambient Intelligence and Humanized Computing

|November 7, 2022

Summary

CheXPrune significantly reduces the size of deep neural networks for automatic radiological report generation (ARRG) by 70% through multi-attention based pruning. This sparse model maintains accuracy, improving clinical workflow efficiency.

Keywords:

Chest radiographs Deep-learning Multi-attention Pruning Radiological report generation Radiological reports Sparse DNN Textual description

More Related Videos

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

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Aug 22, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Area of Science:

Artificial Intelligence
Medical Imaging Analysis
Natural Language Processing

Background:

Automatic Radiological Report Generation (ARRG) aids clinical workflow but faces challenges due to large deep neural network (DNN) sizes.
Existing DNNs show promise in ARRG but are difficult to deploy because of their complexity.
Pruning methods are explored to reduce DNN size and complexity for practical ARRG applications.

Purpose of the Study:

To introduce CheXPrune, a novel multi-attention based sparse method for ARRG.
To significantly compress DNNs used in ARRG without compromising performance.
To enhance the deployability of ARRG systems in clinical settings.

Main Methods:

Developed an encoder-decoder architecture with visual and semantic attention mechanisms.
Implemented a one-shot weight pruning strategy during training, achieving 70% sparsity.
Evaluated the sparse model's performance on the OpenI dataset using standard metrics.

Main Results:

CheXPrune achieved a 3.33x compression rate through 70% model pruning.
The sparse model demonstrated comparable accuracy to its dense counterpart.
Empirical results confirmed the effectiveness of the proposed pruning method.

Conclusions:

CheXPrune offers an effective solution for creating smaller, deployable ARRG models.
The multi-attention sparse approach successfully reduces model size while preserving accuracy.
This method has the potential to accelerate the integration of ARRG into clinical workflows.