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 Experiment Videos

LXNet: A lightweight CNN for lung disease classification from Chest X-ray with XAI-based interpretability.

Juiria Humayan1, Md Najmus Sakib Nahid1, Amir Sohel1

  • 1Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.

Plos One
|June 17, 2026
PubMed
Summary

Related Concept Videos

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

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

Imaging Studies for Cardiovascular System III: X-Ray

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...

You might also read

Related Articles

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

Sort by
Same author

Enhancing security in financial transactions: a novel blockchain-based federated learning framework for detecting counterfeit data in fintech.

PeerJ. Computer science·2024
Same author

Mechanistic Insights into the Stabilization of In Situ Formed γ-NiOOH Species on Ni<sub>60</sub>Nb<sub>40</sub> Nanoglass for Effective Urea Electro-Oxidation.

Small (Weinheim an der Bergstrasse, Germany)·2024
Same author

Intelligent Framework for Early Detection of Severe Pediatric Diseases from Mild Symptoms.

Diagnostics (Basel, Switzerland)·2023
Same author

Region of interest (ROI) selection using vision transformer for automatic analysis using whole slide images.

Scientific reports·2023
Same author

Early Detection and Diagnosis of Chronic Kidney Disease Based on Selected Predominant Features.

Journal of healthcare engineering·2023
Same author

The Perception of Health Professionals in Bangladesh toward the Digitalization of the Health Sector.

International journal of environmental research and public health·2022
This summary is machine-generated.

A new lightweight Artificial Intelligence (AI) model, LXNet, accurately diagnoses nine lung diseases from Chest X-Rays (CXR). This explainable Convolutional Neural Network (CNN) offers a computationally efficient solution for global health challenges.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Science

Background:

  • Lung disease diagnosis from Chest X-rays (CXR) is crucial globally, especially in resource-limited areas.
  • Existing Artificial Intelligence (AI) models for CXR analysis are often computationally intensive and lack interpretability, hindering clinical adoption.
  • There is a need for efficient and explainable AI solutions for multiclass lung disease classification.

Purpose of the Study:

  • To develop and evaluate LXNet, a lightweight and explainable Convolutional Neural Network (CNN).
  • To achieve accurate nine-class lung disease classification using CXR.
  • To demonstrate the model's superior performance and interpretability compared to existing deep learning architectures.

Main Methods:

  • LXNet, a CNN with 0.35 million parameters and a no-pooling final block, was developed for lung disease classification.

Related Experiment Videos

  • The model was trained and evaluated on a diverse dataset of 6,743 CXR images.
  • Data augmentation techniques including adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE), grayscale normalization, and stratified class balancing were employed.
  • LXNet was benchmarked against DenseNet201, ResNet50V2, and InceptionV3 using 5-fold cross-validation.
  • Explainable AI methods (Grad-CAM, Score-CAM, LIME) were used for model interpretability.

    • Main Results:

    • LXNet achieved 96.1% accuracy in 5-fold cross-validation, outperforming baseline models (DenseNet201: 90.3%, InceptionV3: 88.9%).
    • The model demonstrated significantly lower computational cost and training time (308 seconds) compared to baselines.
    • Explainable AI techniques provided meaningful visualizations, enhancing model transparency.
    • Statistical significance was confirmed using Wilcoxon signed-rank tests (p=0.03125).

    Conclusions:

    • LXNet presents a promising, lightweight, and explainable AI solution for multiclass lung disease classification from CXRs.
    • The model's efficiency and accuracy suggest potential for improved diagnostics, particularly in resource-limited settings.
    • Further validation is required to address limited generalizability and confirm clinical applicability.