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 Video

Updated: Mar 5, 2026

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

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

Published on: October 13, 2023

2.2K

Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification.

Qiangchang Wang, Yuanjie Zheng, Gongping Yang

    IEEE Journal of Biomedical and Health Informatics
    |March 24, 2017
    PubMed
    Summary

    A novel multiscale rotation-invariant convolutional neural network (MRCNN) effectively classifies lung tissue on CT scans. This method addresses data imbalance and outperforms existing techniques for interstitial lung disease analysis.

    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

    Oxygen Dynamics in the Rhizosphere of <i>Vallisneria spiralis</i> Characterized by a Fluorescent Planar Optode.

    Plants (Basel, Switzerland)·2026
    Same author

    Diazepam combined with aripiprazole in the treatment of a catatonic stupor patient with venous thrombosis: a case report.

    Frontiers in psychiatry·2026
    Same author

    Antidepressants for Child and Adolescent Depression: Evidence, Controversies, and Clinical Implications.

    Current neuropharmacology·2026
    Same author

    Systematic Review and Meta-Analysis of Mood Stabilizers in the Treatment of Adolescent Patients With Nonsuicidal Self-Injury in China.

    The Journal of clinical psychiatry·2026
    Same author

    Improved method for optical coherence tomography angiography: from reconstruction to clinical indicator quantification.

    Journal of biomedical optics·2026
    Same author

    WRCANet: wavelet residual cross-attention network for meibomian gland segmentation.

    Biomedical optics express·2026

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Artificial Intelligence

    Background:

    • Accurate classification of lung tissue types on high-resolution computed tomography (CT) is crucial for diagnosing interstitial lung diseases.
    • Existing methods often struggle with variations in image scale and rotation, and suffer from imbalanced datasets.
    • Developing robust models that are invariant to scale and rotation and handle data imbalance is a significant challenge.

    Purpose of the Study:

    • To propose a new multiscale rotation-invariant convolutional neural network (MRCNN) for classifying lung tissue types.
    • To enhance image analysis by incorporating Gabor-local binary patterns for scale and rotation invariance.
    • To address the challenge of imbalanced sample sizes across different lung tissue classes.

    Main Methods:

    Related Experiment Videos

    Last Updated: Mar 5, 2026

    Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
    07:53

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

    Published on: October 13, 2023

    2.2K
    • Development of a multiscale rotation-invariant convolutional neural network (MRCNN).
    • Integration of Gabor-local binary patterns to achieve invariance to image scales and rotations.
    • Implementation of a novel approach to manage imbalanced datasets by adjusting overlapping patch sizes.

    Main Results:

    • The proposed MRCNN model demonstrated superior performance in classifying lung tissue types.
    • The Gabor-local binary pattern effectively provided scale and rotation invariance.
    • The method for handling imbalanced data proved successful in improving classification accuracy.
    • Experimental results on a public interstitial lung disease database confirmed the model's effectiveness.

    Conclusions:

    • The multiscale rotation-invariant convolutional neural network (MRCNN) offers a powerful and robust solution for lung tissue classification on CT scans.
    • The MRCNN model, incorporating Gabor-local binary patterns and a strategy for data imbalance, achieves state-of-the-art performance.
    • This approach holds significant promise for improving the diagnosis and analysis of interstitial lung diseases.