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

You might also read

Related Articles

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

Sort by
Same author

Soil nutrition and foliar intervention in <i>Brassica napus</i> (L.) to impair biological fitness of green peach aphid (<i>Myzus persicae</i> Sulzer).

Frontiers in insect science·2026
Same author

Lynch syndrome caused by a pathogenic SINE-VNTR-Alu (SVA) insertion in MSH2 gene identified by long-read DNA sequencing.

Familial cancer·2026
Same author

Nanoparticle-modified fishpond sediments improve metal immobilization, redox homeostasis, and stress tolerance in <i>Spinacia oleracea</i> under multi-metal exposure.

Frontiers in plant science·2026
Same author

Retraction Note: Analyzing fibrous tissue pattern in fibrous dysplasia bone images using deep R-CNN networks for segmentation.

Soft computing·2026
Same author

Enhancing aqueous solubility prediction with residual gated graph convolutions and sequential modeling.

Computational biology and chemistry·2026
Same author

Tuning the electronic and photovoltaic properties of naphthalene diamine through molecular engineering with efficient acceptors: a quantum chemical study.

Scientific reports·2026

Related Experiment Video

Updated: May 24, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

Conv-MTD: A CNN Based Multi-Label Medical Tubes Detection and Classification Model to Facilitate Resource-Constrained

Moneeb Abbas, Wen-Chung Kuo, Khalid Mahmood

    IEEE Journal of Biomedical and Health Informatics
    |March 4, 2025
    PubMed
    Summary

    This study introduces Conv-MTD, a deep learning model for detecting medical tube placement in chest X-rays. It accurately identifies normal, abnormal, and borderline placements, improving patient safety.

    More Related Videos

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.3K
    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    460

    Related Experiment Videos

    Last Updated: May 24, 2025

    Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
    08:20

    Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

    Published on: October 27, 2023

    1.3K
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.3K
    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    460

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Deep Learning

    Background:

    • Medical tube malposition is a critical issue in critically ill patients, leading to significant morbidity and mortality.
    • Current verification methods (capnography, pH testing, auscultation, CXR) are manual and can be subjective.
    • Accurate medical tube placement is essential for patient care, nutrition, and treatment delivery.

    Purpose of the Study:

    • To develop and evaluate Conv-MTD, a deep learning model for automated medical tube detection (MTD) in chest X-ray (CXR) images.
    • To assist radiologists in precisely identifying and categorizing medical tube placements as normal, abnormal, or borderline.
    • To enable real-time, low-cost, and automated assessments on resource-constrained devices.

    Main Methods:

    • Proposed Conv-MTD model utilizing the EfficientNet-B7 architecture.
    • Incorporated auxiliary heads in intermediate layers to address vanishing gradient issues.
    • Optimized the model using post-training 16-bit floating-point (FP16) quantization for reduced memory and latency.

    Main Results:

    • Achieved high performance with an average area under the receiver-operator curve (AUC-ROC) of 0.95.
    • Demonstrated effective detection and categorization of medical tube placements.
    • Quantization reduced memory consumption and inference latency, suitable for resource-constrained environments.

    Conclusions:

    • Conv-MTD offers a robust and accurate solution for automated medical tube detection in CXR images.
    • The model has the potential for deployment on point-of-care devices, enhancing healthcare accessibility.
    • This AI-driven approach can significantly improve the safety and efficiency of medical procedures involving tube placement.