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: Dec 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images.

Julia M H Noothout, Bob D De Vos, Jelmer M Wolterink

    IEEE Transactions on Medical Imaging
    |August 4, 2020
    PubMed
    Summary

    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

    Aleatoric uncertainty in accelerated prostate MRI reconstruction: echo-train dropout versus Gaussian noise Monte Carlo sampling.

    Magma (New York, N.Y.)·2026
    Same author

    Graph Neural Networks Reveal Candidate Protein Biomarkers Underlying Abdominal Aortic Aneurysm Biology.

    Computational and structural biotechnology journal·2026
    Same author

    Deep Learning for Cardiac Image Analysis: Unveiling Advances in Deep Learning Architectures.

    JACC. Cardiovascular imaging·2026
    Same author

    Radiographic evaluation of the psoas and iliopsoas muscle as predictors for spinal cord ischemia after fenestrated and branched endovascular aortic repair.

    Journal of vascular surgery·2026
    Same author

    The SENSS (Stress, Exercise, Nutrition, Sleep, Self-management) study: study protocol for a randomized controlled trial to evaluate an integrated, personalized and stepped care lifestyle approach for people with Parkinson's disease.

    Frontiers in neurology·2026
    Same author

    Neural network surrogates for musculoskeletal models: An application to implant alignment in total knee arthroplasty.

    Journal of biomechanics·2026

    This study introduces a fast, accurate method for automatically finding anatomical landmarks in medical images using fully convolutional neural networks (FCNNs). The global-to-local approach achieves performance comparable to human experts across various imaging types.

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Machine Learning

    Background:

    • Accurate localization of anatomical landmarks is crucial for medical image analysis and diagnosis.
    • Manual landmark identification is time-consuming and subject to inter-observer variability.

    Purpose of the Study:

    • To develop a fast and accurate automated method for anatomical landmark localization in diverse medical images.
    • To leverage fully convolutional neural networks (FCNNs) in a global-to-local approach for improved landmark detection.

    Main Methods:

    • A global FCNN analyzes image patches for simultaneous regression (displacement vectors) and classification (landmark presence).
    • Global landmark locations are determined by weighted averaging of predicted displacement vectors.
    • Specialized FCNNs refine global locations through local sub-image analysis, combining regression and classification.

    More Related Videos

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    3.4K

    Related Experiment Videos

    Last Updated: Dec 13, 2025

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.2K
    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    3.4K

    Main Results:

    • The method was evaluated on coronary computed tomography angiography (CCTA), olfactory MRI, and cephalometric X-ray datasets.
    • Demonstrated performance comparable to a second human observer.
    • Successfully localized landmarks across different image modalities, dimensions, and anatomical regions.

    Conclusions:

    • The proposed global-to-local FCNN approach provides a robust and efficient solution for automated anatomical landmark localization.
    • The method shows versatility and accuracy across a wide range of medical imaging applications.