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: Jun 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

517

VOLUMETRIC LANDMARK DETECTION WITH A MULTI-SCALE SHIFT EQUIVARIANT NEURAL NETWORK.

Tianyu Ma1, Ajay Gupta2, Mert R Sabuncu1,2

  • 1School of Electrical and Computer Engineering; and Meinig School of Biomedical Engineering, Cornell University.

Proceedings. IEEE International Symposium on Biomedical Imaging
|June 25, 2024
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

<i>In Situ</i> Study of Structure Formation under Stress in Stretchable Conducting Nanocomposites.

The journal of physical chemistry letters·2023
Same author

SARS-CoV-2 vaccination induced cerebral venous sinus thrombosis: Do megakaryocytes, platelets and lipid mediators make up the orchestra?

Free neuropathology·2023
Same author

The Role of Montelukast Sodium in Children with Adenoid Hypertrophy - A Comparative Study.

Indian journal of otolaryngology and head and neck surgery : official publication of the Association of Otolaryngologists of India·2023
Same author

AIE-active cyclometalated iridium(III) complexes for the detection of lipopolysaccharides and wash-free imaging of bacteria.

Dalton transactions (Cambridge, England : 2003)·2023
Same author

Comparison of Radiological and Clinical Outcomes between Expandable and Non-expandable Cages Following Cervical Corpectomy: A Systematic Review and Meta-analysis.

Asian spine journal·2023
Same author

Optic Nerve Diameter on Non-Contrast Computed Tomography and Intracranial Hypertension in Patients With Acute Brain Injury: A Validation Study.

Journal of neurotrauma·2023

We developed a memory-efficient deep learning method for fast 3D landmark detection in medical images. This approach improves accuracy for anatomical landmark detection, like carotid artery bifurcations in CT scans.

Area of Science:

  • Medical imaging
  • Computer vision
  • Deep learning

Background:

  • Deep neural networks excel in computer vision tasks, including landmark detection.
  • Accurate anatomical landmark detection in volumetric medical images (e.g., CT scans) is challenging due to GPU memory limitations that restrict neural network capacity and output precision.

Purpose of the Study:

  • To propose a novel multi-scale, end-to-end deep learning method for fast and memory-efficient landmark detection in 3D images.
  • To enhance the robustness and uncertainty quantification of the landmark detection model.

Main Methods:

  • A multi-scale architecture using shift-equivariant network blocks for landmark detection at different spatial scales.
  • Coarse-to-fine scale connections with differentiable resampling layers for end-to-end training.
Keywords:
3D landmark detectionConvolutional Neural Networks

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K
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

2.7K

Related Experiment Videos

Last Updated: Jun 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

517
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K
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

2.7K
  • A noise injection strategy to improve model robustness and enable uncertainty quantification.

    • Main Results:

    • The method achieves fast and memory-efficient landmark detection in 3D images.
    • Evaluated on 263 CT volumes for carotid artery bifurcation detection, the method surpassed state-of-the-art accuracy.
    • Achieved a mean Euclidean distance error of 2.81mm for carotid artery bifurcation detection.

    Conclusions:

    • The proposed multi-scale, end-to-end deep learning approach offers an effective solution for memory-constrained 3D anatomical landmark detection.
    • The method demonstrates superior accuracy and robustness, paving the way for improved analysis of medical imaging data.