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: May 2, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

335

Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

Adhish Prasoon1, Kersten Petersen1, Christian Igel1

  • 1Department of Computer Science, University of Copenhagen, Denmark.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 1, 2014
PubMed
Summary
This summary is machine-generated.

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

Independent prognostic value of peak width of skeletonized mean diffusivity on clinical progression in Alzheimer's disease.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026
Same author

A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning.

Scientific data·2026
Same author

High-resolution automated mapping of potential Aedes larval container habitats using drone imagery and supervised machine learning in Dar es Salaam, Tanzania.

PLoS neglected tropical diseases·2026
Same author

Improving metagenome binning by integrating intrinsic features and taxonomy.

Nature biotechnology·2026
Same author

Biomechanical index for predicting the risk of acute coronary syndrome.

Frontiers in cardiovascular medicine·2026
Same author

Cross-disorder comparison of brain structures among 4836 individuals with mental disorders and controls utilizing danish population-based clinical MRI scans.

Molecular psychiatry·2026

This study introduces a novel deep learning system using three 2D convolutional neural networks (CNNs) for medical image segmentation. The proposed method outperforms existing techniques in segmenting tibial cartilage in knee MRI scans.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Medical image segmentation is crucial for anatomical structure identification.
  • Deep learning, particularly convolutional neural networks (CNNs), excels at hierarchical image representation and classification.
  • Traditional voxel/pixel classification methods are common but can be improved.

Purpose of the Study:

  • To develop and evaluate a novel deep learning system for voxel classification in medical image segmentation.
  • To improve the accuracy of segmenting anatomical structures, specifically tibial cartilage in knee MRI scans.
  • To demonstrate the efficacy of a 2D CNN-based approach over existing 3D multi-scale methods.

Main Methods:

  • Integration of three 2D convolutional neural networks (CNNs), each associated with a specific plane (xy, yz, zx) of the 3D image.

More Related Videos

A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
09:21

A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

Published on: April 17, 2026

31

Related Experiment Videos

Last Updated: May 2, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

335
A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
09:21

A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

Published on: April 17, 2026

31
  • Application of the proposed system to the segmentation of tibial cartilage in low-field knee Magnetic Resonance Imaging (MRI) scans.
  • Testing the method on a dataset of 114 unseen MRI scans.

    • Main Results:

    • The proposed system, utilizing only 2D features at a single scale, achieved superior performance compared to a state-of-the-art method employing 3D multi-scale features.
    • The deep learning architecture autonomously learned relevant features directly from the images, leading to improved segmentation accuracy.
    • The method demonstrated robust performance on unseen data, validating its generalizability.

    Conclusions:

    • A novel deep learning approach integrating three 2D CNNs offers a more effective solution for medical image segmentation than traditional 3D multi-scale methods.
    • Autonomous feature learning by deep learning architectures is a key advantage for complex segmentation tasks.
    • This system shows significant potential for accurate and efficient segmentation of tibial cartilage in knee MRI analysis.