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 Videos

Three-dimensional classification of spinal deformities using fuzzy clustering.

Luc Duong1, Farida Cheriet, Hubert Labelle

  • 1Research Center, Sainte-Justine Hospital, Montreal, Quebec, Canada.

Spine
|April 20, 2006
PubMed
Summary

Fuzzy clustering automatically classifies adolescent idiopathic scoliosis (AIS) 3D spine models into clinically relevant patterns. This unsupervised learning approach enables a new, reliable 3D classification system for AIS.

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

Retinal lesion annotation on fundus imaging: an interobserver variability study.

Scientific reports·2026
Same author

Automatic dental crown generation with spatial constraint modeling.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Predicting facial deformation during respiratory mask fitting with semi-supervised graph neural networks.

Medical engineering & physics·2026
Same author

DTG: Dual transformers-based generative adversarial networks for retinal 2D/3D OCT image classification.

Medical image analysis·2026
Same author

Canadian Spine Society: 25th Annual Scientific Conference, February 25 to 28, 2025, Fairmont Le Manoir Richelieu, La Malbaie, Charlevoix, Que., Canada.

Canadian journal of surgery. Journal canadien de chirurgie·2025
Same author

Automatic Segmentation of the Left Ventricle Through the Cardiac Cycle in Pediatric Echocardiography Videos Using SegFormer Architecture.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Area of Science:

  • Orthopedics and Biomechanics
  • Medical Imaging and Informatics
  • Machine Learning in Healthcare

Background:

  • Current adolescent idiopathic scoliosis (AIS) classification relies on subjective 2D measurements with low reliability.
  • A robust, objective 3D classification system for AIS is needed to guide surgical treatment.
  • Existing classification systems for AIS lack interobserver and intraobserver reliability.

Purpose of the Study:

  • To evaluate fuzzy clustering for automatic detection of 3D curve patterns in AIS.
  • To determine the clinical relevance of automatically identified 3D spinal deformity patterns.
  • To explore the potential for a novel 3D classification system for AIS.

Main Methods:

  • A prospective study analyzed 409 three-dimensional (3D) reconstructions of adolescent idiopathic scoliosis (AIS) spines.

Related Experiment Videos

  • Unsupervised learning, specifically fuzzy k-means clustering, was applied to the 3D spine models.
  • Clinical parameters were used to analyze data distribution and identify similar curve patterns.

    • Main Results:

    • The fuzzy clustering algorithm successfully segmented the AIS spine models into five distinct 3D curve patterns.
    • These identified patterns showed similarity to established classifications like Lenke and King.
    • A 12-class system further enabled the identification of subpatterns with significant 3D components.

    Conclusions:

    • Automatic, clinically relevant 3D classification of AIS is achievable using unsupervised learning algorithms.
    • This method offers a more objective and reliable approach to AIS classification.
    • The developed approach can form the basis for a new 3D classification system for AIS, defined by expert surgeons.