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

Assessing hip osteoarthritis severity utilizing a probabilistic neural network based classification scheme.

I Boniatis1, L Costaridou, D Cavouras

  • 1University of Patras, Faculty of Medicine, Department of Medical Physics, 26500 Patras, Greece.

Medical Engineering & Physics
|April 21, 2006
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

A Comparative Study of Unsupervised and Deep Learning Methods for Automatic Segmentation of Abdominal Aortic Aneurysm on CT Images: Preliminary Results.

Advances in experimental medicine and biology·2025
Same author

Clinical, dermoscopic and histological assessment of melanocytic lesions: a comparative study of the accuracy of the diagnostic methods.

Hippokratia·2023
Same author

A two-stage method for microcalcification cluster segmentation in mammography by deformable models.

Medical physics·2015
Same author

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer-aided diagnosis image analysis system.

Journal of microscopy·2015
Same author

Towards a solution of the wires' slippage problem of the Ilizarov external fixator.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2014
Same author

Breast cancer characterization based on image classification of tissue sections visualized under low magnification.

Computational and mathematical methods in medicine·2013

A new computer system accurately classifies hip osteoarthritis (OA) severity from X-rays using novel textural features. This technology aids in objective OA assessment and patient management.

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Biomedical Engineering

Background:

  • Osteoarthritis (OA) is a degenerative joint disease affecting hip joints.
  • Accurate grading of OA severity is crucial for effective patient management.
  • Current radiographic assessment methods can be subjective.

Purpose of the Study:

  • To develop and evaluate a computer-based classification system for characterizing hip OA severity from pelvic radiographs.
  • To discriminate between normal, mild/moderate, and severe hip OA.
  • To establish a quantitative regression model for OA severity estimation.

Main Methods:

  • Extraction of run-length, Laws', and novel textural features from digitized hip joint spaces (HJSs) in pelvic radiographs.

Related Experiment Videos

  • Utilizing a probabilistic neural network (PNN) classifier with a hierarchical tree structure for feature set evaluation.
  • Development of a mathematical regression model based on novel textural features for quantitative OA severity prediction.

    • Main Results:

    • The novel textural features set achieved 100% classification accuracy for distinguishing normal, mild/moderate, and severe hip OA.
    • A mathematical regression model using novel textural features showed a high correlation (r=0.85, p<0.001) with measured hip joint space narrowing.
    • The proposed system demonstrated high efficacy in classifying OA severity.

    Conclusions:

    • A computer-based system using novel textural features from radiographs can accurately classify hip OA severity.
    • The developed regression model provides a reliable quantitative estimation of OA severity.
    • This automated system holds potential value for objective OA patient management and clinical decision-making.