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 15, 2026

Development and Evaluation of a Rat Model of Full-Thickness Cartilage Defects
04:34

Development and Evaluation of a Rat Model of Full-Thickness Cartilage Defects

Published on: May 19, 2023

Pattern-recognition system, designed on GPU, for discriminating between injured normal and pathological knee

Spiros Kostopoulos1, Konstantinos Sidiropoulos, Dimitris Glotsos

  • 1Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos, Egaleo, 12210 Athens, Greece.

Magnetic Resonance Imaging
|January 22, 2013
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

Multiligament-injured knee: what the general orthopedic surgeon should know.

EFORT open reviews·2026
Same author

Effects of a Greek Yoghurt-based Complex on the Human Facial Skin Microbiome.

In vivo (Athens, Greece)·2026
Same author

Treatment of infected proximal tibial metaphyseal nonunions using the Ilizarov method: A prospective clinical study.

Injury·2026
Same author

Functional Outcomes and Recurrence After Arthroscopy-Based Treatment of Pigmented Villonodular Synovitis of the Knee: A 20-Year Single-Center Series.

Cancers·2026
Same author

Hippocampal volume from T1 MRI as an atrophy biomarker: automated calculation and Scheltens' scale correlation.

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

Clinical Outcomes of Arthroscopic Bankart Repair With Remplissage Versus Bankart Repair With Remplissage and Arthroscopic Subscapularis Augmentation in Recurrent Anterior Shoulder Instability.

Orthopaedic journal of sports medicine·2026

A new pattern-recognition (PR) system accurately distinguishes normal from pathological knee cartilage using MRI data. This AI tool, optimized on a GPU, offers rapid and reliable diagnostic support for clinicians.

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Biomedical engineering

Background:

  • Knee articular cartilage assessment is crucial for diagnosing joint pathologies.
  • Distinguishing between normal and pathological cartilage using medical imaging presents challenges.
  • Current diagnostic methods may benefit from advanced computational tools.

Purpose of the Study:

  • To develop and evaluate a pattern-recognition (PR) system for classifying normal versus pathological knee articular cartilage.
  • To assess the system's performance on medial femoral (MFC) and tibial condyles (MTC) using 3-T MRI data.
  • To optimize the PR system design using parallel programming for enhanced efficiency.

Main Methods:

  • Utilized a probabilistic neural network classifier with textural features from segmented regions of interest (ROIs).

More Related Videos

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis
07:06

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

Related Experiment Videos

Last Updated: May 15, 2026

Development and Evaluation of a Rat Model of Full-Thickness Cartilage Defects
04:34

Development and Evaluation of a Rat Model of Full-Thickness Cartilage Defects

Published on: May 19, 2023

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis
07:06

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

  • Employed leave-one-out and external cross-validation for robust performance assessment.
  • Implemented Compute Unified Device Architecture (CUDA) parallel programming on a graphics processing unit (GPU) for system design optimization.

    • Main Results:

    • Achieved high classification accuracies: 93.2% for MFC and 95.5% for MTC.
    • Demonstrated strong performance on unseen data with accuracies of 89% (MFC) and 86% (MTC).
    • GPU-based system design was significantly faster (3.5 minutes) compared to CPU (15 hours).

    Conclusions:

    • The developed PR system effectively discriminates between normal and pathological knee cartilage.
    • The GPU-optimized system offers a computationally efficient solution for cartilage analysis.
    • This system holds potential as a valuable second-opinion tool in clinical settings.