Communication science et technologie
Volume 23, Numéro 2, Pages 27-35
2025-11-18

Deep Learning-based Classification Of Knee Osteoarthritis Using Gaussian Noise Augmentation And Knowledge Distillation



Authors : Messaoudene Khadidja .

Abstract

Knee osteoarthritis (KOA) is a degenerative joint disease characterized by cartilage deterioration, leading to pain, stiffness, and impaired joint function. Accurate detection and grading are crucial for early intervention, but challenges such as limited data, redundant features, and suboptimal classification performance hinder reliable diagnostic tools. This study pro- poses an effective pipeline for classifying KOA into Kellgren- Lawrence (KL) grades 0 (no OA) and 2 (moderate OA) using data augmentation, deep feature extraction, and refined feature selection. The method was tested on 688 knee radiographs from the Osteoarthritis Initiative (OAI), with regions of interest (ROIs) extracted and augmented using Gaussian noise. Deep features were obtained via DenseNet-201, followed by knowledge distillation for feature selection, and classification was performed using a fine Gaussian Support Vector Machine (GSVM) with 5-fold cross-validation. The pipeline achieved 94.5% accuracy and a 96% AUC, whereas omitting feature selection reduced accuracy to 82%, and excluding augmentation lowered it to 88%, underscoring their importance. The integration of Gaussian noise augmentation, DenseNet-201, and knowledge distillation significantly enhanced classification performance, demonstrating strong potential for improving automated diagnostic systems and supporting early KOA detection and clinical decision-making.

Keywords

knee OsteoArthritis; X-ray images; Knowledge distillation; DenseNet-201; GSVM.

Les articles similaires

Predictive Modeling Of Ozone Dosing In Drinking Water Treatment Plant Using Deep Learning Comparative Study Between Deep Neural Networks And Convolutional Neural Networks

Hellal Aouatef .  Djeddou Messaoud .  Loukam Imed .  A. Hameed Ibrahim .  Al Dallal Jehad .  Shawaqfah Moayyad . 
pages 69-83.

Le Bruit, Nuisance Sonore En Algérie: Aspect Linguistique Et Sociétal/ Noise, Noise Pollution In Algeria : Linguistic And Societal Aspect

Boutaleb Djamila . 
pages 101-111.

Automatic Diagnosis System For Classification, Segmentation, Detection And Tracking Of Skin Lesion Based On Deep Convolutional Neural Networks

Benyahia Samia .  Meftah Boudjelal . 
pages 23-27.

Classification Of Hate Speech Using Deep Neural Networks.

Geet D’sa Ashwin .  Illina Irina .  Fohr Dominique . 
pages 1-12.

Theoretical Studies Of Ethylnitrolic Acid Using Gaussian

Nikafshar S. .  Moradi Mirazizi Y. .  Nikafshar S. . 
pages 567-584.

Formats de citation