KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK

Knee osteoarthritis severity detection is one of the most challenging applications in computer vision due to the similarity between X-ray images of the adjacent stages. Handling huge number of X-ray images and the ability to detect the correct disease stage is based on advanced artificial intellige...

Full description

Saved in:
Bibliographic Details
Main Authors: Delveen Luqman Abd Alnabi, Shereen Sh Ahmed, Nisreen Luqman Abd Alnabi
Format: Article
Language:English
Published: University of Zakho 2025-04-01
Series:Science Journal of University of Zakho
Subjects:
Online Access:https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1450
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849316086038659072
author Delveen Luqman Abd Alnabi
Shereen Sh Ahmed
Nisreen Luqman Abd Alnabi
author_facet Delveen Luqman Abd Alnabi
Shereen Sh Ahmed
Nisreen Luqman Abd Alnabi
author_sort Delveen Luqman Abd Alnabi
collection DOAJ
description Knee osteoarthritis severity detection is one of the most challenging applications in computer vision due to the similarity between X-ray images of the adjacent stages. Handling huge number of X-ray images and the ability to detect the correct disease stage is based on advanced artificial intelligence technologies, like machine learning and deep learning. This study presents a novel deep learning-based fusion framework designed for detecting the severity of knee osteoarthritis and classifying its stages. The study utilizes two X-ray image datasets containing three challenges: imbalanced data, low contrast, and low data size. Data augmentation, adaptive histogram equalization, and limited oversampling techniques were used to solve these problems. Five deep learning architectures were utilized as base models (EfficientNetB0, EfficientNetV2B0, XceptionNet, ResNetRS101, and RegNetY032), followed by average pooling and dense layers. The feature-level, decision-level, score-level, and meta-based fusion technologies were also performed on the outputs of the best three trained models to minimize the individual models’ errors. The study registered 70% and 90.61% classification accuracies using both datasets. The study also found that the best models are the score-level and meta-based fusion models in all scenarios.
format Article
id doaj-art-cba8e8a6588a496596b39c86003e50f7
institution Kabale University
issn 2663-628X
2663-6298
language English
publishDate 2025-04-01
publisher University of Zakho
record_format Article
series Science Journal of University of Zakho
spelling doaj-art-cba8e8a6588a496596b39c86003e50f72025-08-20T03:51:58ZengUniversity of ZakhoScience Journal of University of Zakho2663-628X2663-62982025-04-0113210.25271/sjuoz.2025.13.2.1450KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORKDelveen Luqman Abd Alnabi0Shereen Sh Ahmed1Nisreen Luqman Abd Alnabi2College of Administration and Economics, University of Duhok, Duhok, Kurdistan Region, IraqCollege of Science, University of Zakho, Duhok, Kurdistan Region, IraqTechnical College of Administration, Duhok Polytechnique University, Duhok, Kurdistan Region, Iraq Knee osteoarthritis severity detection is one of the most challenging applications in computer vision due to the similarity between X-ray images of the adjacent stages. Handling huge number of X-ray images and the ability to detect the correct disease stage is based on advanced artificial intelligence technologies, like machine learning and deep learning. This study presents a novel deep learning-based fusion framework designed for detecting the severity of knee osteoarthritis and classifying its stages. The study utilizes two X-ray image datasets containing three challenges: imbalanced data, low contrast, and low data size. Data augmentation, adaptive histogram equalization, and limited oversampling techniques were used to solve these problems. Five deep learning architectures were utilized as base models (EfficientNetB0, EfficientNetV2B0, XceptionNet, ResNetRS101, and RegNetY032), followed by average pooling and dense layers. The feature-level, decision-level, score-level, and meta-based fusion technologies were also performed on the outputs of the best three trained models to minimize the individual models’ errors. The study registered 70% and 90.61% classification accuracies using both datasets. The study also found that the best models are the score-level and meta-based fusion models in all scenarios. https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1450Deep learningDeep learning fusionDisease classificationFeature-level fusionKnee osteoarthritis
spellingShingle Delveen Luqman Abd Alnabi
Shereen Sh Ahmed
Nisreen Luqman Abd Alnabi
KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
Science Journal of University of Zakho
Deep learning
Deep learning fusion
Disease classification
Feature-level fusion
Knee osteoarthritis
title KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
title_full KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
title_fullStr KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
title_full_unstemmed KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
title_short KNEE OSTEOARTHRITIS STAGE CLASSIFICATION BASED ON HYBRID FUSION DEEP LEARNING FRAMEWORK
title_sort knee osteoarthritis stage classification based on hybrid fusion deep learning framework
topic Deep learning
Deep learning fusion
Disease classification
Feature-level fusion
Knee osteoarthritis
url https://sjuoz.uoz.edu.krd/index.php/sjuoz/article/view/1450
work_keys_str_mv AT delveenluqmanabdalnabi kneeosteoarthritisstageclassificationbasedonhybridfusiondeeplearningframework
AT shereenshahmed kneeosteoarthritisstageclassificationbasedonhybridfusiondeeplearningframework
AT nisreenluqmanabdalnabi kneeosteoarthritisstageclassificationbasedonhybridfusiondeeplearningframework