Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique

Abstract Knee osteoarthritis (KOA) represents a well-documented degenerative arthropathy prevalent among the elderly population. KOA is a persistent condition, also referred to as progressive joint Disease, stemming from the continual deterioration of cartilage. Predominantly afflicting individuals...

Full description

Saved in:
Bibliographic Details
Main Authors: Punita Panwar, Sandeep Chaurasia, Jayesh Gangrade, Ashwani Bilandi, Dayananda Pruthviraja
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78203-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846172115043090432
author Punita Panwar
Sandeep Chaurasia
Jayesh Gangrade
Ashwani Bilandi
Dayananda Pruthviraja
author_facet Punita Panwar
Sandeep Chaurasia
Jayesh Gangrade
Ashwani Bilandi
Dayananda Pruthviraja
author_sort Punita Panwar
collection DOAJ
description Abstract Knee osteoarthritis (KOA) represents a well-documented degenerative arthropathy prevalent among the elderly population. KOA is a persistent condition, also referred to as progressive joint Disease, stemming from the continual deterioration of cartilage. Predominantly afflicting individuals aged 45 and above, this ailment is commonly labeled as a “wear and tear” joint disorder, targeting joints such as the knee, hand, hips, and spine. Osteoarthritis symptoms typically increase gradually, contributing to the deterioration of articular cartilage. Prominent indicators encompass pain, stiffness, tenderness, swelling, and the development of bone spurs. Diagnosis typically involves the utilization of Radiographic X-ray images, Magnetic Resonance Imaging (MRI), and Computed Tomography (CT) Scan by medical professionals and experts. However, this conventional approach is time-consuming, and also sometimes tedious for medical professionals. In order to address the limitation of time and expedite the diagnostic process, deep learning algorithms have been implemented in the medical field. In the present investigation, four pre-trained models, specifically CNN, AlexNet, ResNet34 and ResNet-50, were utilized to predict the severity of KOA. Further, a Deep stack ensemble technique was employed to achieve optimal performance resulting to the accuracy of 99.71%.
format Article
id doaj-art-9d890839547b4d40b7d9410041b4128d
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9d890839547b4d40b7d9410041b4128d2024-11-10T12:18:00ZengNature PortfolioScientific Reports2045-23222024-11-0114111410.1038/s41598-024-78203-xOptimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble techniquePunita Panwar0Sandeep Chaurasia1Jayesh Gangrade2Ashwani Bilandi3Dayananda Pruthviraja4Department of Computer Science & Engineering, School of Computer Science & Engineering, Manipal University JaipurDepartment of Computer Science & Engineering, School of Computer Science & Engineering, Manipal University JaipurDepartment of Artificial Intelligence & Machine Learning, Computer Science & Engineering, Manipal University JaipurDepartment of Orthopedics , MBBS, Mahatma Gandhi Medical CollegeDepartment of Information Technology, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher EducationAbstract Knee osteoarthritis (KOA) represents a well-documented degenerative arthropathy prevalent among the elderly population. KOA is a persistent condition, also referred to as progressive joint Disease, stemming from the continual deterioration of cartilage. Predominantly afflicting individuals aged 45 and above, this ailment is commonly labeled as a “wear and tear” joint disorder, targeting joints such as the knee, hand, hips, and spine. Osteoarthritis symptoms typically increase gradually, contributing to the deterioration of articular cartilage. Prominent indicators encompass pain, stiffness, tenderness, swelling, and the development of bone spurs. Diagnosis typically involves the utilization of Radiographic X-ray images, Magnetic Resonance Imaging (MRI), and Computed Tomography (CT) Scan by medical professionals and experts. However, this conventional approach is time-consuming, and also sometimes tedious for medical professionals. In order to address the limitation of time and expedite the diagnostic process, deep learning algorithms have been implemented in the medical field. In the present investigation, four pre-trained models, specifically CNN, AlexNet, ResNet34 and ResNet-50, were utilized to predict the severity of KOA. Further, a Deep stack ensemble technique was employed to achieve optimal performance resulting to the accuracy of 99.71%.https://doi.org/10.1038/s41598-024-78203-xKnee osteoarthritisMagnetic resonance imaging (MRI)Deep learning algorithmsConvolutional neural networkDeep Stack Ensemble
spellingShingle Punita Panwar
Sandeep Chaurasia
Jayesh Gangrade
Ashwani Bilandi
Dayananda Pruthviraja
Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
Scientific Reports
Knee osteoarthritis
Magnetic resonance imaging (MRI)
Deep learning algorithms
Convolutional neural network
Deep Stack Ensemble
title Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
title_full Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
title_fullStr Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
title_full_unstemmed Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
title_short Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique
title_sort optimizing knee osteoarthritis severity prediction on mri images using deep stacking ensemble technique
topic Knee osteoarthritis
Magnetic resonance imaging (MRI)
Deep learning algorithms
Convolutional neural network
Deep Stack Ensemble
url https://doi.org/10.1038/s41598-024-78203-x
work_keys_str_mv AT punitapanwar optimizingkneeosteoarthritisseveritypredictiononmriimagesusingdeepstackingensembletechnique
AT sandeepchaurasia optimizingkneeosteoarthritisseveritypredictiononmriimagesusingdeepstackingensembletechnique
AT jayeshgangrade optimizingkneeosteoarthritisseveritypredictiononmriimagesusingdeepstackingensembletechnique
AT ashwanibilandi optimizingkneeosteoarthritisseveritypredictiononmriimagesusingdeepstackingensembletechnique
AT dayanandapruthviraja optimizingkneeosteoarthritisseveritypredictiononmriimagesusingdeepstackingensembletechnique