Detection of Knee Osteoarthritis Using Image Segmentation and Artificial Neural Networks

Yasrebi, Ehsan; Zabbah, Iman; Ramezani, Morteza; Valeh, Hamid; Salarniya, Setare

doi:10.22034/ijos.2020.121422

Detection of Knee Osteoarthritis Using Image Segmentation and Artificial Neural Networks

Document Type : Original Article

Authors

ehsan yasrebi

iman zabbah

morteza ramezani

hamid valeh

setare salarniya

https://doi.org/10.22034/ijos.2020.121422

Abstract

Abstract
Background: Knee osteoarthritis is one of the common diseases in humans and due to its increasing spread, early diagnosis of this disease is very important. Consideration of cartilage volume in knee osteoarthritis studies from radiological images is very necessary. The aim of this study is to help improve the diagnosis of knee osteoarthritis with the help of artificial intelligence and image processing techniques.
Methods: This is a diagnostic study that has been evaluated on 957 MRI images. Images were collected from Tehran Hospital database, such that 111 samples were related to healthy individuals and 48 samples to people with knee osteoarthritis. In this study, in order to diagnose osteoarthritis automatically, a new method called “image distinguishing and teaching it to artificial neural network”,using MATLAB software was used. MRI images were received and after pre-processing they were processed to diagnose osteoarthritis conditions with the help of artificial neural networks.
Findings: Experiments show acceptable performance of the proposed method, such that using this technique the diagnose of knee osteoarthritis was possible, with 93% accuracy.
Results: the proposed model can be used in screening plans in order to identify people in danger of developing osteoarthritis and can serve as doctor assistants.

Keywords

Keywords: Digital Image Processing

Osteoarthritis of Knee

MRI

Computational Neural Networks

Knee

Ezadpanah A, Moazami M, Khoshraftar Yazdi N. Effect of a period of therapeutic exercise and detraining after that on balance in the women with knee osteoarthritis. Mrj. 2016;9 (1):101-109
Tavakkoli M, Bahrpyma F. Effect of Grade 1 Mobilization of Patellofemoral Joint on Reducing Pain and Joint Stiffness and Improving Physical Function in Patients with Knee Osteoarthritis. Horizon Med Sci. 2010; 16 (1):18-24
Erfanian zorufi F, Moazzami M, Mohamadi M. 'The Effect of Resistance Training on Static Balance and Pain in Elderly Women with Varus Knee and Osteoarthritis by Using Elastic Band', Journal of Paramedical Sciences & Rehabilitation. 2016; 5(2): pp. 14-24.
Moradi S, Haghpanahi M. Effect of Longitudinal tear meniscus with Acl stability and unstability of this Acl on the knee using Finite Element Analyses. IJOS. 2016; 14 (2 and 3) :57-63
Mahdi Nejad M, Jafari Z. Comparing effects of Glucosamine and Chondroitin sulphate combination with Naproxen on pain, physical function and radiologic findings in patients with knee osteoarthritis. 2013; 3(2): 1-12.
Haqin S, Tehrani A, Forouzanfar M H, Faezi T, Noorollahzadeh E, Gholami J et al. 2009 Risk factors of knee osteoarthritis. WHO-ILAR-COPCORD study. Tehran Univ Med J. 66 (10) :721-728.
MN T. Total knee arthroplasty in patients with osteoarthritis: Results of 34 operations. Tehran Univ Med J. 2009; 67 (2):146-150.
Shojaedin S S, Sayyah M, Mehrabian H, Sheikh Oveisi J, Barati A H, Razi M. Comparing the radiographic grading scales, knee pain, signs, movement dysfunctions and the quality of life related to osteoarthritis in ex-elite track and field athletes and non-athletes. Feyz. 2012; 16 (1): 58-64 .
Shojaedin S S, Sayyah M, Mehrabian H, Sheikh Oveisi J, Barati A H, Razi M. Comparing the radiographic grading scales, knee pain, signs, movement dysfunctions and the quality of life related to osteoarthritis in ex-elite track and field athletes and non-athletes. Feyz. 2012; 16 (1): 58-64.
Hassanzadeh M, Zabbah I, Layeghi K. Diagnosis of Coronary Heart Disease using Mixture of Experts Method. Journal of Health and Biomedical Informatics. 2018; 5 (2): 274-285.
Dehghan P, Mogharabi M, Zabbah I, Layeghi K, Maroosi A. Modeling Breast Cancer Using Data Mining Methods. Journal of Health and Biomedical Informatics. 2018; 4 (4): 266-278.
Zabbah I, Yasrebi Naeini S E, Ramazanpoor Z, Sahragard K. The Diagnosis of Thyroid Diseases Using Combinati on of Neural Networks through Hierarchical Method. Journal of Health and Biomedical Informatics. 2017; 4 (1): 21-31.
Rahmani N, Mohseni Bandpei M A, Nodehi A. Eligibility of Magnetic Resonance Imaging Technique in Determining Articular Cartilage Lesions in Patients with Knee Osteoarthritis A Systematic Review of the Literature. Journal of Mazandaran University of Medical Sciences. 2012; 21(1): pp.332-342.
Anifah L, Purnama IK, Hariadi M, Purnomo MH. Osteoarthritis classification using self organizing map based on gabor kernel and contrast-limited adaptive histogram equalization. Open Biomed Eng J. 2013; 7:18-28.
Oka H, Muraki S, Akune T, Mabuchi T, Suzuki H Yoshida et al. Fully automatic quantification of knee osteoarthritis severity on plain radiographs Osteoarthritis Cartilage. 2008;16(2): pp. 1300-1306.
Ababneh S Y, Prescott J W, Gurcan M Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research. Medical image analysis. 2011; 15(4): 438–448.
S Li, X Cui, M Yu, H Kim, K-S Kwack. Detecting and visualizing cartilage thickness without a shape model, in Systems, Man, and Cybernetics (SMC). 2012; IEEE International Conference on, 2012: pp. 232–236.