X-ray image analysis for automated knee osteoarthritis detection

Knee issues are very frequent among people of all ages, and osteoarthritis is one of the most common reasons behind them. The primary feature in observing extremity and advancement of osteoarthritis is joint space narrowing (cartilage loss) which is manually computed on knee x-rays by a radiologist. Such manual inspections require an expert radiologist to analyze the x-ray image; moreover, it is a tedious and time-consuming task. In this paper, we present a computer-vision-based system that can assist the radiologists by analyzing the radiological symptoms in knee x-rays for osteoarthritis. Different image processing techniques have been applied on knee radiographs to enhance their quality. The knee region is extracted automatically using template matching. The knee joint space width is calculated, and the radiographs are classified based on the comparison with the standard normal knee joint space width. The experimental evaluation performed on a large knee x-ray dataset shows that our method is able to efficiently detect osteoarthritis, achieving more than 97% detection accuracy.

[1]  Marcin Grzegorzek,et al.  Spatiotemporal features of human motion for gait recognition , 2018, Signal Image Video Process..

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Dan Zhang,et al.  Real-time smoke removal for the surveillance images under fire scenario , 2019, Signal Image Video Process..

[4]  C. Helmick,et al.  Vital Signs: Prevalence of Doctor-Diagnosed Arthritis and Arthritis-Attributable Activity Limitation — United States, 2013–2015 , 2017, MMWR. Morbidity and mortality weekly report.

[5]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Arif Mahmood,et al.  Improving security surveillance by hidden cameras , 2016, Multimedia Tools and Applications.

[7]  Li Bai,et al.  An edge-weighted second order variational model for image decomposition , 2016, Digit. Signal Process..

[8]  A.B. Suksmono,et al.  Automated detection of unimpaired joint space for knee osteoarthritis assessment , 2005, Proceedings of 7th International Workshop on Enterprise networking and Computing in Healthcare Industry, 2005. HEALTHCOM 2005..

[9]  G. Stachowiak,et al.  Detection and prediction of osteoarthritis in knee and hand joints based on the X-ray image analysis , 2016 .

[10]  M. Galli,et al.  Reliability of the Ahlbäck classification of knee osteoarthritis. , 2003, Osteoarthritis and cartilage.

[11]  Suneeta Agarwal,et al.  Computer Assisted Automated Detection of Knee Osteoarthritis using X-ray Images , 2015 .

[12]  Li Bai,et al.  Implementation of high‐order variational models made easy for image processing , 2016 .

[13]  K. Kaufman,et al.  Semi-automated digital image analysis of joint space width in knee radiographs , 2005, Skeletal Radiology.

[14]  Tehreem Fatima,et al.  Automatic detection of Plasmodium parasites from microscopic blood images , 2019, Journal of Parasitic Diseases.

[15]  Marco Grangetto,et al.  DOST: a distributed object segmentation tool , 2017, Multimedia Tools and Applications.

[16]  Soo Beom Choi,et al.  Simple Scoring System and Artificial Neural Network for Knee Osteoarthritis Risk Prediction: A Cross-Sectional Study , 2016, PloS one.

[17]  Subramoniam.M Subramoniam.M,et al.  Support Vector Machine Approach for the Diagnosis of Arthritis From Digital X-Ray Images Using Local Ternary Pattern , 2011 .

[18]  Pengyu Wang,et al.  Intravascular optical coherence tomography image segmentation based on Gaussian mixture model and adaptive fourth-order PDE , 2019, Signal, Image and Video Processing.

[19]  Qi Tian,et al.  A survey of recent advances in visual feature detection , 2015, Neurocomputing.

[20]  E. Vignon,et al.  Quantitative evaluation of joint space width in femorotibial osteoarthritis: comparison of three radiographic views. , 1998, Osteoarthritis and cartilage.

[21]  G Welsh,et al.  Joint space in radiologically normal knees. , 1991, British journal of rheumatology.

[22]  Caixia Deng,et al.  Image edge detection based on wavelet transform and Canny operator , 2009, 2009 International Conference on Wavelet Analysis and Pattern Recognition.

[23]  J. Lynch,et al.  Comparison of fixed-flexion positioning with fluoroscopic semi-flexed positioning for quantifying radiographic joint-space width in the knee: test-retest reproducibility , 2003, Skeletal Radiology.

[24]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[25]  Jingjie Zheng,et al.  A feature-based solution for 3D registration of CT and MRI images of human knee , 2015, Signal Image Video Process..

[26]  B. Matthews Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[27]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Ravindra S. Hegadi,et al.  Block based texture analysis approach for knee osteoarthritis identification using SVM , 2015, 2015 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE).

[29]  Pooja U. Patravali,et al.  Detection of Osteoarthritis using Knee X-Ray Image Analyses: A Machine Vision based Approach , 2016 .

[30]  M. Karimi,et al.  EVALUATION OF GROUND REACTION FORCES IN PATIENTS WITH VARIOUS SEVERITIES OF KNEE OSTEOARTHRITIS , 2016 .

[31]  Lior Shamir,et al.  Knee X-Ray Image Analysis Method for Automated Detection of Osteoarthritis , 2009, IEEE Transactions on Biomedical Engineering.

[32]  Jh. Kellgren Radiological assessment of osteoarthritis , 1957 .

[33]  Timothy F. Cootes,et al.  Automated Shape and Texture Analysis for Detection of Osteoarthritis from Radiographs of the Knee , 2015, MICCAI.

[34]  Marcin Grzegorzek,et al.  A computer vision-based system for monitoring Vojta therapy , 2018, Int. J. Medical Informatics.

[35]  M. Nevitt,et al.  Diagnostic performance of 3D standing CT imaging for detection of knee osteoarthritis features , 2015, The Physician and sportsmedicine.

[36]  I Ketut Eddy Purnama,et al.  Osteoarthritis Classification Using Self Organizing Map Based on Gabor Kernel and Contrast-Limited Adaptive Histogram Equalization , 2013, The open biomedical engineering journal.

[37]  Flavia Cicuttini,et al.  Association of cartilage defects with loss of knee cartilage in healthy, middle-age adults: a prospective study. , 2005, Arthritis and rheumatism.

[38]  Jacob Cohen A Coefficient of Agreement for Nominal Scales , 1960 .

[39]  L. Ferrucci,et al.  Early detection of radiographic knee osteoarthritis using computer-aided analysis. , 2009, Osteoarthritis and cartilage.

[40]  Simo Saarakkala,et al.  Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach , 2017, Scientific Reports.

[41]  Jennifer M. Hootman,et al.  Prevalence of doctor-diagnosed arthritis and arthritis-attributable activity limitation --- United States, 2007-2009. , 2010, MMWR. Morbidity and mortality weekly report.

[42]  G. Gold,et al.  Atlas of individual radiographic features in osteoarthritis, revised. , 2007, Osteoarthritis and cartilage.

[43]  Arif Mahmood,et al.  Image Morphing in Frequency Domain , 2011, Journal of Mathematical Imaging and Vision.

[44]  Nicholas Bellamy,et al.  Design and conduct of clinical trials in patients with osteoarthritis : Recommendations from a task force of the Osteoarthritic Research Society , 1996 .

[45]  V. Rajini,et al.  Local Binary Pattern Approach to the Classification of Osteoarthritis in Knee X-ray Images , 2013 .

[46]  Mohamed S. Shehata,et al.  Local null space pursuit for real-time moving object detection in aerial surveillance , 2020, Signal Image Video Process..

[47]  Xinge You,et al.  A Blind Watermarking Scheme Using New Nontensor Product Wavelet Filter Banks , 2010, IEEE Transactions on Image Processing.

[48]  Noel E. O'Connor,et al.  Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity Using Convolutional Neural Networks , 2017, MLDM.

[49]  W. Dunn,et al.  Sensitivity of standing radiographs to detect knee arthritis: a systematic review of Level I studies. , 2015, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[50]  Li Bai,et al.  New second order Mumford–Shah model based on Γ-convergence approximation for image processing , 2016 .

[51]  J. Kellgren,et al.  Radiological Assessment of Osteo-Arthrosis , 1957, Annals of the rheumatic diseases.

[52]  T P Andriacchi,et al.  Methods for evaluating the progression of osteoarthritis. , 2000, Journal of rehabilitation research and development.

[53]  Aboul Ella Hassanien,et al.  Retinal fundus vasculature multilevel segmentation using whale optimization algorithm , 2018, Signal Image Video Process..