A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative

Abdelbasset Brahim; Rachid Jennane; Rabia Riad; Thomas Janvier; Laila Khedher; Hechmi Toumi; Eric Lespessailles

doi:10.1016/j.compmedimag.2019.01.007

A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative

Comput Med Imaging Graph. 2019 Apr:73:11-18. doi: 10.1016/j.compmedimag.2019.01.007. Epub 2019 Jan 29.

Authors

Abdelbasset Brahim¹, Rachid Jennane², Rabia Riad², Thomas Janvier², Laila Khedher², Hechmi Toumi³, Eric Lespessailles³

Affiliations

¹ University of Orléans, I3MTO Laboratory, EA 4708, 45067 Orléans, France. Electronic address: brahim.abdelbasset@yahoo.fr.
² University of Orléans, I3MTO Laboratory, EA 4708, 45067 Orléans, France.
³ University of Orléans, I3MTO Laboratory, EA 4708, 45067 Orléans, France; Hospital of Orléans, Rheumatology Department, 45032 Orléans, France.

PMID: 30784984
DOI: 10.1016/j.compmedimag.2019.01.007

Abstract

This paper presents a fully developed computer aided diagnosis (CAD) system for early knee OsteoArthritis (OA) detection using knee X-ray imaging and machine learning algorithms. The X-ray images are first preprocessed in the Fourier domain using a circular Fourier filter. Then, a novel normalization method based on predictive modeling using multivariate linear regression (MLR) is applied to the data in order to reduce the variability between OA and healthy subjects. At the feature selection/extraction stage, an independent component analysis (ICA) approach is used in order to reduce the dimensionality. Finally, Naive Bayes and random forest classifiers are used for the classification task. This novel image-based approach is applied on 1024 knee X-ray images from the public database OsteoArthritis Initiative (OAI). The results show that the proposed system has a good predictive classification rate for OA detection (82.98% for accuracy, 87.15% for sensitivity and up to 80.65% for specificity).

Keywords: Classification; Computer aided diagnosis system; Intensity normalization; OsteoArthritis.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Aged
Bayes Theorem
Diagnosis, Computer-Assisted*
Early Diagnosis*
Female
Humans
Machine Learning*
Male
Middle Aged
Multivariate Analysis
Osteoarthritis, Knee / diagnostic imaging*
X-Rays