Texture analysis using complex wavelet decomposition for knee osteoarthritis detection: Data from the osteoarthritis initiative. (May 2018)

• Record Type: Journal Article
• Authors: Riad, Rabia; Jennane, Rachid; Brahim, Abdelbasset; Janvier, Thomas; Toumi, Hechmi; Lespessailles, Eric
• Is Part Of: Computers & electrical engineering. Volume 68(2018)
• Page Start: 181
• Page End: 191
• Publication Date: 2018-05
• Subjects: Texture analysis -- Wavelet decomposition -- Relative phase -- Image classification -- OsteoArthritis -- X-ray; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.04.004
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The classification of subjects with different stages of knee OsteoArthritis (OA) using bone texture analysis is a challenging task in medical imaging. This paper presents a new approach for texture analysis of radiographic OA in knee X-ray images. First, a preprocessing step based on a 2D finite impulse response filter is applied on the X-ray images. Then, a set of image content descriptors is extracted from the complex wavelet decomposition using different statistics of a new concept of the relative phases of complex coefficients. The Von Mises and wrapped Cauchy probability density functions are used to model the distribution of relative phase coefficients. Finally, the estimated parameters for each image are used in the classification task, to verify the effectiveness and robustness of the proposed texture analysis on knee X-ray images from the OsteoArthritis Initiative (OAI). Results show that the proposed approach leads to improved texture analysis with a classification rate of 80.38%.