Title: Segmentation of cartilage in knee magnetic resonance images using Gabor and matched filter and classification of osteoarthritis using adaptive neuro-fuzzy inference system

Authors: P. Jayashree; U.S. Ragupathy

Addresses: Department of Electronics and Instrumentation Engineering, Kongu Engineering College, India ' Department of Electronics and Instrumentation Engineering, Kongu Engineering College, India

Abstract: Osteoarthritis (OA) is a group of mechanical abnormalities occurring in the joints like knee, finger and hip regions. Knee region contains complex objects, detecting the presence of particular structures in such images can be a daunting task. OA in knee image can be identified by segmenting the bone and cartilage. Manual and some semiautomatic segmentation methods are time consuming and complex. A method is described here for classification of OA which deals with segmentation of cartilage region from femur and tibia bone. The images are preprocessed using contrast enhancement technique and contrast limited adaptive histogram equalisation (CLAHE) and further processed using matched and Gabor filter for clear recognition of cartilage. The noises present are further eliminated using median filter. Using grey level co-occurrence matrix (GLCM), features are extracted. Adaptive neuro-fuzzy inference system (ANFIS) classifier is used for classification of OA. The datasets are obtained from osteoarthritis initiative (OAI) database and Ganga Hospital, Coimbatore.

Keywords: osteoarthritis; magnetic resonance images; MRI; matched filter; Gabor filter; CLAHE; grey level co-occurrence matrix; GLCM; adaptive neuro-fuzzy inference system; ANFIS.

DOI: 10.1504/IJBET.2021.119929

International Journal of Biomedical Engineering and Technology, 2021 Vol.37 No.3, pp.290 - 307

Received: 16 Jul 2018
Accepted: 31 Oct 2018
Published online: 04 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article