Machine learning classification on texture analyzed T2 maps of osteoarthritic cartilage: oulu knee osteoarthritis study

Abstract

Objective: To introduce local binary pattern (LBP) texture analysis to cartilage osteoarthritis (OA) research and compare the performance of different classification systems in discrimination of OA subjects from healthy controls using gray-level co-occurrence matrix (GLCM) and LBP texture data. Classification algorithms were used to reduce the dimensionality of texture data into a likelihood of subject belonging to the reference class.

Method: T2 relaxation time mapping with multi-slice multi-echo spin echo sequence was performed for eighty symptomatic OA patients and 63 asymptomatic controls on a 3T clinical MRI scanner. Relaxation time maps were subjected to GLCM and LBP texture analysis, and classification algorithms were deployed with an in-house developed software. Implemented algorithms were K nearest neighbors, support vector machine, and neural network classifier.

Results: LBP and GLCM discerned OA patients from controls with a significant difference in all studied regions. Classification models comprising GLCM and LBP showed high accuracy in classing OA patients and controls. The best performance was obtained with a multilayer perceptron type classifier with an overall accuracy of 90.2 %.

Conclusion: LBP texture analysis complements prior results with GLCM, and together LBP and GLCM serve as significant input data for classification algorithms trained for OA assessment. Presented algorithms are adaptable to versatile OA evaluations also for future gradational or predictive approaches.

Keywords: GLCM; LBP; Osteoarthritis; Pattern recognition and data classification; T2 relaxation time; Texture analysis.