Hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images

The objective of this research is to develop a computer-based diagnosis system which is capable of recognizing normal and edematous humeral head images by using texture features derived from Hermite transform. The performance of Hermite-based texture features in classification of humeral bone was compared with curvelet, contourlet and gray level co-occurrence matrix-based texture feature descriptors. To measure the performance of the extracted features, we deployed MLP (multilayer perceptron), SVM (support vector machine) and KNN (K-nearest neighbors) methods and demonstrated their power in differentiating the normal and abnormal regions. The proposed approach was tested on our own dataset which consists of 79 normal and 91 edematous humeral heads in PD (proton density)-weighted MR (magnetic resonance) images. The highest classification accuracy of Hermite-based method was 98.23% by MLP. In most cases, Hermite-based texture features surpassed the results of other proposed methods under all of the three classifiers. Our results suggest that the proposed system is a promising tool for classification of edematous and normal bone from PD-weighted MR images. This study is unique in the literature of using PD-weighted MR images and Hermite transform to classify bone edema .