Multiple kernel learning for classification of diffuse lung disease using HRCT lung images.

A novel algorithm is presented for classification of four patterns of diffuse lung disease: normal, emphysema, honeycombing and ground glass opacity, on the basis of textural analysis of high resolution computed tomography (HRCT) lung images. The algorithm incorporates scale-space features based on Gaussian derivative filters and multi-dimensional multi-scale features based on wavelet and contourlet transforms of the original images. The mean, standard deviation, skewness and kurtosis along with generalized Gaussian density are used to model the output of filters and transforms, and construct feature vectors. Multi-class multiple kernel learning (m-MKL) classifier is used to evaluate the performance of the feature extraction scheme. The method is tested on a collection of 89 slices from 38 patients, each slice of size 512×512, 16 bits/pixel in DICOM format. The dataset contains 70,000 ROIs from slices already marked by experienced radiologists. The average sensitivity and specificity achieved is 94.16% and 98.68%, respectively.