Multi-classifier framework for lung tissue classification

Abstract

Many systems have been developed for computer analysis of the lungs in high resolution computed tomography (HRCT) scans for detection and analysis of Interstitial Lung Diseases (ILDs). This paper presents a novel approach for classification of lung tissue patterns affected with Interstitial Lung Diseases (ILDs) in high resolution computed tomography (HRCT) scans. The proposed scheme makes use of texture features obtained using Discrete Wavelet Transform (DWT) and multiple classifiers to obtain the initial decisions on the input image. The decisions obtained from all the classifiers are fused to obtain the final decision on the input pattern. The method is tested on a private database containing HRCT images belongs to four ILDs patterns (viz. consolidation, emphysema, ground glass, nodular) and normal lung tissue. The performance of the method is compared with its single classifier based counterpart and found to be superior.