Efficient Segmentation of Lung Using FIDRM Filter and Successive Peak Quantization Transform

Abstract

Abstract:Computed Tomography (CT) is the main source for analyzing the lung diseases and the preplanning of pulmonary surgeries. The accurate interpretation of chest CT scan makes a challenge to radiologists due to its complex visual nature. This paper proposes a novel method to segment the left and right lungs from the background of CT images to assist the pathologists for the easy and accurate diagnosis of pulmonary diseases. The segmentation of lung is a challenging task due to the anatomical difference of different people. This paper develops a novel algorithm namely successive peak based quantization transform (SPQT) to segment the lungs from the background. This method extracts 8 bit patterns from the input lung image and at last a BYTE data which is formed from 8 bit patterns is produced. Prior to SPQT lung segmentation, the lung image which may contain impulse noise is reduced into noise free one by using 'Fuzzy Impulse Detection and Reduction Method' (FIDRM). The novel lung image hikes the accuracy to a significant level than the existing algorithms.