Denoising and fissure extraction in high resolution isotropic CT images using Dual Tree Complex Wavelet Transform

The human lungs are divided into five distinct anatomic compartments called the lobes, which are separated by the pulmonary fissures. Identification of pulmonary fissures, which form the boundaries between the lobes in the lungs, may be useful during clinical interpretation of computed tomography (CT) examinations to assess the early diagnosis of presence and characterization of manifestation of several lung diseases like cancer. Extraction of pulmonary fissure (areas containing fissures which are boundaries of lung lobes and having absence of bronchial trees) is quite complex because it has various shape and appearance along with low contrast and high noise associated with isotropic lung HRCT images. This paper presents a fully automatic method for segmenting the lung lobes by identifying the lobar fissure in High Resolution isotropic Computed Tomography (HRCT) images using Dual Tree Complex Wavelet Transform (DTCWT).