A novel method for lung segmentation on chest CT images: complex-valued artificial neural network with complex wavelet transform

Abstract

Image segmentation is an important step in many computer vision algorithms. The objective of segmentation is to obtained an optimal region of convergences (ROC). Error in this stage will impact all higher level activities. This paper focuses on a new efficient method denoted as Complex-Valued Artificial Neural Network with Complex Wavelet Transform (CWT-CVANN) for the segmentation of lung region on chest CT images. In this combined architecture is composed of two cascade stages: feature extraction with various levels of complex wavelet transform, and segmentation with complex-valued artificial neural network. Hem, 32 CT images of 6 female and 26 male patients were recorded from, Baskent University Radiology Department. (This collection includes 10 images with benign nodules and 22 images with malign nodules. Averaged age of patients is 64. Each CT slice used in this study has dimensions of 752x 752 pixels with grey level) In only two seconds of processing time per each CT image, 99.79% averaged accuracy rate is obtained using 3(rd) level CWT-CVANN for segmentation of the lung region. Thus, it is concluded that CWT-CVANN is a comprising method in luny region segmentation problem.