Efficient Segmentation of Lung Abnormalities in CT Images

Authors:
Aryaz Baradarani;Q. M. Wu
Affiliations:
University of Windsor N9B3P4;University of Windsor N9B3P4
Venue:
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Year:
2009

Citing 5
Cited 0

Fractal functions and wavelet expansions based on several scaling functions

Journal of Approximation Theory
Sampled-Data Design of FIR Dual Filter Banks for Dual-Tree Complex Wavelet Transforms via LMI Optimization

IEEE Transactions on Signal Processing - Part II
SDP Approximation of a Fractional Delay and the Design of Dual-Tree Complex Wavelet Transform

IEEE Transactions on Signal Processing
The application of multiwavelet filterbanks to image processing

IEEE Transactions on Image Processing
Fast and automatic video object segmentation and tracking for content-based applications

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces an efficient technique for lung abnormalities segmentation in CT images based on the use of dual-tree complex wavelet transform (DT-CWT) and multilevel histogram thresholding. Recently, a scalar wavelet-based method has shown favorable results compared with previous approaches in honeycomb detection in pediatric CT images. Using our recently designed dual-tree complex filter bank and employing high resolution intensity similarities, we show that DT-CWT outperforms the results obtained with discrete wavelet transform (DWT) in general. Our early experiments show that multi-wavelets (MW) can also present a promising performance than DWT. The results indicate that DT-CWT performs slightly better than multi-wavelets, however, it can significantly outperform scalar wavelets. The former is probably due to better edge preserving property of multi-wavelets, while the latter is obtained because of good directionality and shift-invariance of dual-tree complex wavelet transform.