Computational and Mathematical Methods in Medicine
Volume 2014 (2014), Article ID 758439, 14 pages
http://dx.doi.org/10.1155/2014/758439
Ultrasound Image Enhancement Using Structure-Based Filtering
1Department of Computer Science, National Taiwan Ocean University, No. 2, Peining Road, Keelung City 202, Taiwan
2Chang-Gung Memorial Hospital, No. 222, Mai-Chin Road, Keelung City 204, Taiwan
Received 21 February 2014; Accepted 4 June 2014; Published 19 June 2014
Academic Editor: Kumar Durai
Copyright © 2014 Shyh-Kuang Ueng et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Ultrasound images are prone to speckle noises. Speckles blur features which are essential for diagnosis and assessment. Thus despeckling is a necessity in ultrasound image processing. Linear filters can suppress speckles, but they smooth out features. Median filter based despeckling algorithms produce better results. However, they may produce artifact patterns in the resulted images and oversmooth nonuniform regions. This paper presents an innovative despeckle procedure for ultrasound images. In the proposed method, the diffusion tensor of intensity is computed at each pixel at first. Then the eigensystem of the diffusion tensor is calculated and employed to detect and classify the underlying structure. Based on the classification result, a feasible filter is selected to suppress speckles and enhance features. Test results show that the proposed despeckle method reduces speckles in uniform areas and enhances tissue boundaries and spots.