Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Lal, Madana; * | Kaur, Lakhwindera | Gupta, Savitab
Affiliations: [a] Department of Computer Engineering, Punjabi University, Patiala, India | [b] Department of Computer Science and Engineering, University Institute of Engineering and Technology, Panjab University, Chandigarh, India
Correspondence: [*] Corresponding author: Madan Lal, Department of Computer Engineering, Punjabi University, Patiala 147002, India. Tel.: +91 9988696700; E-mail: madanlal@pbi.ac.in.
Abstract: BACKGROUND:Since breast ultrasound images are of low contrast, contain inherent noise and shadowing effect due to its imaging process, segmentation of breast tumors depicting ultrasound image is a challenging task. Thus, a robust breast ultrasound image segmentation technique is inevitable. OBJECTIVE:To develop an automatic lesion segmentation technique for breast ultrasound images. METHODS:First, the technique automatically detects the suspicious tumor region of interest and discards the unwanted complex background regions. Next, based on the concept of information gain, the technique applies an existing neutrosophic clustering method to the detected region to segment the desired tumor area. The proposed technique computes information gain values from the local neighbourhood of each pixel, which is further used to update the membership values and the cluster centers for the neutrosophic clustering process. Integrating the concept of entropy and neutrosophic logic features into the technique enabled to generate better segmentation results. RESULTS:Results of proposed method were compared both qualitatively and quantitatively with fuzzy c-means, neutrosophic c-means and neutrosophic ℓ-means clustering methods. It was observed that the proposed method outperformed the other three methods and yielded the best Mean (TP: 94.72, FP: 5.85, SI: 93.75, HD: 8.2, AMED: 2.4) and Standard deviation (TP: 3.2, FP: 3.7, SI: 3.8, HD: 2.6, AMED: 1.3) values for different quality metrics on the current set of breast ultrasound images. CONCLUSION:Study demonstrated that the proposed technique is robust to the shadowing effect and produces more accurate segmentation of the tumor region, which is very similar to that visually segmented by Radiologist.
Keywords: Ultrasound images, breast tumor, fuzzy c-means clustering, neutrosophic clustering, information gain
DOI: 10.3233/XST-17313
Journal: Journal of X-Ray Science and Technology, vol. 26, no. 2, pp. 209-225, 2018
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl