DocumentCode :
2632582
Title :
A novel microcalcification shape metric to classify regions of interests
Author :
Tay, Peter C. ; Ma, Yiming
Author_Institution :
Dept. of Eng. & Technol., Western Carolina Univ., Cullowhee, NC, USA
fYear :
2010
fDate :
23-25 May 2010
Firstpage :
201
Lastpage :
204
Abstract :
This paper proposes a microcalcification shape feature to aid in classifying regions of interest that are difficult to diagnosis. The proposed feature extraction method is based on a wavelet approximation of a microcalcification´s contour distance sequence, which is the Euclidean distance of each contour point to the centroid. A novel metric is proposed to quantify the roughness of a microcalcification. Experimental results from evaluations that include several published features are presented to establish the robustness of the proposed roughness feature.
Keywords :
biological organs; cancer; feature extraction; gynaecology; medical image processing; wavelet transforms; Euclidean distance; breast cancers; clustered regions; feature extraction method; microcalcification contour distance sequence; microcalcification shape; pleomorphic regions; regions-of-interests classification; wavelet approximation; Band pass filters; Breast cancer; Equations; Feature extraction; Filter bank; Filtering; Frequency; Mammography; Robustness; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Analysis & Interpretation (SSIAI), 2010 IEEE Southwest Symposium on
Conference_Location :
Austin, TX
Print_ISBN :
978-1-4244-7801-9
Type :
conf
DOI :
10.1109/SSIAI.2010.5483882
Filename :
5483882
Link To Document :
بازگشت