Title :
Application of shape analysis to mammographic calcifications
Author :
Shen, Liang ; Rangayyan, Rangaraj M. ; Desautels, J. E Leo
Author_Institution :
Dept. of Electr. & Comput. Eng., Calgary Univ., Alta., Canada
fDate :
6/1/1994 12:00:00 AM
Abstract :
The authors have developed a set of shape factors to measure the roughness of contours of calcifications in mammograms and for use in their classification as malignant or benign. The analysis of mammograms is performed in three stages. First, a region growing technique is used to obtain the contours of calcifications. Then, three measures of shape features, including compactness, moments, and Fourier descriptors are computed for each region. Finally, their applicability for classification is studied by using the three shape measures to form feature vectors. Classification of 143 calcifications from 18 biopsy-proven cases as benign or malignant using the three measures with the nearest-neighbor method was 100% accurate
Keywords :
diagnostic radiography; medical image processing; Fourier descriptors; benign lesion; biopsy-proven cases; breast cancer; calcification contours roughness; compactness; feature vectors; malignant lesion; mammographic calcifications; medical diagnostic imaging; moments; nearest-neighbor method; region growing technique; shape analysis; shape factors set; Biopsy; Breast cancer; Breast tumors; Cancer detection; Diseases; Filtering; Mammography; Modems; Performance analysis; Shape measurement;
Journal_Title :
Medical Imaging, IEEE Transactions on