Title :
Texture descriptors for mammographic mass characterization
Author :
Sivaramakrishna, R. ; Powell, K.A. ; Obuchowski, N. ; Chilcote, W.
Author_Institution :
Dept. of Biomed. Eng., Cleveland Clinic Found., OH, USA
Abstract :
Compares the performance of different texture descriptors in distinguishing benign from malignant mammographic lesions. The best discriminators are the models fit from the Laws, Haralick, and 3D geometric surface temperature descriptors, in that order. Fractal dimension was not a good texture descriptor
Keywords :
fractals; image texture; mammography; medical image processing; tumours; Haralick descriptors; Laws descriptors; benign mammographic lesions; fractal dimension; malignant mammographic lesion; mammographic mass characterization; performance; receiver operating characteristic curves; texture descriptors; three dimensional geometric surface temperature descriptors; Analysis of variance; Biomedical engineering; Cancer; Entropy; Fractals; Kernel; Lesions; Radiology; Surface texture; Temperature;
Conference_Titel :
[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-5674-8
DOI :
10.1109/IEMBS.1999.804188
