Title :
Mammographic image segmentation using combined morphological filtering and contextual Bayesian labeling
Author :
Li, H. ; Freedman, M.T. ; Wang, Y. ; Lo, S.C.B. ; Mun, S.K.
Author_Institution :
Dept. of Radiol., Georgetown Univ. Med. Center, Washington, DC, USA
Abstract :
The objective of this study is to develop an efficient method to highlight the geometric characteristics of defined patterns, and isolate the suspicious regions which in turn provide the improved segmentation of objects. In this paper, a combined method of using morphological operations and contextual Bayesian relaxation labeling was developed to enhance and segment various mammographic contexts and textures. This method has been used to segment mammographic images for the extraction of masses. The testing results showed that the proposed method can detect all suspected masses as well as high contrast objects
Keywords :
Bayes methods; diagnostic radiography; feature extraction; image segmentation; medical image processing; breast cancer; contextual Bayesian labeling; geometric characteristics; high contrast objects; mammographic image segmentation; masses extraction; medical diagnostic imaging; morphological filtering; suspected masses; suspicious regions; Bayesian methods; Biomedical imaging; Breast cancer; Context modeling; Educational institutions; Filtering; Image segmentation; Labeling; Morphological operations; Stochastic processes;
Conference_Titel :
Biomedical Engineering Conference, 1996., Proceedings of the 1996 Fifteenth Southern
Conference_Location :
Dayton, OH
Print_ISBN :
0-7803-3131-1
DOI :
10.1109/SBEC.1996.493263
