Title :
Stochastic model and probabilistic decision-based classifier for mass detection in digital mammography
Author :
Li, Huai ; Liu, K. J Ray ; Lo, Shih-Chung B. ; Wang, Yue
Author_Institution :
Odyssey Technol. LLC, Jessup, MD, USA
Abstract :
We have developed a combined method utilizing morphological operations, a finite generalized Gaussian mixture (FGGM) modeling, and a contextual Bayesian relaxation labeling technique (CBRL) to enhance and extract suspicious masses. A feature space is constructed based on multiple feature extraction from the regions of interest (ROIs). Finally, a multi-modular probabilistic decision-based classifier is employed to distinguish true masses from non-masses
Keywords :
Bayes methods; Gaussian processes; decision theory; diagnostic radiography; feature extraction; image classification; image enhancement; image segmentation; mathematical morphology; medical image processing; probability; stochastic processes; contextual Bayesian relaxation labeling; digital mammography; feature space; finite generalized Gaussian mixture modeling; mass detection; masses enhancement; morphological operations; multi-modular probabilistic decision-based classifier; multiple feature extraction; regions of interest; stochastic model; Bayesian methods; Biomedical imaging; Context modeling; Educational institutions; Feature extraction; Image segmentation; Labeling; Medical diagnostic imaging; Morphological operations; Stochastic processes;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.632177
