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

Volume

3

fYear

1997

Firstpage

539

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1997. Proceedings., International Conference on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-8186-8183-7

Type

conf

DOI

10.1109/ICIP.1997.632177

Filename

632177