COPD detection using three-dimensional Gaussian Markov random fields based on binary features

Al Makady, Yasseen, Hamad, Mahmoodi, Sasan and Bennett, Michael (2020) COPD detection using three-dimensional Gaussian Markov random fields based on binary features. In Proceeding of IEEE International Conference on Image Processing. IEEE. 5 pp . (In Press)

Record type: Conference or Workshop Item (Paper)

Abstract

This paper proposes new descriptors based on three-dimensional
Gaussian Markov random fields (3D-GMRF) for volumetric texture classification. The estimated parameters of 3DGMRF are decomposed into sign and magnitude components and then are encoded into a single binary code to describe the local texture. Our experiments on a synthetic dataset of volumetric texture show that this approach leads to significant reduction in descriptor size, while preserving the discriminative power of 3D-GMRF features. The descriptors proposed here demonstrate strong performance in distinguishing between healthy and chronic obstructive pulmonary disease (COPD) subjects, using a medical dataset. These descriptors are successfully employed to measure the differences between various groups from the medical dataset, in order to determine which group is at risk of COPD.

Text

Yasseen_Accepted_ICIP2020_18May

Download (1MB)