Copd Detection Using Three-Dimensional Gaussian Markov Random Fields Based On Binary Features

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 text...

Full description

Saved in:
Bibliographic Details
Published inProceedings - International Conference on Image Processing pp. 340 - 344
Main Authors Almakady, Yasseen, Mahmoodi, Sasan, Bennett, Michael
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2020
Subjects
3D texture
3D-GMRF
Biomedical imaging
COPD
Diseases
Feature extraction
Histograms
Lung
Mathematical model
Three-dimensional displays
Volumetric texture classification
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2381-8549
DOI:10.1109/ICIP40778.2020.9191062