Table 2 Selected LBP texture features for machine learning–based classifications of IIM and non-IIM disease groups.

From: Texture analysis of muscle MRI: machine learning-based classifications in idiopathic inflammatory myopathies

Code

Selected LBP texture features

Intraclass correlation coefficient (ICC)

Feature class

Feature name code

Intra-observer

Inter-observer

TexFL1

First-order

Total energy

0.978

0.968

TexFL2

First-order

Variance

0.974

0.942

TexFL3

GLCM

Cluster shade

0.937

0.897

TexFL4

GLCM

Contrast

0.881

0.824

TexFL5

GLCM

Difference entropy

0.941

0.930

TexFL6

GLRLM

Long run emphasis

0.822

0.801

TexFL7

GLRLM

Long run low gray-level emphasis

0.890

0.803

TexFL8

GLSZM

Gray-level nonuniformity

0.919

0.896

TexFL9

NGTDM

Busyness

0.911

0.892

  1. LBP local binary pattern, GLCM gray-level co-occurrence matrix, GLRLM gray-level run length matrix, GLSZM gray-level size zone matrix, NGTDM neighboring gray-tone difference matrix.
Back to article page