Skip to main content

Table 2 Radiomic feature selection results based on LASSO

From: Computed tomography-based predictive nomogram for differentiating primary progressive pulmonary tuberculosis from community-acquired pneumonia in children

Region

Features

Group

Filters

p-value

 

X7_fos_maximum

Intensity

X HHL

<0.001***

 

X0_GLCM_maximum_probability

GLCM

X LLL

0.008**

consolidation

X6_GLCM_IMC1

GLCM

X HLH

<0.001***

 

X1_GLRLM_LRLGLE

GLRLM

X LLH

0.002**

 

X1_GLRLM_LRE

GLRLM

X LLH

0.002**

lymph node

Max3D

Shape

NA

<0.001***

Sph_dis

Shape

NA

<0.001***

Compactness1

Shape

NA

<0.001***

Surface_to_volume_ratio

Shape

NA

<0.001***

X2_fos_minimum

Intensity

X HLH

<0.001***

 

X0_GLRLM_LRHGLE

GLRLM

X HHL

<0.001***

  1. NOTE. * denotes p-value< 0.05; ** denotes p-value< 0.01; *** denotes p-value< 0.001