Age groups related glioblastoma study based on radiomics approach

Figures & data

Table 1. Patients characteristics.

Characteristics	n	Percentage
Gender
Male	59	64.5%
Female	37	38.5%
Age group (range from 27 to 78 years old)
<45 years old	29	30.2%
≥45 years old	67	69.8%

Table 2. List of customized features.

Feature name		n
Intensity		21
T-energy	H-entropy
T-kurtosis	T-max
T-mean abosolute deviation	T-mean
T-media	T-min
T-range	T-root mean square
T-skewness	Standard-deviation
H-uniformity	T-variance
Gauss-fitting^a	Gauss-fitting^b
Gauss-fitting^c	H-mean
H-variance	H-skewness
H-kurtosis
Shape		15
Compactness	Compactness-square
Max-length	Disproportion
Sphericity	Superificial-area
Surface to volume ratio	Volume
Region to bounding-box ratio	Max major-length
Min minor-length	eccentricity
Orientation	Solidity
Fourier-descriptors
Texture
GLCMa		8
Energy	Contrast
Correlation	Homogeneity
Variance	Sum average
Entropy	Dissimilarity
GLRLMb		13
Short run emphasis	Long run emphasis
Gray-level nonuniformity	Run-length nonuniformity
Run percentage	Low gray-level run emphasis
High gray-level run emphasis	Short run low gray-level emphasis
Short run high gray-level emphasis	Long run low gray-level emphasis
Long run high gray-level emphasis	Gray-level vaiance
Run-length variance
GLSZMc		13
Small zone emphasis	Large zone emphasis
Gray-level nonuniformity	Zone-size nonuniformity
Zone percentage	Low gray-level zone emphasis
High gray-level zone emphasis	Small zone low gray-level emphasis
Small zone high gray-level emphasis	Large zone low gray-level emphasis
Large zone high gray-level emphasis	Gray-level variance
Zone-size variance
NGTDM^d		5
Coarseness	Contrast
Busyness	Complexity
Strength
Wavelet decomposition		480
LLL decomposition	HLL decomposition
LHL decomposition	HHL decomposition
LLH decomposition	HLH decomposition
LHH decomposition	HHH decomposition
Total of customized features		555

^aGLCM: Gray-level co-occurrence matrix.

^bGLRLM: Gray-level run-length matrix.

^cGLSZM: Gray-level size zone matrix.

^dNGTDM: Neighborhood gray-tone difference matrix.

Figure 1. An example of segmentation result of glioma. (a) Segmentation results of a piece of T1 Contrast MRI image and (b) segmentation results in three dimensions.

Figure 2. Boxplot result of a remarkable feature. (p value =0.001).

Table 3. Five highly correlated features to age group.

Feature	p value
Kurtosis of decomposition HLH (feature 378)	.001
Minimum of intensity (feature 8)	.003
Kurtosis of decomposition LLL (feature 138)	.003
Histogram skewness of decomposition LHH  (feature 448)	.003
Long run high gray-level emphasis of decomposition  of HHL (feature 295)	.004

Figure 3. Radiomics heat map. (a) Unsupervised hierarchical clustering of 101 image features from 96 glioblastoma patients. Quantitative imaging features were normalized [0, 1], then clustered linking with Euclidean metric distance. (b) Selected radiomics features corresponding to the age group. (c) Cluster results show strong consistency with age grouping (T test, p value =0.006).