Retrospective Study
Copyright ©The Author(s) 2022.
World J Clin Oncol. Aug 24, 2022; 13(8): 702-711
Published online Aug 24, 2022. doi: 10.5306/wjco.v13.i8.702
Table 1 Explanation of geometric, sharpness, color and color texture variables studied[7]
Geometry variablesAreaLesion surface area, measured in cm2
Maximum diameterThe longest line that joins two points on the border of the lesion, measured in cm
Perimeter Total boundary length of the region of interest (i.e. lesion), measured in cm
Circularity Ratio of the perimeter of the lesion divided by the perimeter of a circle with the same midpoint and same area as the lesion
Mean radius (Rm)Mean value of the lesion’s radii
Standard deviation of RmStandard deviation of the mean radius
Coefficient of variation of RmExpresses the standard deviation as a percentage of the mean
EccentricityDistance between color and geometric midpoint within the lesion
Eccentricity ratioDistance between midpoint and color midpoint expressed as a fraction of the maximum diameter
Sharpness variablesSD of gray intensityIntensity of gray on the border of the lesion
Coefficient of variation of SD of gray intensitySD of gray intensity in grayscale image. The higher the value, the more discrete the lesion is from the surrounding normal skin (Manousaki et al[7], 2016)
Color texture variablesGrayscale lacunarity of lesion (Lac gray) It is estimated in grayscale image and assesses image texture heterogeneity or incomplete space filling within the lesion
Color variablesRange of gray, red, green, blueRange of values of gray, red, green, blue intensity
Mean gray, red, green, blueMean value of gray, red, green, blue intensity within the lesion
SD of gray, red, green, blueStandard deviation of gray, red, green, blue intensity within the lesion
Coefficient of variation of gray, red, green, blueExpresses the standard deviation of gray, red, green, blue intensity values as mean percentage
Skewness from Gaussian curve (gray, red, green, blue)Deviation of each color’s histogram from the normal distribution curve
Table 2 Demographic, clinical and image processing characteristics of melanoma patients with positive and negative sentinel lymph node biopsy
Study group, SLNB+; n = 20
Control group, SLNB-; n = 79
P value
Male12 (60%)40 (50%)0.62
Female8 (40%)39 (50%)
Age (yr)61 (13)68 (15)0.05
Tumor thickness (mm)2.6 (2.7)2.2 (3.0)0.64
Subtype Superficial spread3 (15%)44 (56%)0.04
Nodular10 (50%)25 (32%)
Secondary nodular7 (35%)10 (12%)
Geometric variables
Area (cm2)3.4 (2.9)2.8 (4.7)0.49
MaxD (cm)2.4 (1.2)2 (1.1)0.22
Perimeter (cm)6.6 (3.0)5.7 (3.3)0.25
Circularity (ratio)1.1 (0.1)1.1 (0.1)0.44
Rm (cm)0.98 (0.5)0.84 (0.5)0.21
SDRm0.14 (0.1)0.12 (0.1)0.48
CVRm13 (7.1)13 (5.5)0.88
Delta (cm)0.04 (0.03)0.03 (0.03)0.04
Delta ratio1.8 (0.9)1.6 (1.3)0.42
Sharpness variables
Sharpness31 (9)26 (8)0.02
CV sharpness22 (6)18 (7)0.02
Color texture variables
Lac gray2 (0.28)1.97 (0.30)0.65
Color variables
Mean gray104 (21)113 (24)0.12
SD gray32 (6)30 (7)0.12
CV gray8 (2)10 (1)0.07
Range gray201 (21)187 (32)0.03
Skewness gray0.52 (0.5)0.23 (0.6)0.03
Mean red144 (26)157 (32)0.06
SD red37 (9)33 (11)0.14
CV red27 (10)23 (11)0.14
Range red205 (23)190 (37)0.04
Skewness red0.03 (0.43)-0.04 (0.83)0.003
Mean green89 (23)96 (23)0.24
SD green33 (7)31 (6)0.19
CV green39 (12)35 (13)0.13
Range green209 (24)195 (33)0.04
Skewness green0.64 (0.46)0.41 (0.60)0.08
Mean blue87 (22)94 (25)0.22
SD blue33 (7)31 (6)0.24
CV blue40 (10)35 (13)0.14
Range blue218 (23)201 (34)0.02
Skewness blue0.67 (0.47)0.42 (0.56)0.05
Table 3 Multivariate analysis of univariately significant predictors of a positive sentinel lymph node result
Coefficient (β)
Standard Error
Wald χ2
P value
Odds ratio
Age- to 0.99
Subtype, nevus-associated2.651.284.280.03814.191.15 to 174.76
Subtype, nodular2.371.015.510.01910.711.48 to 77.48
Subtype, secondary nodular2.901.087.220.00718.212.19 to 151.22
Eccentricity0.380.137.840.0051.461.12 to 1.89