Hierarchical classification strategy for Phenotype extraction from epidermal growth factor receptor endocytosis screening

Table 1 Description of phenotype texture measurements

Feature name	Expression	Description
std	\(f_{1}=\sqrt {\sum \limits _{i}(i-mean)^{2}H\,(i)}\)	The standard deviation of
		intensity from all the pixels
		in a region.
Smoothness	\(f_{2}=1-\frac {1}{(1+{f_{1}^{2}})}\)	The relative smoothness of the
		intensity in a region. It is 0 for a
		region of constant intensity and
		1 for a region with large excursion
		in the values of its intensity levels.
Skewness	\(f_{3}=\sum \limits _{i}(i-mean)^{3}H\,(i)\)	The order moment about the
		mean. The departure from
		symmetry about the mean
		intensity. It is 0 for symmetric
		histograms, positive for
		histograms skewed to the right
		and negative for histograms
		skewed to the left.
Uniformity	\(f_{4}=\sum \limits _{i}H^{2}\,(i)\)	The sum of squared elements in
		Histogram. It reaches maximum
		when all intensity levels are equal
		and decreases from there.
Entropy	\(f_{5}=-\sum \limits _{i}H(i)\log _{2}{H\,(i)}\)	The statistical measure of
		randomness.

ISSN: 1471-2105