Automatic Spine Tissue Segmentation from MRI Data Based on Cascade of Boosted Classifiers and Active Appearance Model

Table 2

Comparison (percentage) of True Positive Fraction, False Negative Fraction, and False Fraction for automatically segmented data using presented method and manually segmented data from each expert (significance level ). To achieve reliable results a mean value obtained from 100 procedure passes with 25 algorithm iterations each is presented. : standard deviation for True Positive Fraction, : standard deviation for False Negative Fraction, : standard deviation for False Fraction.

	TPF	FNF	FF
Computer				3.42	3.42	3.64
Expert 1				3.32	3.32	4.58
Expert 2				2.98	2.98	3.60
Expert 3				1.56	1.56	4.78
Expert 4				1.33	1.33	5.32
Expert 5				4.81	4.81	4.74