Detection and Classification of Cancer from Microscopic Biopsy Images Using Clinically Significant and Biologically Interpretable Features

Table 2

Quantitative evaluation of segmentation methods on the basis of average values of various performance metrics for a set of 20 microscopic images [8].

	Accuracy	Sensitivity	Specificity	FPR	PRI	GCE	VOI
Color -means	0.987799	0.707025	0.989218	0.010782	0.975985	0.009205	0.115479
-means	0.990444	0.748991	0.994933	0.005067	0.981119	0.012839	0.10818
FCM	0.987008	0.614717	0.998235	0.001765	0.974447	0.015902	0.136348
Texture based	0.97144	0.306398	0.990445	0.009555	0.944609	0.029276	0.250797