Breast Cancer Detection with Reduced Feature Set

Table 7

Comparison of the methods and accuracy of previous studies and this study.

Author	Method	Feature number	Accuracy	Sensitivity
Krishnan et al. [36]	40% test data, SVM (poly.)	30	92.62%	92.69%
	40% test data, SVM (RBF)		93.72%	94.50%
Bagui et al. [37]	64% test data, -RNN	30	96.00%	95.09%
	64% test data, -RNN	Best 3	98.10%	98.05%
Sweilam et al. [38]	PSO + SVM	30	93.52%	91.52%
	QPSO + SVM		93.06%	90.00%
Mangasarian et al. [39]	10-CV, MSM-T	Best 3	97.50%	—
Mert et al. [40]	10-CV, PNN	3 (2IC + DWT)	96.31%	98.88%
	LOO, PNN		97.01%	97.78%
Zheng et al. [41]	-SVM	6	97.38%	—
This study	10-CV, -NN	1 feature reduced by ICA	91.03%	94.67%
	40% test, -NN		92.56%	94.02%
	10-CV, ANN		90.50%	96.91%
	40% test, ANN		90.89%	97.00%
	10-CV, RBFNN		90.49%	96.63%
	40% test, RBFNN		89.98%	96.01%
	10-CV, SVM (linear)		90.33%	96.35%
	40% test, SVM (linear)		90.01%	95.00%
	10-CV, SVM (quadratic)		89.98%	95.24%
	40% test, SVM (quadratic)		91.01%	96.42%
	10-CV, SVM (RBF)		90.86%	97.47%
	40% test, SVM (RBF)		91.03%	97.56%