Tabu Search and Machine-Learning Classification of Benign and Malignant Proliferative Breast Lesions

Table 1

Summary of machine-learning algorithms for breast cancer diagnosis.

Author	Feature	Algorithm	Accuracy (%)	Dataset
Asri et al. [36]	FNA	SVM	97.13	UCI
Ivančáková et al. [28]	FNA	SVM	97.66	WDBC
Mondal et al. [24]	Entropy	SVM	91.5	Gene Expression Omnibus
Ghasemzadeh et al. [30]	Gabor wavelet	SVM	96	Mammography (DDSM)
Ayoub Shaikh and Ali [37]	Wrapper subset eval	SVM	97	Breast Cancer Digital Repository (BCDR)
Wang et al. [18]	Full features	SVM	33.34	SEER
Mengjie Yu [38]	Concave points	SVM	99.77	UCI
Wei et al. [33]	BiCNN	CNN	97	BreaKHis
Bejnordi et al. [39]	Morphology	CNN	92	WSIs
Arau et al. [31]	Full features	CNN	83	Histology Dataset
Yap et al. [16]	FCN-alexnet	CNN	98	B&K Medical Panther 2002 and B&K Medical Hawk 2102 US systems
			92
Ting et al. [21]	Wise	CNN	90.50	Digital Mammogram
Zhou et al. [25]	CNN	CNN	95.8	SWE data
Sun et al. [20]	mRMR	Deep neural network	18.7	METABRIC/MDNNMD
Kaur et al. [40]	CNN	MLP	86	Mini-MIAS
Joshi et al. [22]	Scaling	NN	96.47	WDBC
Radiya-Dixit et al. [34]	Computational method	LR	91.8	BIDMC-MGH
Tahmassebi et al. [29]	Volume distribution	LR	92	WDBC
Braman et al. [41]	Heterogeneity	LR	93	ISPY1-TRIAL
Maysanjaya et al. [42]	Wrapper	NB	99.27.	UCI
Chaurasia et al. [23]	FNA	NB	97.36	WDBC
Tamilvanan [26]	Dimensionality reduction	NB	82	WDBC
Qiao et al. [17]	BI-RADS	AdaBoost	93.48	138 pathologically proven breast tumors
Turkki et al. [32]	Morphological	KNN	95	FinProg
Amrane et al. [19]	FNA	KNN	97.51	WDBC