Involvement of Machine Learning for Breast Cancer Image Classification: A Survey

Table 15

SVM for breast image classification.

Reference	Descriptor	Image type	Number of images	Key findings
Zhang et al. [122]	Fractional Fourier transform information utilized as features	Mammogram	200	They selected ROI for avoiding redundant complexity.; When SVM and Principal Component Analysis were used together the achieved Accuracy, Sensitivity and Specificity are %, % and % respectively.
Shirazi and Rashedi [123]	GLCM	Ultrasound	322	ROI extracted for reducing redundant complexity.; SVM and Mixed Gravitational Search Algorithm (MGSA) used together for feature reduction.; The achieved Accuracy 86.00%; however SVM with MGSA method achieved 93.10% Accuracy.
Sewak et al. [124]	Radius, perimeter, area, compactness, smoothness, concavity, concave points, symmetry, fractal dimension, and texture of nuclei calculated	Biopsies	569	Achieved Accuracy, Sensitivity, and Specificity are 99.29%, 100.00%, and 98.11%, respectively.
Dheeba and Tamil Selvi [125]	The laws texture features utilized	Mammogram	322	The achieved Accuracy is 86.10%.