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

Table 18

Bayesian classifier.

Reference	Descriptor	Image type	Number of images	Key findings
Benndorf et al. [136]	BI-RADS features utilized.	—	2766	For the training data the AUC value is 0.959 for the inclusive model, whereas AUC value is 0.910 for the descriptor model.
Rodríguez-López and Cruz-Barbosa [137]	Eight image feature nodes utilized.	—	—	NB model obtained 79.00% Accuracy, 80.00% Sensitivity.
Nugroho et al. [138]	Eight image feature nodes utilized.	Mammogram	—	Naive Bayes model along with SMO; obtained ROC value is 0.903.; Bayesian Network model along with SMO; obtained Accuracy was 83.68%.
Rodríguez-López and Cruz-Barbosa [139]	Eight image features have been; utilized.	—	231	Bayesian Network model obtained 82.00% Accuracy, 80.00% Sensitivity, and 83.00% Specificity when they utilized only three features.
Shivakumari et al. [140]		—	231	Analyze the Ljubljana breast image dataset.; NB algorithm along with feature ranking techniques; the best achieved Accuracy was %.
Rodríguez-López and Cruz-Barbosa [141]	Seven different clinical features extracted.	Mammogram	690	Obtained Accuracy, Sensitivity, and Specificity are 82.00%, 80.00%, and 83.00%, respectively.