Review Article

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

Table 10

Convolutional Neural Network.

ReferenceDescriptorImage typeNumber of imagesKey findings

Albayrak and Bilgin [86] Global FeaturesHistopathology100 Cluster-based segmentation has been performed to find out the cellular structure.
Blob analysis has been performed on the segmented images.
To reduce the high dimensionality, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) methods have been utilized.
Before the dimensionality reduction the Precision, Recall, and -score values were 97.20%, 66.00%, and 0.78%, respectively, but when the dimensionality reduction method was utilized the Precision, Recall, and -score values were 100.00%, 94.00%, and 0.96%, respectively
The best average Accuracy is 73.00% (without dimensionality reduction) and 96.8% (with dimensionality reduction).

Jiao et al. [87] Global and Local Features.Mammogramā€” They performed their experiments on the DDSM database.
Total required parameter is and time for the per image processing is 1.10 ms.
The best classification achieved is 96.70%; however they show that when they utilize the VGG model the Accuracy was 97.00% which is slightly better than their model.
However in terms of memory size and time per image processing their model gives better performance than the VGG model.

Zejmo et al. [88] Global FeaturesCytology40 GoogleNet and AlexNet models have been utilized.
The best Accuracy obtained when they utilized GoogleNet model was 83.00%.