Multiple Classifier Framework System for Fast Sequential Prediction of Breast Cancer using Deep Learning Models

Abstract

A multiway classification model based on CNN is proposed in this paper for Breast Cancer Histopathalogy images of varied magnification level (40X, 100X, 200X, 400X) consisting of total 8 sub-classes (4 Benign and 4 malignant). The study describes the performance metrics when the Dynamic Selection of Classifiers (DSC) methodology was used in the Multiple Classifier Framework System (MCFS) instead of the traditional way of approaching the problem which treats all the sub-classes individually. The obtained metrics suggest that the DSC approach is safer as it firstly classifies the histopathology image as Benign or Malignant which significantly reduces the risk of misclassification. The next classifier then classifies the image into one of subsequent sub-classes in benign and malignant category to provide a secondary opinion to the pathologist such that relevant pathology tests can be performed. Furthermore, the data augmentation strategies applied (such as -Horizontal flip, Vertical Flip, Random Zoom, Random Rotations) to the existing dataset for class balancing seems to show no improvement when the models were trained using the augmented dataset. For evaluating their performances various metrics such as precision, sensitivity, F-score etc. are used.