Optimization of CNN Model for Breast Cancer Classification

Mikhailov N., Shakeel M., Urmanov A., Lee M., Demirci M. F.

16th International Conference on Electronics Computer and Computation, ICECCO 2021, Kaskelen, Kazakhstan, 25 - 26 November 2021, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/icecco53203.2021.9663847
  • City: Kaskelen
  • Country: Kazakhstan
  • Keywords: activation function, breast cancer, convolutional neural network, data balancing, deep learning
  • Ankara Yıldırım Beyazıt University Affiliated: No

Abstract

© 2021 IEEE.Application of deep learning techniques for breast cancer classification using histopathology images has gained interest during recent years. In this study, an open-source convolutional neural network (CNN) model developed for breast cancer classification model is optimized by performing sensitivities on various CNN parameters such as data balancing, activation functions and adding/removing CNN layers. Some of the parameters are less-sensitive in affecting model's performance. The results show that by balancing the number of positive and negative samples, accuracy of the model can be improved. However, some additional work is required to reach to that point. Furthermore, the computation time is reduced by almost 30% by increasing the learning rate from 0.01 to 0.05 while the training and validation accuracy and loss are comparable to that of the original CNN model.