Comparison of Two Convolutional Neural Network Models for Automated Classification of Brain Cancer Types

EasyChair Preprint 4721

Abstract

Background: Convolutional neutral network (CNN) is widely used in the classification of brain cancer types and many architectures of the CNN have been developed. Comparasions of various architectures on a specific clinical task is essential.

Objective: This study aims to compare a deep transfer learning model with AlexNet and GoogleNet architectures for brain tumor classification on the T1-w magnetic resonance imaging (MRI) images.

Material and Methods: The comparison of the AlexNet and the GoogleNet architectures was implemented on the T1-w MRI images with three tumor types: glioma, meningioma and pituitary. The total images were 3,064 consisted of 1,426 gliomas, 708 meningiomas, and 930 pituitaries. 80% of datasets were for training and 20% of datasets were for testing.

Results: It is found that the accuracies for the AlexNet is 94.6% and for the GoogleNet is 92%. The sensitivity, specificity, precision and recall for the AlexNet are 94%, 95.2%, 94.6% and 46.9%, respectively. While sensitivity, specificity, precision and recall for the GoogleNet are 96.3%, 96.8%, 87.3% and 45.9%, respectively.

Keyphrases: Convolutional Neural Network, automatic classification, brain cancer, deep transfer learning model

@booklet{EasyChair:4721,
  author    = {Muhammad Shofi Fuad and Choirul Anam and Kusworo Adi and Geoff Dougherty},
  title     = {Comparison of Two Convolutional Neural Network Models for Automated Classification of Brain Cancer Types},
  howpublished = {EasyChair Preprint 4721},
  year      = {EasyChair, 2020}}