Multi-Classification of Brain Tumor Images Using Transfer Learning Based Deep Neural Network

TL;DR

This paper presents a transfer learning-based deep neural network approach with data augmentation for accurate multi-class brain tumor image classification, achieving over 96% accuracy.

Contribution

It introduces a novel combination of image augmentation, transfer learning with Inception-v3, and customized deep neural network layers for improved brain tumor classification.

Findings

Achieved 96.25% overall accuracy.

Enhanced classification performance over existing methods.

Effective use of transfer learning with customized layers.

Abstract

In recent advancement towards computer based diagnostics system, the classification of brain tumor images is a challenging task. This paper mainly focuses on elevating the classification accuracy of brain tumor images with transfer learning based deep neural network. The classification approach is started with the image augmentation operation including rotation, zoom, hori-zontal flip, width shift, height shift, and shear to increase the diversity in image datasets. Then the general features of the input brain tumor images are extracted based on a pre-trained transfer learning method comprised of Inception-v3. Fi-nally, the deep neural network with 4 customized layers is employed for classi-fying the brain tumors in most frequent brain tumor types as meningioma, glioma, and pituitary. The proposed model acquires an effective performance with an overall accuracy of 96.25% which is much improved than some existing multi-classification methods. Whereas, the fine-tuning of hyper-parameters and inclusion of customized DNN with the Inception-v3 model results in an im-provement of the classification accuracy.