Deep Transfer Learning for Brain Magnetic Resonance Image Multi-class Classification

Authors

  • Yusuf Brima Department of Computer Science and Engineering, University of Dhaka, Dhaka-1000, Bangladesh
  • Mosaddek Hossain Kamal Tushar Department of Computer Science and Engineering, University of Dhaka, Dhaka-1000, Bangladesh
  • Upama Kabir Department of Computer Science and Engineering, University of Dhaka, Dhaka-1000, Bangladesh
  • Tariqul Islam National Institute of Neuroscience and Hospital, Dhaka, Bangladesh

DOI:

https://doi.org/10.3329/dujase.v6i2.59215

Keywords:

Brain Tumor; CAD; Convolutional Neural Network (CNN); Computer Vision; Deep Transfer Learning; Magnetic Resonance Imaging (MRI).

Abstract

Magnetic Resonance Imaging (MRI) is a principal diagnostic approach used in radiology to create images of a patient’s anatomical and physiological structures. MRI is the prevalent medical imaging practice to find abnormalities in soft tissues. Traditionally they are analyzed by a radiologist to detect abnormalities in soft tissues, especially the brain. However, the process of interpreting a massive volume of a patient's MRI is laborious. Hence, Machine Learning methodologies can aid in detecting abnormalities in soft tissues with considerable accuracy. This research has curated a novel dataset and developed a framework that uses Deep Transfer Learning to perform a multi-classification of tumors in the brain MRI images. This paper adapted the Deep Residual Convolutional Neural Network (ResNet-50) architecture for the experiments and discriminative learning techniques to train the model. Using the novel dataset and two publicly available MRI brain datasets, this proposed approach attained a classification accuracy of 86.40% on the curated dataset, 93.80% on the Harvard Whole Brain Atlas 97.05% accuracy on the School of Biomedical Engineering dataset. Our experimental results demonstrate the proposed framework for transfer learning is a potential and effective method for brain tumor multi-classification tasks.

DUJASE Vol. 6 (2) 14-29, 2021 (July)

Abstract
119
PDF
86

Downloads

Published

2022-06-15

How to Cite

Brima, Y. ., Kamal Tushar, M. H., Kabir, U. ., & Islam, T. (2022). Deep Transfer Learning for Brain Magnetic Resonance Image Multi-class Classification. Dhaka University Journal of Applied Science and Engineering, 6(2), 14–29. https://doi.org/10.3329/dujase.v6i2.59215

Issue

Section

Articles