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

TL;DR

This paper presents a deep transfer learning framework using ResNet50 for multi-class brain tumor classification in MRI images, achieving high accuracy on multiple datasets, thus aiding radiologists in diagnosis.

Contribution

The study introduces a novel dataset and demonstrates the effectiveness of deep transfer learning with ResNet50 for brain tumor multi-classification in MRI images.

Findings

Achieved 86.40% accuracy on the curated dataset.

Achieved 93.80% accuracy on Harvard Whole Brain Atlas dataset.

Achieved 97.05% accuracy on the School of Biomedical Engineering dataset.

Abstract

Magnetic Resonance Imaging (MRI) is a principal diagnostic approach used in the field of radiology to create images of the anatomical and physiological structure of patients. 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. The process of interpreting a massive volume of patient's MRI is laborious. Hence, the use of Machine Learning methodologies can aid in detecting abnormalities in soft tissues with considerable accuracy. In this research, we have 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. In this paper, we adopted the Deep Residual Convolutional Neural Network (ResNet50) architecture for the experiments along with 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 dataset, and 97.05% accuracy on the School of Biomedical Engineering dataset. Results of our experiments significantly demonstrate our proposed framework for transfer learning is a potential and effective method for brain tumor multi-classification tasks.