Hybrid Deep Learning Models for Multi-classification of Tumour from Brain MRI

Abstract

Background: Brain tumour categorisation can be assisted with computer-aided diagnostic (CAD) for medical applications. Biopsies to classify brain tumours can be costly and time-consuming. Radiologists may also misclassify brain tumour types when handling large amounts of data with multiple classes. In this case, technological advancements and machine learning can help. Objective: This study proposes hybrid deep learning approaches for classifying brain tumours using convolutional neural networks (CNN) and machine learning (ML) classifiers. Methods: A new 23-layer CNN architecture is developed for brain deep feature extraction from magnetic resonance imaging (MRI). Random forest (RF) and support vector machine (SVM) classifiers are then used to evaluate the extracted in-depth features from the flattened layer of the CNN model. This study is unique because it employs CNN, CNN-RF, CNN-SVM, and tuned Inception V3 deep learning models on multi-class brain MRI datasets. The proposed hybrid method is run on two publicly available datasets. Results: Among the four models, the CNN-RF model achieves 96.52% accuracy on the Fig share 3c dataset, while the CNN-SVM model achieves 95.41% accuracy on the large Kaggle 4c dataset with four classes (glioma, meningioma, normal, pituitary). Conclusion: Experimental outcomes show that the hybrid techniques can significantly enhance the classification performance, especially on multi-class datasets (glioma, meningioma, normal, pituitary). This study also examines the various weight strategies for dealing with overfitting analytics.   Keywords: Brain Tumour, Convolutional Neural Network, Feature Extraction, Multi-Classification, Machine Learning Classifiers