Isolated Convolutional-Neural-Network-Based Deep-Feature Extraction for Brain Tumor Classification Using Shallow Classifier

Abstract

In today's world, a brain tumor is one of the most serious diseases. If it is detected at an advanced stage, it might lead to a very limited survival rate. Therefore, brain tumor classification is crucial for appropriate therapeutic planning to improve patient life quality. This research investigates a deep-feature-trained brain tumor detection and differentiation model using classical/linear machine learning classifiers (MLCs). In this study, transfer learning is used to obtain deep brain magnetic resonance imaging (MRI) scan features from a constructed convolutional neural network (CNN). First, multiple layers (19, 22, and 25) of isolated CNNs are constructed and trained to evaluate the performance. The developed CNN models are then utilized for training the multiple MLCs by extracting deep features via transfer learning. The available brain MRI datasets are employed to validate the proposed approach. The deep features of pre-trained models are also extracted to evaluate and compare their performance with the proposed approach. The proposed CNN deep-feature-trained support vector machine model yielded higher accuracy than other commonly used pre-trained deep-feature MLC training models. The presented approach detects and distinguishes brain tumors with 98% accuracy. It also has a good classification rate (97.2%) for an unknown dataset not used to train the model. Following extensive testing and analysis, the suggested technique might be helpful in assisting doctors in diagnosing brain tumors.

Keywords: brain tumor; machine learning; magnetic resonance imaging (MRI).

Figure 1

Working framework of the proposed approach.

Figure 2

Details about the Kaggle “Brain Tumor Classification (MRI)” dataset [32].

Figure 3

Complete description of the 22-layer CNN model.

Figure 4

The performance comparison of various deep-feature-trained classical classifier models.

Figure 5

Deep-feature vector size comparison of all CNN models. Bold is used to highlight the best results.

Figure 6

Confusion matrix of proposed deep-feature-trained SVM model. Blue color (dark and light) represent the number of correctly classified samples whereas other colors represent the misclassified samples.

Figure 7

Details about the unseen brain MRI dataset used for testing the proposed model [38].

Figure 8

Confusion matrix of the testing of the proposed trained model for an unseen dataset. Blue color (dark and light) represent the number of correctly classified samples whereas other colors represent the misclassified samples.