BrainNet: Optimal Deep Learning Feature Fusion for Brain Tumor Classification

• Published in: Computational intelligence and neuroscience Vol. 2022; pp. 1 - 13
• Main Authors: Zahid, Usman, Ashraf, Imran, Khan, Muhammad Attique, Alhaisoni, Majed, Yahya, Khawaja M., Hussein, Hany S., Alshazly, Hammam
• Format: Journal Article
• Language: English
• Published: New York Hindawi 04.08.2022; John Wiley & Sons, Inc; Hindawi Limited
• Subjects: Accuracy; Algorithms; Automation; Brain; Brain cancer; Brain tumors; Classification; Computational neuroscience; Datasets; Deep learning; Machine learning; Magnetic resonance imaging; Mathematical optimization; Medical imaging; Medical imaging equipment; Neural networks; Particle swarm optimization; Support vector machines; Transfer learning; Tumors; Wavelet transforms; United States > US
• ISSN: 1687-5265; 1687-5273
• DOI: 10.1155/2022/1465173

Early detection of brain tumors can save precious human life. This work presents a fully automated design to classify brain tumors. The proposed scheme employs optimal deep learning features for the classification of FLAIR, T1, T2, and T1CE tumors. Initially, we normalized the dataset to pass them to the ResNet101 pretrained model to perform transfer learning for our dataset. This approach results in fine-tuning the ResNet101 model for brain tumor classification. The problem with this approach is the generation of redundant features. These redundant features degrade accuracy and cause computational overhead. To tackle this problem, we find optimal features by utilizing differential evaluation and particle swarm optimization algorithms. The obtained optimal feature vectors are then serially fused to get a single-fused feature vector. PCA is applied to this fused vector to get the final optimized feature vector. This optimized feature vector is fed as input to various classifiers to classify tumors. Performance is analyzed at various stages. Performance results show that the proposed technique achieved a speedup of 25.5x in prediction time on the medium neural network with an accuracy of 94.4%. These results show significant improvement over the state-of-the-art techniques in terms of computational overhead by maintaining approximately the same accuracy.