ABES: attention bi-directional ensemble SVM for early detection of brain tumors

• Published in: Neural computing & applications 2024-09, Vol.36 (26), p.16179-16193
• Main Authors: Subramaniam, Erana Veerappa Dinesh, Krishnasamy, Valarmathi
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Back propagation networks; Brain; Brain cancer; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Datasets; Deep learning; Image Processing and Computer Vision; Machine learning; Neural networks; Optimization; Original Article; Performance evaluation; Performance measurement; Probability and Statistics in Computer Science; Sensitivity analysis; Support vector machines; Tumors
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-09688-w

Brain tumor is the most serious and deadly disease, and it is formed due to abnormal cell production. There are two different sorts of tumors including benign (non-cancerous) and malignant (cancerous), and the third level of a brain tumor is cancerous, which is a highly deadly form of cancer. Detecting brain tumors early is crucial for accurate diagnosis and efficient treatment planning. Although numerous techniques are established, the prediction techniques are time-consuming, have higher computational complexity, prone to overfitting, and have limited accuracy. Thus we proposed an Attention Bi-directional Gated Recurrent Unit Ensemble Support Vector Machine (ABES model) for detecting brain tumors. Here, the Bi-GRU layer learns the most important context information for every image. The attention layer also uses the attention mechanism to assign weights to each Bi-GRU layer output. The ensemble SVM classifier performs the categorization of brain tumors. Then, the training set is used to train the Attention BiGRU model and Ensemble SVM classifiers. The ABES classifier weights are optimized by utilizing the improved whale optimization algorithm. To demonstrate the efficiency of our proposed method, we compare it to four existing methods including Fully Automatic Heterogeneous Segmentation-based Support Vector Machine, Whale Harris Hawks Optimization-based Deep Learning, Machine learning-based back propagation neural networks, and Deep Convolutional Neural Network. Also, the ABES model is validated using the MRI dataset and the Figshare brain tumor dataset. Accuracy, precision, specificity, and sensitivity are the performance metrics used to evaluate classification performance, which achieves 97.2% accuracy, 98.61% Precision, 96.48% Specificity, and 97.34% Sensitivity, respectively.