Detection of abnormal brain in MRI via improved AlexNet and ELM optimized by chaotic bat algorithm

• Published in: Neural computing & applications Vol. 33; no. 17; pp. 10799 - 10811
• Main Authors: Lu, Siyuan, Wang, Shui-Hua, Zhang, Yu-Dong
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2021; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Alzheimer's disease; Artificial Intelligence; Artificial neural networks; Automation; Brain; Brain cancer; Brain diseases; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Deep learning; Discriminant analysis; Experiments; Feature selection; Image Processing and Computer Vision; Machine learning; Magnetic resonance imaging; Medical imaging; Medical research; Neural networks; Probability and Statistics in Computer Science; S. I : Hybridization of Neural Computing with Nature Inspired Algorithms; Signal processing; Special Issue on Hybridization between Neural Computing and Nature Inspired Algorithms for Solving Multi-Criteria Decision-Making Problems; Support vector machines; Tumors; Wavelet transforms; Deep learning; AlexNet; Extreme learning machine; Magnetic resonance image; Computer-aided diagnosis
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-020-05082-4

Computer-aided diagnosis system is becoming a more and more important tool in clinical treatment, which can provide a verification of the doctors’ decisions. In this paper, we proposed a novel abnormal brain detection method for magnetic resonance image. Firstly, a pre-trained AlexNet was modified with batch normalization layers and trained on our brain images. Then, the last several layers were replaced with an extreme learning machine. A searching method was proposed to find the best number of layers to be replaced. Finally, the extreme learning machine was optimized by chaotic bat algorithm to obtain better classification performance. Experiment results based on 5 × hold-out validation revealed that our method achieved state-of-the-art performance.