Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and Jaya algorithm

• Published in: Multimedia tools and applications Vol. 77; no. 17; pp. 22629 - 22648
• Main Authors: Zhang, Yu-Dong, Zhao, Guihu, Sun, Junding, Wu, Xiaosheng, Wang, Zhi-Heng, Liu, Hong-Min, Govindaraj, Vishnu Varthanan, Zhan, Tianmin, Li, Jianwu
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2018; Springer Nature B.V
• Subjects: Algorithms; Brain; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Genetic algorithms; Image detection; Machine learning; Medical imaging; Multimedia Information Systems; Neural networks; Oversampling; Particle swarm optimization; Special Purpose and Application-Based Systems; Wavelet analysis; Jaya algorithm; Pathological brain detection; Extreme learning machine; Synthetic minority oversampling
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-017-5023-0

Pathological brain detection is an automated computer-aided diagnosis for brain images. This study provides a novel method to achieve this goal.We first used synthetic minority oversampling to balance the dataset. Then, our system was based on three components: wavelet packet Tsallis entropy, extreme learning machine, and Jaya algorithm. The 10 repetitions of K-fold cross validation showed our method achieved perfect classification on two small datasets, and achieved a sensitivity of 99.64 ± 0.52%, a specificity of 99.14 ± 1.93%, and an accuracy of 99.57 ± 0.57% over a 255-image dataset. Our method performs better than six state-of-the-art approaches. Besides, Jaya algorithm performs better than genetic algorithm, particle swarm optimization, and bat algorithm as ELM training method.