Authors: Nilesh Bhaskarrao Bahadure; Arun Kumar Ray; Har Pal Thethi
Addresses: School of Electronics Engineering, Kalinga Institute of Industrial Technology (KIIT) University, Bhubaneswar, Odissa, India ' School of Electronics Engineering, Kalinga Institute of Industrial Technology (KIIT) University, Bhubaneswar, Odissa, India ' Department of Electronics & Telecommunication Engineering, Lovely Professional University (LPU), Jalandhar, Punjab, India
Abstract: In this study, we have presented image analysis for the brain tumour segmentation and detection based on Berkeley wavelet transformation, enabled by genetic algorithm and support vector machine. The proposed system uses double classification analysis to conclude tumour type. The proposed system also investigated auto-report generation technique using user-friendly graphical user interface in MATLAB. The experimental results of proposed technique is been evaluated and validated for performance and quality analysis on magnetic resonance (MR) medical images based on accuracy, sensitivity, specificity and dice similarity index coefficient. The experimental results achieved 97.77% accuracy, 98.98% sensitivity, 94.44% specificity and an average of 0.9849 dice similarity index coefficient, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from MR images. The experimental result is validated by extracting 89 features and selecting the relevant features appropriately using genetic algorithm optimise by support vector machine.
Keywords: Berkeley wavelet transformation; feature extraction; genetic algorithm; magnetic resonance imaging; MRI; support vector machine.
International Journal of Biomedical Engineering and Technology, 2020 Vol.32 No.3, pp.246 - 266
Received: 28 Mar 2017
Accepted: 04 Jun 2017
Published online: 19 Mar 2020 *