Cumulant Features based Classification of Brain MR Images using ANN and LS-SVM Algorithm
Harikumar Rajaguru1, Sannasi Chakravarthy S R2
1Sannasi Chakravarthy S R, Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, India.
2Harikumar Rajaguru, Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, India.
Manuscript received on 23 August 2019. | Revised Manuscript received on 04 September 2019. | Manuscript published on 30 September 2019. | PP: 4008-4012 | Volume-8 Issue-11, September 2019. | Retrieval Number: K24310981119/2019©BEIESP | DOI: 10.35940/ijitee.K2431.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Automatic classification of magnetic resonance (MR) brain images using machine learning algorithms has a significant role in clinical diagnosis of brain tumour. The higher order spectra cumulant features are powerful and competent tool for automatic classification. The study proposed an effective cumulant-based features to predict the severity of brain tumour. The study at first stage implicates the one-level classification of 2-D discrete wavelet transform (DWT) of taken brain MR image. The cumulants of every sub-bands are then determined to calculate the primary feature vector. Linear discriminant analysis is adopted to extract the discriminative features derived from the primary ones. A three layer feed-forward artificial neural network (ANN) and least square based support vector machine (LS-SVM) algorithms are considered to compute that the brain MR image is either belongs to normal or to one of seven other diseases (eight-class scenario). Furthermore, in one more classification problem, the input MR image is categorized as normal or abnormal (two-class scenario). The correct classification rate (CCR) of LS-SVM is superior than the ANN algorithm thereby the proposed study with LS-SVM attains higher accuracy rate in both classification scenarios of MR images. Keywords:
Keywords: Magnetic resonance, Brain tumour, Cumulant features, Wavelet transform, Linear discriminant analysis, Neural network, Support vector machine (SVM).
Scope of the Article: Software Engineering Decision Support