Exploring Statistical Parameters of Machine Learning Techniques for Detection and Classification of Brain Tumor
Manu Singh1, Vibhakar Shrimali2

1Manu Singh, Department of Computer Science & Engineering, Guru Gobind Singh Indraprastha University, New Delhi, India.
2Dr. Vibhakar Shrimali, Department of Electronics & Communication Engineering, GB Pant Govt. Engineering College, New Delhi, India.

Manuscript received on 13 August 2019 | Revised Manuscript received on 19 August 2019 | Manuscript published on 30 August 2019 | PP: 4118-4124 | Volume-8 Issue-10, August 2019 | Retrieval Number: J98600881019/2019©BEIESP | DOI: 10.35940/ijitee.J9860.0881019
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: A computerized system can improve the disease identifying abilities of doctor and also reduce the time needed for the identification and decision-making in healthcare. Gliomas are the brain tumors that can be labeled as Benign (non- cancerous) or Malignant (cancerous) tumor. Hence, the different stages of the tumor are extremely important for identification of appropriate medication. In this paper, a system has been proposed to detect brain tumor of different stages by MR images. The proposed system uses Fuzzy C-Mean (FCM) as a clustering technique for better outcome. The main focus in this paper is to refine the required features in two steps with the help of Discrete Wavelet Transform (DWT) and Independent Component Analysis (ICA) using three machine learning techniques i.e. Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine (SVM). The final outcome of our experiment indicated that the proposed computerized system identifies the brain tumor using RF, ANN and SVM with 100%, 91.6% and 95.8%, accuracy respectively. We have also calculated Sensitivity, Specificity, Matthews’s Correlation Coefficient and AUC-ROC curve. Random forest shows the highest accuracy as compared to Support Vector Machine and Artificial Neural Networks.
Keywords: Brain Tumor, Classification, Discrete Wavelet Transform, Independent Component Analysis, Magnetic Resonance Imaging.

Scope of the Article: Classification