Improved Classification of Brain Tumor in MR Images using RNN Classification Framework
K.Kalaiselvi1, C. Karthikeyan2, M. Shenbaga Devi3, C. Kalpana4
1K.Kalaiselvi*, Dept of CSE, Karpagam Institute of Technology, India
2C. Karthikeyan, Dept of CSE, Karpagam Institute of Technology, India
3M. Shenbaga Devi, Dept of CSE, Karpagam Institute of Technology, India
4C. Kalpana, Dept of CSE, Karpagam Institute of Technology, India
Manuscript received on December 15, 2019. | Revised Manuscript received on December 22, 2019. | Manuscript published on January 10, 2020. | PP: 1098-1101 | Volume-9 Issue-3, January 2020. | Retrieval Number: C7983019320/2020©BEIESP | DOI: 10.35940/ijitee.C7983.019320
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Classification of brain tumor for medical applications is considered as an important constraint in computer-aided diagnosis (CAD). In this paper, we study the classification of brain tumor by considering the constraint as a classification problem in order to segregate the tumors among pituitary tumors, gliomatumorand meningioma tumor. This method adopts deep learning principle to extract the brain features from the MRI images. In this study, Recurrent Neural Network is used to classify the extracted features from brain. The experiments are carried out in terms of three fold crossvalidation process over MRI brain image dataset. The results show that the proposed RNN classifier classifies the brain tumors effectively with 98% of mean classification accuracy than other existing methods.
Keywords: Brain Tumor Classification, RNN, CAD, Classification
Scope of the Article: Classification