Combining Wavelet Statistical Texture and Recurrent Neural Network for Tumour Detection and Classification Over MRI
Shaik Salma Begum1, D. Rajya Lakshmi2
1Shaik Salma Begum, Research Scholar, Department of Computer Science and Engineering, Jawaharlal Nehru Technology University, Kakinada, (A. P). India.
2Dr. D. Rajya Lakshmi, Principal, University College of Engineering, JNTUK, Narasaraopet, Guntur, (A. P). India.
Manuscript received on February 05, 2019. | Revised Manuscript received on February 14, 2019. | Manuscript published on August 30, 2019. | PP: 3769-3778 | Volume-8 Issue-6, August 2019. | Retrieval Number: F9388088619/19©BEIESP | DOI: 10.35940/ijeat.F9388.088619
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: Brain tumor is one of the major causes of death among other types of the cancer because Brain is a very sensitive, complex and central part of the body. Proper and timely diagnosis can prevent the life of a person to some extent. Therefore, in this paper we have introduced brain tumor detection system based on combining wavelet statistical texture features and recurrent neural network (RNN). Basically, the system consists of four phases such as (i) feature extraction (ii) feature selection (iii) classification and (iii) segmentation. First, noise removal is performed as the preprocessing step on the brain MR images. After that texture features (both the dominant run length and co-occurrence texture features) are extracted from these noise free MR images. The high number of features is reduced based on sparse principle component analysis (SPCA) approach. The next step is to classify the brain image using Recurrent Neural Network (RNN). After classification, proposed system extracts tumor region from MRI images using modified region growing segmentation algorithm (MRG). This technique has been tested against the datasets of different patients received from muthu neuro center hospital. The experimentation result proves that the proposed system achieves the better result compared to the existing approaches.
Keywords: Brain tumor, Wavelet statistical texture, Recurrent neural network, Feature extraction, Segmentation, dominant run length, Co-occurrence texture features.