Classification on Magnetic Resonance Imaging (MRI) Brain Tumour using BPNN, SVM and CNN
Faiyaz Ahmad
Faiyaz Ahmad, Department of Computer Engineering Jamia Millia Islamia , New Delhi.
Manuscript received on 10 August 2019. | Revised Manuscript received on 15 August 2019. | Manuscript published on 30 September 2019. | PP: 8601-8607 | Volume-8 Issue-3 September 2019 | Retrieval Number: C6442098319/2019©BEIESP | DOI: 10.35940/ijrte.C6442.098319
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: In this works, the main objective is to detect the high grade gliomas (HGG) and low grade gliomas (LGG) from Magnetic Resonance Imaging (MRI) Brain Tumour images by applying the efficient image segmentation and classify among them. So hybrid image segmentation techniques applied in this work, first one is canny edge detection which is used to locate the boundary of the image and second is fuzzy c-mean clustering which is used to clubbed together of the similarity intensity value into clusters. Also further eight feature extracted using Intensity based Histogram and GrayLevel Co-occurrence Matrix (GLCM). Now three classifiers learning algorithm applied in this system, first one is backpropogation neural network (BPNN) which consists of multi-layer perceptrons to solve the complex problem for the given inputs. Second one is convolution neural network (CNN) are the part of neural networks which have very effective in areas such as image recognition and image classification. Third is Support vector machine (SVM) which can be used for both classification and regression challenges. Each of one is evaluated performance based on different techniques. It found that SVM and CNN gives 88% accuracy for this work.
Keywords: Gliomas, MRI, GLCM, CNN, SVM, Canny Edge Detection, BPNN
Scope of the Article: Classification