Portal de Periódicos da CAPES

Convolutional Neural Network for Brain Tumor Analysis Using MRI Images

2019; Engg Journals Publications; Volume: 11; Issue: 1 Linguagem: Inglês

10.21817/ijet/2019/v11i1/191101022

2319-8613

Sourabh Hanwat, Jayanta K. Chandra,

Digital Imaging for Blood Diseases

Brain Cancer is one of the most dangerous problems today.Brain Tumor is controlled growth of cancerous or non-cancerous unhealthy cells in the brain.In the present world brain tumor are a very dangerous disease and the main reason for many deaths.Magnetic Resonance Imaging is mostly used the medical image for the brain tumor analysis.The main objective of the paper is to classify the brain tumor various stages using Convolutional Neural Network algorithmbased on Brain MRI images.Brain tumor analysis is done with the help of Convolutional Neural Network and the work is also compared with another popular machine learning classifier like Random Forest and K Nearest Neighbors.During the comparison, the Convolutional Neural Network is considered as one of the best classifiers for classifying the various stages of a brain tumor.The average accuracy of the brain tumor classification with the help of Convolutional Neural Network classifier is 98% with cross-entropy is 0.097 and validation accuracy is 71% so the Convolutional Neural Network is found to be one of the efficient methods for performing different stages of brain tumor classification.