Journal de recherche sur les tumeurs
Libre accès

Abstrait

Identification of Brain Tumor Detection from MRI Image Using Convolution Neural Network

Sunil Kumar, Renu Dhir, Nisha Chaurasia

The death of the brain tumor patient is increasing day by day due to the proper screening of the tumor in the primary stage. Because it affects the human body’s vital nerve system, a brain tumor or cancer is one of the most deadly types of cancer. The brain is incredibly vulnerable to infections that can impair its functions. Brain cells are sensitive and challenging to regenerate when infected with dangerous diseases. The tumor is classified as benign or malignant tumors. This thesis proposes superior brain tumor detection using CNN approaches based on deep learning techniques to detect and classify benign and malignant tumors. This paper discusses using a Convolution Neural Network (CNN) system to classify different types of brain tumors. We have used performance parameters such as accuracy, precision, and sensitivity for evaluating performance models. The dataset used is a 3064 T MRI images dataset containing Br35H MRI images, and it is divided into 70% training, 15% validation, and 15% testing. The CNN method selects the feature of the Br35H dataset. We achieved a classification accuracy of 99.04 percent and 99.00 percent for validation accuracy.