CNN Based Training and Classification of MRI Brain Images

Brain tumor is nothing but an abnormal growth caused by cells reproducing themselves in an uncontrolled manner. The treatment planning is a key stage to improve the quality of life of oncological patients. In recent years, deep learning has gained a huge fame in solving problems from various fields...

Full description

Saved in:
Bibliographic Details
Main Authors: Bhanumathi, V., Sangeetha, R.
Format: Conference Proceeding
Language:English
Subjects:
Biomedical imaging
Communication systems
Convolution Neural Networks
Deep Learning
Feature extraction
Image segmentation
Magnetic resonance imaging
Training
Tumors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain tumor is nothing but an abnormal growth caused by cells reproducing themselves in an uncontrolled manner. The treatment planning is a key stage to improve the quality of life of oncological patients. In recent years, deep learning has gained a huge fame in solving problems from various fields including Medical Image Analysis. Nowadays, CNN plays a major role in fine tuning and analyzing the brain tumors present in the Magnetic Resonance Imaging (MRI) images. In this paper, we introduced different classification techniques such as Alex Net, Vgg Net and Google Net, for pre-trained and fine tuning process of brain tumor images. For this analysis, the extracted features and the results of the classifiers such as Alex Net, Vgg Net and Google Net are compared the results of proposed technique are validated for its performance and quality for MRI brain images based on iteration, time elapsed and accuracy.
ISSN:2575-7288
DOI:10.1109/ICACCS.2019.8728447