BRAIN TUMOR DETECTION USING DEEP NEURAL NETWORK AND MACHINE LEARNING ALGORITHM

Authors

  • Ruchita Rathod, Dr. Rais Abdul Hamid Khan

Abstract

The determination of tumor extent may be a major challenging task in brain tumor planning and quantitative evaluation. Magnetic Resonance Imaging (MRI) is one among the non-invasive techniques that has emanated as a front- line diagnostic tool for brain tumor without radiation. Deep learning has shown remarkable progress in image-recognition jobs. Works on going from convolutional neural networks (CNN) to variational auto encoders have discovered endless applications in the medical picture investigation field, driving it forward at a fast speed. In radiology, the experienced doctor outwardly assessed clinical pictures for the recognition, portrayal, and observing of illnesses. In this work, automatic brain tumor detection is proposed by using Machine learning and Convolutional Neural Networks (CNN) classification. The deeper architecture design is performed by small kernels. The neuron’s weight is given as small. It is observed that CNN achieves a good rate of accuracy with low complexity as compared to all other  methods. This improved accuracy will help doctors to treat well.

 

Downloads

Download data is not yet available.

Downloads

Published

2021-05-12

How to Cite

Ruchita Rathod, Dr. Rais Abdul Hamid Khan. (2021). BRAIN TUMOR DETECTION USING DEEP NEURAL NETWORK AND MACHINE LEARNING ALGORITHM. PalArch’s Journal of Archaeology of Egypt / Egyptology, 18(08), 1085-1093. Retrieved from https://archives.palarch.nl/index.php/jae/article/view/8814