Accurate Brain Tumor Segmentation and Classification using CNN

Recently, the clinical industry is acquiring required clinical assets by incorporating the Internet of Things [IoT] technology. As a result, treatment is becoming the most effective strategy to address the existence of growth-impaired patients. This growth is being assessed by using a magnetic reson...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohanraj, S., Saran, R. M., Sakthi, R., Shafiq Mohamed, S.
Format: Conference Proceeding
Language:English
Subjects:
Brain tumour
Convolution Neural Network
Convolutional neural networks
Deep learning
Estimation
Image segmentation
Industries
Internet of Things
Magnetic resonance
Magnetic resonance imaging
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, the clinical industry is acquiring required clinical assets by incorporating the Internet of Things [IoT] technology. As a result, treatment is becoming the most effective strategy to address the existence of growth-impaired patients. This growth is being assessed by using a magnetic resonance imaging (MRI) technique. The volume of information provided by MRI prevents actual task grouping, which limits the use of cautious calculable estimations in the clinical CNN (Convolution Neural Network) by examining small 3x3 portions. Little bits allow extremely fine-grained control of a design and reduce overfitting. The proposed technology can quickly handle MRI (Magnetic Resonance Imaging) with a high success rate. Profound learning approaches may also authorize the accurate execution and objective evaluation of the substantial MRI image data.
ISSN:2768-5330
DOI:10.1109/ICICCS53718.2022.9788281