brain tumer

1

• Brain Tumor Detection Using Convolutional Neural
  Network

• TEAM MEMBERS-
• T. Sai(18121140)
• U.Revanth(18121122)
• S.Darshitha(18121107)

2
Contents 
3
Project objective-

• The main objective of the project is to extract
  brain tumor from 2D Magnetic Resonance brain
  Images (MRI) by Fuzzy C-Means clustering
  algorithm which was followed by traditional
  classifiers and convolutional neural network. 

• Software Required-
• Opencv-python

4
INTRODUCTION-

• Brain tumor is one of the vital organs in the
  human body, which consists of billions of cells.
•  The abnormal group of cell is formed from the
  uncontrolled division of cells, which is also
  called as tumor. 
• Brain MRI image is mainly used to detect the
  tumor and tumor progress modelling process. 
• This information is mainly used for tumor
  detection and treatment processes.
•  MRI image provides detailed information about
  brain structureand anomaly detection in brain
  tissue.

5
Types of Brain Tumer 

•  Brain tumor are divided into two types 
• low grade tumer (grade1 and grade2) 
• Low grade brain tumor is called as benign .
• Benign tumor is not cancerous tumor.
•  Hence it doesnt spread other parts of the
  brains.
• 2.High grade tumer(grade3 and grade4) .
•  The high grade tumor is also called as
  malignant.
• the malignant tumor is a cancerous tumor.
•  So it spreads rapidly with indefinite boundaries
  to other region of the body easily.
•  It leads to immediate death.

6
Process of detecting brain tumer
7
Segmentation processes of an MRI 
8
Deceased and non-deceased brain
9
Accuracy
10
ADVANTAGES-

• It can segment the Brain regions from the image
  accurately.
• It is useful to classify the Brain Tumor images
  for accurate detection.
• Brain Tumor will be detected in an early stages

11
Applications 

• The main aim of the application is
  tumor identification.
• The main reason behind the development of
  this application is to provide proper treatment
  as soon as possible and protect the human life
  which is in danger.
• This application is helpful to doctors as well
  as patient.
• The manual identification is not fast, accurate
  and efficient. to overcome those problem
  this application is design.
• It is user friendly application.

12
THANK YOU