Scribd
Upload
300 views

Brain Tumor ML

The document summarizes a student project on early stage prediction of brain tumors using machine learning. It introduces the students presenting the project, their objective to develop a user-friendly application to predict the chances of developing a brain tumor. It discusses the current process of manual analysis by radiologists, and the need for automated analysis using machine learning given the large number of images. The project involves preprocessing MRI images, segmentation, clustering, training a classification model using Python and related tools, and classifying new images as containing a tumor or not.

Uploaded by

SHREEKANTH B K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
300 views

Brain Tumor ML

The document summarizes a student project on early stage prediction of brain tumors using machine learning. It introduces the students presenting the project, their objective to develop a user-friendly application to predict the chances of developing a brain tumor. It discusses the current process of manual analysis by radiologists, and the need for automated analysis using machine learning given the large number of images. The project involves preprocessing MRI images, segmentation, clustering, training a classification model using Python and related tools, and classifying new images as containing a tumor or not.

Uploaded by

SHREEKANTH B K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

SRI SIDDHARTHA INSTITUTE OF TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE AND


ENGINEERING

Project Phase-1 seminar on


“EARLY STAGE PREDICTION OF BRAIN
TUMOR USING MACHINE LEARNING”

Presented by Under the guidance of


NARENDRA S G (16CS409) Mrs.SOWMYA M N
SAGAR M R (16CS085) Asst. Professor,
SHREEKANTH B K (16CS099) Dept of CSE, SSIT,
THEJAS N M (16CS114) Tumkur.
• INTRODUCTION
• MOTIVATION
• OBJECTIVE
• LITERATURE SURVEY
• SYSTEM DESIGN
• REQUIRED TOOLS
• REFERENCE
• Brain tumor occurs because of anomalous development of cells. Millions of
deaths can be prevented through early detection of brain tumor. Tumours
can start in the brain, or elsewhere in the body can spread to the brain.

• Symptoms include new or increasingly strong headaches, blurred vision, loss


of balance, confusion and seizures. In some cases, there may be no
symptoms.

• According to the American Brain Tumor Association, about 80,000 men,


women, and children were expected to be diagnosed with a primary brain
tumor during 2017.
OBJECTIVE
• To develop a user friendly application model for patient to
predict the chances of getting affected to brain tumor.
• In the present scenario, the
radiologists have to manually
study the tumors with the
available medical imaging tools
and generate a report. The
process is time consuming.

• The task becomes near


impossible when we’re faced
with a massive number of
images, say 10,000 or even
100,000.
PROBLEM STATEMENT
The point of the step is tumor identification in brain MRI
images. we design a system to correctly classify new brain
MRI images into images with tumor and images without
tumor.– reframe the statement
• In “Image Preprocessing and enhancement” by Riddhi.S.Kapse
Preprocessing and enhancement techniques are used to improve the
detection of the suspicious region from Magnetic Resonance Image
(MRI).
The preprocessing and enhancement method consists of two steps:
First the removal of film artifacts such as labels and X-ray marks are
removed from the MRI using tracking algorithm.
Second, the removal of high frequency components using weighted
median filtering technique. -- use IEEE format for references
• In “Segmentation methods” by Dr.S S Salankar, edge-based
segmentation, an edge filter is applied to the image, pixels are
categorized as edge or non-edge depending on the filter output,
and pixels which are not divided by an edge are owed to the
same category
• In “Clustering techniques” by Madhuri.babar :Clustering is a
learning task, where one needs to identify a finite set of categories
known as clusters to categorize pixels.
K-means algorithm is the most well-known and widely-used in
unsupervised clustering technique in partitioned clustering algorithms.
Purpose of this algorithm is to minimize the distances of all the
elements to their cluster centres.
Brain MRI Image Processing
images

Image dataset
Training Testing
data data

Learning
algorithm

Classification
Image input Predicted output
model
• Language used is Python.
• Matlab for image smoothing, enhancement,resizing.
• Scikit-image is a python package links with other python modules l
ike Numpy,Scipy for reading and writing images, displaying image
s, basic manipulations, filtering images, extracting features.
• ScikitLearn is a python library for machine learning which is used
to build models and has efficient tools for classification .
•Requires more information regarding your progress in the project.
Also mention in what stage you are in right now.
• Annapa V N Reddy, Chitta venkata phani krishna,” CONTENT B
ASED IMAGE RETRIEVAL FOR DETECTING BRAIN TUMOR”.
• Nameirakpam Dhanachandra, ”Image Segmentation using K-means
Clustering Algorithm”, National Institute of Technology, Manipur
• “Detection of Brain Tumor from MRI Images”, Riddhi.S.Kapse , Dr.
S.S. Salankar, Madhuri.Babar
• “A survey on detection of brain tumor from MRI brain images”, S U
Swathy ; G. Glan Deva Dhas ; S S Kumar
• “Brain Tumor Detection based on Machine Learning Algorithms “,
Komal Sharma, Akwinder Kaur, Shruti Gujral

You might also like