An Optimized Machine Learning Approach for MRI Brain Image classification

The unprecedented improvements in computing capabilities and the introduction of advanced techniques for the analysis, interpretation, processing, and visualization of images have greatly diversified the domain of medical sciences and resulted in the field of medical imaging. The Magnetic Re

Project Title

An Optimized Machine Learning Approach for MRI Brain Image classification

Project Area of Specialization

Artificial Intelligence

Project Summary

The unprecedented improvements in computing capabilities and the introduction of advanced techniques
for the analysis, interpretation, processing, and visualization of images have greatly diversified the domain
of medical sciences and resulted in the field of medical imaging. The Magnetic Resonance Imaging (MRI),
an advanced imaging technique, is capable of producing high quality images of the human body including
the brain for diagnosis purposes. This paper proposes a simple but efficient solution for the classification
of MRI brain images into normal, and abnormal images containing disorders and injuries. It uses images
with brain tumor, acute stroke and alzheimer, besides normal images, from the public dataset developed by
harvard medical school, for evaluation purposes. The proposed model is a four step process, in which the
steps are named: 1). Pre-processing, 2). Features Extraction, 3). Features Reduction, and 4). Classification.
Median filter, being one of the best algorithms, is used for the removal of noise such as salt and pepper, and
unwanted components such as scalp and skull, in the pre-processing step. During this stage, the images are
converted from gray scale to colored images for further processing. In second step, it uses Discrete Wavelet
Transform (DWT) technique to extract different features from the images. In third stage, Color Moments
(CMs) are used to reduce the number of features and get an optimal set of characteristics. Images with the
optimal set of features are passed to different classifiers for the classification of images.
 

Project Objectives

The main objectives are as follows:
1) classification of images with an accuracy almost the
same or even slightly better than other classifiers and
that too with a set of only nine parameters.
2) reduction the complexity of the proposed method compared with other techniques as it processes each image
against a limited set of features.
 

Project Implementation Method

One real world dataset is used in proposed work, which was
taken from the Harvard Medical School . The proposed
model used in the research have
four (4) phases which are pre-processing, features extraction,
features reduction and classification. Features are extracted
in feature extraction stage from brain MRI images for their
potential use in characterizing them, which are, then, used in
our research work. Recent studies suggested that ANN and
hybrid classification techniques are most suitable methods
for classification due to their high accuracy rates. This article
presents our investigations for the classification of MRI brain
images on well-known classification techniques . To the best of our knowledge, no classification technique has been used with an
optimal set of only nine features. For the classification of
MRI brain images into normal and abnormal groups, the
proposed model and the classification techniques that it uses,
have proved best in terms of accuracy compared with similar
techniques found in the Literature.

Benefits of the Project

The robotized classification of images, obtained from Magnetic Resonance Imaging (MRI), is a critical proce-dure and for this reason, a number of classification strategies
are developed in the most recent decades. It plays a vital
role in analyzing and examining human mind. Brain MRI
has significantly enhanced the findings and treatments of
cerebrum pathology due to rich data, it produces, about the
delicate tissue life structures. The non-obtrusive and torment
free properties of cerebrum MRI get the consideration of
scientists and clinicians.
Brain MRI provides better results, when it is contrasted
with other imaging modalities such as Computed Tomography (CT), Positron Emanation Tomography (PET), where
delicate tissue outline is important. Manual review of cerebrum MRI is a hectic job due to huge amount of information,
it contains. To overcome this issue, automatic methods are
introduced for the examination of brain MRI images

Technical Details of Final Deliverable

The final deliverable will be flutter app which will tell whether the uploaded MRI image is normal or abnormal

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

IT , Medical , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Artificial Intelligence(AI), Big Data

Sustainable Development Goals

Good Health and Well-Being for People, Industry, Innovation and Infrastructure, Partnerships to achieve the Goal

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com