A proposed quantitative approach to classify brain MRI

Analysis of magnetic resonance images of brain is done statistically using t test in excel and SPSS. The methodology would help the medical specialists to mechanize the examination of MRI’s of brain to differentiate the tumor from non tumor pictures to upgrade the therapeutic medical considerations....

Full description

Saved in:
Bibliographic Details
Published in:International journal of system assurance engineering and management 2017-11, Vol.8 (Suppl 2), p.577-584
Main Authors: Bhatia, Madhulika, Bansal, Abhay, Yadav, Divakar
Format: Article
Language:English
Subjects:
Brain
Engineering
Engineering Economics
Image analysis
Image classification
Image detection
Image segmentation
Logistics
Magnetic resonance imaging
Marketing
Matlab
Medical imaging
Neurology
Organization
Original Article
Physicians
Pictures
Preprocessing
Quality Control
Reliability
Safety and Risk
Tomography
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Analysis of magnetic resonance images of brain is done statistically using t test in excel and SPSS. The methodology would help the medical specialists to mechanize the examination of MRI’s of brain to differentiate the tumor from non tumor pictures to upgrade the therapeutic medical considerations. Tumor brain images can be classified from non tumor brain MRI images using a novel approach which detect grey matter in MRI images. The basic images preprocessing steps are followed like displaying of grey matter, segmentation, grey matter extraction and all is executed in Matlab environment. Statistical technique like t test in excel and SPSS is performed for classification of brain MRI images on the basis of grey matter extracted is done using Matlab. Our novel approach uses the benefits of existing preprocessing methods and filters available in Matlab for effectual extraction and analysis of brain MRI images. The work has been tested on 50 variables on forty-six subjects. Out of forty-six, twenty-four belong to healthy group and rest twenty-two belong to unhealthy. The work is assessed using t test in SPSS. The brain images are taken from the BRAINIX database and neuroimaging data repository. The proposed algorithm will be an easy approach for doctors and physicians to provide easy option for medical image analysis.
ISSN:0975-6809
0976-4348
DOI:10.1007/s13198-016-0465-8