Computer Based Method to Automatically Identify the Regions of Intracerebral Haemorrhage on Diffusion Weighted Magnetic Resonance Images

Supriya Santosh Shanbhag, G. R. Udupi and K. Ranganath
Additional contact information
Supriya Santosh Shanbhag: Department of E&C Gogte Institute of Technology
G. R. Udupi: Department of Computer Science and Engineering, S. G. Balekundri Institute of Technology, Belagavi, Karnataka, India.
K. Ranganath: Ragavs Diagnostic & Research Centre, Jayanagar, Bangalore, India

European Journal of Engineering and Technology Research, 2018, vol. 3, issue 11, 89-94

Abstract: In recent times several methods for automated diagnostic systems have been proposed to overcome the problems faced due to large number of patients, and the necessity of having high accuracy when dealing with a human life. Traditional way of examining the Diffusion Weighted (DW) brain images of the subjects with Intracerebral Haemorrhage (ICH) involves the inspection of specific features, by a human observer. Present work makes an effort to develop a computer based method to automatically identify the regions of ICH on DW brain images of the ICH subjects, and thereby help in transforming the conventional qualitative investigative criteria into a quantitative feature classification problem. In this direction feature extraction techniques, namely Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) are employed to provide description of the significant properties of the DW brain images. Subsequently, K-Nearest Neighbor (KNN) method of image classification is employed to analyze the properties of the extracted features. The maximum classification efficiency of the KNN classifier for the correct output classification of the ICH subjects using DCT method is obtained as 71.50% for k value = 1.00, and using DWT method is obtained as 90.00% for k value = 9.00, respectively. Results imply that the technique proposed in the present work could positively be helpful in the fast diagnosis of the ICH subjects, even in the absence of a medical expert.

Keywords: Automatic Identification; Discrete Cosine Transform; Discrete Wavelet Transform; Diffusion Weighted Images; Intracerebral Haemorrhage; K-Nearest Neighbor; Magnetic Resonance Images (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eu-opensci.org/index.php/ejeng/article/view/60952 Abstract page (text/html)
https://eu-opensci.org/index.php/ejeng/article/download/60952/11973 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:epw:ejeng0:v:3:y:2018:i:11:id:60952

DOI: 10.24018/ejeng.2018.3.11.952

Access Statistics for this article

More articles in European Journal of Engineering and Technology Research from European Open Science
Bibliographic data for series maintained by Support ().