Earticle

초록

영어

Non Cerebral regions affect the accuracy of segmentation process in many automated approaches towards delineating objects of interest. Further this will have its impact on proper diagnosis and treatment planning in many cognitive related disorders. As large volumes of data are produced though medical imaging, fast and accurate processing is much sought. As manual delineation is time taking and unwanted portions need more processing steps, regions like skull should be removed. In the current work, a simple algorithm is proposed that involves modeling of histogram in such a way that only brain tissue is extracted. It will involve deriving two threshold values from the intensity distribution by using Gaussian fit. The significance of Gaussian fit is that it helps in finding the maximum deviation of histogram of given MR image with respect to approximated distribution. The thresholds calculated, partitions the given coronal slice into two regions skull and brain. After a binary mask is generated, a sequence of morphological operations is used to get the final result.

목차

Abstract
 1. Introduction
 2. Literature Review
 3. Proposed Method
  3.1. Threshold Selection
  3.2. Hole filling
  3.3. Morphological Image Processing
 4. Results
 5. Discussion
 6. Conclusions
 References

키워드

저자

• G. L. N. Murthy [ Dept. of ECE, LBRCE, Mylavaram, Andhra Pradesh, India ]
• B. Anuradha [ Dept. of ECE, S.V. University College of Engineering, Tirupati, A.P, India ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Software Engineering and Its Applications

• 간기

  월간

• pISSN

  1738-9984

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605