Abstract

Introduction: Brain image segmentation is one of the most important clinical tools used in radiology and radiotherapy. But accurate segmentation is a very difficult task because these images mostly contain noise, inhomogeneities, and sometimes aberrations. The purpose of this study was to introduce a novel, locally statistical active contour model (ACM) for magnetic resonance image segmentation in the presence of intense inhomogeneity with the ability to determine the position of contour and energy diagram. 

Methods: A Gaussian distribution model with different means and variances was used for inhomogeneity, and a moving window was used to map the original image into another domain in which the intensity distributions of inhomogeneous objects were still Gaussian but were better separated. The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field by the original signal within the window. Then, a statistical energy function is defined for each local region. Also, to evaluate the performance of our method, experiments were conducted on MR images of the brain for segment tumors or normal tissue as visualization and energy functions. 

Results: In the proposed method, we were able to determine the size and position of the initial contour and to count iterations to have a better segmentation. The energy function for 20 to 430 iterations was calculated. The energy function was reduced by about 5and 7% after 70 and 430 iterations, respectively. These results showed that, with increasing iterations, the energy function decreased, but it decreased faster during the early iterations, after which it decreased slowly. Also, this method enables us to stop the segmentation based on the threshold that we define for the energy equation.

Conclusion: An active contour model based on the energy function is a useful tool for medical image segmentation. The proposed method combined the information about neighboring pixels that belonged to the same class, thereby making it strong to separate the desired objects from the background.

 

Keywords: image segmentation; active contour model; intensity inhomogeneity; energy function; brain MRI
 
» HTML Fulltext    » PDF Fulltext    » doi: 10.19082/2443

Latest Issue:

In October-December 2018, the journal publishes several original research, including an outstanding Prospective Cohort Study, some experimental studies, and an editorial on a topic of current interest in today’s medical research. Read more:


 

The 6th World Conference on Research Integrity (WCRI) is to be held on June 2-5, 2019 in Hong Kong.

The WCRI is the largest and most significant international conference on research integrity. Since the first conference in Lisbon in 2007, it has given researchers, teachers, funding agencies, government officials, journal editors, senior administrators, and research students opportunities to share experiences and to discuss and promote integrity in research. Read more:


 

TDR Clinical Research and Development Fellowships

Call for applications

Deadline for submission: 7 March 2019, 16:00 (GMT)

TDR provides fellowships for early- to mid-career researchers and clinical trial staff (e.g. clinicians, pharmacists, medical statisticians, data managers, other health researchers) in low- and middle-income countries (LMICs) to learn how to conduct clinical trials. Read more:


Meta-Analysis Workshops in New York, USA, and London, UK, in April and May 2019

Don't miss this exceptional opportunity to learn how to perform and report a Meta-analysis correctly. Two Meta-analysis workshops are organized in April and May 2019 by Dr. Michael Borenstein in New York, USA (April 08-10, 2019) and London, UK (May 27-29).

About the Instructor

Dr. Michael Borenstein, one of the authors of Introduction to Meta-Analysis, is widely recognized for his ability to make statistical concepts accessible to researchers as well as to statisticians. He has lectured widely on meta-analysis, including at the NIH, CDC, and FDA. Read more: