Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.

Link to publisher's homepage at http://ieeexplore.ieee.org/

Saved in:
Bibliographic Details
Main Authors: Mohammad Khusairi, Osman, Mohd Yusoff, Mashor, Prof. Dr., Hasnan, Jaafar
Other Authors: khusairi@ppinang.uitm.edu.my
Format: Working Paper
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2013
Subjects:
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/26514
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-26514
record_format dspace
spelling my.unimap-265142013-07-08T03:20:48Z Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation. Mohammad Khusairi, Osman Mohd Yusoff, Mashor, Prof. Dr. Hasnan, Jaafar khusairi@ppinang.uitm.edu.my yusoff@unimap.edu.my hasnan@kb.usm.my Clustering Medical image segmentation Thresholding Tissue sections Tuberculosis bacilli Link to publisher's homepage at http://ieeexplore.ieee.org/ Image segmentation is a key step in most medical image analysis. However, the process is particularly difficult due to limitation of the imaging equipments and variation in biological system. Therefore, accurate and robust segmentation are important for quantitative assessment of medical images in order to achieve correct clinical diagnosis. This paper studies the performance of clustering and adaptive thresholding algorithms for segmenting the tuberculosis (TB) bacilli in tissue sections. Images are obtained by analyzing the Ziehl-Neelsen (ZN) stained tissue slide and capturing using a digital camera attached to a light microscope. Three clustering algorithms namely k-mean clustering, moving k-mean clustering and fuzzy c-mean clustering, and two adaptive thresholding algorithms, Otsu and iterative thresholding, are evaluated for segmentation of TB bacilli. The saturation component, derived from C-Y colour model is utilised as input to these algorithms as it provides good separation between the TB bacilli and the background. The segmentation results are further compared with the manual-segmentation image. Acceptable segmentation accuracy of up to 99.00% was achieved by using the clustering algorithms and the Otsu's thresholding. However, k-mean clustering was chosen as it produced the highest TB segmentation rate. 2013-07-08T03:20:48Z 2013-07-08T03:20:48Z 2012-05-14 Working Paper 978-146731550-0 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6220378 http://hdl.handle.net/123456789/26514 en Proceedings of the International Conference on Computer, Information and Telecommunication Systems (CITS 2012) Institute of Electrical and Electronics Engineers (IEEE)
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Clustering
Medical image segmentation
Thresholding
Tissue sections
Tuberculosis bacilli
spellingShingle Clustering
Medical image segmentation
Thresholding
Tissue sections
Tuberculosis bacilli
Mohammad Khusairi, Osman
Mohd Yusoff, Mashor, Prof. Dr.
Hasnan, Jaafar
Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
description Link to publisher's homepage at http://ieeexplore.ieee.org/
author2 khusairi@ppinang.uitm.edu.my
author_facet khusairi@ppinang.uitm.edu.my
Mohammad Khusairi, Osman
Mohd Yusoff, Mashor, Prof. Dr.
Hasnan, Jaafar
format Working Paper
author Mohammad Khusairi, Osman
Mohd Yusoff, Mashor, Prof. Dr.
Hasnan, Jaafar
author_sort Mohammad Khusairi, Osman
title Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
title_short Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
title_full Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
title_fullStr Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
title_full_unstemmed Performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
title_sort performance comparison of clustering and thresholding algorithms for tuberculosis bacilli segmentation.
publisher Institute of Electrical and Electronics Engineers (IEEE)
publishDate 2013
url http://dspace.unimap.edu.my/xmlui/handle/123456789/26514
_version_ 1643794969872302080
score 13.214268