Cell Death State Classification by Using Image Processing Methods
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE credits
Student thesis
Abstract [en]
The cell population is used to determine the effect of a drug to understand the disease mechanisms. Thus the analysis of the population behavior provides new insights in medicine development. This project focuses on developing a simple method for cell images which have low resolution and high complexity. The various techniques such as image thresholding, watershed segmentation, opening, dilation, contrast stretching are applied in segmentation and analysis of the image. The estimate of the cell boundary is done using the nucleus image which is assumed as the central part of the considered cells. The cancer cell images of Scott and White(SW) cel line of Beta Catenin(BC) and Krupel Like Factor(KLF) genes have been analyzed and the corresponding average intensity data of the population and a comparison of the Otsu and Huang thresholding methods has been produced. The softwares used in the project are MATLAB 2014 and ImageJ.
Place, publisher, year, edition, pages
2017.
Keywords [en]
segmentation, gene expression, cancer, watershed, dilation, statistical signicance.
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-14019OAI: oai:DiVA.org:bth-14019DiVA, id: diva2:1082854
External cooperation
Tampere University of Technology
Subject / course
ET2566 Master's Thesis (120 credits) in Electrical Engineering with emphasis on Signal processing
Educational program
ETASX Master of Science Programme in Electrical Engineering with emphasis on Signal Processing
Supervisors
Examiners
2017-03-202017-03-182017-03-20Bibliographically approved