Title :
Study on quantitative measurement of chromatin size of cervical cell images
Author :
Jing Rui Tang;Nor Ashidi Mat Isa;Ewe Seng Ch´ng
Author_Institution :
Imaging and Intelligent Systems Research Team (ISRT), School of Electrical and Electronic Engineering, Universiti Sains Malaysia, 14300 Nibong Tebal, Pulau Pinang, Malaysia
Abstract :
Changes in the morphology of the cell nucleus are the main interest of the cytotechnologists during diagnostic and change in nucleus chromatin is the hall mark of the malignant nucleus. In this study, Fuzzy C-Means clustering technique is implemented to segment the chromatin from the cervical cell nucleus. The size of the chromatin is studied thoroughly to investigate and further quantify the relationship between the classification of cervical cell and the size of the chromatin. The sample images in this study, capturing from ThinPrep slides, include cases reported as negative for intraepithelial lesion and malignancy (NILM), low-grade squamous intraepithelial lesions (LSIL) and high-grade squamous intraepithelial lesions (HSIL). Simulation results reveal significant difference in chromatin size for these three classes. The results suggest that a computer-aided tool which is capable to analyse the images would be useful to assist in quantifying the criteria for cervical cell classification.
Keywords :
"Standards","Image segmentation","Lesions","Cervical cancer","Area measurement","Size measurement"
Conference_Titel :
Technology, Informatics, Management, Engineering & Environment (TIME-E), 2015 International Conference on
DOI :
10.1109/TIME-E.2015.7389740