Volume 22, Issue 2 (2-2013)
J Mazandaran Univ Med Sci 2013, 22(2): 59-65 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Emadian O, Taheri-Gorji H, Hadadnia J, Khalilian A. Differentiation cervical epithelial cells by image processing techniques. J Mazandaran Univ Med Sci 2013; 22 (2) :59-65
URL: http://jmums.mazums.ac.ir/article-1-2656-en.html
URL: http://jmums.mazums.ac.ir/article-1-2656-en.html
Abstract: (14781 Views)
Background and purpose: Different patterns of the three main categories of squamous cells in cervical Pap smears specimens partially represent the hormonal status of the patient. So far using the optical microscope for counting and differentiation of the cells due to a lot of wasted time and possible errors have been prevented easy to use it in labs. Thus our objective was to design and implement an accurate and fast assessment device based on image processing techniques to identify and differentiate these cells from each other.
Materials and methods: In this study 20 images of Pap smear slides have been used, that were provided by Liquid based cytology (LBC) method belonging to patients or clients who have been referred to Shahriyar pathology laboratory in Sari. 150 cells from each slide were divided into 50 superficial cells, 50 intermediate cells and 50 parabasal cells under the supervision of pathologist and using MATLAB software and image processing techniques these cells approved and differentiated. Finally, another pathologist blindly confirmed the result of processing of cells for identification accuracy using an optical microscope.
Results: The proposed method is able to identify three cell categories based on the size of the cell nucleus cytoplasm size and their ratio to each other which is called N/C is five times faster than using the conventional light microscope. Kappa coefficient was calculated and was equal to k = 0.981 (P < 0.001) that represents a 98% overlap between the results of the second experienced pathologist observations and our proposed method.
Conclusion: After ensuring the acceptable performance of this approach for detecting and counting the three categories of cervical cells and for the design of a prospective study involving simultaneous measurement of the estrogen and progesterone hormones of patient, we hoped to evaluate the effectiveness of this method as a cheap and quick alternative method to verify the accuracy hormonal status of patients.
Type of Study: Research(Original) |
Subject:
Pathology
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Articles Copyright © The Author(s). Owned by Mazandaran University of Medical Sciences.
Contact Us
Address: Journal Office, Building No. 2, Mazandaran University of Medical Sciences, Moallem Square, Sari.Tel: +98 (011)34484874 Postal code: 48175-866 E-Mail: jmums@mazums.ac.ir Telefax: +98 (011)33262679
