Automatic detection system of cervical cancer cells using color intensity classification

Authors:
Eko Supriyanto;Nur Azureen M. Pista;Lukman Hakim Ismail;Bustanur Rosidi;Tati Latifah Mengko
Affiliations:
Biotechnology Research Alliance, Faculty of Biomedical Engineering and Health Science, Universiti Teknologi Malaysia, Johor, Malaysia;Biotechnology Research Alliance, Faculty of Biomedical Engineering and Health Science, Universiti Teknologi Malaysia, Johor, Malaysia;Biotechnology Research Alliance, Faculty of Biomedical Engineering and Health Science, Universiti Teknologi Malaysia, Johor, Malaysia;Biotechnology Research Alliance, Faculty of Biomedical Engineering and Health Science, Universiti Teknologi Malaysia, Johor, Malaysia;Bandung Institute of Technology, Indonesia
Venue:
Proceedings of the 15th WSEAS international conference on Computers
Year:
2011

Citing 3
Cited 0

Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Image Segmentation of Uterine Cervix Images for Indexing in PACS

CBMS '04 Proceedings of the 17th IEEE Symposium on Computer-Based Medical Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

The conventional Pap smear has been undeniably responsible in reducing the number of incidence and mortality of cervical cancer. However, few concerns have arisen such as the shortage of skilled and experienced pathologists and the increasing workload as a result of more individuals having gained access to preventive health care which eventually will make the reviewing procedure becomes time consuming and highly prone to human errors. In order to solve this problem, an automated detection system of cervical cancer cells has been developed. The detection of cervical cancer cells is based on the morphology of the cells and level set operations. Test result shows, that by using color intensity classification the system is able to differentiate between normal and cancerous cells. This system will hopefully help the pathologist to reduce the work-load and minimize human error while maintaining and improving the accuracy of the system.