Skip to the main content

Technical gazette, Vol. 26 No. 6, 2019.

Original scientific paper

https://doi.org/10.17559/TV-20190528192618

Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy

Igor Hut* orcid id orcid.org/0000-0003-1483-0411 ; University of Belgrade, Faculty of Mechanical Engineering, Department of Biomedical Engineering, Kraljice Marije 16, 11120 Belgrade 35, Serbia
Branislava Jeftic orcid id orcid.org/0000-0002-8987-303X ; University of Belgrade, Faculty of Mechanical Engineering, Department of Biomedical Engineering, Kraljice Marije 16, 11120 Belgrade 35, Serbia
Lidija Matija orcid id orcid.org/0000-0001-8492-7177 ; University of Belgrade, Faculty of Mechanical Engineering, Department of Biomedical Engineering, Kraljice Marije 16, 11120 Belgrade 35, Serbia
Zarko Cojbasic orcid id orcid.org/0000-0002-4581-1048 ; University of Nis, Faculty of Mechanical Engineering, Department for Mechatronics and Control, Aleksandra Medvedeva 14, 18106 Nis, Serbia
Djuro Koruga ; TFT NANO CENTER LTD., Vojislava Ilica 88, 11010 Belgrade 48, Serbia

Full text: english pdf 1.037 Kb

page 1694-1699

downloads: 718

cite

Abstract

Semi-automated system for classification of cervical smear images based on Optomagnetic Imaging Spectroscopy (OMIS) and machine learning is proposed. Optomagnetic Imaging Spectroscopy has been applied to screen 700 cervical samples prepared according to Liquid Based Cytology (LBC) principles and to record spectra of the samples. Peak intensities and peak shift frequencies from the spectra have been used as features in classification models. Several machine learning algorithms have been tested and results of classification have been compared. Results suggest that the presented approach can be used to improve standard LBC screening tests for cervical cancer detection. Developed system enables detection of pre-cancerous and cancerous states with sensitivity of 79% and specificity of 83% along with AUC (ROC) of 88% and could be used as an improved alternative procedure for cervical cancer screening. Moreover, this can be achieved via portable apparatus and with immediately available results.

Keywords

cervical cancer; classification; LBC; machine learning; OMIS; screening

Hrčak ID:

228517

URI

https://hrcak.srce.hr/228517

Publication date:

27.11.2019.

Visits: 1.687 *