Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy
Апстракт
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 result...s.
Кључне речи:
screening / OMIS / machine learning / LBC / classification / cervical cancerИзвор:
Tehnički vjesnik, 2019, 26, 6, 1694-1699Издавач:
- Univ Osijek, Tech Fac, Slavonski Brod
Финансирање / пројекти:
- Tumour Trace Ltd, UK
- Tumour Trace d.o.o, Serbia
- Развој нових метода и техника за рану дијагностику канцера грлића материце, дебелог црева, усне дупље и меланома на бази дигиталне слике и ексцитационо-емисионих спектара у видљивом и инфрацрвеном домену (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-41006)
DOI: 10.17559/TV-20190528192618
ISSN: 1330-3651
WoS: 000499332300022
Scopus: 2-s2.0-85075699718
Институција/група
Inovacioni centarTY - JOUR AU - Hut, Igor AU - Jeftić, Branislava AU - Matija, Lidija AU - Ćojbašić, Žarko AU - Koruga, Đuro PY - 2019 UR - https://machinery.mas.bg.ac.rs/handle/123456789/3004 AB - 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. PB - Univ Osijek, Tech Fac, Slavonski Brod T2 - Tehnički vjesnik T1 - Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy EP - 1699 IS - 6 SP - 1694 VL - 26 DO - 10.17559/TV-20190528192618 ER -
@article{ author = "Hut, Igor and Jeftić, Branislava and Matija, Lidija and Ćojbašić, Žarko and Koruga, Đuro", year = "2019", 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.", publisher = "Univ Osijek, Tech Fac, Slavonski Brod", journal = "Tehnički vjesnik", title = "Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy", pages = "1699-1694", number = "6", volume = "26", doi = "10.17559/TV-20190528192618" }
Hut, I., Jeftić, B., Matija, L., Ćojbašić, Ž.,& Koruga, Đ.. (2019). Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy. in Tehnički vjesnik Univ Osijek, Tech Fac, Slavonski Brod., 26(6), 1694-1699. https://doi.org/10.17559/TV-20190528192618
Hut I, Jeftić B, Matija L, Ćojbašić Ž, Koruga Đ. Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy. in Tehnički vjesnik. 2019;26(6):1694-1699. doi:10.17559/TV-20190528192618 .
Hut, Igor, Jeftić, Branislava, Matija, Lidija, Ćojbašić, Žarko, Koruga, Đuro, "Machine Learning Classification of Cervical Tissue Liquid Based Cytology Smear Images by Optomagnetic Imaging Spectroscopy" in Tehnički vjesnik, 26, no. 6 (2019):1694-1699, https://doi.org/10.17559/TV-20190528192618 . .