Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra
2022
Authors
Jeftić, BranislavaHut, Igor
Stanković, Ivana
Šakota Rosić, Jovana
Matija, Lidija
Koruga, Đuro
Conference object (Published version)
Metadata
Show full item recordAbstract
In order to further investigate performance of Optomagnetic Imaging Spectroscopy in cervical cancer detection, deep learning algorithm has been used for classification of optomagnetic spectra of the samples. Optomagnetic spectra reflect cell properties and based on those properties it is possible to differ-entiate normal cells from cells showing different levels of dysplasia and cancer cells. In one of the previous research, Optomagnetic imaging spectroscopy has demonstrated high percentages of accuracy, sensitivity and specificity in cervical cancer detection, particularly in the case of binary classification. Somewhat lower accuracy percentages were obtained in the case of four class classification. Compared to the results obtained by conventional machine learning classification algorithms, proposed deep learning algorithm achieves similar accuracy results (80%), greater sensitivity (83.3%), and comparable specificity percentages (78%).
Keywords:
Optomagnetic Imaging Spectroscopy / cervical cancer / deep learning / convolutional neural networkSource:
Contemporary Materials, 2022, 13, 2, 178-184Funding / projects:
- Development of methods and techniques for early diagnostic of cervical, colon, oral cavity cancer and melanoma based on a digital image and excitation-emission spectrum in visible and infrared domain (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-41006)
Collections
Institution/Community
Mašinski fakultetTY - CONF AU - Jeftić, Branislava AU - Hut, Igor AU - Stanković, Ivana AU - Šakota Rosić, Jovana AU - Matija, Lidija AU - Koruga, Đuro PY - 2022 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4849 AB - In order to further investigate performance of Optomagnetic Imaging Spectroscopy in cervical cancer detection, deep learning algorithm has been used for classification of optomagnetic spectra of the samples. Optomagnetic spectra reflect cell properties and based on those properties it is possible to differ-entiate normal cells from cells showing different levels of dysplasia and cancer cells. In one of the previous research, Optomagnetic imaging spectroscopy has demonstrated high percentages of accuracy, sensitivity and specificity in cervical cancer detection, particularly in the case of binary classification. Somewhat lower accuracy percentages were obtained in the case of four class classification. Compared to the results obtained by conventional machine learning classification algorithms, proposed deep learning algorithm achieves similar accuracy results (80%), greater sensitivity (83.3%), and comparable specificity percentages (78%). C3 - Contemporary Materials T1 - Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra EP - 184 IS - 2 SP - 178 VL - 13 DO - 10.7251/COMEN2202178J ER -
@conference{ author = "Jeftić, Branislava and Hut, Igor and Stanković, Ivana and Šakota Rosić, Jovana and Matija, Lidija and Koruga, Đuro", year = "2022", abstract = "In order to further investigate performance of Optomagnetic Imaging Spectroscopy in cervical cancer detection, deep learning algorithm has been used for classification of optomagnetic spectra of the samples. Optomagnetic spectra reflect cell properties and based on those properties it is possible to differ-entiate normal cells from cells showing different levels of dysplasia and cancer cells. In one of the previous research, Optomagnetic imaging spectroscopy has demonstrated high percentages of accuracy, sensitivity and specificity in cervical cancer detection, particularly in the case of binary classification. Somewhat lower accuracy percentages were obtained in the case of four class classification. Compared to the results obtained by conventional machine learning classification algorithms, proposed deep learning algorithm achieves similar accuracy results (80%), greater sensitivity (83.3%), and comparable specificity percentages (78%).", journal = "Contemporary Materials", title = "Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra", pages = "184-178", number = "2", volume = "13", doi = "10.7251/COMEN2202178J" }
Jeftić, B., Hut, I., Stanković, I., Šakota Rosić, J., Matija, L.,& Koruga, Đ.. (2022). Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra. in Contemporary Materials, 13(2), 178-184. https://doi.org/10.7251/COMEN2202178J
Jeftić B, Hut I, Stanković I, Šakota Rosić J, Matija L, Koruga Đ. Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra. in Contemporary Materials. 2022;13(2):178-184. doi:10.7251/COMEN2202178J .
Jeftić, Branislava, Hut, Igor, Stanković, Ivana, Šakota Rosić, Jovana, Matija, Lidija, Koruga, Đuro, "Deep learning algorithm for cervical cancer detection based on images of optomagnetic spectra" in Contemporary Materials, 13, no. 2 (2022):178-184, https://doi.org/10.7251/COMEN2202178J . .