AGGREGATED EVALUATION OF DIELECTRIC IMPEDANCE SPECTROSCOPY RESULTS BASED ON STATISTICAL PARAMETERS AND HAUSDORFF METRIC
- Authors: Demushkina K.M.1
-
Affiliations:
- Penza State University
- Issue: No 2 (2025)
- Pages: 147-155
- Section: MODELS, SYSTEMS, MECHANISMS IN THE TECHNIQUE
- URL: https://journal-vniispk.ru/2227-8486/article/view/307589
- DOI: https://doi.org/10.21685/2227-8486-2025-2-12
- ID: 307589
Cite item
Full Text
Abstract
Background. The paper considers a method for the noninvasive diagnosis of breast cancer using dielectric impedance spectroscopy. A method is proposed for the formation of an aggregated assessment of the condition of the breast based on the results of an examination by dielectric impedance spectroscopy, which increases the reliability of the detection of neoplasms. Materials and methods. To evaluate the results of bioimpedance spectroscopy, the following algorithm was developed: based on the results of multiple measurements of the active and reactive components of the complex resistance of the mammary gland in the informative frequency range of 20 Hz – 20 MHz, statistical parameters and the Hausdorff metric of the frequency characteristics of the components of the relative permittivity are calculated, which are normalized by the MINIM method. The aggregated breast condition assessment is formed from normalized estimates of statistical parameters and Hausdorff metrics using the PCA/LOO method. Results. As a result of the study, three objects were ranked according to the volume of heterogeneous inclusions. The results obtained coincided with the experimental data. Conclusions. The use of statistical parameters and the Hasudorf metric allows for a comparative assessment of objects with heterogeneous inclusions, and based on an aggregated assessment, to determine the dynamics of cancer cell development.
About the authors
Kseniya M. Demushkina
Penza State University
Author for correspondence.
Email: riabova.ksenija@yandex.ru
Postgraduate student
(40 Krasnaya street, Penza, Russia)References
- Federal'naya sluzhba gosudarstvennoy statistiki = Federal State Statistics Service. (In Russ.). Available at: https://rosstat.gov.ru/ (accessed 17.03.2025).
- Jossinet J. The impedivity of freshly excised human breast tissue. Physiol. Meas. 1998;19(1):61–75.
- Zarafshani A. Feasibility Test of Quantitative Assessment of Breast Density Based on Dielectric Impedance Spectroscopy. JABB. 2017;2(6).
- Grzegorczyk T.M. et al. Fast 3-D Tomographic Microwave Imaging for Breast Cancer Detection. IEEE Trans. Med. Imaging. 2012;31(8):1584–1592.
- Safronov M. et al. Mobile ECG Monitoring Device with Bioimpedance Measurement and Analysis. 2019 24th Conference of Open Innovations Association (FRUCT). Moscow, 2019:375–380. doi: 10.1109/DSPA60853.2024.10510118
- Kuzmin A., Baranov V. Bioimpedance spectroscopy of breast phantoms. Journal of Electrical Bioimpedance. 2025;16(1):50–55. doi: 10.2478/joeb-2025-0007
- Kosyakova N.V. Assessment of regional healthcare using the Minmax method in order to study the experience of organizing drug provision for patients with orphan diseases. Zdorov'e i obrazovanie v XXI veke = Health and education in the 21st century. 2017;(12). (In Russ.). Available at: https://cyberleninka.ru/article/n/otsenka-regionalnogo-zdravoohraneniya-metodom-minmax-s-tselyu-izucheniya-opyta-organizatsii-lekarstvennogo-obespecheniya-bolnyh-s (accessed 09.06.2025).
- Rodriguez A., Wright G., Emrich S., Clark P.L. MinMax: A versatile tool for calculating and comparing synonymous codon usage and its impact on protein folding. Protein Sci. 2018;(27):356–362. doi: 10.1002/pro.3336
- Haque Md.S. Hassan Md.R., Binmakhashen G.M. et al. Breast Density Classifica-tion for Cancer Detection Using DCT-PCA Feature Extraction and Classifier Ensemble. Intelligent Systems Design and Applications. 2018;March:702–711. doi: 10.1007/978-3- 319-76348-4_68
- Ibrahim S., Nazir S., Velastin S. Feature Selection Using Correlation Analysis and Principal Component Analysis for Accurate Breast Cancer Diagnosis. Journal of Imaging. 2021;7:225. doi: 10.3390/jimaging7110225
- Yuan J., Li Y., Liu C., Zha X. Leave-One-Out Cross-Validation Based Model Selection for Manifold Regularization. 7th International Symposium on Neural Networks. 2010:457–464.
Supplementary files
