CLASSIFICATION OF BREAST CANCER FROM ELECTRICAL IMPEDANCE MEASUREMENTS DATASET IN SAMPLES OF FRESHLY EXCISED BREAST TISSUES

  • Pranav Verma School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
  • Sasikala Ramasamy School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
  • Dhanapal Durai Dominic Panneer Selvam Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Malaysia

Abstract

The breast cancerous issues are increasing day by day for various reasons and even it can be found in young women. Early detection decreases the death rate and reduces painful medical treatments such as surgery and chemotherapy. Electrical Impedance Spectroscopy is a powerful and painless, low-cost detection technique, and it can be used with Mammography and MRI scans. The paper analyses the EIS dataset for classifying freshly exercised breast tissues using four different machine learning algorithms: Support Vector Machine, Decision Tree, Random Forest and Modified Random Forest. The results are verified with ANOVA statistical models on four different accuracy results of six classes. The results proved that Modified Random Forest (MRF) works best as providing an accuracy mean value as 99% on 106 datasets with 15% as testing size during the training phase. The one way ANOVA results are also proved that standard error of 0.005, the significance of 0.003 and covariance of 1.14 for MRF.


Keywords: Machine learning, decision tree, random forest, support vector method, modified random forest

References

[1] N. Chumuang, P. Pramkeaw, & A. Farooq, "Electrical Impedance Of Breast’s Tissue Classification By Using Bootstrap Aggregating", 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Sorrento, Italy 2019, pp. 551-556, 2019.
[2] C. Sebu, "Electrical Impedance Mammography: the key to low-cost, portable and non-invasive breast cancer screening?", Xjenza, 5, 2, pp. 154-157, 2017. Table 4 Welch and Brown statistics Statistic df1 df2 Sig. Welch 6.730 3 9.803 0.010 Brown-Forsythe 6.471 3 9.032 0.013 Table 5 Covariance calculations Algorithms Covariance SVM 8.97 DT 4.37 RF 2.64 MRF 1.14
[3] E.K. Murphy, A. Mahara, X. Wu, & R.J. Halter, "Phantom experiments using soft-prior regularization EIT for breast cancer imaging", Physiological Measurement, 38, 6, p. 1262, 2017.
[4] Z. Haeri, M. Shokoufi, M. Jenab, R. Janzen, & F. Golnaraghi, "Electrical impedance spectroscopy for breast cancer diagnosis: Clinical study", Integrative Cancer Science and Therapeutics, 3, 6, p. 1-6, 2016.
[5] N. Zain, & K. Kanaga, "A review on breast electrical impedance tomography clinical accuracy", ARPN Journal of Engineering and Applied Sciences, 10, 1, pp. 6230-6234, 2015.
[6] R.J. Halter, A. Hartov, S.P. Poplack, W.A. Wells, K.M. Rosenkranz, R.J. Barth, P.A. Kaufman, & K.D. Paulsen, "Real-time electrical impedance variations in women with and without breast cancer", IEEE Transactions on Medical Imaging, 34, 1, pp. 38-48, 2014.
[7] S. Hong, K. Lee, U. Ha, H. Kim, Y. Lee, Y. Kim, & H.-J. Yoo, "A 4.9 mΩ-sensitivity mobile electrical impedance tomography IC for early breast-cancer detection system", IEEE Journal of Solid-State Circuits, 50, 1, pp. 245-257, 2014.
[8] N.M. Zain, & K.K. Chelliah, "Breast imaging using electrical impedance tomography: correlation of quantitative assessment with visual interpretation", Asian Pacific Journal of Cancer Prevention, 15, 3, pp. 1327-1331, 2014.
[9] S.N. Prasad, D. Houserkov, & J. Campbell, "Breast imaging using 3D electrical impedence tomography", Biomedical Papers of the Medical Faculty of Palacky University in Olomouc, 152, 1, pp. 151-154, 2008.
[10] J.E. Da Silva, J.M. De Sá, & J. Jossinet, "Classification of breast tissue by electrical impedance spectroscopy", Medical and Biological Engineering and Computing, 38, 1, pp. 26-30, 2000.
Published
2021-05-31
How to Cite
VERMA, Pranav; RAMASAMY, Sasikala; PANNEER SELVAM, Dhanapal Durai Dominic. CLASSIFICATION OF BREAST CANCER FROM ELECTRICAL IMPEDANCE MEASUREMENTS DATASET IN SAMPLES OF FRESHLY EXCISED BREAST TISSUES. Platform : A Journal of Science and Technology, [S.l.], v. 4, n. 1, p. 107-116, may 2021. ISSN 2637-0530. Available at: <https://myjms.mohe.gov.my/index.php/pjst/article/view/12711>. Date accessed: 21 may 2022.