Machine Learning for the Analysis of Conductivity From Mono Frequency Electrical Impedance Mammography as a Breast Cancer Risk Factor

Computational approaches have been used for analyzing risk factors together with conventional mammograms for breast cancer detection. Currently, other screening methods like electro-impedance mammography are available. Notwithstanding, as far as we know there is not related work evaluating the role...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access 2021, Vol.9, p.152397-152407
Hauptverfasser: Romero Coripuna, Rosario Lissiet, Hernandez Farias, Delia Irazu, Murillo Ortiz, Blanca Olivia, Padierna, Luis Carlos, Fraga, Teodoro Cordova
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Computational approaches have been used for analyzing risk factors together with conventional mammograms for breast cancer detection. Currently, other screening methods like electro-impedance mammography are available. Notwithstanding, as far as we know there is not related work evaluating the role of electrical-conductivity index of the mammary gland as a quantitative factor for early detection of breast cancer. This paper aims to demonstrate the importance of including breast conductivity index as a quantitative local risk-factor by analyzing a dataset of Mexican patients from a machine learning perspective. There are 12 attributes distributed into two groups: electrical-conductivity (3) and medical records (9). According to the obtained results with unsupervised methods, the performance in terms of accuracy of using only electrical-conductivity (43%) is better than using all available features (38%) and the medical records (33%). On the other hand, we identified that SVM achieves higher results in comparison with other algorithms when only the electrical-features are used. The obtained results demonstrate the important role of conductivity index as a quantitative local risk-factor for being considered in screening processes. Besides, it emerges as an important aspect to be included in the development of automatic tools for experts to perform breast cancer diagnosis.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3122948