Affiliations: [a] División de Ciencias e Ingenierías Campus León Universidad de Guanajuato, León, Guanajuato, México | [b] Escuela profesional de Física, Facultad deCiencias Naturales y Formales, Universidad Nacional de SanAgustín, Arequipa, Perú | [c] Unidad de Investigación en EpidemiologíaClínica, Unidad Médica de Alta Especialidad No. 1 Bajío, Instituto Mexicano del Seguro Social; León, Guanajuato, México | [d] OOAD Guanajuato, Instituto Mexicano del SeguroSocial, León, Guanajuato, México
Correspondence:
[*]
Corresponding author. Delia Irazú Hernández-Farías, División de Ciencias e Ingenierías Campus León Universidad de Guanajuato, León, Guanajuato, México. E-mail: dirazuherfa@hotmail.com.
Abstract: Breast cancer is a very important health concern around the world. Early detection of such a disease increases the chances of survival. Among the available screening tools, there is the Electro-Impedance Mammography (EIM), which is a novel and less invasive method that captures the potential difference stored in breast tissues under the assumption that electrical properties among normal and pathologically altered tissues are different. In this paper, we address breast cancer detection as a multi-class problem aiming to determine the corresponding label in terms of the Breast Imaging Electrical Impedance classification system, the standard used by physicians for interpreting an EIM mammogram. For experimental purposes, for the first time in the literature, we took advantage of a dataset comprising EIM of Mexican patients. Aiming to establish a baseline for this task, traditional supervised learning methods were used together with two different feature extraction techniques: raw pixel data and transfer learning. Besides, data augmentation was exploited for compensating data imbalance. Different experimental settings were evaluated reaching classification rates over 0.85 in F-score. KNN emerges as a very promising classifier for addressing this task. The obtained results allow us to validate the usefulness of traditional methods for classifying electro-impedance mammograms.
Keywords: Breast cancer screening, electro-impedance mammography, medical image classification, BI-EIM, machine learning, transfer learning
