ANN Classification of Female Breast Tumor Type Prediction Using EIM Parameters

Electrical Impedance Myography (EIM) is a painless, non-invasive electrical bio-impedance measurement technique for assessing neurological disease states. In this electro-physiological technique, the EIM parameters, namely resistance, reactance, and phase magnitude, depend on several anatomic factors such as muscle girth, skin thickness, fat thickness. EIM may also be affected by several non-anatomic factors like frequency, electrode size, and inter-electrode distance. This paper explores the female breast tumor type classification by extracting EIM parameters from a 3D model of the female breast. The extracted EIM parameters from the simulation employ an artificial neural network (ANN) to identify benign and malignant tumor types. A 3D finite element (FEM) model of a female breast with a rectangular shape of electrodes are developed with a base shape of an 80 mm outer radius. The subsequent shapes are designed as -20% and +20% of the base shape, as mentioned above. This paper presents the EIM parameters that can classify female breast tumor types with an accuracy of 96.2% using an ANN.