Georgia Southern University
Artificial Neural Network (ANN) Classification of Female Breast Tumor Type and Location Prediction Using Electrical Impedance Myography (EIM) Parameters
Abstract
dc:description.abstractElectrical Impedance Myography (EIM) is a painless, non-invasive electrical bio-impedance measurement technique for assessing neurological disease states. In this electrophysiological 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 thesis paper presents two separate studies. The first study 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. The second study presents the female breast tumor location classification by extracting EIM parameters from a female breast 3D model and then use EIM parameters in an artificial neural network (ANN) to predict the locations of the female breast tumors. 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 thesis paper presents that the EIM parameters can classify female breast tumor types and predict locations of tumors using an ANN.
Degree
thesis:*- Name thesis:degree_name
- Master of Science, Electrical Engineering
- Level thesis:degree_level
- Thesis (restricted to Georgia Southern)
- Discipline thesis:degree_discipline
- Department of Electrical and Computer Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kabir, Shahriar
- Contributors dc:contributor
-
- Sungkyun Lim
- Adel El Shahat
Subjects
dc:subject × 17- Artificial neural network
- ANN
- Benign tumor
- Female breast cancer
- Breast tumor
- Electrical impedance myography
- EIM
- Finite element method
- FEM
- Machine learning
- ML
- Malignant tumor
- Tumor type classification
- Tumor location prediction
- Biomedical
- Biomedical Devices and Instrumentation
- Electrical and Electronics
Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/2105