Discretized Target Size Detection in Electrical Impedance Tomography Using Neural Network Classifier
- PDF / 1,310,835 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 92 Downloads / 180 Views
Discretized Target Size Detection in Electrical Impedance Tomography Using Neural Network Classifier Shu-Wei Huang1 · Gustavo K. Rohde2 · Hao-Min Cheng3 · Shien-Fong Lin1 Received: 15 July 2020 / Accepted: 3 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Electrical impedance tomography (EIT) uses non-invasive and non-radiative imaging to detect inhomogeneous electrical properties in tissues. The inverse problem of EIT is a highly nonlinear, ill-posed problem, which causes inaccuracy in target size calculation. We propose a novel approach to discretize the target size and use a neural network (NN) classifier to classify the unknown size in discrete steps. The target size is discretized into distinct steps, and each step can be a unique class. The data is pre-processed with the cumulative distribution transform (CDT) to enhance distinguishability. First, the NN is trained with simulated datasets, divided into time difference (t-d) group and CDT group. After training, the NN classifier is tested by experimental data recorded in a phantom experiment. Linear discriminant analysis (LDA) is performed to assess the distinguishability of classes. There is a significant increase in distance between classes after the CDT pre-processing. The density of the classes has an upward trend with a higher degree of clustering after CDT pre-processing. The CDT data clustering into distinguishable classes is essential to excellent NN classification results. Such an approach is a significant paradigm shift by turning the cumbersome inverse calculation with uncertain accuracy into a classification problem with predetermined step errors. The accuracy and resolution can be further extended by increasing the discretization steps. Keywords Electrical impedance tomography · Neural network classifier · Cumulative distribution transform
1 Introduction Electrical impedance tomography (EIT) is a non-invasive, non-ionizing, and low-cost imaging modality based on detecting inhomogeneous electrical properties of the tissue. It involves electrical current injection on the tissue surface
B
Shien-Fong Lin [email protected] Shu-Wei Huang [email protected] Gustavo K. Rohde [email protected] Hao-Min Cheng [email protected]
1
Institute of Biomedical Engineering, National Chiao Tung University, Hsinchu, Taiwan
2
Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA
3
Center for Evidence-Based Medicine, Taipei Veterans General Hospital, and Faculty of Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan
to establish boundary potential (the forward problem), and image reconstruction using boundary potential to evaluate the conductivity distribution in the object (the inverse problem). The inverse problem of EIT is highly nonlinear and ill-posed. The linear [1], nonlinear iterative [2], and direct nonlinear approximation [3] methods are three types of inverse solver algorithms. They can effectively solve for the target positio
Data Loading...
