Creating 3D Meshes with Electrodes from Segmented CT Images for TIE

• Grant number: 22/06923-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2022
• End date: July 31, 2023
• Field of knowledge: Engineering - Biomedical Engineering - Bioengineering
• Principal Investigator: Marcos de Sales Guerra Tsuzuki
• Grantee: Hector Shin Emura
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

From information on electrical potential at the perimeter of an object (collected by sampling in a simulated environment), an Electrical Impedance Tomography (EIT) system must be able to estimate a distribution of impedances inside, in a non-invasive way. An algorithm will be developed to include electrodes in segmented skin from 3D CT images. The finite element mesh with lungs, heart, airways, bones and skin will be created. Incorrect placement of electrodes will be simulated (possible source of EIT error). A convolutional neural network based on LeNet will be developed to reconstruct 3D images. The network will be trained with data augmentation, including incorrectly positioned electrodes.