Application of Kolmogorov-Arnold Network for Image Reconstruction in Electrical Impedance Tomography

• Grant number: 24/10136-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2024
• End date: September 30, 2025
• Field of knowledge: Engineering - Biomedical Engineering - Bioengineering
• Principal Investigator: Marcos de Sales Guerra Tsuzuki
• Grantee: Henrique Sturlini Martins
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Electrical Impedance Tomography (EIT) is a non-invasive imaging technique that stands out for not relying on harmful radiation and for the portability of its equipment, making it promising for medical applications such as lung imaging and brain activity monitoring. However, it faces challenges in image quality due to the ill-posed nature of the inverse problem. This research project aims to use the Kolmogorov-Arnold network, an advanced deep learning technique, to improve image reconstruction in EIT. The Kolmogorov-Arnold model will be trained on a simulated EIT dataset. We aim to develop a Kolmogorov-Arnold model adapted for EIT, create a comprehensive set of simulated data, train and validate the model, and publish the results.