Abstract
Quantitative imaging is a critical task in various applications, including medical diagnostics, non-destructive evaluation and material characterisation. This work addresses the problem of three-dimensional (3D) permittivity profile reconstruction of a region of interest (RoI) by leveraging a deep learning model. This is performed by training the model to establish a mapping between the spatio-temporal electric field data and the corresponding permittivity profile of the RoI. The deep learning model is designed to handle the time-varying electric field data efficiently, using a combination of convolutional layers to extract spatial features and Long Short-Term Memory (LSTM) networks, to model temporal dependencies. The effectiveness of this approach is demonstrated through comprehensive validations in different scenarios, offering a powerful tool for quantitative permittivity prediction in a wide range of applications.
Original language | English |
---|---|
Title of host publication | Proceedings of the 19th European Conference on Antennas and Propagation, EuCAP 2025 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Number of pages | 5 |
Publication status | Accepted - 31 Dec 2024 |
Event | 19th European Conference on Antennas and Propagation 2025 - Stockholm, Sweden Duration: 30 Mar 2025 → 04 Apr 2025 https://eucap.org/ |
Publication series
Name | EuCAP Proceedings |
---|---|
ISSN (Print) | 2164-3342 |
Conference
Conference | 19th European Conference on Antennas and Propagation 2025 |
---|---|
Abbreviated title | EuCAP 2025 |
Country/Territory | Sweden |
City | Stockholm |
Period | 30/03/2025 → 04/04/2025 |
Internet address |
Keywords
- quantitative imaging
- permittivity
- deep learning
- inverse problem