A Trained Regularization Approach Based on Born Iterative Method for Electromagnetic Imaging

TL;DR

This paper introduces a trained regularization approach using a nested Born iterative method with a U-net based network for electromagnetic imaging, achieving high-quality results with low memory usage.

Contribution

It develops a novel trained Born iterative method incorporating a U-net based regularization network, improving image quality and efficiency in electromagnetic imaging.

Findings

Outperforms conventional sparse-based Born iterative method (SBIM)

Achieves high-quality image restoration with fewer iterations

Maintains low memory requirements during training

Abstract

A trained-based Born iterative method (TBIM) is developed for electromagnetic imaging (EMI) applications. The proposed TBIM consists of a nested loop; the outer loop executes TBIM iteration steps, while the inner loop executes a trained iterative shrinkage thresholding algorithm (TISTA). The applied TISTA runs linear Landweber iterations implemented with a trained regularization network designed based on U-net architecture. A normalization process was imposed in TISTA that made TISTA training applicable within the proposed TBIM. The iterative utilization of the regularization network in TISTA is a bottleneck that demands high memory allocation through the training process. Therefore TISTA within each TBIM step was trained separately. The TISTA regularization network in each TBIM step was initialized using the weights from the previous TBIM step. The above approach achieved high-quality image restoration after running few TBIM steps while maintained low memory allocation through the training process. The proposed framework can be extended to Newton or quasi-Newton schemes, where within each Newton iteration, a linear ill-posed problem is optimized that differs from one example to another. The numerical results illustrated in this work show the superiority of the proposed TBIM compared to the conventional sparse-based Born iterative method (SBIM).