Fusing Sparsity with Deep Learning for Rotating Scatter Mask Gamma Imaging

TL;DR

This paper introduces a novel method combining sparsity regularization and deep neural network denoising to improve image reconstruction in rotating scatter mask gamma imaging, addressing the under-determined data challenge.

Contribution

It proposes a new fusion approach of model-based and data-driven techniques for enhanced image reconstruction in gamma imaging systems.

Findings

Superior reconstruction quality compared to existing methods

Efficient algorithm with improved accuracy

Effective handling of under-determined data acquisition

Abstract

Many nuclear safety applications need fast, portable, and accurate imagers to better locate radiation sources. The Rotating Scatter Mask (RSM) system is an emerging device with the potential to meet these needs. The main challenge is the under-determined nature of the data acquisition process: the dimension of the measured signal is far less than the dimension of the image to be reconstructed. To address this challenge, this work aims to fuse model-based sparsity-promoting regularization and a data-driven deep neural network denoising image prior to perform image reconstruction. An efficient algorithm is developed and produces superior reconstructions relative to current approaches.