Deep Guess acceleration for explainable image reconstruction in sparse-view CT

TL;DR

This paper presents a novel deep learning-based acceleration scheme for sparse-view CT reconstruction, significantly improving speed and accuracy over traditional methods while maintaining interpretability and robustness to noise.

Contribution

Introduces the Deep Guess acceleration scheme that uses neural networks to initialize and speed up regularized MBIR in sparse-view CT reconstruction.

Findings

Outperforms state-of-the-art data-driven methods in sparse CT reconstruction

Reduces computational time for MBIR algorithms

Demonstrates robustness to noise and applicability without ground truth

Abstract

Sparse-view Computed Tomography (CT) is an emerging protocol designed to reduce X-ray dose radiation in medical imaging. Traditional Filtered Back Projection algorithm reconstructions suffer from severe artifacts due to sparse data. In contrast, Model-Based Iterative Reconstruction (MBIR) algorithms, though better at mitigating noise through regularization, are too computationally costly for clinical use. This paper introduces a novel technique, denoted as the Deep Guess acceleration scheme, using a trained neural network both to quicken the regularized MBIR and to enhance the reconstruction accuracy. We integrate state-of-the-art deep learning tools to initialize a clever starting guess for a proximal algorithm solving a non-convex model and thus computing an interpretable solution image in a few iterations. Experimental results on real CT images demonstrate the Deep Guess effectiveness in (very) sparse tomographic protocols, where it overcomes its mere variational counterpart and many data-driven approaches at the state of the art. We also consider a ground truth-free implementation and test the robustness of the proposed framework to noise.