Deep Guess acceleration for explainable image reconstruction in sparse-view CT
This work addresses the need for faster and more accurate medical imaging with reduced radiation dose, representing an incremental improvement over prior model-based iterative reconstruction techniques.
The paper tackles the problem of slow and artifact-prone image reconstruction in sparse-view CT by introducing a Deep Guess acceleration scheme that uses a neural network to initialize a proximal algorithm, achieving improved accuracy and faster convergence compared to existing methods.
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.