.png){kind=icon}
.png){kind=icon}
Return
Deep Guess acceleration for explainable image reconstruction in sparse-view CT
.png){kind=icon}
OA
AI
DOI：10.1016/j.compmedimag.2025.102530.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sparse-view Computed Tomography (CT) is an emerging protocol designed to reduce X-ray dose radiation in medical imaging. Reconstructions based on the traditional Filtered Back Projection algorithm 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 a (mathematically) interpretable solution image in a few iterations. Experimental results on real and synthetic 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.
Keywords:
Non-convex optimization
Sparse view computed tomography
Model-based iterative reconstruction
Deep neural networks
Interpretable reconstruction
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K