This paper presents a new method for reconstructing regions of interest (ROI) from a limited number of computed tomography (CT) measurements. Classical model-based iterative reconstruction methods lead to images with predictable features. Still, they often suffer from tedious parameterization and slow convergence. On the contrary, deep learning methods are fast, and they can reach high reconstruction quality by leveraging information from large datasets, but they lack interpretability. At the crossroads of both methods, deep unfolding networks have been recently proposed. Their design includes the physics of the imaging system and the steps of an iterative optimization algorithm. Motivated by the success of these networks for various applications, we introduce an unfolding neural network called U-RDBFB designed for ROI CT reconstruction from limited data. Few-view truncated data are effectively handled thanks to a robust non-convex data fidelity term combined with a sparsity-inducing regularization function. We unfold the Dual Block coordinate Forward-Backward (DBFB) algorithm, embedded in an iterative reweighted scheme, allowing the learning of key parameters in a supervised manner. Our experiments show an improvement over several state-of-the-art methods, including a model-based iterative scheme, a multi-scale deep learning architecture, and deep unfolding methods.

翻译：本文提出了一种从有限计算机断层扫描（CT）测量数据中重建感兴趣区域（ROI）的新方法。经典的基于模型迭代重建方法能生成具有可预测特征的图像，但通常存在参数化繁琐、收敛速度慢的问题。相反，深度学习方法速度快，能通过利用大规模数据集信息达到高重建质量，但缺乏可解释性。位于两种方法交汇处的深度展开网络近年被提出，其设计包含成像系统的物理机制和迭代优化算法的步骤。受此类网络在各领域应用成功的启发，我们提出一种名为U-RDBFB的展开神经网络，用于有限数据条件下的ROI CT重建。通过将稳健非凸数据保真项与稀疏诱导正则化函数相结合，有效处理了少视角截断数据。我们将对偶坐标前向后向（DBFB）算法展开，嵌入迭代重加权策略中，实现关键参数的监督学习。实验表明，该方法在性能上优于多种现有先进方法，包括基于模型的迭代方案、多尺度深度学习架构及深度展开方法。