Efficient Flow Matching for Sparse-View CT Reconstruction
Centrum Wiskunde en Informatica(数学与信息学研究中心);LIACS, Leiden University(莱顿大学LIACS);Great Bay University(大湾大学);Mathematical Institute, Utrecht University(乌得勒支大学数学研究所)
Jiayang Shi, Lincen Yang, Zhong Li, Tristan van Leeuwen, Daniel M. Pelt, K. Joost Batenburg
Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems. However, diffusion-based reconstruction relies on Stochastic Differential Equations (SDEs) for forward diffusion and reverse denoising, where such stochasticity can interfere with repeated data consistency corrections in CT reconstruction. Since CT reconstruction is often time-critical in clinical and interventional scenarios, improving reconstruction efficiency is essential. In contrast, Flow Matching (FM) models sampling as a deterministic Ordinary Differential Equation (ODE), yielding smooth trajectories without stochastic noise injection. This deterministic formulation is naturally compatible with repeated data consistency operations. Furthermore, we observe that FM-predicted velocity fields exhibit strong correlations across adjacent steps. Motivated by this, we propose an FM-based CT reconstruction framework (FMCT) and an efficient variant (EFMCT) that reuses previously predicted velocity fields over consecutive steps to substantially reduce the number of Neural network Function Evaluations (NFEs), thereby improving inference efficiency. We provide theoretical analysis showing that the error introduced by velocity reuse is bounded when combined with data consistency operations. Extensive experiments demonstrate that FMCT/EFMCT achieve competitive reconstruction quality while significantly improving computational efficiency compared with diffusion-based methods. The codebase is open-sourced at https://github.com/EFMCT/EFMCT.
LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction
School of Mathematical Sciences, Capital Normal University(首都师范大学数学科学学院);National Center for Applied Mathematics Beijing, Capital Normal University(首都师范大学北京国家应用数学中心);Academy for Multidisciplinary Studies, Capital Normal University(首都师范大学交叉科学研究院)
NerT-CA: Efficient Dynamic Reconstruction from Sparse-view X-ray Coronary Angiography
Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, The Netherlands(数学与计算机科学系,埃因霍温理工大学,埃因霍温,荷兰);Philips Healthcare, Best, The Netherlands(飞利浦医疗,贝斯特,荷兰);Department of Electrical Engineering, Eindhoven University of Technology, The Netherlands(电子工程系,埃因霍温理工大学,荷兰)
AS-Net: Fast Photoacoustic Reconstruction with Multi-feature Fusion from Sparse Data
ShanghaiTech University(上海科技大学);Chinese Academy of Sciences(中国科学院);Shanghai Institute of Microsystem and Information Technology(上海微系统与信息技术研究所);University of Chinese Academy of Sciences(中国科学院大学)
NeRF-CA: Dynamic Reconstruction of X-ray Coronary Angiography with Extremely Sparse-views
Department of Mathematics & Computer Science, Eindhoven University of Technology(数学与计算机科学系,埃因霍温理工大学);Philips Healthcare(飞利普医疗);Department of Electrical Engineering, Eindhoven University of Technology(电子工程系,埃因霍温理工大学);ASML(ASML公司)
DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction
Institute of Computing Technology, CAS(中国科学院计算技术研究所);Suzhou Institute of Intelligent Computing Technology, CAS(中国科学院苏州智能计算技术研究院);Shenzhen Institutes of Advanced Technology, CAS(中国科学院深圳先进技术研究院);Beijing Information Science and Technology University(北京信息科技大学);University of Science and Technology of China(中国科学技术大学)
MVMS-RCN: A Dual-Domain Unfolding CT Reconstruction with Multi-sparse-view and Multi-scale Refinement-correction
Xiangtan University(湘潭大学);Zhejiang Normal University(浙江师范大学);The University of Liverpool(利物浦大学);University of Strathclyde(斯特拉斯克莱德大学);Hunan National Applied Mathematics Center(湖南国家应用数学中心)
Combining Deep Learning and Adaptive Sparse Modeling for Low-dose CT Reconstruction
传统的基于模型的图像重建(MBIR)方法将前向模型和噪声模型与简单的对象先验相结合。最近深度学习方法在图像重建中的应用提供了一种成功的数据驱动方法,可以解决在测量欠采样或各种类型噪声的情况下重建图像时面临的挑战。在这项工作中,我们提出了一个混合监督-无监督学习框架的X射线计算机断层扫描(CT)图像重建。所提出的学习公式利用稀疏或无监督学习的先验知识和神经网络重构器来模拟定点迭代过程。每个建议的训练块由确定性MBIR求解器和神经网络组成。信息并行地流过这两个重构器,然后被最佳地组合,并且多个这样的块被级联以形成重构流水线。我们证明了这种学习的混合模型在训练数据有限的情况下用于低剂量CT图像重建的有效性,其中我们使用NIH AAPM Mayo Clinic低剂量CT Grand Challenge数据集进行训练和测试。在我们的实验中,我们研究了有监督的深度网络重构器和基于稀疏表示(无监督)的学习或分析先验的组合。我们的研究结果表明,所提出的框架相比,最近的重建方法有前途的性能。
An evaluation framework for sparse 4D (3D + time) imaging reconstruction via bootstrapped cross-validation
Synchrotron Radiation Research and NanoLund, Lund University(隆德大学同步辐射研究与纳米隆德中心);Medical Radiation Physics, Lund University(隆德大学医学放射物理);University College London(伦敦大学学院)