提出轻量级2.5D网络，高效重建稀疏视角3D锥束CT图像
Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction
- 用轴交换操作替代全3D卷积，实现端到端重建
- 在低投影数下显著减少伪影并保留复杂流体细节
- 适合需要高精度且内存受限的医学与惯性约束聚变成像
从有限投影中重建3D锥束计算机断层扫描（CBCT）图像是医学和惯性约束聚变（ICF）等领域的重要逆问题。传统方法如滤波反投影（FBP）和基于模型的正则化在投影数量少时性能不佳。过去十年中，深度学习（DL）在解决CT逆问题方面取得显著进展。典型方法是训练2D或3D网络以学习端到端映射。然而，2D网络无法充分利用全局信息；而3D网络随图像尺寸增大面临高昂内存开销，变得不切实际。本文提出Swap-Net，一种用于稀疏视角3D CBCT重建的内存高效2.5D网络。Swap-Net通过一系列新颖的轴交换操作，在无需使用完整3D卷积的情况下，实现端到端3D体积重建。仿真结果表明，无论定量还是定性指标，Swap-Net均持续优于基线方法，在减少伪影和保留复杂流体模拟细节方面表现突出，对ICF领域具有重要意义。
原文摘要 · Abstract (English)
Reconstructing 3D cone beam computed tomography (CBCT) images from a limited set of projections is an important inverse problem in many imaging applications from medicine to inertial confinement fusion (ICF). The performance of traditional methods such as filtered back projection (FBP) and model-based regularization is sub-optimal when the number of available projections is limited. In the past decade, deep learning (DL) has gained great popularity for solving CT inverse problems. A typical DL-based method for CBCT image reconstruction is to learn an end-to-end mapping by training a 2D or 3D network. However, 2D networks fail to fully use global information. While 3D networks are desirable, they become impractical as image sizes increase because of the high memory cost. This paper proposes Swap-Net, a memory-efficient 2.5D network for sparse-view 3D CBCT image reconstruction. Swap-Net uses a sequence of novel axes-swapping operations to produce 3D volume reconstruction in an end-to-end fashion without using full 3D convolutions. Simulation results show that Swap-Net consistently outperforms baseline methods both quantitatively and qualitatively in terms of reducing artifacts and preserving details of complex hydrodynamic simulations of relevance to the ICF community.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。