首个稀疏视角CBCT重建的通用大模型，降低辐射风险
DeepSparse: A Foundation Model for Sparse-View CBCT Reconstruction
- 用双维度跨尺度融合网络整合2D多视角与3D多尺度特征
- 在多个数据集上优于现有方法，重建质量显著提升
- 适合医学影像、低剂量CT研究者使用
锥形束计算机断层扫描（CBCT）是医学领域关键的三维成像技术，但高质量成像所需的高辐射暴露引发重大担忧，尤其对脆弱人群。稀疏视角重建通过减少X射线投影数量来降低辐射，但现有方法存在计算负担重、泛化能力差的问题。为此，我们提出DeepSparse，首个用于稀疏视角CBCT重建的基础模型，包含DiCE（双维度跨尺度嵌入）网络，融合多视角2D特征与多尺度3D特征。此外，我们设计了HyViP（混合视角采样预训练）框架，在大规模含稀疏与密集视角投影的数据集上预训练模型，并采用两阶段微调策略适应新数据集。大量实验与消融研究显示，DeepSparse在重建质量上超越当前最优方法，为更安全高效的CBCT成像铺平道路。
原文摘要 · Abstract (English)
Cone-beam computed tomography (CBCT) is a critical 3D imaging technology in the medical field, while the high radiation exposure required for high-quality imaging raises significant concerns, particularly for vulnerable populations. Sparse-view reconstruction reduces radiation by using fewer X-ray projections while maintaining image quality, yet existing methods face challenges such as high computational demands and poor generalizability to different datasets. To overcome these limitations, we propose DeepSparse, the first foundation model for sparse-view CBCT reconstruction, featuring DiCE (Dual-Dimensional Cross-Scale Embedding), a novel network that integrates multi-view 2D features and multi-scale 3D features. Additionally, we introduce the HyViP (Hybrid View Sampling Pretraining) framework, which pretrains the model on large datasets with both sparse-view and dense-view projections, and a two-step finetuning strategy to adapt and refine the model for new datasets. Extensive experiments and ablation studies demonstrate that our proposed DeepSparse achieves superior reconstruction quality compared to state-of-the-art methods, paving the way for safer and more efficient CBCT imaging.
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。