arXiv cs.AI· Jiening Zhu, Chengzhu Zhang, Jason Fan, LiCheng Kuo, Weixing Cai, Xiuxiu He, Laura Cervino, Jean Moran, Xiang Li, Tianfang Li, Yabo Fu·· 14 小时前AI 评分38
EUReCA：面向临床采集的端到端统一 CBCT 重建模型
EUReCA: End-to-End Unified CBCT Reconstruction Across Clinical Acquisitions
AI 导读
EUReCA 是一个几何感知的前馈模型，用同一套权重即可处理 8-100 个投影的临床直线加速器 CBCT 重建，无需按视角数重新训练，同一架构和训练方案可迁移到其他临床轨迹。在模拟数据上，10-100 视角下 PSNR 达 29.9-33.2 dB，优于所有适用的前馈基线，并超过迭代优化方法且速度快数个数量级。在 15 例实测患者 CBCT 扫描上，每个测试视角数下均取得最佳性能。
正文 · 原文
Authors:Jiening Zhu, Chengzhu Zhang, Jason Fan, LiCheng Kuo, Weixing Cai, Xiuxiu He, Laura Cervino, Jean Moran, Xiang Li, Tianfang Li, Yabo Fu
Abstract:Cone-beam computed tomography (CBCT) is widely used for image-guided radiotherapy, but reducing the number of projections to lower dose and scan time makes reconstruction increasingly ill-posed. We present EUReCA (End-to-end Unified REconstruction across Clinical Acquisitions), a geometry-aware feed-forward model for variable-view clinical linac CBCT. For a given acquisition trajectory, EUReCA accepts 8-100 projections with a single set of weights, without view-count-specific retraining; the same architecture and training recipe extend unchanged to other clinical trajectories. It combines learned projection features with an in-frame Feldkamp-Davis-Kress (FDK) reconstruction. The model encodes each projection with a shared multiscale backbone, back-projects features into multiresolution 3D grids using the acquisition geometry, aggregates variable numbers of views at fixed computational cost, and refines the volume with a global 3D transformer and multilevel decoder. On simulated data, EUReCA achieved 29.9-33.2 dB PSNR with 10-100 views and outperformed all applicable feed-forward baselines; it also exceeded iterative optimization-based methods while running orders of magnitude faster. On 15 measured patient CBCT scans evaluated against vendor reconstructions, EUReCA achieved the best performance at every tested view count. These results suggest that geometry-aware, measurement-anchored feed-forward reconstruction can provide a practical and flexible foundation for variable-view linac CBCT.
| Subjects: | Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37740 [eess.IV] |
| (or arXiv:2610.37740v1 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37740 arXiv-issued DOI via DataCite |
Submission history
From: Jiening Zhu [view email]
[v1]
Tue, 27 Oct 2026 16:52:56 UTC (8,467 KB)
来源：arXiv cs.AI · arxiv.org