基于分割的自监督稀疏视图CT重建中的设计选择
Design Choices in Splitting-Based Self-Supervised Sparse-View CT Reconstruction
浏览论文内容
中文总结 AI 辅助
研究基于分割的自监督稀疏视图CT重建中关键设计选择的影响，引入统一框架分解重建为三组件，通过实验表明最优划分策略依赖噪声结构，多划分分割表现优，结果为方法设计提供指南并凸显独立性假设局限。
中文摘要 AI 辅助
自监督数据分割已成为稀疏视图CT重建的一种有前景的范式，可从不完整测量中训练，无需完全采样的真实数据。然而，关键设计选择（包括划分策略、预处理和推理）的影响仍未得到充分理解。本文引入统一框架，将基于分割的重建分解为这三个组件，实现对现有方法及两个增量扩展（多划分分割和替代推理策略）的可控比较。在模拟LoDoPaB-CT数据上的实验以及在真实2DeteCT数据集上的验证表明，最优划分策略强烈依赖于测量噪声结构。基于格点的分割在独立噪声下表现良好，而角度掩蔽在相关噪声和真实测量数据下更稳健。多划分分割在多种设置下始终优于纯投影方式分割。互补的感知和结构指标揭示了掩蔽策略之间的差异，这些差异仅从PSNR和SSIM中不太明显。这些结果为设计自监督稀疏视图CT重建方法提供了实用指南，并突出了现实成像环境中常见独立性假设的局限性。
英文摘要
Self-supervised data splitting has emerged as a promising paradigm for sparse-view CT reconstruction, enabling training from incomplete measurements without fully sampled ground truth. However, the influence of key design choices, including partitioning strategy, preprocessing, and inference, remains insufficiently understood. In this work, we introduce a unified framework that decomposes splitting-based reconstruction into these three components, enabling controlled comparison of existing methods and two incremental extensions: multi-partition splitting and an alternative inference strategy. Experiments on simulated LoDoPaB-CT data under independent and correlated noise, together with validation on the real-world 2DeteCT dataset, show that the optimal partitioning strategy strongly depends on the measurement noise structure. Lattice-based splitting performs favorably under independent noise, whereas angular masking is more robust under correlated noise and real measured data. Multi-partition splitting consistently improves over pure projection-wise splitting in several settings. Complementary perceptual and structural metrics, including LPIPS and HaarPSI, reveal differences between masking strategies that are less apparent from PSNR and SSIM alone. These results provide practical guidelines for designing self-supervised sparse-view CT reconstruction methods and highlight the limitations of common independence assumptions in realistic imaging environments.
发表机构
- University of Innsbruck（因斯布鲁克大学）
- Institute of Basic Sciences in Engineering Science, University of Innsbruck（因斯布鲁克大学工程科学基础科学研究所）
- University of Cambridge（剑桥大学）
- Yeungnam University（岭南大学）
- University of Applied Sciences Kufstein（库夫施泰因应用科学大学）
机构由 AI 辅助整理，请以论文原文为准。
