通过姿态对齐提升医学影像中部分形状的重建精度
Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models
- 用目标特定姿态调整现有统计模型，保持线性模型高效性
- 对平移完全恢复，小旋转近似准确，显著提升重建效果
- 无需原始训练数据，可作为预处理直接嵌入现有流程
在医学影像中，点分布模型常用于基于完整形状的统计模型来重建和补全部分形状。然而，训练数据与目标形状之间的姿态差异是常被忽视但至关重要的因素，尤其当观察到的形状部分较小时，会导致偏差。本文揭示了姿态对齐在部分形状重建中的重要性，并提出一种高效方法，将现有模型适配到特定目标。该方法在保持线性模型计算效率的同时，显著提升重建准确性和预测方差。对于平移，能精确恢复对齐模型；对小旋转，提供良好近似，且无需访问原始训练数据。因此，现有形状模型可通过简单预处理步骤进行适应，适用于即插即用场景。
原文摘要 · Abstract (English)
In medical imaging, point distribution models are often used to reconstruct and complete partial shapes using a statistical model of the full shape. A commonly overlooked, but crucial factor in this reconstruction process, is the pose of the training data relative to the partial target shape. A difference in pose alignment of the training and target shape leads to biased solutions, particularly when observing small parts of a shape. In this paper, we demonstrate the importance of pose alignment for partial shape reconstructions and propose an efficient method to adjust an existing model to a specific target. Our method preserves the computational efficiency of linear models while significantly improving reconstruction accuracy and predicted variance. It exactly recovers the intended aligned model for translations, and provides a good approximation for small rotations, all without access to the original training data. Hence, existing shape models in reconstruction pipelines can be adapted by a simple preprocessing step, making our approach widely applicable in plug-and-play scenarios.
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。