arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.02177eess.IVcs.CV
收藏

面向扇形束CT重建的基于梯度的几何学习

Gradient-Based Geometry Learning for Fan-Beam CT Reconstruction

FAU Erlangen-Nürnberg(埃尔朗根-纽伦堡大学);Siemens Healthcare GmbH(西门子医疗有限公司)
Mareike Thies, Fabian Wagner, Noah Maul, Lukas Folle, Manuela Meier, Maximilian Rohleder, Linda-Sophie Schneider, Laura Pfaff, Mingxuan Gu, Jonas Utz, Felix Den… 展开作者

Mareike Thies, Fabian Wagner, Noah Maul, Lukas Folle, Manuela Meier, Maximilian Rohleder, Linda-Sophie Schneider, Laura Pfaff, Mingxuan Gu, Jonas Utz, Felix Denzinger, Michael Manhart, Andreas Maier

AI总结:

该研究将扇形束CT重建的可微公式扩展到采集几何结构,实现梯度向几何参数的传播,首次用解析梯度优化自动对焦启发的运动补偿算法,显著提升重建质量,还可应用于扫描仪校准等场景。

摘要:

将计算机断层扫描(CT)重建算子整合到可微流水线中已在诸多应用中被证实有效。这类方法通常聚焦于投影数据,且保持采集几何结构固定。然而,精确掌握采集几何结构对于获得高质量重建结果至关重要。本文将扇形束CT重建的可微公式扩展至采集几何结构层面,使得重建图像上损失函数的梯度信息能够反向传播到几何参数中。作为概念验证实验,该思路被应用于刚性运动补偿。代价函数由一个经训练的神经网络参数化,该网络仅从受运动影响的重建结果中回归出图像质量指标。借助所提方法,我们首次基于解析梯度优化了这种受自动对焦启发的算法。与受运动影响的重建结果相比,该算法的均方误差(MSE)降低了35.5%,结构相似性指数(SSIM)提升了12.6%。除运动补偿外,我们认为该可微方法还可应用于扫描仪校准或结合深度模型的混合技术等场景。

英文摘要:

Incorporating computed tomography (CT) reconstruction operators into differentiable pipelines has proven beneficial in many applications. Such approaches usually focus on the projection data and keep the acquisition geometry fixed. However, precise knowledge of the acquisition geometry is essential for high quality reconstruction results. In this paper, the differentiable formulation of fan-beam CT reconstruction is extended to the acquisition geometry. This allows to propagate gradient information from a loss function on the reconstructed image into the geometry parameters. As a proof-of-concept experiment, this idea is applied to rigid motion compensation. The cost function is parameterized by a trained neural network which regresses an image quality metric from the motion affected reconstruction alone. Using the proposed method, we are the first to optimize such an autofocus-inspired algorithm based on analytical gradients. The algorithm achieves a reduction in MSE by 35.5 % and an improvement in SSIM by 12.6 % over the motion affected reconstruction. Next to motion compensation, we see further use cases of our differentiable method for scanner calibration or hybrid techniques employing deep models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑