Pan Hujie, Zhang Fuhao, Li Xuesong, Xu Min
Appl Opt. 2021 Aug 1;60(22):6469-6478. doi: 10.1364/AO.427578.
Classic algorithms for computed tomography of chemiluminescence include two main steps: tomographic weight matrix calculation using imaging models, and inverse calculation using algebraic reconstruction techniques (ARTs). However, pre-calculated weight matrices require a large amount of storage, and accurate voxel weights may not be obtained using a simplified imaging model. In this study, we propose a new, to the best of our knowledge, method named the multi-weight encode reconstruction network (Multi-WERNet) to learn the implicit light propagation physics from the multi-projections of different flames and simultaneously reconstruct the 3D flame chemiluminescence. The reconstructed results from Multi-WERNet are close to those of ART, and no radial streak is found, which is commonly seen in ART-based methods. With the help of information from different flames, the results reconstructed with 5 views using Multi-WERNet outperform the ART method. Moreover, Multi-WERNet successfully learns the implicit light propagation physics as a voxel weight encoder and can be transferred to unseen cases. Finally, Multi-WERNet is found to have higher robustness than ART in reconstruction with imperfect projections, which makes the algorithm more practical.
使用成像模型进行断层权重矩阵计算，以及使用代数重建技术（ART）进行反演计算。然而，预先计算的权重矩阵需要大量存储空间，并且使用简化成像模型可能无法获得准确的体素权重。在本研究中，据我们所知，我们提出了一种名为多权重编码重建网络（Multi-WERNet）的新方法，以从不同火焰的多投影中学习隐式光传播物理，并同时重建三维火焰化学发光。Multi-WERNet的重建结果与ART的结果接近，并且未发现基于ART的方法中常见的径向条纹。借助来自不同火焰的信息，使用Multi-WERNet从5个视图重建的结果优于ART方法。此外，Multi-WERNet成功地将隐式光传播物理学习为体素权重编码器，并且可以转移到未见案例。最后，发现在使用不完美投影进行重建时，Multi-WERNet比ART具有更高的鲁棒性，这使得该算法更具实用性。
