We address the problem of reconstructing X-Ray tomographic images from scarce measurements by interpolating missing acquisitions using a self-supervised approach. To do so, we train shallow neural networks to combine two neighbouring acquisitions into an estimated measurement at an intermediate angle. This procedure yields an enhanced sequence of measurements that can be reconstructed using standard methods, or further enhanced using regularisation approaches. Unlike methods that improve the sequence of acquisitions using an initial deterministic interpolation followed by machine-learning enhancement, we focus on inferring one measurement at once. This allows the method to scale to 3D, the computation to be faster and crucially, the interpolation to be significantly better than the current methods, when they exist. We also establish that a sequence of measurements must be processed as such, rather than as an image or a volume. We do so by comparing interpolation and up-sampling methods, and find that the latter significantly under-perform. We compare the performance of the proposed method against deterministic interpolation and up-sampling procedures and find that it outperforms them, even when used jointly with a state-of-the-art projection-data enhancement approach using machine-learning. These results are obtained for 2D and 3D imaging, on large biomedical datasets, in both projection space and image space.
翻译:我们通过采用自我监督的方法,从稀缺的测量中通过对缺失的获取进行内插,对X光成像图像进行重建,以解决从稀缺的测量中重建X光成像的问题。为此,我们训练浅度神经网络,将两个相邻的获取合并为中间角度的估计测量。这一程序产生一个强化的测量序列,可以使用标准方法加以重建,或者使用规范化方法进一步加强。与采用初步确定性内插法和机械学习强化后改进采购序列的方法不同,我们注重一次推断一种测量。这样,就可以将方法推广到3D,计算速度和关键程度要快得多,内部推断比现有方法要好得多。我们还确定测量序列必须按此进行处理,而不是作为图像或数量进行。我们这样做的方法是比较内插法和升级方法,发现后者明显不完善。我们比较了拟议方法的性能与确定性内插法和升级程序,并发现它超越了它们,即使在使用了现有方法时,也比目前的方法更好得多。 我们还确定测量了测量序列的顺序,而不是作为图像或大规模图像的模型学习方法。