CoIL: Coordinate-Based Internal Learning for Tomographic Imaging
CoIL: Coordinate-Based Internal Learning for Tomographic Imaging
复制标题
DOI：
10.1109/tci.2021.3125564
复制
发表时间：
2021-01-01
影响因子：
5.4
通讯作者：
Kamilov, Ulugbek
中科院分区：
文献类型：
--
作者：
Sun, Yu;Liu, Jiaming;Kamilov, Ulugbek
我们提出了基于坐标的内部学习（CoIL）作为一种新的深度学习（DL）方法，用于连续表示测量值。与学习从测量到所需图像的映射的传统DL方法不同，CoIL训练多层感知器（MLP）通过将测量的坐标映射到其响应来编码完整的测量场。CoIL是一种自监督方法，除了测试对象本身的测量之外，不需要训练示例。一旦MLP被训练，CoIL生成新的测量结果，可以在大多数图像重建方法中使用。我们使用几种广泛使用的重建方法，包括纯粹基于模型的方法和基于DL的方法，在稀疏视图计算机断层扫描上验证CoIL。我们的研究结果表明，线圈的能力，不断提高所有考虑的方法，通过提供高保真度的测量领域的性能。
We propose Coordinate-based Internal Learning (CoIL) as a new deep-learning (DL) methodology for continuous representation of measurements. Unlike traditional DL methods that learn a mapping from the measurements to the desired image, CoIL trains a multilayer perceptron (MLP) to encode the complete measurement field by mapping the coordinates of the measurements to their responses. CoIL is a self-supervised method that requires no training examples besides the measurements of the test object itself. Once the MLP is trained, CoIL generates new measurements that can be used within most image reconstruction methods. We validate CoIL on sparse-view computed tomography using several widely-used reconstruction methods, including purely model-based methods and those based on DL. Our results demonstrate the ability of CoIL to consistently improve the performance of all the considered methods by providing high-fidelity measurement fields.