arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.01658eess.IVcs.LGstat.ML
收藏

基于卷积和空间Transformer网络的无监督稀疏视图反投影

Unsupervised Sparse-view Backprojection via Convolutional and Spatial Transformer Networks

Columbia University(哥伦比亚大学)

Xueqing Liu, Paul Sajda

摘要:

许多成像技术依赖于断层重建,这需要在给定有限数量的投影的情况下求解多维逆问题。反投影是用于断层摄影重建的一类流行算法,然而,当投影角度稀疏和/或如果传感器特性不均匀时,反投影通常导致差的图像重建。已经开发了几种基于深度学习的算法来解决这个逆问题,并使用有限数量的投影重建图像。然而,这些算法通常需要地面实况的示例(即,重建图像的示例)来产生良好的性能。在本文中,我们介绍了一种无监督稀疏视图反投影算法,它不需要地面实况。该算法由两个模块组成的生成器投影框架;卷积神经网络和空间Transformer网络。我们评估我们的算法使用计算机断层扫描(CT)图像的人类胸部。我们表明,我们的算法显着优于过滤反投影时,投影角度非常稀疏,以及当传感器特性不同的角度。我们的方法具有实际应用的医学成像和其他成像方式(如雷达),稀疏和/或非均匀的投影可能会被收购由于时间或采样的限制。

英文摘要:

Many imaging technologies rely on tomographic reconstruction, which requires solving a multidimensional inverse problem given a finite number of projections. Backprojection is a popular class of algorithm for tomographic reconstruction, however it typically results in poor image reconstructions when the projection angles are sparse and/or if the sensors characteristics are not uniform. Several deep learning based algorithms have been developed to solve this inverse problem and reconstruct the image using a limited number of projections. However these algorithms typically require examples of the ground-truth (i.e. examples of reconstructed images) to yield good performance. In this paper, we introduce an unsupervised sparse-view backprojection algorithm, which does not require ground-truth. The algorithm consists of two modules in a generator-projector framework; a convolutional neural network and a spatial transformer network. We evaluated our algorithm using computed tomography (CT) images of the human chest. We show that our algorithm significantly out-performs filtered backprojection when the projection angles are very sparse, as well as when the sensor characteristics vary for different angles. Our approach has practical applications for medical imaging and other imaging modalities (e.g. radar) where sparse and/or non-uniform projections may be acquired due to time or sampling constraints.

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。

↑