arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.00646eess.IVcs.LG
收藏

断层图像重建中的幻觉问题

On hallucinations in tomographic image reconstruction

Washington University in St. Louis(圣路易斯华盛顿大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Sayantan Bhadra, Varun A. Kelkar, Frank J. Brooks, Mark A. Anastasio

摘要:

层析图像重建一般是一个不适定的线性逆问题。这种不适定的逆问题通常使用所寻求的对象属性的先验知识进行正则化。最近,深度神经网络已经被积极地研究用于通过从训练图像学习对象属性的先验来正则化图像重建问题。然而,对这些深度网络学习到的先验信息的分析,以及它们泛化到可能位于训练分布之外的数据的能力,仍在探索中。不准确的先验可能导致重建图像中出现虚假结构,这是医学成像中严重关注的原因。在这项工作中,我们提出了通过将图像估计分解为广义测量和零分量来说明重建方法所施加的先验效果。为了理解正则化重建方法中先验的影响,引入了幻觉图的概念。数值研究进行对应的程式化的断层成像方式。不同的重建方法下提出的形式主义的行为进行了讨论的数值研究的帮助下。

英文摘要:

Tomographic image reconstruction is generally an ill-posed linear inverse problem. Such ill-posed inverse problems are typically regularized using prior knowledge of the sought-after object property. Recently, deep neural networks have been actively investigated for regularizing image reconstruction problems by learning a prior for the object properties from training images. However, an analysis of the prior information learned by these deep networks and their ability to generalize to data that may lie outside the training distribution is still being explored. An inaccurate prior might lead to false structures being hallucinated in the reconstructed image and that is a cause for serious concern in medical imaging. In this work, we propose to illustrate the effect of the prior imposed by a reconstruction method by decomposing the image estimate into generalized measurement and null components. The concept of a hallucination map is introduced for the general purpose of understanding the effect of the prior in regularized reconstruction methods. Numerical studies are conducted corresponding to a stylized tomographic imaging modality. The behavior of different reconstruction methods under the proposed formalism is discussed with the help of the numerical studies.

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。

↑