arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00930physics.med-phcs.CVcs.LGcs.SYeess.IVeess.SY
收藏

医学图像变换的无监督动态建模

Unsupervised dynamic modeling of medical image transformation

Uppsala University(乌普萨拉大学);Elekta Instrument AB(医科达仪器公司)

Niklas Gunnarsson, Peter Kimstrand, Jens Sjölund, Thomas B. Schön

AI总结:

本文提出一种基于CVAE和LG-SSM的无监督动态模型,通过空间变换解释医学图像序列的时间运动,实现更清晰重建、辅助信息传递及缺失样本插补,在心脏超声上执行时间优于传统配准且性能相当。

摘要:

时空成像在心脏诊断、手术引导和放射治疗监测等方面有应用。本文仅基于序列图像,通过识别潜在的动态来解释时间运动。我们的动态模型将观测的高维序列图像输入映射到低维潜在空间,其中隐藏状态过程与输入的低维表示之间存在线性关系。为此,我们使用条件变分自编码器(CVAE)将高维图像非线性映射到低维空间,并在其中用线性高斯状态空间模型(LG-SSM)对动态进行建模。该模型是Kalman变分自编码器的修改版本,可端到端训练,且CVAE和LG-SSM中的权重通过最大化边际似然的证据下界同时更新。与原始模型不同,我们用从一幅图像到另一幅图像的空间变换来解释运动。这产生了更清晰的重建,并使得能够通过图像序列传递辅助信息(如分割)。我们在心脏超声时间序列上的实验表明,该动态模型在执行时间上优于传统图像配准,且性能相似。此外,我们的模型提供了对缺失样本进行插补和外推的可能性。

英文摘要:

Spatiotemporal imaging has applications in e.g. cardiac diagnostics, surgical guidance, and radiotherapy monitoring, In this paper, we explain the temporal motion by identifying the underlying dynamics, only based on the sequential images. Our dynamical model maps the inputs of observed high-dimensional sequential images to a low-dimensional latent space wherein a linear relationship between a hidden state process and the lower-dimensional representation of the inputs holds. For this, we use a conditional variational auto-encoder (CVAE) to nonlinearly map the higher-dimensional image to a lower-dimensional space, wherein we model the dynamics with a linear Gaussian state-space model (LG-SSM). The model, a modified version of the Kalman variational auto-encoder, is end-to-end trainable, and the weights, both in the CVAE and LG-SSM, are simultaneously updated by maximizing the evidence lower bound of the marginal likelihood. In contrast to the original model, we explain the motion with a spatial transformation from one image to another. This results in sharper reconstructions and the possibility of transferring auxiliary information, such as segmentation, through the image sequence. Our experiments, on cardiac ultrasound time series, show that the dynamic model outperforms traditional image registration in execution time, to a similar performance. Further, our model offers the possibility to impute and extrapolate for missing samples.

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。

↑