arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.10657cs.LG
收藏

基于物理字典的稀疏信号分解驱动的深度神经网络求解逆问题

Solving inverse problems with deep neural networks driven by sparse signal decomposition in a physics-based dictionary

ICTEAM Institute(ICTEAM研究所);Université catholique de Louvain(鲁汶天主教大学)

Gaetan Rensonnet, Louise Adam, Benoit Macq

摘要:

深度神经网络(DNN)具有令人印象深刻的能力来反演非常复杂的模型,即从模型的输出中学习生成参数。一旦经过训练,DNN的前向传递通常比用于解决逆问题的传统基于优化的方法快得多。然而,这是以较低的可解释性为代价的,这是大多数医疗应用中的基本限制。我们提出了一种解决一般反问题的方法,它结合了DNN的效率和传统分析方法的可解释性。首先将测量值投影到基于模型的响应的密集字典上。然后将得到的稀疏表示馈送到DNN,该DNN具有由问题的物理驱动的架构,以进行快速参数学习。我们的方法可以处理生成的前向模型,这些模型的评估成本很高,并且在准确性和计算时间方面表现出与完全学习的DNN相似的性能,同时保持高度的可解释性,并且更容易训练。具体的结果示出了基于模型的脑参数估计的磁共振成像(MRI)的一个例子。

英文摘要:

Deep neural networks (DNN) have an impressive ability to invert very complex models, i.e. to learn the generative parameters from a model's output. Once trained, the forward pass of a DNN is often much faster than traditional, optimization-based methods used to solve inverse problems. This is however done at the cost of lower interpretability, a fundamental limitation in most medical applications. We propose an approach for solving general inverse problems which combines the efficiency of DNN and the interpretability of traditional analytical methods. The measurements are first projected onto a dense dictionary of model-based responses. The resulting sparse representation is then fed to a DNN with an architecture driven by the problem's physics for fast parameter learning. Our method can handle generative forward models that are costly to evaluate and exhibits similar performance in accuracy and computation time as a fully-learned DNN, while maintaining high interpretability and being easier to train. Concrete results are shown on an example of model-based brain parameter estimation from magnetic resonance imaging (MRI).

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。

↑