arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.04058math.OCcs.AIcs.NAmath.FAmath.NA
收藏

使用迭代深度神经网络求解病态反问题

Solving ill-posed inverse problems using iterative deep neural networks

KTH - Royal Institute of Technology(瑞典皇家理工学院);Elekta AB(医科达公司)

Jonas Adler, Ozan Öktem

AI总结:

本文提出了一种部分学习方法,利用深度学习和经典正则化理论解决非线性反问题,通过卷积网络学习梯度组件,提升重建速度和PSNR性能。

摘要:

我们提出了一种部分学习方法,用于求解非线性正则化反问题。该方法结合经典正则化理论和深度学习进展,利用正则化函数、前向算子和噪声模型的先验信息进行学习。结果是一种梯度样迭代方案,其中梯度组件通过卷积网络学习,输入数据不一致性和正则化器的梯度。我们在非线性断层成像问题中测试了该方法,使用Sheep-Logan幻影和头CT模拟数据,结果优于FBP和TV重建,PSNR提升5.4 dB,速度显著加快,单GPU约0.4秒完成512x512体积重建。

英文摘要:

We propose a partially learned approach for the solution of ill posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regularization theory and recent advances in deep learning to perform learning while making use of prior information about the inverse problem encoded in the forward operator, noise model and a regularizing functional. The method results in a gradient-like iterative scheme, where the "gradient" component is learned using a convolutional network that includes the gradients of the data discrepancy and regularizer as input in each iteration. We present results of such a partially learned gradient scheme on a non-linear tomographic inversion problem with simulated data from both the Sheep-Logan phantom as well as a head CT. The outcome is compared against FBP and TV reconstruction and the proposed method provides a 5.4 dB PSNR improvement over the TV reconstruction while being significantly faster, giving reconstructions of 512 x 512 volumes in about 0.4 seconds using a single GPU.

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。

↑