arrow
返回

MoDL: Model-Based Deep Learning Architecture for Inverse Problems

delete2019-02-01
delete728
delete
OA
AI
H
Hemant Kumar Aggarwal *
M
Merry Mani
M
Mathews Jacob
DOI:10.1109/TMI.2018.2865356delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
We introduce a model-based image reconstruction framework with a convolution neural network (CNN)-based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with the arbitrary structure. Since the forward model is explicitly accounted for, a smaller network with fewer parameters is sufficient to capture the image information compared to direct inversion approaches. Thus, reducing the demand for training data and training time. Since we rely on end-to-end training with weight sharing across iterations, the CNN weights are customized to the forward model, thus offering improved performance over approaches that rely on pre-trained denoisers. Our experiments show that the decoupling of the number of iterations from the network complexity offered by this approach provides benefits, including lower demand for training data, reduced risk of overfitting, and implementations with significantly reduced memory footprint. We propose to enforce data-consistency by using numerical optimization blocks, such as conjugate gradients algorithm within the network. This approach offers faster convergence per iteration, compared to methods that rely on proximal gradients steps to enforce data consistency. Our experiments show that the faster convergence translates to improved performance, primarily when the available GPU memory restricts the number of iterations.
Keyword:
Deep learning
parallel imaging
convolutional neural network
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Medical Imaging 封面图
IEEE Transactions on Medical Imaging
IF:
9.8
论文数:
6.2K
被引数:
3.7W

机构

U
University of Iowa
学者数:
2.8W
论文数: 2.3W
被引数: 600
引用论文

引用论文

Learning a variational network for reconstruction of accelerated MRI data学习用于重建加速MRI数据的变分网络
err2017-11-08
err1.2K
errOAAI
errHammernik, Kerstin; Klatzer, Teresa; Kobler, Erich; Recht, Michael P.; Sodickson, Daniel K.; Pock, Thomas; Knoll, Florian
err分享
err收藏
err分享
err收藏
A Perspective on Deep Imaging
err2016-01-01
err352
errOAAI
errWang, Ge
err分享
err收藏
err分享
err收藏
学者 查看更多内容