期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 37, 期 6, 页码 1440-1453出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2018.2832656
关键词
Deep learning; inverse problems; biomedical image reconstruction; low-dose computed tomography
类别
资金
- European Research Council (H2020-ERC Project GlobalBioIm) [692726]
- European Union's Horizon 2020 Framework Programme for Research and Innovation [665667]
- European Research Council (ERC) [692726] Funding Source: European Research Council (ERC)
We present a new image reconstruction method that replaces the projector in a projected gradient descent (PGD) with a convolutional neural network (CNN). Recently, CNNs trained as image-to-image regressors have been successfully used to solve inverse problems in imaging. However, unlike existing iterative image reconstruction algorithms, these CNN-based approaches usually lack a feedback mechanism to enforce that the reconstructed image is consistent with the measurements. We propose a relaxed version of PGD wherein gradient descent enforces measurement consistency, while a CNN recursively projects the solution closer to the space of desired reconstruction images. We show that this algorithm is guaranteed to converge and, under certain conditions, converges to a local minimum of a non-convex inverse problem. Finally, we propose a simple scheme to train the CNN to act like a projector. Our experiments on sparse-view computed-tomography reconstruction show an improvement over total variation-based regularization, dictionary learning, and a state-of-the-art deep learning-based direct reconstruction technique.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据