RARE: Image Reconstruction Using Deep Priors Learned Without Groundtruth
RARE: Image Reconstruction Using Deep Priors Learned Without Groundtruth
复制标题
DOI：
10.1109/jstsp.2020.2998402
复制
发表时间：
2020-10-01
影响因子：
7.5
通讯作者：
Kamilov, Ulugbek S.
中科院分区：
文献类型：
--
作者：
Liu, Jiaming;Sun, Yu;Kamilov, Ulugbek S.
正则化去噪(RED)是一种使用图像去噪器作为先验的图像重建框架。最近的工作表明，RED具有与预先训练的卷积神经网络(CNN)相对应的学习去噪器的最先进的性能。在这项工作中，我们建议通过考虑与为更一般的伪像去除而训练的网络相对应的先验来拓宽当前以去噪为中心的RED的观点。提出的算法家族的主要好处是，它可以利用在只包含欠采样测量的数据集上学习的先验知识，被称为通过伪影去除正则化(REARE)。这使得很少适用于这样的问题，即几乎不可能有用于训练的完全采样的地面真实数据。我们在模拟和实验收集的数据上验证了REARE，从严重采样不足的k空间测量中将自由呼吸的全身3D磁共振成像重建为十个呼吸期。我们的结果证实了学习正则化直接用于欠采样和噪声测量的迭代反演的潜力。
Regularization by denoising (RED) is an image reconstruction framework that uses an image denoiser as a prior. Recent work has shown the state-of-the-art performance of RED with learned denoisers corresponding to pre-trained convolutional neural nets (CNNs). In this work, we propose to broaden the current denoiser-centric view of RED by considering priors corresponding to networks trained for more general artifact-removal. The key benefit of the proposed family of algorithms, called regularization by artifact-removal (RARE), is that it can leverage priors learned on datasets containing only undersampled measurements. This makes RARE applicable to problems where it is practically impossible to have fully-sampled groundtruth data for training. We validate RARE on both simulated and experimentally collected data by reconstructing a free-breathing whole-body 3D MRIs into ten respiratory phases from heavily undersampled k-space measurements. Our results corroborate the potential of learning regularizers for iterative inversion directly on undersampled and noisy measurements.