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.

中文翻译：

---

罕见：使用深度先验学习的图像重建，无需地面实况

去噪正则化 (RED) 是一种使用图像去噪器作为先验的图像重建框架。最近的工作已经展示了 RED 的最先进性能，其学习降噪器对应于预训练的卷积神经网络 (CNN)。在这项工作中，我们建议通过考虑与为更一般的伪影去除而训练的网络相对应的先验来拓宽当前以降噪器为中心的 RED 观点。所提出的算法系列的主要好处，称为通过工件去除（RARE）进行正则化，它可以利用在仅包含欠采样测量的数据集上学习的先验。这使得 RARE 适用于几乎不可能有完全采样的地面实况数据进行训练的问题。我们通过将自由呼吸的全身 3D MRI 从严重欠采样的 k 空间测量重建为十个呼吸阶段，在模拟和实验收集的数据上验证了 RARE。我们的结果证实了直接在欠采样和噪声测量上学习正则化器进行迭代反演的潜力。