Reliable MRI is crucial for accurate interpretation in therapeutic and diagnostic tasks. However, undersampling during MRI acquisition as well as the overparameterized and non-transparent nature of deep learning (DL) leaves substantial uncertainty about the accuracy of DL reconstruction. With this in mind, this study aims to quantify the uncertainty in image recovery with DL models. To this end, we first leverage variational autoencoders (VAEs) to develop a probabilistic reconstruction scheme that maps out (low-quality) short scans with aliasing artifacts to the diagnostic-quality ones. The VAE encodes the acquisition uncertainty in a latent code and naturally offers a posterior of the image from which one can generate pixel variance maps using Monte-Carlo sampling. Accurately predicting risk requires knowledge of the bias as well, for which we leverage Stein’s Unbiased Risk Estimator (SURE) as a proxy for mean-squared-error (MSE). A range of empirical experiments is performed for Knee MRI reconstruction under different training losses (adversarial and pixel-wise) and unrolled recurrent network architectures. Our key observations indicate that: 1) adversarial losses introduce more uncertainty; and 2) recurrent unrolled nets reduce the prediction uncertainty and risk.

中文翻译：

---

深度 MRI 重建中的不确定性量化。

可靠的 MRI 对于准确解释治疗和诊断任务至关重要。然而，MRI 采集过程中的欠采样以及深度学习 (DL) 的过度参数化和不透明性质给 DL 重建的准确性带来了很大的不确定性。考虑到这一点，本研究旨在量化深度学习模型图像恢复的不确定性。为此，我们首先利用变分自动编码器（VAE）开发一种概率重建方案，将具有混叠伪影的（低质量）短扫描映射到诊断质量的扫描。VAE 将采集不确定性编码在潜在代码中，并自然地提供图像的后验，从中可以使用蒙特卡罗采样生成像素方差图。准确预测风险还需要了解偏差，为此我们利用 Stein 的无偏风险估计器 (SURE) 作为均方误差 (MSE) 的代理。在不同的训练损失（对抗性和像素级）和展开的循环网络架构下，对膝关节 MRI 重建进行了一系列经验实验。我们的主要观察结果表明：1）对抗性损失带来了更多的不确定性；2）循环展开的网络降低了预测的不确定性和风险。