超越均方误差：基于莱斯似然去噪的自监督心脏T2和T1ρ磁共振成像
Beyond MSE: Rician Likelihood Denoising for Self-Supervised Cardiac $T2$ and $T1ρ$ MRI
- University of Utah（犹他大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对心脏MRI自监督去噪中MSE损失假设不匹配幅度噪声的问题，提出基于莱斯噪声模型的最大似然估计方法，实现无偏去噪，性能与监督基线相当。
AI中文摘要：
磁共振成像在空间分辨率、采集时间和噪声之间存在固有的权衡。这种权衡导致扫描时间长且成本高昂。深度学习改善了图像去噪，但心脏磁共振成像仍然困难，因为高分辨率、快速采集通常缺乏相应的低噪声金标准。自监督去噪通过从噪声图像对甚至单个噪声采集中学习，提供了一种潜在的解决方案。然而，我们表明，Noise2Void风格的盲点去噪使用均方误差（MSE）损失并假设零均值、独立同分布（i.i.d.）噪声，不适用于磁共振幅度图像。当应用于带有合成莱斯噪声的短轴T2加权和T1ρ加权心脏磁共振成像时，它会产生有偏的去噪图像以及有偏的T2和T1ρ参数图。为了解决这一局限性，我们将自监督去噪表述为在已知莱斯噪声模型下的最大似然估计。这产生了与监督基线竞争的无偏去噪器。
英文摘要：
Magnetic resonance imaging involves an inherent trade-off among spatial resolution, acquisition time, and noise. This trade-off contributes to long scan times and high cost. Deep learning has improved image denoising, but cardiac MRI remains difficult because high-resolution, rapid acquisitions generally lack corresponding low-noise ground truth. Self-supervised denoising offers a potential solution by learning from noisy image pairs or even single noisy acquisitions. However, we show that Noise2Void-style blind-spot denoising, which uses a mean squared error (MSE) loss and assumes zero-mean, independent and identically distributed (i.i.d.) noise, is poorly suited to MR magnitude images. When applied to short-axis $T2$-weighted and $T1ρ$-weighted cardiac MRI with synthetic Rician noise, it produces biased denoised images and biased parametric maps of $T2$ and $T1ρ$. To address this limitation, we formulate self-supervised denoising as maximum likelihood estimation under a known Rician noise model. This yields unbiased denoisers that are competitive with supervised baselines.
