Department of Biomedical Engineering, Stony Brook University, School of Medicine, Stony Brook, NY 11794-5281, USA.
ALA Scientific Instruments, Inc., Farmingdale, NY, USA.
Neuroimage. 2021 Feb 15;227:117584. doi: 10.1016/j.neuroimage.2020.117584. Epub 2020 Dec 4.
The fMRI community has made great strides in decoupling neuronal activity from other physiologically induced T* changes, using sensors that provide a ground-truth with respect to cardiac, respiratory, and head movement dynamics. However, blood oxygenation level-dependent (BOLD) time-series dynamics are also confounded by scanner artifacts, in complex ways that can vary not only between scanners but even, for the same scanner, between sessions. Unfortunately, the lack of an equivalent ground truth for BOLD time-series has thus far stymied the development of reliable methods for identification and removal of scanner-induced noise, a problem that we have previously shown to severely impact detection sensitivity of resting-state brain networks. To address this problem, we first designed and built a phantom capable of providing dynamic signals equivalent to that of the resting-state brain. Using the dynamic phantom, we then compared the ground-truth time-series with its measured fMRI data. Using these, we introduce data-quality metrics: Standardized Signal-to-Noise Ratio (ST-SNR) and Dynamic Fidelity that, unlike currently used measures such as temporal SNR (tSNR), can be directly compared across scanners. Dynamic phantom data acquired from four "best-case" scenarios: high-performance scanners with MR-physicist-optimized acquisition protocols, still showed scanner instability/multiplicative noise contributions of about 6-18% of the total noise. We further measured strong non-linearity in the fMRI response for all scanners, ranging between 8-19% of total voxels. To correct scanner distortion of fMRI time-series dynamics at a single-subject level, we trained a convolutional neural network (CNN) on paired sets of measured vs. ground-truth data. The CNN learned the unique features of each session's noise, providing a customized temporal filter. Tests on dynamic phantom time-series showed a 4- to 7-fold increase in ST-SNR and about 40-70% increase in Dynamic Fidelity after denoising, with CNN denoising outperforming both the temporal bandpass filtering and denoising using Marchenko-Pastur principal component analysis. Critically, we observed that the CNN temporal denoising pushes ST-SNR to a regime where signal power is higher than that of noise (ST-SNR > 1). Denoising human-data with ground-truth-trained CNN, in turn, showed markedly increased detection sensitivity of resting-state networks. These were visible even at the level of the single-subject, as required for clinical applications of fMRI.
功能磁共振成像（fMRI）领域在利用能够提供心脏、呼吸和头部运动动力学真实情况的传感器，将神经元活动与其他生理诱导的 T*变化解耦方面取得了重大进展。然而，血氧水平依赖（BOLD）时间序列动力学也受到扫描器伪影的影响，其影响方式非常复杂，不仅在不同的扫描器之间有所不同，甚至在同一扫描器的不同扫描之间也有所不同。不幸的是，由于缺乏 BOLD 时间序列的等效真实情况，因此迄今为止，仍然无法开发出可靠的方法来识别和消除扫描器引起的噪声，我们之前已经表明，这一问题严重影响了静息态脑网络检测的灵敏度。为了解决这个问题，我们首先设计并构建了一个能够提供与静息态大脑等效动态信号的幻影。然后，我们使用动态幻影将真实时间序列与其测量的 fMRI 数据进行比较。利用这些数据，我们引入了数据质量指标：标准化信噪比（ST-SNR）和动态保真度，与当前使用的时间信噪比（tSNR）等指标不同，它们可以在不同的扫描器之间直接比较。从四个“最佳情况”场景中获取的动态幻影数据：具有经过 MR 物理学家优化的采集协议的高性能扫描仪，仍然显示出约 6-18%的总噪声的扫描仪不稳定性/乘法噪声贡献。我们还测量了所有扫描仪的 fMRI 响应的强烈非线性，范围在总体素的 8-19%之间。为了在单个主体水平上校正 fMRI 时间序列动力学的扫描器失真，我们在测量值和真实值的成对数据上训练了一个卷积神经网络（CNN）。CNN 学习了每个会话噪声的独特特征，提供了一个定制的时间滤波器。在动态幻影时间序列上的测试表明，经过去噪后，ST-SNR 增加了 4-7 倍，动态保真度增加了约 40-70%，CNN 去噪的效果优于时间带通滤波和使用 Marchenko-Pastur 主成分分析的去噪。至关重要的是，我们观察到，CNN 时间去噪将 ST-SNR 推到信号功率高于噪声的区域（ST-SNR>1）。用经过真实值训练的 CNN 对人类数据进行去噪，反过来又显著提高了静息态网络的检测灵敏度。即使在单个主体的水平上也可以看到这些变化，这是 fMRI 临床应用所需要的。
