Mobarak-Abadi Mahdi, Mahmoudi-Aznaveh Ahmad, Dehghani Hamed, Zarei Mojtaba, Vahdat Shahabeddin, Doyon Julien, Khatibi Ali
Institute of Medical Science and Technology, Shahid Beheshti University, Tehran, Iran.
Cyberspace Research Institute, Shahid Beheshti University, Tehran, Iran.
Front Psychiatry. 2024 Jun 28;15:1323109. doi: 10.3389/fpsyt.2024.1323109. eCollection 2024.
There are distinct challenges in the preprocessing of spinal cord fMRI data, particularly concerning the mitigation of voluntary or involuntary movement artifacts during image acquisition. Despite the notable progress in data processing techniques for movement detection and correction, applying motion correction algorithms developed for the brain cortex to the brainstem and spinal cord remains a challenging endeavor.
In this study, we employed a deep learning-based convolutional neural network (CNN) named DeepRetroMoCo, trained using an unsupervised learning algorithm. Our goal was to detect and rectify motion artifacts in axial T2*-weighted spinal cord data. The training dataset consisted of spinal cord fMRI data from 27 participants, comprising 135 runs for training and 81 runs for testing.
To evaluate the efficacy of DeepRetroMoCo, we compared its performance against the sct_fmri_moco method implemented in the spinal cord toolbox. We assessed the motion-corrected images using two metrics: the average temporal signal-to-noise ratio (tSNR) and Delta Variation Signal (DVARS) for both raw and motion-corrected data. Notably, the average tSNR in the cervical cord was significantly higher when DeepRetroMoCo was utilized for motion correction, compared to the sct_fmri_moco method. Additionally, the average DVARS values were lower in images corrected by DeepRetroMoCo, indicating a superior reduction in motion artifacts. Moreover, DeepRetroMoCo exhibited a significantly shorter processing time compared to sct_fmri_moco.
Our findings strongly support the notion that DeepRetroMoCo represents a substantial improvement in motion correction procedures for fMRI data acquired from the cervical spinal cord. This novel deep learning-based approach showcases enhanced performance, offering a promising solution to address the challenges posed by motion artifacts in spinal cord fMRI data.
脊髓功能磁共振成像（fMRI）数据的预处理存在明显挑战，尤其是在图像采集过程中减轻自愿或非自愿运动伪影方面。尽管在运动检测和校正的数据处理技术方面取得了显著进展，但将为大脑皮层开发的运动校正算法应用于脑干和脊髓仍然是一项具有挑战性的工作。
在本研究中，我们采用了一种基于深度学习的卷积神经网络（CNN），名为DeepRetroMoCo，使用无监督学习算法进行训练。我们的目标是检测并纠正轴向T2 *加权脊髓数据中的运动伪影。训练数据集由27名参与者的脊髓fMRI数据组成，包括135次用于训练的扫描和81次用于测试的扫描。
为了评估DeepRetroMoCo的有效性，我们将其性能与脊髓工具箱中实现的sct_fmri_moco方法进行了比较。我们使用两个指标评估运动校正后的图像：原始数据和运动校正后数据的平均时间信噪比（tSNR）和Delta变化信号（DVARS）。值得注意的是，与sct_fmri_moco方法相比，当使用DeepRetroMoCo进行运动校正时，颈髓中的平均tSNR显著更高。此外，DeepRetroMoCo校正后的图像中平均DVARS值更低，表明运动伪影减少得更明显。此外，与sct_fmri_moco相比，DeepRetroMoCo的处理时间明显更短。
我们的研究结果有力地支持了这样一种观点，即DeepRetroMoCo在从颈髓获取的fMRI数据的运动校正程序方面代表了实质性的改进。这种基于深度学习的新方法展示了更高的性能，为解决脊髓fMRI数据中运动伪影带来的挑战提供了一个有前景的解决方案。
