Addeh Abdoljalil, Vega Fernando, Morshedi Amin, Williams Rebecca J, Pike G Bruce, MacDonald M Ethan
Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada.
Department of Electrical & Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada.
Magn Reson Med. 2025 Mar;93(3):1365-1379. doi: 10.1002/mrm.30330. Epub 2024 Oct 31.
External physiological monitoring is the primary approach to measure and remove effects of low-frequency respiratory variation from BOLD-fMRI signals. However, the acquisition of clean external respiratory data during fMRI is not always possible, so recent research has proposed using machine learning to directly estimate respiratory variation (RV), potentially obviating the need for external monitoring. In this study, we propose an extended method for reconstructing RV waveforms directly from resting state BOLD-fMRI data in healthy adult participants with the inclusion of both BOLD signals and derived head motion parameters.
In the proposed method, 1D convolutional neural networks (1D-CNNs) used BOLD signals and head motion parameters to reconstruct the RV waveform for the whole fMRI scan time. Resting-state fMRI data and associated respiratory records from the Human Connectome Project in Young Adults (HCP-YA) dataset are used to train and test the proposed method.
Compared to using only BOLD-fMRI data for a CNN input, this approach yielded improvements of 14% in mean absolute error, 24% in mean square error, 14% in correlation, and 12% in dynamic time warping. When tested on independent datasets, the method demonstrated generalizability, even in data with different TRs and physiological conditions.
This study shows that the respiratory variations could be reconstructed from BOLD-fMRI data in the young adult population, and its accuracy could be improved using supportive data such as head motion parameters. The method also performed well on independent datasets with different experimental conditions.
外部生理监测是测量并去除BOLD-fMRI信号中低频呼吸变化影响的主要方法。然而，在功能磁共振成像（fMRI）过程中获取纯净的外部呼吸数据并非总是可行的，因此最近的研究提出使用机器学习直接估计呼吸变化（RV），这可能无需外部监测。在本研究中，我们提出了一种扩展方法，用于直接从健康成年参与者的静息态BOLD-fMRI数据中重建RV波形，该方法纳入了BOLD信号和导出的头部运动参数。
在所提出的方法中，一维卷积神经网络（1D-CNN）使用BOLD信号和头部运动参数来重建整个fMRI扫描时间内的RV波形。来自人类连接组计划青年成人数据集（HCP-YA）的静息态fMRI数据及相关呼吸记录用于训练和测试所提出的方法。
与仅将BOLD-fMRI数据用作卷积神经网络（CNN）输入相比，该方法在平均绝对误差方面提高了14%，在均方误差方面提高了24%，在相关性方面提高了14%，在动态时间规整方面提高了12%。在独立数据集上进行测试时，该方法显示出通用性，即使在具有不同重复时间（TR）和生理条件的数据中也是如此。
本研究表明，可以从青年成人人群的BOLD-fMRI数据中重建呼吸变化，并且使用诸如头部运动参数等支持数据可以提高其准确性。该方法在具有不同实验条件的独立数据集上也表现良好。
