Using BOLD-fMRI to Compute the Respiration Volume per Time (RTV) and Respiration Variation (RV) with Convolutional Neural Networks (CNN) in the Human Connectome Development Cohort
This method could lower costs, reduce complexity, and decrease participant burden in fMRI studies by eliminating the need for respiratory bellows, though it is incremental as it applies existing CNN techniques to a specific data reconstruction task.
The study tackled the problem of unavailable or poor-quality respiratory signals in fMRI studies by proposing a one-dimensional CNN model to reconstruct respiratory measures (RV and RVT) from BOLD signals, showing that the CNN can capture informative features and produce realistic timeseries.
In many fMRI studies, respiratory signals are unavailable or do not have acceptable quality. Consequently, the direct removal of low-frequency respiratory variations from BOLD signals is not possible. This study proposes a one-dimensional CNN model for reconstruction of two respiratory measures, RV and RVT. Results show that a CNN can capture informative features from resting BOLD signals and reconstruct realistic RV and RVT timeseries. It is expected that application of the proposed method will lower the cost of fMRI studies, reduce complexity, and decrease the burden on participants as they will not be required to wear a respiratory bellows.