Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
This incremental work addresses the need for a cost-effective and less burdensome tool for fMRI researchers and participants by eliminating the requirement for peripheral respiratory recording devices.
The study tackled the problem of missing or poor-quality respiratory signals in fMRI studies by developing a CNN model that estimates respiratory variation waveforms from head motion parameters and BOLD signals, showing that combining these inputs enhances estimation.
Motivation: In many fMRI studies, respiratory signals are often missing or of poor quality. Therefore, it could be highly beneficial to have a tool to extract respiratory variation (RV) waveforms directly from fMRI data without the need for peripheral recording devices. Goal(s): Investigate the hypothesis that head motion parameters contain valuable information regarding respiratory patter, which can help machine learning algorithms estimate the RV waveform. Approach: This study proposes a CNN model for reconstruction of RV waveforms using head motion parameters and BOLD signals. Results: This study showed that combining head motion parameters with BOLD signals enhances RV waveform estimation. Impact: 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.