Purpose To introduce a novel convolutional neural network (CNN)‐based approach for frequency‐and‐phase correction (FPC) of MR spectroscopy (MRS) spectra to achieve fast and accurate FPC of single‐voxel MEGA‐PRESS MRS data. Methods Two neural networks (one for frequency and one for phase) were trained and validated using published simulated and in vivo MEGA‐PRESS MRS dataset with wide‐range artificial frequency and phase offsets applied. The CNN‐based approach was subsequently tested and compared to the current deep learning solution: multilayer perceptrons (MLP). Furthermore, random noise was added to the original simulated dataset to further investigate the model performance at varied signal‐to‐noise ratio (SNR) levels (i.e., 10, 5, and 2.5). Additional frequency and phase offsets (i.e., small, moderate, large) were also applied to the in vivo dataset, and the CNN model was compared to the conventional approach SR and model‐based SR implementation (mSR). Results The CNN model is more robust to noise compared to the MLP‐based approach due to having smaller mean absolute errors in both frequency (0.01 ± 0.01 Hz at SNR = 10 and 0.01 ± 0.02 Hz at SNR = 2.5) and phase (0.12 ± 0.09° at SNR = 10 and −0.07 ± 0.44° at SNR = 2.5) offset prediction. Furthermore, better performance was demonstrated for FPC when compared to the MLP‐based approach, and SR when applied to the in vivo dataset for both with and without additional offsets. Conclusion A CNN‐based approach provides a solution to the automated preprocessing of MRS data, and the experimental results demonstrate the quantitatively improved spectra quality compared to the state‐of‐the‐art approach.

Deep learning is an effective image processing approach that has been enthusiastically adopted in Magnetic Resonance Spectroscopy (MRS). Methods such as multilayer perceptrons (MLP) and convolutional neural networks (CNN) have been applied to frequency and phase correction (FPC) to help resolve frequency and phase shifts that arise in MRS. However, both methods need to be trained separately with frequency and phase offsets to perform FPC. In this study, we aim to introduce a spectrum registration technique using CNNs that perform simultaneous correction of both frequency and phase shifts of single voxel MEGA-PRESS MRS simulated data.

Frequency and Phase Correction (FPC) is an essential technique to resolve frequency and phase shifts that arise in Magnetic Resonance Spectroscopy (MRS). As of today, a deep learning method using multilayer perceptrons has been developed to correct these shifts. However, a more robust network such as convolutional neural networks (CNN) can be considered as this approach more accurately obtains spatial information and extract key features of the given data. In this study, we aim to investigate the feasibility and utility of CNNs for FPC of single voxel MEGA-PRESS MRS simulated and in vivo data.