Related Experiment Video
Updated: May 24, 2025
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
Published on: June 30, 2018
Deep learning based image enhancement for dynamic non-Cartesian MRI: Application to "silent" fMRI.
Frank Riemer1, Marius Eldevik Rusaas2, Lydia Brunvoll Sandøy2
1Mohn Medical Imaging and Visualization Centre (MMIV), Department of Radiology, Haukeland University Hospital, 5021, Bergen, Norway; Neuro-SysMed, Department of Neurology, Haukeland University Hospital, 5021, Bergen, Norway; Department of Physics and Technology, University of Bergen, 5007, Bergen, Norway.
Deep learning image enhancement improves silent functional MRI (fMRI) quality. A 3D-UNet model significantly reduced errors and preserved temporal signal changes, making it suitable for noise-sensitive fMRI studies.
Area of Science:
- Medical Imaging
- Neuroimaging
- Artificial Intelligence
Background:
- Silent functional MRI (fMRI) is crucial for noise-sensitive environments but often suffers from reduced image quality due to undersampled k-space.
- Deep learning (DL) offers potential solutions for enhancing image quality in undersampled MRI data.
Purpose of the Study:
- To investigate the efficacy of DL-based image enhancement for silent fMRI, focusing on preserving temporal signal dynamics.
- To compare 2D and 3D UNet architectures for enhancing undersampled 3D radial fMRI data.
Main Methods:
- Constructed a ground-truth dataset using Human Connectome Project (HCP) resting-state fMRI data.
- Simulated undersampled non-Cartesian k-space data using a 'Looping Star' sequence trajectory.
- Trained and compared 2D-UNet and 3D-UNet models for image enhancement.
Main Results:
- The 3D-UNet model significantly outperformed the 2D-UNet, achieving a 97% reduction in mean square error.
- The 3D-UNet successfully preserved temporal signal variations in resting-state fMRI (rs-fMRI) data, including correlated activity in the posterior cingulate cortex (PCC).
- Noise was effectively mitigated, and image quality was improved.
Conclusions:
- Deep learning, particularly 3D-UNet, is effective for enhancing silent fMRI image quality and preserving temporal BOLD signal characteristics.
- 3D convolutions are advantageous over deeper 2D networks for handling global artifacts in fMRI.
- The developed DL approach shows promise for improving fMRI studies in challenging acoustic environments.
