Fast Slice-Wise Deep Learning Motion Correction for Spinal Cord Functional MRI
Organizations: Polytechnique Montréal, Montréal, QC, Canada · Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · Faculty of Associated Medical Sciences, Chiang Mai University, Chiang Mai, Thailand
Abstract
Respiratory and bulk motion displace the spinal cord between the volumes of a functional MRI time series. Current methods such as the Spinal Cord Toolbox (SCT) take several minutes per time series, and general-purpose brain tools register whole volumes, whereas the cord moves mainly slice by slice. We propose a lightweight convolutional neural network that regresses the in-plane translation aligning each axial slice to a reference. Two models, trained without motion labels, correct large and then residual motion. On a 3T (120 scans) and a 7T (59 scans) dataset, the proposed method improves on SCT on every metric (tSNR +10 to +25%, DVARS -20 to -38%), leaves almost no slice displaced by more than one voxel (<0.1%), performs on par with a slice-wise AFNI variant and better than slice-wise FSL FLIRT, and runs in about 10 s per scan, about 30 times faster than SCT. The code is available at https://github.com/ivadomed/moco-dl and the method is available in SCT v7.4.
Figures & tables
| Method | tSNR | DVARS | Sharp. | Outl. | Time (s) |
|---|---|---|---|---|---|
| Raw | 14.39 ∗ | 9.67 ∗ | 0.177 ∗ | 0.788 ∗ | – |
| sct_fmri_moco | 17.65 ∗ | 9.98 ∗ | 0.164 ∗ | 2.347 ∗ | 251.8 ∗ |
| AFNI | 18.74 ∗ | 8.18 ∗ | 0.171 ∗ | 0.041 ∗ | 18.4 ∗ |
| FSL FLIRT | 18.40 ∗ | 8.23 ∗ | 0.173 ∗ | 0.010 ∗ | 256.5 ∗ |
| Ours | 19.34 | 7.96 | 0.170 | 0.003 | 10.4 |
| Method | tSNR | DVARS | Sharp. | Outl. | Time (s) |
|---|---|---|---|---|---|
| Raw | 6.87 ∗ | 26.31 ∗ | 0.170 ∗ | 15.62 ∗ | – |
| sct_fmri_moco | 9.76 ∗ | 20.17 ∗ | 0.170 ∗ | 4.73 ∗ | 405.0 ∗ |
| AFNI | 12.09 | 12.23 | 0.196 ∗ | 0.12 | 32.4 ∗ |
| FSL FLIRT | 11.78 ∗ | 12.63 | 0.193 | 0.21 ∗ | 351.1 ∗ |
| Ours | 12.21 | 12.40 | 0.193 | 0.06 | 10.7 |
Medical Image Registration
Medical image registration aligns scans across time, patients, or imaging modalities to track anatomy and support diagnosis, treatment, and image-guided procedures.
See all 104 papers