DeepRetroMoCo: Deep Neural Network-based Retrospective Motion Correction Algorithm for Spinal Cord Functional MRI

Overview

Journal Front Psychiatry

Specialty Psychiatry

Date 2024 Jul 15

PMID 39006826

Authors

Mahdi Mobarak-Abadi

Ahmad Mahmoudi-Aznaveh

Hamed Dehghani

Mojtaba Zarei

Shahabeddin Vahdat

Julien Doyon

Ali Khatibi

Affiliations

Soon will be listed here.

Abstract

Background And Purpose: There are distinct challenges in the preprocessing of spinal cord fMRI data, particularly concerning the mitigation of voluntary or involuntary movement artifacts during image acquisition. Despite the notable progress in data processing techniques for movement detection and correction, applying motion correction algorithms developed for the brain cortex to the brainstem and spinal cord remains a challenging endeavor.

Methods: In this study, we employed a deep learning-based convolutional neural network (CNN) named DeepRetroMoCo, trained using an unsupervised learning algorithm. Our goal was to detect and rectify motion artifacts in axial T2*-weighted spinal cord data. The training dataset consisted of spinal cord fMRI data from 27 participants, comprising 135 runs for training and 81 runs for testing.

Results: To evaluate the efficacy of DeepRetroMoCo, we compared its performance against the sct_fmri_moco method implemented in the spinal cord toolbox. We assessed the motion-corrected images using two metrics: the average temporal signal-to-noise ratio (tSNR) and Delta Variation Signal (DVARS) for both raw and motion-corrected data. Notably, the average tSNR in the cervical cord was significantly higher when DeepRetroMoCo was utilized for motion correction, compared to the sct_fmri_moco method. Additionally, the average DVARS values were lower in images corrected by DeepRetroMoCo, indicating a superior reduction in motion artifacts. Moreover, DeepRetroMoCo exhibited a significantly shorter processing time compared to sct_fmri_moco.

Conclusion: Our findings strongly support the notion that DeepRetroMoCo represents a substantial improvement in motion correction procedures for fMRI data acquired from the cervical spinal cord. This novel deep learning-based approach showcases enhanced performance, offering a promising solution to address the challenges posed by motion artifacts in spinal cord fMRI data.

Citing Articles

EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data.

Banerjee R, Kaptan M, Tinnermann A, Khatibi A, Dabbagh A, Buchel C bioRxiv. 2025; .

PMID: 39829895 PMC: 11741348. DOI: 10.1101/2025.01.07.631402.

References

Figley C, Stroman P . Investigation of human cervical and upper thoracic spinal cord motion: implications for imaging spinal cord structure and function. Magn Reson Med. 2007; 58(1):185-189. DOI: 10.1002/mrm.21260. View

Fratini M, Moraschi M, Maraviglia B, Giove F . On the impact of physiological noise in spinal cord functional MRI. J Magn Reson Imaging. 2014; 40(4):770-7. DOI: 10.1002/jmri.24467. View

Eippert F, Kong Y, Jenkinson M, Tracey I, Brooks J . Denoising spinal cord fMRI data: Approaches to acquisition and analysis. Neuroimage. 2016; 154:255-266. DOI: 10.1016/j.neuroimage.2016.09.065. View

Kinany N, Pirondini E, Mattera L, Martuzzi R, Micera S, Van De Ville D . Towards reliable spinal cord fMRI: Assessment of common imaging protocols. Neuroimage. 2022; 250:118964. DOI: 10.1016/j.neuroimage.2022.118964. View

Varoquaux G, Cheplygina V . Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digit Med. 2022; 5(1):48. PMC: 9005663. DOI: 10.1038/s41746-022-00592-y. View

Risser L, Vialard F, Wolz R, Murgasova M, Holm D, Rueckert D . Simultaneous multi-scale registration using large deformation diffeomorphic metric mapping. IEEE Trans Med Imaging. 2011; 30(10):1746-59. DOI: 10.1109/TMI.2011.2146787. View

Stroman P, Figley C, Cahill C . Spatial normalization, bulk motion correction and coregistration for functional magnetic resonance imaging of the human cervical spinal cord and brainstem. Magn Reson Imaging. 2008; 26(6):809-14. DOI: 10.1016/j.mri.2008.01.038. View

Power J, Barnes K, Snyder A, Schlaggar B, Petersen S . Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion. Neuroimage. 2011; 59(3):2142-54. PMC: 3254728. DOI: 10.1016/j.neuroimage.2011.10.018. View

Gros C, De Leener B, Badji A, Maranzano J, Eden D, Dupont S . Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage. 2018; 184:901-915. PMC: 6759925. DOI: 10.1016/j.neuroimage.2018.09.081. View

10.

Maknojia S, Churchill N, Schweizer T, Graham S . Resting State fMRI: Going Through the Motions. Front Neurosci. 2019; 13:825. PMC: 6700228. DOI: 10.3389/fnins.2019.00825. View

11.

Ceritoglu C, Wang L, Selemon L, Csernansky J, Miller M, Ratnanather J . Large Deformation Diffeomorphic Metric Mapping Registration of Reconstructed 3D Histological Section Images and in vivo MR Images. Front Hum Neurosci. 2010; 4:43. PMC: 2889720. DOI: 10.3389/fnhum.2010.00043. View

12.

Ashburner J, Andersson J, Friston K . Image registration using a symmetric prior--in three dimensions. Hum Brain Mapp. 2000; 9(4):212-25. PMC: 6871943. DOI: 10.1002/(sici)1097-0193(200004)9:4<212::aid-hbm3>3.0.co;2-#. View

13.

Powers J, Ioachim G, Stroman P . Ten Key Insights into the Use of Spinal Cord fMRI. Brain Sci. 2018; 8(9). PMC: 6162663. DOI: 10.3390/brainsci8090173. View

14.

Prados F, Ashburner J, Blaiotta C, Brosch T, Carballido-Gamio J, Cardoso M . Spinal cord grey matter segmentation challenge. Neuroimage. 2017; 152:312-329. PMC: 5440179. DOI: 10.1016/j.neuroimage.2017.03.010. View

15.

Alexander M, Kozyrev N, Bosma R, Figley C, Richards J, Stroman P . fMRI Localization of Spinal Cord Processing Underlying Female Sexual Arousal. J Sex Marital Ther. 2015; 42(1):36-47. DOI: 10.1080/0092623X.2015.1010674. View

16.

Wen D, Wei Z, Zhou Y, Li G, Zhang X, Han W . Deep Learning Methods to Process fMRI Data and Their Application in the Diagnosis of Cognitive Impairment: A Brief Overview and Our Opinion. Front Neuroinform. 2018; 12:23. PMC: 5932168. DOI: 10.3389/fninf.2018.00023. View

17.

Cohen-Adad J, Piche M, Rainville P, Benali H, Rossignol S . Impact of realignment on spinal functional MRI time series. Annu Int Conf IEEE Eng Med Biol Soc. 2007; 2007:2126-9. DOI: 10.1109/IEMBS.2007.4352742. View

18.

Khatibi A, Vahdat S, Lungu O, Finsterbusch J, Buchel C, Cohen-Adad J . Brain-spinal cord interaction in long-term motor sequence learning in human: An fMRI study. Neuroimage. 2022; 253:119111. DOI: 10.1016/j.neuroimage.2022.119111. View

19.

Kinany N, Pirondini E, Martuzzi R, Mattera L, Micera S, Van De Ville D . Functional imaging of rostrocaudal spinal activity during upper limb motor tasks. Neuroimage. 2019; 200:590-600. DOI: 10.1016/j.neuroimage.2019.05.036. View

20.

Dalca A, Bobu A, Rost N, Golland P . Patch-Based Discrete Registration of Clinical Brain Images. Patch Based Tech Med Imaging (2016). 2017; 9993:60-67. PMC: 5435454. DOI: 10.1007/978-3-319-47118-1_8. View