Retrospective Head Motion Estimation in Structural Brain MRI with 3D CNNs

Head motion is one of the most important nuisance variables in neuroimaging, particularly in studies of clinical or special populations, such as children. However, the possibility of estimating motion in structural MRI is limited to a few specialized sites using advanced MRI acquisition techniques. Here we propose a supervised learning method to retrospectively estimate motion from plain MRI. Using sparsely labeled training data, we trained a 3D convolutional neural network to assess if voxels are corrupted by motion or not. The output of the network is a motion probability map, which we integrate across a region of interest (ROI) to obtain a scalar motion score. Using cross-validation on a dataset of \(n=48\) healthy children scanned at our center, and the cerebral cortex as ROI, we show that the proposed measure of motion explains away 37% of the variation in cortical thickness. We also show that the motion score is highly correlated with the results from human quality control of the scans. The proposed technique can not only be applied to current studies, but also opens up the possibility of reanalyzing large amounts of legacy datasets with motion into consideration: we applied the classifier trained on data from our center to the ABIDE dataset (autism), and managed to recover group differences that were confounded by motion.

[1]  Mert R. Sabuncu,et al.  The influence of head motion on intrinsic functional connectivity MRI , 2012, NeuroImage.

[2]  Bruce Fischl,et al.  FreeSurfer , 2012, NeuroImage.

[3]  D. Louis Collins,et al.  Simultaneous segmentation and grading of anatomical structures for patient's classification: Application to Alzheimer's disease , 2012, NeuroImage.

[4]  M. Dylan Tisdall,et al.  Head motion during MRI acquisition reduces gray matter volume and thickness estimates , 2015, NeuroImage.

[5]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[6]  Oliver Speck,et al.  Measurement and Correction of Microscopic Head Motion during Magnetic Resonance Imaging of the Brain , 2012, PloS one.

[7]  Daniel P. Kennedy,et al.  The Autism Brain Imaging Data Exchange: Towards Large-Scale Evaluation of the Intrinsic Brain Architecture in Autism , 2013, Molecular Psychiatry.

[8]  Nancy Kanwisher,et al.  Spurious group differences due to head motion in a diffusion MRI study , 2013, NeuroImage.

[9]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[10]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[11]  Dan Rettmann,et al.  PROMO: Real‐time prospective motion correction in MRI using image‐based tracking , 2010, Magnetic resonance in medicine.

[12]  Bruce Fischl,et al.  Volumetric navigators for prospective motion correction and selective reacquisition in neuroanatomical MRI , 2012, Magnetic resonance in medicine.

[13]  G H Glover,et al.  Image‐based method for retrospective correction of physiological motion effects in fMRI: RETROICOR , 2000, Magnetic resonance in medicine.

[14]  P. Batchelor,et al.  Matrix description of general motion correction applied to multishot images , 2005, Magnetic resonance in medicine.

[15]  Abraham Z. Snyder,et al.  Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion , 2012, NeuroImage.

[16]  Nicholas Lange,et al.  Longitudinal changes in cortical thickness in autism and typical development. , 2014, Brain : a journal of neurology.

[17]  Alex Martin,et al.  Age-related temporal and parietal cortical thinning in autism spectrum disorders. , 2010, Brain : a journal of neurology.

[18]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.