Automatic Artifact Removal of Resting-State fMRI with Deep Neural Networks

Functional Magnetic Resonance Imaging (fMRI) is a noninvasive technique for studying brain activity. During an fMRI session, the subject executes a set of tasks (task-related fMRI study) or no tasks (resting-state fMRI), and a sequence of 3-D brain images is obtained for further analysis. In the course of fMRI, some sources of activation are caused by noise and artifacts. The removal of these sources is essential before the analysis of the brain activations. Deep Neural Network (DNN) architectures can be used for denoising and artifact removal. The main advantage of DNN models is the automatic learning of abstract and meaningful features, given the raw data. This work presents advanced DNN architectures for noise and artifact classification, using both spatial and temporal information in resting-state fMRI sessions. The highest performance is achieved by a voting schema using information from all the domains, with an average accuracy of over 98% and a very good balance between the metrics of sensitivity and specificity (98.5% and 97.5% respectively).

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jing Sui,et al.  Discriminating schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data , 2019, EBioMedicine.

[3]  Michel José Anzanello,et al.  Chemometrics and Intelligent Laboratory Systems , 2009 .

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[6]  Essa Yacoub,et al.  The WU-Minn Human Connectome Project: An overview , 2013, NeuroImage.

[7]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[8]  Dinggang Shen,et al.  The UNC/UMN Baby Connectome Project (BCP): An overview of the study design and protocol development , 2019, NeuroImage.

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

[10]  Sergios Theodoridis,et al.  Machine Learning: A Bayesian and Optimization Perspective , 2015 .

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[12]  Stephen M. Smith,et al.  Probabilistic independent component analysis for functional magnetic resonance imaging , 2004, IEEE Transactions on Medical Imaging.

[13]  Naixue Xiong,et al.  Spatio-temporal deep learning method for ADHD fMRI classification , 2019, Inf. Sci..

[14]  Kevin Murphy,et al.  Is fMRI “noise” really noise? Resting state nuisance regressors remove variance with network structure , 2015, NeuroImage.

[15]  Gustavo Carneiro,et al.  On the importance of normalisation layers in deep learning with piecewise linear activation units , 2015, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[16]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Vince D. Calhoun,et al.  A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data , 2009, NeuroImage.

[18]  Nicha C. Dvornek,et al.  Combining phenotypic and resting-state fMRI data for autism classification with recurrent neural networks , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[19]  Ludovica Griffanti,et al.  Automatic denoising of functional MRI data: Combining independent component analysis and hierarchical fusion of classifiers , 2014, NeuroImage.

[20]  M. Lindquist.  The Statistical Analysis of fMRI Data. , 2008, 0906.3662.

[21]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[22]  Steen Moeller,et al.  ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging , 2014, NeuroImage.

[23]  Sergios Theodoridis,et al.  Blind fMRI source unmixing via higher-order tensor decompositions , 2019, Journal of Neuroscience Methods.

[24]  Mark W. Woolrich,et al.  Resting-state fMRI in the Human Connectome Project , 2013, NeuroImage.

[25]  Yong Xu,et al.  Enhanced CNN for image denoising , 2018, CAAI Trans. Intell. Technol..

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Kun Ho Lee,et al.  3D-Deep Learning Based Automatic Diagnosis of Alzheimer’s Disease with Joint MMSE Prediction Using Resting-State fMRI , 2019, Neuroinformatics.

[28]  Yujie Liu,et al.  A Deep Learning Framework for Noise Component Detection from Resting-State Functional MRI , 2019, MICCAI.