Dataset Information

Robust Motion Regression of Resting-State Data Using a Convolutional Neural Network Model.

ABSTRACT: Resting-state functional magnetic resonance imaging (rs-fMRI) based on the blood-oxygen-level-dependent (BOLD) signal has been widely used in healthy individuals and patients to investigate brain functions when the subjects are in a resting or task-negative state. Head motion considerably confounds the interpretation of rs-fMRI data. Nuisance regression is commonly used to reduce motion-related artifacts with six motion parameters estimated from rigid-body realignment as regressors. To further compensate for the effect of head movement, the first-order temporal derivatives of motion parameters and squared motion parameters were proposed previously as possible motion regressors. However, these additional regressors may not be sufficient to model the impact of head motion because of the complexity of motion artifacts. In addition, while using more motion-related regressors could explain more variance in the data, the neural signal may also be removed with increasing number of motion regressors. To better model how in-scanner motion affects rs-fMRI data, a robust and automated convolutional neural network (CNN) model is developed in this study to obtain optimal motion regressors. The CNN network consists of two temporal convolutional layers and the output from the network are the derived motion regressors used in the following nuisance regression. The temporal convolutional layer in the network can non-parametrically model the prolonged effect of head motion. The set of regressors derived from the neural network is compared with the same number of regressors used in a traditional nuisance regression approach. It is demonstrated that the CNN-derived regressors can more effectively reduce motion-related artifacts.

SUBMITTER: Yang Z

PROVIDER: S-EPMC6482337 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Concussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and that individuals suffering from a concussion are more prone to experience additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, the most significant challenge in concussion management is the lack of objective, clinically- accepted, brain-based approaches for determining whether an athlete has suffered a concussion. Here, we report on our efforts to address this challenge. Specifically, we introduce a deep learning long short-term memory (LSTM)-based recurrent neural network that is able to distinguish between non-concussed and acute post-concussed adolescent athletes using only short (i.e. 90 s long) samples of resting state EEG data as input. The athletes were neither required to perform a specific task nor expected to respond to a stimulus during data collection. The acquired EEG data were neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and validated using data from 27 male, adolescent athletes with sports related concussion, benchmarked against 35 non-concussed adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of > 90% and achieved an ensemble median Area Under the Receiver Operating Characteristic Curve (ROC/AUC) equal to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state, raw EEG data. Our concussion classifier represents a promising first step towards the development of an easy-to-use, objective, brain-based, automatic classification of concussion at an individual level.

Project description:Individuals can be characterized in a population according to their brain measurements and activity, given the inter-subject variability in brain anatomy, structure-function relationships, or life experience. Many neuroimaging studies have demonstrated the potential of functional network connectivity patterns estimated from resting functional magnetic resonance imaging (fMRI) to discriminate groups and predict information about individual subjects. However, the predictive signal present in the spatial heterogeneity of brain connectivity networks is yet to be extensively studied. In this study, we investigate, for the first time, the use of pairwise-relationships between resting-state independent spatial maps to characterize individuals. To do this, we develop a deep Siamese framework comprising three-dimensional convolution neural networks for contrastive learning based on individual-level spatial maps estimated via a fully automated fMRI independent component analysis approach. The proposed framework evaluates whether pairs of spatial networks (e.g., visual network and auditory network) are capable of subject identification and assesses the spatial variability in different network pairs' predictive power in an extensive whole-brain analysis. Our analysis on nearly 12,000 unaffected individuals from the UK Biobank study demonstrates that the proposed approach can discriminate subjects with an accuracy of up to 88% for a single network pair on the test set (best model, after several runs), and 82% average accuracy at the subcortical domain level, notably the highest average domain level accuracy attained. Further investigation of our network's learned features revealed a higher spatial variability in predictive accuracy among younger brains and significantly higher discriminative power among males. In sum, the relationship among spatial networks appears to be both informative and discriminative of individuals and should be studied further as putative brain-based biomarkers.

Project description:Deep convolutional neural network (DCNN) provides a multivariate framework to detect relevant spatio-oscillatory patterns in the data beyond common mass-univariate statistics. Yet, its practical application is limited due to the low interpretability of the results beyond accuracy. We opted to use DCNN with a minimalistic architecture design and large penalized terms to yield a generalizable and clinically relevant network model. Our network was trained based on the scalp topology of the electroencephalography (EEG) from an open access dataset, constituting our primary sample of healthy controls (n = 25) and Parkinson's disease (PD) patients (n = 25), with and without medication. Next, we validated the model on another independent, yet comparable open access EEG dataset (healthy controls (n = 20) and PD patients (n = 20)), which was unseen to the network. We applied Gradient-weighted Class Activation Mapping (Grad-CAM) interpretability technique to create a localization map exhibiting the key network predictors, based on the gradients of the classification score flowing into the last convolutional layer. Accordingly, our results indicated that a sub-second of intrinsic oscillatory power pattern in the beta band over the occipitoparietal, gamma band over the left motor cortex as well as theta band over the frontoparietal cluster, had the largest impact on the network score for dissociating the PD patients from age- and gender-matched healthy controls, across the two datasets. We further found that the off-medication motor symptoms were related to the occipitoparietal off-medication beta power whereas the disease duration was associated with the off-medication beta power of the motor cortex. The on-medication theta power of the frontoparietal was related to the improvement of the motor symptoms. In conclusion, our method enabled us to characterize PD patho-electrophysiology according to the multivariate topographic analysis approach, where both spatial and frequency aspects of the oscillations were simultaneously considered. Moreover, our approach was free from common reference problem of the EEG data analyses.

Dataset Information

Robust Motion Regression of Resting-State Data Using a Convolutional Neural Network Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets