Towards Automated Analysis of Connectomes: The Configurable Pipeline for the Analysis of Connectomes (C-PAC)

Craddock, R. Cameron; Sikka, Sharad; Brian, Cheung; Khanuja, Ranjeet; Satrajit, Ghosh; Chen, Yan; Li, Qingyang; Daniel, Lurie; Vogelstein, Joshua T.; Randal, Burns; Stanley, Colcombe; Maarten, Mennes; Clare, Kelly; Adriana, Di Martino; Castellanos, F. Xavier; Michael, Milham

doi:10.3389/conf.fninf.2013.09.00042

Cited by 126 publications

(73 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consistent with prior work (LaConte et al 2006(LaConte et al , 2007, a minimal image processing strategy was employed for the PEER scans. Using the Configurable Pipeline for the Analysis of Connectomes (C-PAC) (Craddock et al 2013), we performed the following steps: motion correction, image intensity normalization, temporal high-pass filtering (cutoff = 100s), and spatial filtering (FWHM = 6mm). The preprocessed functional data for each participant was then registered to the corresponding high-resolution anatomical T1 image using boundary-based registration via FLIRT (Mark Jenkinson et al 2002;M.…”

Section: Image Processingmentioning

confidence: 99%

Evaluating fMRI-Based Estimation of Eye Gaze during Naturalistic Viewing

et al. 2018

Preprint

View full text Add to dashboard Cite

The collection of eye movement information during functional magnetic resonance imaging (fMRI) is a valuable, though commonly overlooked component of monitoring variations in attention and task compliance, particularly for naturalistic viewing paradigms (e.g., movies). Predictive eye estimation regression (PEER) is a previously developed support vector regression-based method for retrospectively estimating eye gaze from fMRI data that simply adds a 1.5-minute calibration scan to any protocol. Here, we provide a large-scale assessment of PEER for inferring eye fixations on a TR-by-TR basis during movie viewing using a subset of data (n=448) from the Child Mind Institute Healthy Brain Network Biobank. Consistent with prior work, we demonstrate the ability of PEER to provide accurate estimates of fixation location throughout the course of fMRI scans and we establish head motion as the primary determinant of model accuracy. Minimum data requirement analyses suggest model estimation can be carried out with less than half the data obtained in the 1.5-minute calibration scan. We demonstrate the ability to predict the movie an individual is watching (i.e., Despicable Me , The Present ) based on the PEER time series. Out-of-scanner eye tracker-based measurements obtained during a repeat viewing of the movie The Present was used to further validate the time series obtained using PEER. Consistent with prior findings in the eye tracking literature, the fixation sequences showed a high consistency across participants, reducing the ability to identify an individual based on their fixation sequence. Finally, examination of neural activations associated with the PEER time series replicated prior findings regarding the neural correlates of eye movements. In summary, we demonstrate that PEER is an inexpensive, easy-to-use tool for researchers to determine eye fixations from naturalistic viewing data that overcomes the cost and burdens of in-scanner eye tracking.

show abstract

Section: Image Processingmentioning

confidence: 99%

Evaluating fMRI-Based Estimation of Eye Gaze during Naturalistic Viewing

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Accordingly, such an approach has been developed and applied here in which the motion-related regressors computed by ICA-AROMA are concatenated with the affine head motion parameters computed during inter-volume realignment and the mean white matter and cerebrospinal fluid signals, and these nuisance signals were regressed out of the fMRI data in one step [19]. Regional homogeneity (ReHo), amplitude of low frequency and fractional amplitude of low frequency fluctuations (fALFF) were computed from the cleaned fMRI using C-PAC [20]. ReHo was computed using Kendall's coefficient of concordance between each voxel and its 27-voxel neighborhood.…”

Section: Preprocessingmentioning

confidence: 99%

Predicting Longitudinal Disease Severity for Individuals with Parkinson’s Disease using Functional MRI and Machine Learning Prognostic Models

Nguyen¹,

Raval

Treacher³

et al. 2020

Preprint

View full text Add to dashboard Cite

Parkinson's disease is the second most common neurodegenerative disorder and is characterized by the loss of ability to control voluntary movements. Predictive biomarkers of progression in Parkinson's Disease are urgently needed to expedite the development of neuroprotective treatments and facilitate discussions about disease prognosis between clinicians and patients. Resting-state functional magnetic resonance imaging (rs-fMRI) shows promise in predicting progression, with derived measures, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), having been previously been associated with current disease severity. In this work, ReHo and fALFF features from 82 Parkinson's Disease subjects are used to train machine learning predictors of baseline clinical severity and progression at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Depression Rating Scale (MDS-UPDRS) score. This is the first time that rs-fMRI and machine learning have been combined to predict future disease progression. The machine learning models explain up to 30.4% (R 2 = 0.304) of the variance in baseline MDS-UPDRS scores, 55.8% (R 2 = 0.558) of the variance in year 1 scores, and 47.1% (R 2 = 0.471) of the variance in year 2 scores with high statistical significance (p < 0.0001). For distinguishing high-and low-progression individuals (MDS-UPDRS score above or below the median), the models achieve positive predictive values of up to 71% and negative predictive values of up to 84%. The models learn patterns of ReHo and fALFF measures that predict better and worse prognoses. Higher ReHo and fALFF in regions of the default motor network predicted lower current severity and lower future progression. The rs-fMRI features in the temporal lobe, limbic system, and motor cortex were also identified as predictors. These results present a potential neuroimaging biomarker that accurately predicts progression, which may be useful as a clinical decision-making tool and in future trials of neuroprotective treatments.

show abstract

“…This study used a publicly available dataset from the ABIDE Initiative [26]. To ensure that our results were not affected by any custom preprocessing pipeline, we used the preprocessed data provided by ABIDE in the C-PAC [27] pipeline. The preprocessing included the following steps.…”

Section: Data and Preprocessingmentioning

confidence: 99%

The Importance of Anti-Correlations in Graph Theory Based Classification of Autism Spectrum Disorder

Kazeminejad

Sotero

2019

Preprint

View full text Add to dashboard Cite

With the release of the multi-site Autism Brain Imaging Data Exchange, many researchers have applied machine learning methods to distinguish between healthy subjects and autistic individuals by using features extracted from resting state functional MRI data. An important part of applying machine learning to this problem is how to extract these features. Specifically, whether to include anti-correlations between brain regions as relevant features and how best to define these features. For the second question, the graph theoretical properties of the brain network may provide a reasonable answer. In this study, we investigated the first issue by comparing three different approaches. These included using the unaltered correlation matrix, the absolute value of the correlation matrix or the inverted correlation matrix (negative of the original) as the starting point for extracting relevant features using graph theory. We then trained a multi-layer perceptron in a leave-one-site out manner in which the data from a single site was left out as testing data and the model was trained on the data from the other sites. Our results show that on average, using graph features extracted from the anticorrelation-based matrix led to the highest accuracy and AUC scores. We also show that adding the PCA transformation of the original correlation matrix to the feature space leads to an increase in accuracy. This suggests that anti-correlations should not simply be discarded as they may include useful information that would aid the classification task.

show abstract

Towards Automated Analysis of Connectomes: The Configurable Pipeline for the Analysis of Connectomes (C-PAC)

Cited by 126 publications

References 0 publications

Evaluating fMRI-Based Estimation of Eye Gaze during Naturalistic Viewing

Evaluating fMRI-Based Estimation of Eye Gaze during Naturalistic Viewing

Predicting Longitudinal Disease Severity for Individuals with Parkinson’s Disease using Functional MRI and Machine Learning Prognostic Models

The Importance of Anti-Correlations in Graph Theory Based Classification of Autism Spectrum Disorder

Contact Info

Product

Resources

About