Machine Learning Applications to Resting-State Functional MR Imaging Analysis

Billings, John M.; Eder, Maxwell; Flood, William C.; Dhami, Devendra Singh; Natarajan, Sriraam; Whitlow, Christopher T.

doi:10.1016/j.nic.2017.06.010

Cited by 9 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The four linking models consistently indicated that spontaneous brain activity is effectively related to EO and EC resting states, and the two resting states are of opposite brain activity in the sensorimotor and occipital regions. It may provide new insight into the neural mechanisms of the resting state and help computational neuroscientists or neuropsychologists to choose an appropriate resting state condition to investigate various mental disorders from the resting state fMRI technique (Craddock et al, 2009 ; Iidaka, 2015 ; Kim et al, 2015 ; Rive et al, 2016 ; Suk et al, 2016 ; Billings et al, 2017 ; Khazaee et al, 2017 ; de Vos et al, 2018 ; Wang et al, 2018 ; Wei et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Eyes-Open and Eyes-Closed Resting States With Opposite Brain Activity in Sensorimotor and Occipital Regions: Multidimensional Evidences From Machine Learning Perspective

Jie

Chen

et al. 2018

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Studies have demonstrated that there are widespread significant differences in spontaneous brain activity between eyes-open (EO) and eyes-closed (EC) resting states. However, it remains largely unclear whether spontaneous brain activity is effectively related to EO and EC resting states. The amplitude, local functional concordance, inter-hemisphere functional synchronization, and network centrality of spontaneous brain activity were measured by the fraction amplitude of low frequency fluctuation (fALFF), regional homogeneity (ReHo), voxel-mirrored homotopic connectivity (VMHC) and degree centrality (DC), respectively. Using the public Eyes-open/Eyes-closed dataset, we employed the support vector machine (SVM) and bootstrap technique to establish linking models for the fALFF, ReHo, VMHC and DC dimensions. The classification accuracies of linking models are 0.72 (0.59, 0.82), 0.88 (0.79, 0.97), 0.82 (0.74, 0.91) and 0.70 (0.62, 0.79), respectively. Specifically, we observed that brain activity in the EO condition is significantly greater in attentional system areas, including the fusiform gyrus, occipital and parietal cortex, but significantly lower in sensorimotor system areas, including the precentral/postcentral gyrus, paracentral lobule (PCL) and temporal cortex compared to the EC condition from the four dimensions. The results consistently indicated that spontaneous brain activity is effectively related to EO and EC resting states, and the two resting states are of opposite brain activity in sensorimotor and occipital regions. It may provide new insight into the neural substrate of the resting state and help computational neuroscientists or neuropsychologists to choose an appropriate resting state condition to investigate various mental disorders from the resting state functional magnetic resonance imaging (fMRI) technique.

show abstract

Section: Introductionmentioning

confidence: 99%

Eyes-Open and Eyes-Closed Resting States With Opposite Brain Activity in Sensorimotor and Occipital Regions: Multidimensional Evidences From Machine Learning Perspective

Jie

Chen

et al. 2018

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…In this context, rs-FC measures, which reflect statistically relevant BOLD temporal connections among spatially distinct regions within the human brain, present information that might help predict a specific patient's response to neuromodulation therapies. ML algorithms can produce models that can find patterns in intrinsic brain activity to develop rs-FCbased models that distinguish treatment responders from non-responders in psychiatric disorders (25,26). As machinelearned analyses can combine many features to predict an outcome of clinical importance, they are suitable for the translational goal of producing models to accurately predict whether an individual patient will benefit from tDCS (25,26).…”

Section: Introductionmentioning

confidence: 99%

“…ML algorithms can produce models that can find patterns in intrinsic brain activity to develop rs-FCbased models that distinguish treatment responders from non-responders in psychiatric disorders (25,26). As machinelearned analyses can combine many features to predict an outcome of clinical importance, they are suitable for the translational goal of producing models to accurately predict whether an individual patient will benefit from tDCS (25,26).…”

Section: Introductionmentioning

confidence: 99%

Superior temporal gyrus functional connectivity predicts transcranial direct current stimulation response in Schizophrenia: A machine learning study

Paul

Bose²,

Kalmady³

et al. 2022

Front. Psychiatry

View full text Add to dashboard Cite

Transcranial direct current stimulation (tDCS) is a promising adjuvant treatment for persistent auditory verbal hallucinations (AVH) in Schizophrenia (SZ). Nonetheless, there is considerable inter-patient variability in the treatment response of AVH to tDCS in SZ. Machine-learned models have the potential to predict clinical response to tDCS in SZ. This study aims to examine the feasibility of identifying SZ patients with persistent AVH (SZ-AVH) who will respond to tDCS based on resting-state functional connectivity (rs-FC). Thirty-four SZ-AVH patients underwent resting-state functional MRI at baseline followed by add-on, twice-daily, 20-min sessions with tDCS (conventional/high-definition) for 5 days. A machine learning model was developed to identify tDCS treatment responders based on the rs-FC pattern, using the left superior temporal gyrus (LSTG) as the seed region. Functional connectivity between LSTG and brain regions involved in auditory and sensorimotor processing emerged as the important predictors of the tDCS treatment response. L1-regularized logistic regression model had an overall accuracy of 72.5% in classifying responders vs. non-responders. This model outperformed the state-of-the-art convolutional neural networks (CNN) model—both without (59.41%) and with pre-training (68.82%). It also outperformed the L1-logistic regression model trained with baseline demographic features and clinical scores of SZ patients. This study reports the first evidence that rs-fMRI-derived brain connectivity pattern can predict the clinical response of persistent AVH to add-on tDCS in SZ patients with 72.5% accuracy.

show abstract

“…Thus, the multi-class classification algorithm is critical in assisting ASD health practitioners in correct diagnosis of ASD subtypes. It is to be noted that the SFC features may not carry sufficient information for multi-class classification [ 23 ]. Hence, a better choice would be using the DFC which represents correlation as a function of time-frequency between BOLD signals.…”

Section: Introductionmentioning

confidence: 99%

Identification of Autism Subtypes Based on Wavelet Coherence of BOLD FMRI Signals Using Convolutional Neural Network

Al-Hiyali

Yahya

Faye

et al. 2021

Sensors

View full text Add to dashboard Cite

The functional connectivity (FC) patterns of resting-state functional magnetic resonance imaging (rs-fMRI) play an essential role in the development of autism spectrum disorders (ASD) classification models. There are available methods in literature that have used FC patterns as inputs for binary classification models, but the results barely reach an accuracy of 80%. Additionally, the generalizability across multiple sites of the models has not been investigated. Due to the lack of ASD subtypes identification model, the multi-class classification is proposed in the present study. This study aims to develop automated identification of autism spectrum disorder (ASD) subtypes using convolutional neural networks (CNN) using dynamic FC as its inputs. The rs-fMRI dataset used in this study consists of 144 individuals from 8 independent sites, labeled based on three ASD subtypes, namely autistic disorder (ASD), Asperger’s disorder (APD), and pervasive developmental disorder not otherwise specified (PDD-NOS). The blood-oxygen-level-dependent (BOLD) signals from 116 brain nodes of automated anatomical labeling (AAL) atlas are used, where the top-ranked node is determined based on one-way analysis of variance (ANOVA) of the power spectral density (PSD) values. Based on the statistical analysis of the PSD values of 3-level ASD and normal control (NC), putamen_R is obtained as the top-ranked node and used for the wavelet coherence computation. With good resolution in time and frequency domain, scalograms of wavelet coherence between the top-ranked node and the rest of the nodes are used as dynamic FC feature input to the convolutional neural networks (CNN). The dynamic FC patterns of wavelet coherence scalogram represent phase synchronization between the pairs of BOLD signals. Classification algorithms are developed using CNN and the wavelet coherence scalograms for binary and multi-class identification were trained and tested using cross-validation and leave-one-out techniques. Results of binary classification (ASD vs. NC) and multi-class classification (ASD vs. APD vs. PDD-NOS vs. NC) yielded, respectively, 89.8% accuracy and 82.1% macro-average accuracy, respectively. Findings from this study have illustrated the good potential of wavelet coherence technique in representing dynamic FC between brain nodes and open possibilities for its application in computer aided diagnosis of other neuropsychiatric disorders, such as depression or schizophrenia.

show abstract

Machine Learning Applications to Resting-State Functional MR Imaging Analysis

Cited by 9 publications

References 55 publications

Eyes-Open and Eyes-Closed Resting States With Opposite Brain Activity in Sensorimotor and Occipital Regions: Multidimensional Evidences From Machine Learning Perspective

Eyes-Open and Eyes-Closed Resting States With Opposite Brain Activity in Sensorimotor and Occipital Regions: Multidimensional Evidences From Machine Learning Perspective

Superior temporal gyrus functional connectivity predicts transcranial direct current stimulation response in Schizophrenia: A machine learning study

Identification of Autism Subtypes Based on Wavelet Coherence of BOLD FMRI Signals Using Convolutional Neural Network

Contact Info

Product

Resources

About