Detecting abnormalities in resting-state dynamics: An unsupervised learning approach

  title={Detecting abnormalities in resting-state dynamics: An unsupervised learning approach},
  author={Meenakshi Khosla and Keith Wakefield Jamison and Amy Kuceyeski and Mert Rory Sabuncu},
Resting-state functional MRI (rs-fMRI) is a rich imaging modality that captures spontaneous brain activity patterns, revealing clues about the connectomic organization of the human brain. While many rs-fMRI studies have focused on static measures of functional connectivity, there has been a recent surge in examining the temporal patterns in these data. In this paper, we explore two strategies for capturing the normal variability in resting-state activity across a healthy population: (a) an… 

Whole MILC: generalizing learned dynamics across tasks, datasets, and populations

This paper presents a novel self supervised training schema which reinforces whole sequence mutual information local to context (whole MILC) and enables attribution of subject diagnosis to specific spatio-temporal regions in the fMRI signal.

Learnt dynamics generalizes across tasks, datasets, and populations

It is demonstrated that self-supervised pre-training guided by signal dynamics produces embedding that generalizes across tasks, datasets, data collection sites, and data distributions.

Anomaly Detection in Medical Imaging - A Mini Review

A semi-exhaustive literature review of relevant anomaly detection papers in medical imaging is used to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection in medical Imaging.

Machine learning in resting-state fMRI analysis

Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example

A Hybrid of Deep Network and Hidden Markov Model for MCI Identification with Resting-State fMRI

A hybrid architecture by combining Deep Auto-Encoder (DAE) and Hidden Markov Model (HMM) is devised, which achieves the maximal accuracy of 81.08% with the proposed method, outperforming state-of-the-art methods in the literature.

The Autism Brain Imaging Data Exchange: Towards Large-Scale Evaluation of the Intrinsic Brain Architecture in Autism

W Whole-brain analyses reconciled seemingly disparate themes of both hypo- and hyperconnectivity in the ASD literature; both were detected, although hypoconnectivity dominated, particularly for corticocortical and interhemispheric functional connectivity.

Chronnectome fingerprinting: Identifying individuals and predicting higher cognitive functions using dynamic brain connectivity patterns

It is highlighted that the chronnectome captures inherent functional dynamics of individual brain networks and provides implications for individualized characterization of health and disease.

Unsupervised classification of major depression using functional connectivity MRI

It is suggested that subgenual cingulate functional connectivity network signatures may provide promising objective biomarkers for the diagnosis of major depression and that maximum margin clustering‐based unsupervised machine learning approaches may have the potential to inform clinical practice and aid in research on psychiatric disorders.

A failure of left temporal cortex to specialize for language is an early emerging and fundamental property of autism.

Lateralized abnormalities of temporal cortex processing of language in autism are demonstrated across two separate samples, including a large sample of young infants who later are diagnosed with autism, suggesting that this pattern may reflect a fundamental early neural developmental pathology in autism.

Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain

An anatomical parcellation of the spatially normalized single-subject high-resolution T1 volume provided by the Montreal Neurological Institute was performed and it is believed that this tool is an improvement for the macroscopical labeling of activated area compared to labeling assessed using the Talairach atlas brain.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.