Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging

  title={Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging},
  author={Yuhui Du and Zening Fu and Vince D. Calhoun},
  journal={Frontiers in Neuroscience},
Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis… 

Figures and Tables from this paper

Two-Step Feature Selection for Identifying Developmental Differences in Resting fMRI Intrinsic Connectivity Networks
The results indicate that ICN differences exist in brain development, and they are related to task control, cognition, information processing, attention, and other brain functions.
Deep learning of dynamic functional connectivity states during sleep and epilepsy using simultaneous EEG-fMRI
The starting point was the application of Convolutional Neural Networks to classify sleep stages at individual level, provided the success of conventional classifiers reported by previous works, and was extended to an exploratory scenario comprising the classification of epileptic states at individual and group levels, as well as in a single-subject classification scenario.
Analyzing the Effect of Resolution of Network Nodes on the Resting State Functional Connectivity Maps of Schizophrenic Human Brains
  • Pratik JainA. SaoA. Minhas
  • Medicine, Psychology
    2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
  • 2021
This work compared the variations in FC maps of Schizophrenic brains obtained from three different atlases and relied on the capability of the features of FC maps in accurately classifying a given data into healthy or Schizophrenia group to indicate which atlas performs better.
A Tensor-Based Framework for rs-fMRI Classification and Functional Connectivity Construction
A novel tensor framework in which a general FC matrix is obtained without the need to construct an FC matrix for each sample is presented, which effectively boosts the fMRI classification performance and reveals novel connectivity patterns in Alzheimer's disease at its early stages.
Predicting Sex from Resting-State fMRI Across Multiple Independent Acquired Datasets
It is demonstrated that sex can be further classified with high accuracy using the intrinsic BOLD signal fluctuations from resting-state fMRI (rs-fMRI), and the yielded accuracies suggest that sex difference is embodied and well-pronounced in the low-frequency Bold signal fluctuation.
Brain Connectivity Studies on Structure-Function Relationships: A Short Survey with an Emphasis on Machine Learning
Methods from machine learning are focused on, which contribute to the understanding of functional interactions between brain regions and their relation to the underlying anatomical substrate.
A Deep Learning Model for Data-Driven Discovery of Functional Connectivity
A deep learning architecture BrainGNN is proposed that learns the connectivity structure as part of learning to classify subjects and simultaneously applies a graphical neural network to this learned graph and learns to select a sparse subset of brain regions important to the prediction task.


Resting-State Whole-Brain Functional Connectivity Networks for MCI Classification Using L2-Regularized Logistic Regression
The statistical results prove that the L2-regularized Logistic Regression method is statistically significant better than other three algorithms, which means it could be meaningful to assist physicians efficiently in “real-world” diagnostic situations.
Using connectome-based predictive modeling to predict individual behavior from brain connectivity.
This protocol includes the following steps: feature selection, feature summarization, model building, and assessment of prediction significance, and it has been demonstrated that the CPM protocol performs as well as or better than many of the existing approaches in brain-behavior prediction.
Combining Classification with fMRI-Derived Complex Network Measures for Potential Neurodiagnostics
A novel kernel-sum learning approach is described, block diagonal optimization (BDopt), which can be applied to CNA features to single out graph-theoretic characteristics and/or anatomical regions of interest underlying discrimination, while mitigating problems of multiple comparisons.
Extraction of dynamic functional connectivity from brain grey matter and white matter for MCI classification
By combining it with the dynamic FC in the GM, the diagnosis accuracy for MCI subjects can be significantly improved even using RS‐fMRI data alone, and the dynamic FCT can provide valuable functional information in the WM.
Distributed Intrinsic Functional Connectivity Patterns Predict Diagnostic Status in Large Autism Cohort
High accuracy in the main data set is unlikely due to noise overfitting, but rather indicates optimized characterization of a given cohort, and the large number of features in optimal models can be attributed to etiological heterogeneity under the clinical ASD umbrella.
Alzheimer Classification Using a Minimum Spanning Tree of High-Order Functional Network on fMRI Dataset
Compared with the conventional methods, the resting-state fMRI classification method based on minimum spanning tree high-order functional connectivity networks greatly improved the diagnostic accuracy for Alzheimer's disease.
Dynamic connectivity states estimated from resting fMRI Identify differences among Schizophrenia, bipolar disorder, and healthy control subjects
The results provide new information about these illnesses and strongly suggest that state-based analyses are critical to avoid averaging together important factors that can help distinguish these clinical groups.