Limits...
Classification and Extraction of Resting State Networks Using Healthy and Epilepsy fMRI Data

View Article: PubMed Central - PubMed

ABSTRACT

Functional magnetic resonance imaging studies have significantly expanded the field's understanding of functional brain activity of healthy and patient populations. Resting state (rs-) fMRI, which does not require subjects to perform a task, eliminating confounds of task difficulty, allows examination of neural activity and offers valuable functional mapping information. The purpose of this work was to develop an automatic resting state network (RSN) labeling method which offers value in clinical workflow during rs-fMRI mapping by organizing and quickly labeling spatial maps into functional networks. Here independent component analysis (ICA) and machine learning were applied to rs-fMRI data with the goal of developing a method for the clinically oriented task of extracting and classifying spatial maps into auditory, visual, default-mode, sensorimotor, and executive control RSNs from 23 epilepsy patients (and for general comparison, separately for 30 healthy subjects). ICA revealed distinct and consistent functional network components across patients and healthy subjects. Network classification was successful, achieving 88% accuracy for epilepsy patients with a naïve Bayes algorithm (and 90% accuracy for healthy subjects with a perceptron). The method's utility to researchers and clinicians is the provided RSN spatial maps and their functional labeling which offer complementary functional information to clinicians' expert interpretation.

No MeSH data available.


Related in: MedlinePlus

ICA map labeling and organization. Example patient unlabeled and labeled ICA maps with rest scan underlay (most representative axial slices shown).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5037187&req=5

Figure 1: ICA map labeling and organization. Example patient unlabeled and labeled ICA maps with rest scan underlay (most representative axial slices shown).

Mentions: ICA is a data-driven method which uses no a priori information about the brain and has been a popular approach in the analysis of fMRI data (Salimi-Khorshidi et al., 2014). It has the advantage of not requiring a priori, outside knowledge like functional ROI atlases as in seed based analysis, or parameter and measure selections as in graph theory analysis and it can be used complementarily with machine learning. Another difficulty of seed-based correlation mapping, not present in ICA, is that sometimes it is necessary to manually adjust the coordinates of a seed to see a specific network (Zhang et al., 2009). The spatial maps output from ICA have a clear functional and anatomical interpretation: they are the anatomical locations of brain tissue which act synchronously and with the same activity pattern. One difficulty in the process of localizing network maps using ICA is that it outputs many unordered spatial maps (see Figure 1) which requires time consuming interpretation and labeling by a scientist or clinician that manages them (Zhang et al., 2009).


Classification and Extraction of Resting State Networks Using Healthy and Epilepsy fMRI Data
ICA map labeling and organization. Example patient unlabeled and labeled ICA maps with rest scan underlay (most representative axial slices shown).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5037187&req=5

Figure 1: ICA map labeling and organization. Example patient unlabeled and labeled ICA maps with rest scan underlay (most representative axial slices shown).
Mentions: ICA is a data-driven method which uses no a priori information about the brain and has been a popular approach in the analysis of fMRI data (Salimi-Khorshidi et al., 2014). It has the advantage of not requiring a priori, outside knowledge like functional ROI atlases as in seed based analysis, or parameter and measure selections as in graph theory analysis and it can be used complementarily with machine learning. Another difficulty of seed-based correlation mapping, not present in ICA, is that sometimes it is necessary to manually adjust the coordinates of a seed to see a specific network (Zhang et al., 2009). The spatial maps output from ICA have a clear functional and anatomical interpretation: they are the anatomical locations of brain tissue which act synchronously and with the same activity pattern. One difficulty in the process of localizing network maps using ICA is that it outputs many unordered spatial maps (see Figure 1) which requires time consuming interpretation and labeling by a scientist or clinician that manages them (Zhang et al., 2009).

View Article: PubMed Central - PubMed

ABSTRACT

Functional magnetic resonance imaging studies have significantly expanded the field's understanding of functional brain activity of healthy and patient populations. Resting state (rs-) fMRI, which does not require subjects to perform a task, eliminating confounds of task difficulty, allows examination of neural activity and offers valuable functional mapping information. The purpose of this work was to develop an automatic resting state network (RSN) labeling method which offers value in clinical workflow during rs-fMRI mapping by organizing and quickly labeling spatial maps into functional networks. Here independent component analysis (ICA) and machine learning were applied to rs-fMRI data with the goal of developing a method for the clinically oriented task of extracting and classifying spatial maps into auditory, visual, default-mode, sensorimotor, and executive control RSNs from 23 epilepsy patients (and for general comparison, separately for 30 healthy subjects). ICA revealed distinct and consistent functional network components across patients and healthy subjects. Network classification was successful, achieving 88% accuracy for epilepsy patients with a naïve Bayes algorithm (and 90% accuracy for healthy subjects with a perceptron). The method's utility to researchers and clinicians is the provided RSN spatial maps and their functional labeling which offer complementary functional information to clinicians' expert interpretation.

No MeSH data available.


Related in: MedlinePlus