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

Tuning set classifier accuracy. Tuning set classifier accuracy as a function of the resizing parameter R for healthy subjects (column 1) and epilepsy patients (column 2). The value of R that maximized tuning set accuracy was selected for LOOCV training and testing.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 3: Tuning set classifier accuracy. Tuning set classifier accuracy as a function of the resizing parameter R for healthy subjects (column 1) and epilepsy patients (column 2). The value of R that maximized tuning set accuracy was selected for LOOCV training and testing.

Mentions: Figure 3 (and Figure S4) shows how the tuning parameter was selected on the tuning sets. Usually it is unknown how the value of the parameter will affect performance for different classifiers—this is specific to the data and type of algorithm. Standard practice is to pick the parameter that maximizes a classifier's tuning set accuracy. Figure 3's accuracy function may change if a different number of components are used, however, the tuning procedure of Figure 3 will remain the same. The purpose of the tuning step is to select the optimum classifier parameter after training on a tuning or validation set. The decision to select a particular model for ICA order comes from the domain experts.


Classification and Extraction of Resting State Networks Using Healthy and Epilepsy fMRI Data
Tuning set classifier accuracy. Tuning set classifier accuracy as a function of the resizing parameter R for healthy subjects (column 1) and epilepsy patients (column 2). The value of R that maximized tuning set accuracy was selected for LOOCV training and testing.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 3: Tuning set classifier accuracy. Tuning set classifier accuracy as a function of the resizing parameter R for healthy subjects (column 1) and epilepsy patients (column 2). The value of R that maximized tuning set accuracy was selected for LOOCV training and testing.
Mentions: Figure 3 (and Figure S4) shows how the tuning parameter was selected on the tuning sets. Usually it is unknown how the value of the parameter will affect performance for different classifiers—this is specific to the data and type of algorithm. Standard practice is to pick the parameter that maximizes a classifier's tuning set accuracy. Figure 3's accuracy function may change if a different number of components are used, however, the tuning procedure of Figure 3 will remain the same. The purpose of the tuning step is to select the optimum classifier parameter after training on a tuning or validation set. The decision to select a particular model for ICA order comes from the domain experts.

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