+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Utilizing temporal information in fMRI decoding: classifier using kernel regression methods

Utilizing temporal information in fMRI decoding: classifier using kernel regression methods

Neuroimage 58(2): 560-571

This paper describes a general kernel regression approach to predict experimental conditions from activity patterns acquired with functional magnetic resonance image (fMRI). The standard approach is to use classifiers that predict conditions from activity patterns. Our approach involves training different regression machines for each experimental condition, so that a predicted temporal profile is computed for each condition. A decision function is then used to classify the responses from the testing volumes into the corresponding category, by comparing the predicted temporal profile elicited by each event, against a canonical hemodynamic response function. This approach utilizes the temporal information in the fMRI signal and maintains more training samples in order to improve the classification accuracy over an existing strategy. This paper also introduces efficient techniques of temporal compaction, which operate directly on kernel matrices for kernel classification algorithms such as the support vector machine (SVM). Temporal compacting can convert the kernel computed from each fMRI volume directly into the kernel computed from beta-maps, average of volumes or spatial-temporal kernel. The proposed method was applied to three different datasets. The first one is a block-design experiment with three conditions of image stimuli. The method outperformed the SVM classifiers of three different types of temporal compaction in single-subject leave-one-block-out cross-validation. Our method achieved 100% classification accuracy for six of the subjects and an average of 94% accuracy across all 16 subjects, exceeding the best SVM classification result, which was 83% accuracy (p=0.008). The second dataset is also a block-design experiment with two conditions of visual attention (left or right). Our method yielded 96% accuracy and SVM yielded 92% (p=0.005). The third dataset is from a fast event-related experiment with two categories of visual objects. Our method achieved 77% accuracy, compared with 72% using SVM (p=0.0006).

Please choose payment method:

(PDF emailed within 0-6 h: $19.90)

Accession: 036131801

Download citation: RISBibTeXText

PMID: 21729756

DOI: 10.1016/j.neuroimage.2011.06.053

Related references

Non-linear neural spike train decoding via polynomial kernel regression. Conference Proceedings 2007: 4102-4105, 2007

Kernel temporal differences for neural decoding. Computational Intelligence and Neuroscience 2015: 481375, 2015

Kernel regression for fMRI pattern prediction. Neuroimage 56(2): 662-673, 2011

A regularization algorithm for decoding perceptual temporal profiles from fMRI data. Neuroimage 56(1): 258-267, 2011

Decoding overlapping memories in the medial temporal lobes using high-resolution fMRI. Learning and Memory 18(12): 742-746, 2011

Effects of prior information on decoding degraded speech: an fMRI study. Human Brain Mapping 35(1): 61-74, 2014

Decoding multiple sound categories in the human temporal cortex using high resolution fMRI. Plos one 10(2): E0117303, 2015

Decoding of visual information from human brain activity: A review of fMRI and EEG studies. Journal of Integrative Neuroscience 14(2): 155-168, 2015

Accurately decoding visual information from fMRI data obtained in a realistic virtual environment. Frontiers in Human Neuroscience 9: 327, 2015

Modeling and analysis of mechanisms underlying fMRI-based decoding of information conveyed in cortical columns. Neuroimage 56(2): 627-642, 2011

On using prototype reduction schemes and classifier fusion strategies to optimize kernel-based nonlinear subspace methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(3): 455-460, 2005

Both the middle temporal gyrus and the ventral anterior temporal area are crucial for multimodal semantic processing: distortion-corrected fMRI evidence for a double gradient of information convergence in the temporal lobes. Journal of Cognitive Neuroscience 24(8): 1766-1778, 2012

An empirical comparison of different LDA methods in fMRI-based brain states decoding. Bio-MedicalMaterialsandEngineering26Suppl1:S1185, 2015

Kernel Averaged Predictors for Spatio-Temporal Regression Models. Spatial Statistics 2: 15-32, 2012

A primer on regression methods for decoding cis-regulatory logic. Plos Computational Biology 5(1): E1000269, 2009