Pattern Classification and Analysis of Brain Maps through fMRI data with Multiple Methods (original) (raw)
Related papers
Patient classification of fMRI activation maps
Medical Image Computing and Computer-Assisted Intervention-MICCAI 2003, 2003
The analysis of brain activations using functional magnetic resonance imaging (fMRI) is an active area of neuropsychological research. Standard techniques for analysis have traditionally focused on finding the most significant areas of brain activation, and have only recently begun to explore the importance of their spatial characteristics. We compare fMRI contrast images and significance maps to training sets of similar maps using the spatial distribution of activation values. We demonstrate that a Fisher linear discriminant (FLD) classifier for either type of map can differentiate patients from controls accurately for Alzheimer's disease, schizophrenia, and mild traumatic brain injury (MTBI).
Analysis of Fmri Data for Statistical Activation Mapping
Functional Magnetic Resonance Imaging (fMRI) is a non-invasive technique which shows great promise in providing neurological information on healthy subjects and clinical patients by mapping functional activation within the brain. The functional structure of human brain, the correlation between neural activities and the Blood-Oxygen-Level Dependent (BOLD) signal and fMRI experimental design techniques were studied in this work. The 2D and 3D anatomical high resolution and 3D + Time series (4D) low resolution functional images have been reconstructed and normalized. Spin echo-Echo Planar Imaging (EPI) technique has been used for obtaining fMRI data acquisition with spatially high resolution activation map overlaid on EPI image with the reduction of image acquisition time. The steps in the analysis of fMRI data were described and two statistical techniques, e.g., t-statistic and correlation analysis for data from single events have been proposed. The effect of Hemodynamic Response (HDR...
Analysis of Functional MRI Timeseries Using Statistical Parametric Mapping
This paper presents a general approach to the analysis of functional MRI timeseries for one or more subjects. The approach seeks a compromise between efficiency, generality, validity, simplicity and execution speed. The main differences between this technique and previous ones are: (i) a simple bias reduction and regularization of voxel wise autoregressive model parameters, (ii) the combination of effects and their estimated standard deviations across different runs/sessions/subjects, and (iii) overcoming the problem of small number of runs/sessions/subjects. The proposed method was applied to real fMRI database acquired at different fMRI acquisition parameters. The ability of the system in detecting neuronal activation was tested using standard statistical tests implemented in statistical parametric mapping (SPM).
Introduction to the Issue on fMRI Analysis for Human Brain Mapping
IEEE Journal of Selected Topics in Signal Processing, 2000
Functional magnetic resonance imaging (fMRI), one of the most recently developed forms of neuroimaging technology, allows noninvasive assessment of brain activity and has been aptly called "our window into the human brain". By enabling researchers to study temporal and spatial changes in both the healthy and the diseased brain as a function of various stimuli, fMRI has contributed significantly to our understanding of the brain, and its study has been one of the most active areas of research. The study of fMRI data is highly interdisciplinary due to its unique nature and particular challenges. Between the two main groups-the developers of the technology and the ultimate end users-there is a major shift and increasing recognition of the role signal processing plays for extracting, processing, analyzing and modeling fMRI data for human brain mapping. As a result, fMRI analysis for human brain mapping has been gaining importance and momentum within the signal processing community. This special issue aims to underline this major current trend and bring together a diverse but complementary set of contributions to address the current brain mapping challenges and the solutions where signal processing plays an important role.
Biomedical Signal Processing and Control, 2021
Objective: Accuracy and precision of the statistical analysis methods used for brain activation maps are essential. Adjusting models to consider spatiotemporal correlation embedded in fMRI data may increase their accuracy, but it also introduces a high computational cost. The present study aimed to apply and assess the spatiotemporal Gaussian process (STGP) model to improve accuracy and reduce cost. Methods: We applied the spatiotemporal Gaussian process (STGP) model for both simulated and experimental memory tfMRI data and compared the findings with fast, fully Bayesian, and General Linear Models (GLM). To assess their accuracy and precision, the models were fitted to the simulated data (1000 voxels,100 times point for 50 people), and an average of accuracy indexes of 100 repetitions was computed. Functional and activation maps for all models were calculated in experimental data analysis. Results: STGP model resulted in a higher Z-score in the whole brain, in the 1000 most activated voxels, and in the frontal lobe as the approved memory area. Based on the simulated data, the STGP model showed more accuracy and precision than the other two models. However, its computational time was more than the GLM, as the price of model correction, but much less than that of the fast, fully Bayesian model. Conclusion: Spatiotemporal correlation further improved the accuracy of the STGP compared to the GLM and fast, fully Bayesian model. This can result in more accurate activation maps. Moreover, the STGP model's computational speed appears to be reasonable for model application.
Effective functional mapping of fMRI data with support-vector machines
Human Brain Mapping, 2010
There is a growing interest in using support vector machines (SVMs) to classify and analyze fMRI signals, leading to a wide variety of applications ranging from brain state decoding to functional mapping of spatially and temporally distributed brain activations. Studies so far have generated functional maps using the vector of weight values generated by the SVM classification process, or alternatively by mapping the correlation coefficient between the fMRI signal at each voxel and the brain state determined by the SVM. However, these approaches are limited as they do not incorporate both the information involved in the SVM prediction of a brain state, namely, the BOLD activation at voxels and the degree of involvement of different voxels as indicated by their weight values. An important implication of the above point is that two different datasets of BOLD signals, presumably obtained from two different experiments, can potentially produce two identical hyperplanes irrespective of their differences in data distribution. Yet, the two sets of signal inputs could correspond to different functional maps. With this consideration, we propose a new method called Effect Mapping that is generated as a product of the weight vector and a newly computed vector of mutual information between BOLD activations at each voxel and the SVM output. By applying this method on neuroimaging data of overt motor execution in nine healthy volunteers, we demonstrate higher decoding accuracy indicating the greater efficacy of this method. Hum Brain Mapp 31:1502-1511, in Wiley Online Library (wileyonlinelibrary.com). V C 2010 Wiley-Liss, Inc. r Mapping of fMRI Data With Support-Vector Machines r r 1503 r
Adaptive statistical parametric mapping for fMRI
Statistics and Its Interface, 2010
Brain activity is accompanied by changes in cerebral blood flow (CBF) and the differential blood oxygenation that are detectable using functional magnetic resonance imaging (fMRI). The process of identifying brain activation regions can be facilitated by estimating the hemodynamic response function (HRF). There have been some remarkable new developments in statistics to handle this problem. In this paper, we introduce a novel procedure which is capable of adapting itself to any of the existing methods by improving its performance through the application of a penalized smoothing technique. Using a computer experiment and a real fMRI data set, the proposed procedure is assessed by comparing its performance very favorably to the popular SPM based method.
Automated classification of fMRI data employing trial-based imagery tasks
Medical Image Analysis, 2009
Automated interpretation and classification of functional MRI (fMRI) data is an emerging research field that enables the characterization of underlying cognitive processes with minimal human intervention. In this work, we present a method for the automated classification of human thoughts reflected on a trial-based paradigm using fMRI with a significantly shortened data acquisition time (less than one minute). Based on our preliminary experience with various cognitive imagery tasks, six characteristic thoughts were chosen as target tasks for the present work: right hand motor imagery, left hand motor imagery, right foot motor imagery, mental calculation, internal speech/word generation, and visual imagery. These six tasks were performed by five healthy volunteers and functional images were obtained using a T 2 *-weighted echo planar imaging (EPI) sequence. Feature vectors from activation maps, necessary for the classification of neural activity, were automatically extracted from the regions that were consistently and exclusively activated for a given task during the training process. Extracted feature vectors were classified using the support vector machine (SVM) algorithm. Parameter optimization, using a k-fold cross-validation scheme, allowed the successful recognition of the six different categories of administered thought tasks with an accuracy of 74.5% (mean) ± 14.3% (standard deviation) across all five subjects. Our proposed study for the automated classification of fMRI data may be utilized in further investigations to monitor/identify human thought processes and their potential link to hardware/computer control.
Brain Activity Detection - Statistical Analysis of fMRI Data
International Joint Conference on Biomedical Engineering Systems and Technologies, 2009
We are concerned with modelling and analysing fMRI data. An fMRI experiment is a series of images obtained over time under two different conditions, in which regions of activity are detected by observing differences in blood magnetism due to hemodynamic response. In this paper we propose a spatiotemporal model for detecting brain activity in fMRI. The model makes no assumptions about the shape or form of activated areas, except that they emit higher signals in response to a stimulus than non-activated areas do, and that they form connected regions. The Bayesian spatial prior distributions provide a framework for detecting active regions much as a neurologist might; based on posterior evidence over a wide range of spatial scales, simultaneously considering the level of the voxel magnitudes together with the size of the activated area. A single spatiotemporal Bayesian model allows more information to be obtained about the corresponding magnetic resonance study. Despite higher computational cost, a spatiotemporal model improves the inference ability since it takes into account the uncertainty in both the spatial and the temporal dimension. A simulated study is used to test the model applicability and sensitivity.