A SVM-based quantitative fMRI method for resting-state functional network detection

BolT: Fused window transformers for fMRI time series analysis

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.

Identification of Alzheimer’s Disease on the Basis of a Voxel-Wise Approach

Robust prediction of Alzheimer’s disease (AD) helps in the early diagnosis of AD and may support the treatment of AD patients. In this study, for early detection of AD and prediction of mild cognitive impairment (MCI) conversion, we develop an automatic computer-aided diagnosis (CAD) framework based on a merit-based feature selection method through a whole-brain voxel-wise analysis using baseline magnetic resonance imaging (MRI) data. We also explore the impact of different MRI spatial resolution on the voxel-wise metric AD classification and MCI conversion prediction. We assessed the proposed CAD framework using the whole-brain voxel-wise MRI features of 507 J-ADNI participants (146 healthy controls [HCs], 102 individuals with stable MCI [sMCI], 112 with progressive MCI [pMCI], and 147 with AD) among four clinically relevant pairs of diagnostic groups at different imaging resolutions (i.e., 2, 4, 8, and 16 mm). Using a support vector machine classifier through a 10-fold cross-validation strategy at a spatial resolution of 2 mm, the proposed CAD framework yielded classification accuracies of 91.13%, 74.77%, 81.12%, and 81.78% in identifying AD/healthy control, sMCI/pMCI, sMCI/AD, and pMCI/HC, respectively. The experimental results show that a lower spatial resolution (i.e., 2 mm) may provide more robust information to trace the neuronal loss-related brain atrophy in AD.

Structural MRI-based detection of Alzheimer's disease using feature ranking and classification error

BACKGROUND AND OBJECTIVE

This paper presents an automatic computer-aided diagnosis (CAD) system based on feature ranking for detection of Alzheimer's disease (AD) using structural magnetic resonance imaging (sMRI) data.

METHODS

The proposed CAD system is composed of four systematic stages. First, global and local differences in the gray matter (GM) of AD patients compared to the GM of healthy controls (HCs) are analyzed using a voxel-based morphometry technique. The aim is to identify significant local differences in the volume of GM as volumes of interests (VOIs). Second, the voxel intensity values of the VOIs are extracted as raw features. Third, the raw features are ranked using a seven-feature ranking method, namely, statistical dependency (SD), mutual information (MI), information gain (IG), Pearson's correlation coefficient (PCC), t-test score (TS), Fisher's criterion (FC), and the Gini index (GI). The features with higher scores are more discriminative. To determine the number of top features, the estimated classification error based on training set made up of the AD and HC groups is calculated, with the vector size that minimized this error selected as the top discriminative feature. Fourth, the classification is performed using a support vector machine (SVM). In addition, a data fusion approach among feature ranking methods is introduced to improve the classification performance.

RESULTS

The proposed method is evaluated using a data-set from ADNI (130 AD and 130 HC) with 10-fold cross-validation. The classification accuracy of the proposed automatic system for the diagnosis of AD is up to 92.48% using the sMRI data.

CONCLUSIONS

An automatic CAD system for the classification of AD based on feature-ranking method and classification errors is proposed. In this regard, seven-feature ranking methods (i.e., SD, MI, IG, PCC, TS, FC, and GI) are evaluated. The optimal size of top discriminative features is determined by the classification error estimation in the training phase. The experimental results indicate that the performance of the proposed system is comparative to that of state-of-the-art classification models.

Establishment of Relational Model of Congenital Heart Disease Markers and GO Functional Analysis of the Association between Its Serum Markers and Susceptibility Genes

PURPOSE

The purpose of present study was to construct the best screening model of congenital heart disease serum markers and to provide reference for further prevention and treatment of the disease.

METHODS

Documents from 2006 to 2014 were collected and meta-analysis was used for screening susceptibility genes and serum markers closely related to the diagnosis of congenital heart disease. Data of serum markers were extracted from 80 congenital heart disease patients and 80 healthy controls, respectively, and then logistic regression analysis and support vector machine were utilized to establish prediction models of serum markers and Gene Ontology (GO) functional annotation.

RESULTS

Results showed that NKX2.5, GATA4, and FOG2 were susceptibility genes of congenital heart disease. CRP, BNP, and cTnI were risk factors of congenital heart disease (p < 0.05); cTnI, hs-CRP, BNP, and Lp(a) were significantly close to congenital heart disease (p < 0.01). ROC curve indicated that the accuracy rate of Lp(a) and cTnI, Lp(a) and BNP, and BNP and cTnI joint prediction was 93.4%, 87.1%, and 97.2%, respectively. But the detection accuracy rate of the markers' relational model established by support vector machine was only 85%. GO analysis suggested that NKX2.5, GATA4, and FOG2 were functionally related to Lp(a) and BNP.

CONCLUSIONS

The combined markers model of BNP and cTnI had the highest accuracy rate, providing a theoretical basis for the diagnosis of congenital heart disease.

Data-Driven and Predefined ROI-Based Quantification of Long-Term Resting-State fMRI Reproducibility

Resting-state functional magnetic resonance imaging (fMRI) is a promising tool for neuroscience and clinical studies. However, there exist significant variations in strength and spatial extent of resting-state functional connectivity over repeated sessions in a single or multiple subjects with identical experimental conditions. Reproducibility studies have been conducted for resting-state fMRI where the reproducibility was usually evaluated in predefined regions-of-interest (ROIs). It was possible that reproducibility measures strongly depended on the ROI definition. In this work, this issue was investigated by comparing data-driven and predefined ROI-based quantification of reproducibility. In the data-driven analysis, the reproducibility was quantified using functionally connected voxels detected by a support vector machine (SVM)-based technique. In the predefined ROI-based analysis, all voxels in the predefined ROIs were included when estimating the reproducibility. Experimental results show that (1) a moderate to substantial within-subject reproducibility and a reasonable between-subject reproducibility can be obtained using functionally connected voxels identified by the SVM-based technique; (2) in the predefined ROI-based analysis, an increase in ROI size does not always result in higher reproducibility measures; (3) ROI pairs with high connectivity strength have a higher chance to exhibit high reproducibility; (4) ROI pairs with high reproducibility do not necessarily have high connectivity strength; (5) the reproducibility measured from the identified functionally connected voxels is generally higher than that measured from all voxels in predefined ROIs with typical sizes. The findings (2) and (5) suggest that conventional ROI-based analyses would underestimate the resting-state fMRI reproducibility.

Spatially regularized machine learning for task and resting-state fMRI

BACKGROUND

Reliable mapping of brain function across sessions and/or subjects in task- and resting-state has been a critical challenge for quantitative fMRI studies although it has been intensively addressed in the past decades.

NEW METHOD

A spatially regularized support vector machine (SVM) technique was developed for the reliable brain mapping in task- and resting-state. Unlike most existing SVM-based brain mapping techniques, which implement supervised classifications of specific brain functional states or disorders, the proposed method performs a semi-supervised classification for the general brain function mapping where spatial correlation of fMRI is integrated into the SVM learning. The method can adapt to intra- and inter-subject variations induced by fMRI nonstationarity, and identify a true boundary between active and inactive voxels, or between functionally connected and unconnected voxels in a feature space.

RESULTS

The method was evaluated using synthetic and experimental data at the individual and group level. Multiple features were evaluated in terms of their contributions to the spatially regularized SVM learning. Reliable mapping results in both task- and resting-state were obtained from individual subjects and at the group level.

COMPARISON WITH EXISTING METHODS

A comparison study was performed with independent component analysis, general linear model, and correlation analysis methods. Experimental results indicate that the proposed method can provide a better or comparable mapping performance at the individual and group level.

CONCLUSIONS

The proposed method can provide accurate and reliable mapping of brain function in task- and resting-state, and is applicable to a variety of quantitative fMRI studies.

Probability distribution function-based classification of structural MRI for the detection of Alzheimer's disease

High-dimensional classification methods have been a major target of machine learning for the automatic classification of patients who suffer from Alzheimer's disease (AD). One major issue of automatic classification is the feature-selection method from high-dimensional data. In this paper, a novel approach for statistical feature reduction and selection in high-dimensional magnetic resonance imaging (MRI) data based on the probability distribution function (PDF) is introduced. To develop an automatic computer-aided diagnosis (CAD) technique, this research explores the statistical patterns extracted from structural MRI (sMRI) data on four systematic levels. First, global and local differences of gray matter in patients with AD compared to healthy controls (HCs) using the voxel-based morphometric (VBM) technique with 3-Tesla 3D T1-weighted MRI are investigated. Second, feature extraction based on the voxel clusters detected by VBM on sMRI and voxel values as volume of interest (VOI) is used. Third, a novel statistical feature-selection process is employed, utilizing the PDF of the VOI to represent statistical patterns of the respective high-dimensional sMRI sample. Finally, the proposed feature-selection method for early detection of AD with support vector machine (SVM) classifiers compared to other standard feature selection methods, such as partial least squares (PLS) techniques, is assessed. The performance of the proposed technique is evaluated using 130 AD and 130 HC MRI data from the ADNI dataset with 10-fold cross validation(1). The results show that the PDF-based feature selection approach is a reliable technique that is highly competitive with respect to the state-of-the-art techniques in classifying AD from high-dimensional sMRI samples.