Gray matter atrophy and white matter lesions burden in delayed cognitive decline following carbon monoxide poisoning

Gray matter (GM) atrophy and white matter (WM) lesions may contribute to cognitive decline in patients with delayed neurological sequelae (DNS) after carbon monoxide (CO) poisoning. However, there is currently a lack of evidence supporting this relationship. This study aimed to investigate the volume of GM, cortical thickness, and burden of WM lesions in 33 DNS patients with dementia, 24 DNS patients with mild cognitive impairment, and 51 healthy controls. Various methods, including voxel-based, deformation-based, surface-based, and atlas-based analyses, were used to examine GM structures. Furthermore, we explored the connection between GM volume changes, WM lesions burden, and cognitive decline. Compared to the healthy controls, both patient groups exhibited widespread GM atrophy in the cerebral cortices (for volume and cortical thickness), subcortical nuclei (for volume), and cerebellum (for volume) (p < .05 corrected for false discovery rate [FDR]). The total volume of GM atrophy in 31 subregions, which included the default mode network (DMN), visual network (VN), and cerebellar network (CN) (p < .05, FDR-corrected), independently contributed to the severity of cognitive impairment (p < .05). Additionally, WM lesions impacted cognitive decline through both direct and indirect effects, with the latter mediated by volume reduction in 16 subregions of cognitive networks (p < .05). These preliminary findings suggested that both GM atrophy and WM lesions were involved in cognitive decline in DNS patients following CO poisoning. Moreover, the reduction in the volume of DMN, VN, and posterior CN nodes mediated the WM lesions-induced cognitive decline.

Accounting for temporal variability in functional magnetic resonance imaging improves prediction of intelligence

Neuroimaging-based prediction methods for intelligence have seen a rapid development. Among different neuroimaging modalities, prediction using functional connectivity (FC) has shown great promise. Most literature has focused on prediction using static FC, with limited investigations on the merits of such analysis compared to prediction using dynamic FC or region-level functional magnetic resonance imaging (fMRI) times series that encode temporal variability. To account for the temporal dynamics in fMRI, we propose a bi-directional long short-term memory (bi-LSTM) approach that incorporates feature selection mechanism. The proposed pipeline is implemented via an efficient algorithm and applied for predicting intelligence using region-level time series and dynamic FC. We compare the prediction performance using different fMRI features acquired from the Adolescent Brain Cognitive Development (ABCD) study involving nearly 7000 individuals. Our detailed analysis illustrates the consistently inferior performance of static FC compared to region-level time series or dynamic FC for single and combined rest and task fMRI experiments. The joint analysis of task and rest fMRI leads to improved intelligence prediction under all models compared to using fMRI from only one experiment. In addition, the proposed bi-LSTM pipeline based on region-level time series identifies several shared and differential important brain regions across fMRI experiments that drive intelligence prediction. A test-retest analysis of the selected regions shows strong reliability across cross-validation folds. Given the large sample size of ABCD study, our results provide strong evidence that superior prediction of intelligence can be achieved by accounting for temporal variations in fMRI.

Multi-task Learning with High-Dimensional Noisy Images

Recent medical imaging studies have given rise to distinct but inter-related datasets corresponding to multiple experimental tasks or longitudinal visits. Standard scalar-on-image regression models that fit each dataset separately are not equipped to leverage information across inter-related images, and existing multi-task learning approaches are compromised by the inability to account for the noise that is often observed in images. We propose a novel joint scalar-on-image regression framework involving wavelet-based image representations with grouped penalties that are designed to pool information across inter-related images for joint learning, and which explicitly accounts for noise in high-dimensional images via a projection-based approach. In the presence of non-convexity arising due to noisy images, we derive non-asymptotic error bounds under non-convex as well as convex grouped penalties, even when the number of voxels increases exponentially with sample size. A projected gradient descent algorithm is used for computation, which is shown to approximate the optimal solution via well-defined non-asymptotic optimization error bounds under noisy images. Extensive simulations and application to a motivating longitudinal Alzheimer's disease study illustrate significantly improved predictive ability and greater power to detect true signals, that are simply missed by existing methods without noise correction due to the attenuation to null phenomenon.

Recommendations for Processing Head CT Data

Many research applications of neuroimaging use magnetic resonance imaging (MRI). As such, recommendations for image analysis and standardized imaging pipelines exist. Clinical imaging, however, relies heavily on X-ray computed tomography (CT) scans for diagnosis and prognosis. Currently, there is only one image processing pipeline for head CT, which focuses mainly on head CT data with lesions. We present tools and a complete pipeline for processing CT data, focusing on open-source solutions, that focus on head CT but are applicable to most CT analyses. We describe going from raw DICOM data to a spatially normalized brain within CT presenting a full example with code. Overall, we recommend anonymizing data with Clinical Trials Processor, converting DICOM data to NIfTI using dcm2niix, using BET for brain extraction, and registration using a publicly-available CT template for analysis.

The impact of traditional neuroimaging methods on the spatial localization of cortical areas

Localizing human brain functions is a long-standing goal in systems neuroscience. Toward this goal, neuroimaging studies have traditionally used volume-based smoothing, registered data to volume-based standard spaces, and reported results relative to volume-based parcellations. A novel 360-area surface-based cortical parcellation was recently generated using multimodal data from the Human Connectome Project, and a volume-based version of this parcellation has frequently been requested for use with traditional volume-based analyses. However, given the major methodological differences between traditional volumetric and Human Connectome Project-style processing, the utility and interpretability of such an altered parcellation must first be established. By starting from automatically generated individual-subject parcellations and processing them with different methodological approaches, we show that traditional processing steps, especially volume-based smoothing and registration, substantially degrade cortical area localization compared with surface-based approaches. We also show that surface-based registration using features closely tied to cortical areas, rather than to folding patterns alone, improves the alignment of areas, and that the benefits of high-resolution acquisitions are largely unexploited by traditional volume-based methods. Quantitatively, we show that the most common version of the traditional approach has spatial localization that is only 35% as good as the best surface-based method as assessed using two objective measures (peak areal probabilities and "captured area fraction" for maximum probability maps). Finally, we demonstrate that substantial challenges exist when attempting to accurately represent volume-based group analysis results on the surface, which has important implications for the interpretability of studies, both past and future, that use these volume-based methods.

Whole genome association study of brain-wide imaging phenotypes: A study of the ping cohort

Neuropsychological disorders have a biological basis rooted in brain function, and neuroimaging data are expected to better illuminate the complex genetic basis of neuropsychological disorders. Because they are biological measures, neuroimaging data avoid biases arising from clinical diagnostic criteria that are subject to human understanding and interpretation. A challenge with analyzing neuroimaging data is their high dimensionality and complex spatial relationships. To tackle this challenge, we introduced a novel distance covariance tests that can assess the association between genetic markers and multivariate diffusion tensor imaging measurements, and analyzed a genome-wide association study (GWAS) dataset collected by the Pediatric Imaging, Neurocognition, and Genetics (PING) study. We also considered existing approaches as comparisons. Our results showed that, after correcting for multiplicity, distance covariance tests of the multivariate phenotype yield significantly greater power at detecting genetic markers affecting brain structure than standard mass univariate GWAS of individual neuroimaging biomarkers. Our results underscore the usefulness of utilizing the distance covariance to incorporate neuroimaging data in GWAS.

Subclass-based multi-task learning for Alzheimer's disease diagnosis

In this work, we propose a novel subclass-based multi-task learning method for feature selection in computer-aided Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI) diagnosis. Unlike the previous methods that often assumed a unimodal data distribution, we take into account the underlying multipeak distribution of classes. The rationale for our approach is that it is highly likely for neuroimaging data to have multiple peaks or modes in distribution, e.g., mixture of Gaussians, due to the inter-subject variability. In this regard, we use a clustering method to discover the multipeak distributional characteristics and define subclasses based on the clustering results, in which each cluster covers a peak in the underlying multipeak distribution. Specifically, after performing clustering for each class, we encode the respective subclasses, i.e., clusters, with their unique codes. In encoding, we impose the subclasses of the same original class close to each other and those of different original classes distinct from each other. By setting the codes as new label vectors of our training samples, we formulate a multi-task learning problem in a ℓ2,1-penalized regression framework, through which we finally select features for classification. In our experimental results on the ADNI dataset, we validated the effectiveness of the proposed method by improving the classification accuracies by 1% (AD vs. Normal Control: NC), 3.25% (MCI vs. NC), 5.34% (AD vs. MCI), and 7.4% (MCI Converter: MCI-C vs. MCI Non-Converter: MCI-NC) compared to the competing single-task learning method. It is remarkable for the performance improvement in MCI-C vs. MCI-NC classification, which is the most important for early diagnosis and treatment. It is also noteworthy that with the strategy of modality-adaptive weights by means of a multi-kernel support vector machine, we maximally achieved the classification accuracies of 96.18% (AD vs. NC), 81.45% (MCI vs. NC), 73.21% (AD vs. MCI), and 74.04% (MCI-C vs. MCI-NC), respectively.

Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classification

Multivariate pattern analysis (MVPA) methods such as support vector machines (SVMs) have been increasingly applied to fMRI and sMRI analyses, enabling the detection of distinctive imaging patterns. However, identifying brain regions that significantly contribute to the classification/group separation requires computationally expensive permutation testing. In this paper we show that the results of SVM-permutation testing can be analytically approximated. This approximation leads to more than a thousandfold speedup of the permutation testing procedure, thereby rendering it feasible to perform such tests on standard computers. The speedup achieved makes SVM based group difference analysis competitive with standard univariate group difference analysis methods.