ANTsX neuroimaging-derived structural phenotypes of UK Biobank.

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Neurological Effects of Repeated Blast Exposure in Special Operations Personnel.

Exposure to blast overpressure has been a pervasive feature of combat-related injuries. Studies exploring the neurological correlates of repeated low-level blast exposure in career "breachers" demonstrated higher levels of tumor necrosis factor alpha (TNFα) and interleukin (IL)-6 and decreases in IL-10 within brain-derived extracellular vesicles (BDEVs). The current pilot study was initiated in partnership with the U.S. Special Operations Command (USSOCOM) to explore whether neuroinflammation is seen within special operators with prior blast exposure. Data were analyzed from 18 service members (SMs), inclusive of 9 blast-exposed special operators with an extensive career history of repeated blast exposures and 9 controls matched by age and duration of service. Neuroinflammation was assessed utilizing positron emission tomography (PET) imaging with [18F]DPA-714. Serum was acquired to assess inflammatory biomarkers within whole serum and BDEVs. The Blast Exposure Threshold Survey (BETS) was acquired to determine blast history. Both self-report and neurocognitive measures were acquired to assess cognition. Similarity-driven Multi-view Linear Reconstruction (SiMLR) was used for joint analysis of acquired data. Analysis of BDEVs indicated significant positive associations with a generalized blast exposure value (GBEV) derived from the BETS. SiMLR-based analyses of neuroimaging demonstrated exposure-related relationships between GBEV, PET-neuroinflammation, cortical thickness, and volume loss within special operators. Affected brain networks included regions associated with memory retrieval and executive functioning, as well as visual and heteromodal processing. Post hoc assessments of cognitive measures failed to demonstrate significant associations with GBEV. This emerging evidence suggests neuroinflammation may be a key feature of the brain response to blast exposure over a career in operational personnel. The common thread of neuroinflammation observed in blast-exposed populations requires further study.

ANTsX neuroimaging-derived structural phenotypes of UK Biobank.

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Application of Aligned-UMAP to longitudinal biomedical studies.

High-dimensional data analysis starts with projecting the data to low dimensions to visualize and understand the underlying data structure. Several methods have been developed for dimensionality reduction, but they are limited to cross-sectional datasets. The recently proposed Aligned-UMAP, an extension of the uniform manifold approximation and projection (UMAP) algorithm, can visualize high-dimensional longitudinal datasets. We demonstrated its utility for researchers to identify exciting patterns and trajectories within enormous datasets in biological sciences. We found that the algorithm parameters also play a crucial role and must be tuned carefully to utilize the algorithm's potential fully. We also discussed key points to remember and directions for future extensions of Aligned-UMAP. Further, we made our code open source to enhance the reproducibility and applicability of our work. We believe our benchmarking study becomes more important as more and more high-dimensional longitudinal data in biomedical research become available.

Image- versus histogram-based considerations in semantic segmentation of pulmonary hyperpolarized gas images.

PURPOSE: To characterize the differences between histogram-based and image-based algorithms for segmentation of hyperpolarized gas lung images. METHODS: Four previously published histogram-based segmentation algorithms (ie, linear binning, hierarchical k-means, fuzzy spatial c-means, and a Gaussian mixture model with a Markov random field prior) and an image-based convolutional neural network were used to segment 2 simulated data sets derived from a public (n = 29 subjects) and a retrospective collection (n = 51 subjects) of hyperpolarized 129Xe gas lung images transformed by common MRI artifacts (noise and nonlinear intensity distortion). The resulting ventilation-based segmentations were used to assess algorithmic performance and characterize optimization domain differences in terms of measurement bias and precision. RESULTS: Although facilitating computational processing and providing discriminating clinically relevant measures of interest, histogram-based segmentation methods discard important contextual spatial information and are consequently less robust in terms of measurement precision in the presence of common MRI artifacts relative to the image-based convolutional neural network. CONCLUSIONS: Direct optimization within the image domain using convolutional neural networks leverages spatial information, which mitigates problematic issues associated with histogram-based approaches and suggests a preferred future research direction. Further, the entire processing and evaluation framework, including the newly reported deep learning functionality, is available as open source through the well-known Advanced Normalization Tools ecosystem.

Similarity-driven multi-view embeddings from high-dimensional biomedical data.

Diverse, high-dimensional modalities collected in large cohorts present new opportunities for the formulation and testing of integrative scientific hypotheses. Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR contributes an objective function for identifying joint signal, regularization based on sparse matrices representing prior within-modality relationships and an implementation that permits application to joint reduction of large data matrices. We demonstrate that SiMLR outperforms closely related methods on supervised learning problems in simulation data, a multi-omics cancer survival prediction dataset and multiple modality neuroimaging datasets. Taken together, this collection of results shows that SiMLR may be applied to joint signal estimation from disparate modalities and may yield practically useful results in a variety of application domains.

The ANTsX ecosystem for quantitative biological and medical imaging.

The Advanced Normalizations Tools ecosystem, known as ANTsX, consists of multiple open-source software libraries which house top-performing algorithms used worldwide by scientific and research communities for processing and analyzing biological and medical imaging data. The base software library, ANTs, is built upon, and contributes to, the NIH-sponsored Insight Toolkit. Founded in 2008 with the highly regarded Symmetric Normalization image registration framework, the ANTs library has since grown to include additional functionality. Recent enhancements include statistical, visualization, and deep learning capabilities through interfacing with both the R statistical project (ANTsR) and Python (ANTsPy). Additionally, the corresponding deep learning extensions ANTsRNet and ANTsPyNet (built on the popular TensorFlow/Keras libraries) contain several popular network architectures and trained models for specific applications. One such comprehensive application is a deep learning analog for generating cortical thickness data from structural T1-weighted brain MRI, both cross-sectionally and longitudinally. These pipelines significantly improve computational efficiency and provide comparable-to-superior accuracy over multiple criteria relative to the existing ANTs workflows and simultaneously illustrate the importance of the comprehensive ANTsX approach as a framework for medical image analysis.

Functional and Structural Neuroimaging Correlates of Repetitive Low-Level Blast Exposure in Career Breachers.

Combat military and civilian law enforcement personnel may be exposed to repetitive low-intensity blast events during training and operations. Persons who use explosives to gain entry (i.e., breach) into buildings are known as "breachers" or dynamic entry personnel. Breachers operate under the guidance of established safety protocols, but despite these precautions, breachers who are exposed to low-level blast throughout their careers frequently report performance deficits and symptoms to healthcare providers. Although little is known about the etiology linking blast exposure to clinical symptoms in humans, animal studies demonstrate network-level changes in brain function, alterations in brain morphology, vascular and inflammatory changes, hearing loss, and even alterations in gene expression after repeated blast exposure. To explore whether similar effects occur in humans, we collected a comprehensive data battery from 20 experienced breachers exposed to blast throughout their careers and 14 military and law enforcement controls. This battery included neuropsychological assessments, blood biomarkers, and magnetic resonance imaging measures, including cortical thickness, diffusion tensor imaging of white matter, functional connectivity, and perfusion. To better understand the relationship between repetitive low-level blast exposure and behavioral and imaging differences in humans, we analyzed the data using similarity-driven multi-view linear reconstruction (SiMLR). SiMLR is specifically designed for multiple modality statistical integration using dimensionality-reduction techniques for studies with high-dimensional, yet sparse, data (i.e., low number of subjects and many data per subject). We identify significant group effects in these data spanning brain structure, function, and blood biomarkers.

Longitudinal Mapping of Cortical Thickness Measurements: An Alzheimer's Disease Neuroimaging Initiative-Based Evaluation Study.

Longitudinal studies of development and disease in the human brain have motivated the acquisition of large neuroimaging data sets and the concomitant development of robust methodological and statistical tools for quantifying neurostructural changes. Longitudinal-specific strategies for acquisition and processing have potentially significant benefits including more consistent estimates of intra-subject measurements while retaining predictive power. Using the first phase of the Alzheimer's Disease Neuroimaging Initiative (ADNI-1) data, comprising over 600 subjects with multiple time points from baseline to 36 months, we evaluate the utility of longitudinal FreeSurfer and Advanced Normalization Tools (ANTs) surrogate thickness values in the context of a linear mixed-effects (LME) modeling strategy. Specifically, we estimate the residual variability and between-subject variability associated with each processing stream as it is known from the statistical literature that minimizing the former while simultaneously maximizing the latter leads to greater scientific interpretability in terms of tighter confidence intervals in calculated mean trends, smaller prediction intervals, and narrower confidence intervals for determining cross-sectional effects. This strategy is evaluated over the entire cortex, as defined by the Desikan-Killiany-Tourville labeling protocol, where comparisons are made with the cross-sectional and longitudinal FreeSurfer processing streams. Subsequent linear mixed effects modeling for identifying diagnostic groupings within the ADNI cohort is provided as supporting evidence for the utility of the proposed ANTs longitudinal framework which provides unbiased structural neuroimage processing and competitive to superior power for longitudinal structural change detection.

Learning image-based spatial transformations via convolutional neural networks: A review.

Recent methodological innovations in deep learning and associated advancements in computational hardware have significantly impacted the various core subfields of quantitative medical image analysis. The generalizability, computational efficiency and open-source availability of deep learning algorithms and related software, particularly those utilizing convolutional neural networks, have produced paradigm shifts within the field. This impact is evident from topical prevalence in the literature, conference and workshop themes and winning methodologies in relevant competitions. In this work, we review the various state-of-the-art approaches to learning and prediction and/or optimizing image transformations using convolutional neural networks. Although of primary importance within the quantitative imaging domain, image registration algorithmic development, in the context of these deep learning strategies, has received comparatively less attention than its counterparts (e.g., image segmentation). Nevertheless, significant progress has been made in this particular subfield which has been presented in various research venues. We contextualize these contributions within the broader scope of deep learning advancements and, in so doing, attempt to facilitate the leveraging and further development of such techniques within the medical imaging research community.

Multivariate MR biomarkers better predict cognitive dysfunction in mouse models of Alzheimer's disease.

To understand multifactorial conditions such as Alzheimer's disease (AD) we need brain signatures that predict the impact of multiple pathologies and their interactions. To help uncover the relationships between pathology affected brain circuits and cognitive markers we have used mouse models that represent, at least in part, the complex interactions altered in AD, while being raised in uniform environments and with known genotype alterations. In particular, we aimed to understand the relationship between vulnerable brain circuits and memory deficits measured in the Morris water maze, and we tested several predictive modeling approaches. We used in vivo manganese enhanced MRI traditional voxel based analyses to reveal regional differences in volume (morphometry), signal intensity (activity), and magnetic susceptibility (iron deposition, demyelination). These regions included hippocampus, olfactory areas, entorhinal cortex and cerebellum, as well as the frontal association area. The properties of these regions, extracted from each of the imaging markers, were used to predict spatial memory. We next used eigenanatomy, which reduces dimensionality to produce sets of regions that explain the variance in the data. For each imaging marker, eigenanatomy revealed networks underpinning a range of cognitive functions including memory, motor function, and associative learning, allowing the detection of associations between context, location, and responses. Finally, the integration of multivariate markers in a supervised sparse canonical correlation approach outperformed single predictor models and had significant correlates to spatial memory. Among a priori selected regions, expected to play a role in memory dysfunction, the fornix also provided good predictors, raising the possibility of investigating how disease propagation within brain networks leads to cognitive deterioration. Our cross-sectional results support that modeling approaches integrating multivariate imaging markers provide sensitive predictors of AD-like behaviors. Such strategies for mapping brain circuits responsible for behaviors may help in the future predict disease progression, or response to interventions.

Neuroconductor: an R platform for medical imaging analysis.

Neuroconductor (https://neuroconductor.org) is an open-source platform for rapid testing and dissemination of reproducible computational imaging software. The goals of the project are to: (i) provide a centralized repository of R software dedicated to image analysis, (ii) disseminate software updates quickly, (iii) train a large, diverse community of scientists using detailed tutorials and short courses, (iv) increase software quality via automatic and manual quality controls, and (v) promote reproducibility of image data analysis. Based on the programming language R (https://www.r-project.org/), Neuroconductor starts with 51 inter-operable packages that cover multiple areas of imaging including visualization, data processing and storage, and statistical inference. Neuroconductor accepts new R package submissions, which are subject to a formal review and continuous automated testing. We provide a description of the purpose of Neuroconductor and the user and developer experience.

Impact of Reference and Target Region Selection on Amyloid PET SUV Ratios in the Phase 1b PRIME Study of Aducanumab.

SUV ratios (SUVRs) are commonly used to quantify tracer uptake in amyloid-ß PET. Here, we explore the impact of target and reference region-of-interest (ROI) selection on SUVR effect sizes using interventional data from the ongoing phase 1b PRIME study (NCT01677572) of aducanumab (BIIB037) in patients with prodromal or mild Alzheimer disease. Methods: The florbetapir PET SUVR was calculated at baseline (screening) and at weeks 26 and 54 for patients randomized to receive placebo and each of 4 aducanumab doses (1, 3, 6, and 10 mg/kg) using the whole cerebellum, cerebellar gray matter, cerebellar white matter, pons, and subcortical white matter as reference regions. In addition to the prespecified composite cortex target ROI, individual cerebral cortical ROIs were assessed as targets. Results: Of the reference regions used, subcortical white matter, cerebellar white matter, and the pons, alone or in combination, generated the largest effect sizes. The use of the anterior cingulate cortex as a target ROI resulted in larger effect sizes than the use of the composite cortex. SUVR calculations were not affected by correction for brain volume changes over time. Conclusion: Dose- and time-dependent reductions in the amyloid PET SUVR were consistently observed with aducanumab only in cortical regions prone to amyloid plaque deposition, regardless of the reference region used. These data support the hypothesis that florbetapir SUVR responses associated with aducanumab treatment are a result of specific dose- and time-dependent reductions in the amyloid burden in patients with Alzheimer disease.

Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification.

RATIONALE AND OBJECTIVES: We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet-a growing repository of well-known deep learning architectures first introduced here. MATERIALS AND METHODS: Deep convolutional neural network (CNN) models were constructed and trained using a custom multilabel Dice metric loss function and a novel template-based data augmentation strategy. Training (including template generation and data augmentation) employed 205 proton MR images and 73 functional lung MRI. Evaluation was performed using data sets of size 63 and 40 images, respectively. RESULTS: Accuracy for CNN-based proton lung MRI segmentation (in terms of Dice overlap) was left lung: 0.93 ± 0.03, right lung: 0.94 ± 0.02, and whole lung: 0.94 ± 0.02. Although slightly less accurate than our previously reported joint label fusion approach (left lung: 0.95 ± 0.02, right lung: 0.96 ± 0.01, and whole lung: 0.96 ± 0.01), processing time is <1 second per subject for the proposed approach versus ∼30 minutes per subject using joint label fusion. Accuracy for quantifying ventilation defects was determined based on a consensus labeling where average accuracy (Dice multilabel overlap of ventilation defect regions plus normal region) was 0.94 for the CNN method; 0.92 for our previously reported method; and 0.90, 0.92, and 0.94 for expert readers. CONCLUSION: The proposed framework yields accurate automated quantification in near real time. CNNs drastically reduce processing time after offline model construction and demonstrate significant future potential for facilitating quantitative analysis of functional lung MRI.

Amyloid beta-positive subjects exhibit longitudinal network-specific reductions in spontaneous brain activity.

Amyloid beta (Aß) deposition and cognitive decline are key features of Alzheimer's disease. The relationship between Aß status and changes in neuronal function over time, however, remains unclear. We evaluated the effect of baseline Aß status on reference region spontaneous brain activity (SBA-rr) using resting-state functional magnetic resonance imaging and fluorodeoxyglucose positron emission tomography in patients with mild cognitive impairment. Patients (N = 62, [43 Aß-positive]) from the Alzheimer's Disease Neuroimaging Initiative were divided into Aß-positive and Aß-negative groups via prespecified cerebrospinal fluid Aß42 or 18F-florbetapir positron emission tomography standardized uptake value ratio cutoffs measured at baseline. We analyzed interaction of biomarker-confirmed Aß status with SBA-rr change over a 2-year period using mixed-effects modeling. SBA-rr differences between Aß-positive and Aß-negative subjects increased significantly over time within subsystems of the default and visual networks. Changes exhibit an interaction with memory performance over time but were independent of glucose metabolism. Results reinforce the value of resting-state functional magnetic resonance imaging in evaluating Alzheimer''s disease progression and suggest spontaneous neuronal activity changes are concomitant with cognitive decline.

Small Animal Multivariate Brain Analysis (SAMBA) - a High Throughput Pipeline with a Validation Framework.

While many neuroscience questions aim to understand the human brain, much current knowledge has been gained using animal models, which replicate genetic, structural, and connectivity aspects of the human brain. While voxel-based analysis (VBA) of preclinical magnetic resonance images is widely-used, a thorough examination of the statistical robustness, stability, and error rates is hindered by high computational demands of processing large arrays, and the many parameters involved therein. Thus, workflows are often based on intuition or experience, while preclinical validation studies remain scarce. To increase throughput and reproducibility of quantitative small animal brain studies, we have developed a publicly shared, high throughput VBA pipeline in a high-performance computing environment, called SAMBA. The increased computational efficiency allowed large multidimensional arrays to be processed in 1-3 days-a task that previously took ~1 month. To quantify the variability and reliability of preclinical VBA in rodent models, we propose a validation framework consisting of morphological phantoms, and four metrics. This addresses several sources that impact VBA results, including registration and template construction strategies. We have used this framework to inform the VBA workflow parameters in a VBA study for a mouse model of epilepsy. We also present initial efforts towards standardizing small animal neuroimaging data in a similar fashion with human neuroimaging. We conclude that verifying the accuracy of VBA merits attention, and should be the focus of a broader effort within the community. The proposed framework promotes consistent quality assurance of VBA in preclinical neuroimaging, thus facilitating the creation and communication of robust results.

Improved accuracy of lesion to symptom mapping with multivariate sparse canonical correlations.

Lesion to symptom mapping (LSM) is a crucial tool for understanding the causality of brain-behavior relationships. The analyses are typically performed by applying statistical methods on individual brain voxels (VLSM), a method called the mass-univariate approach. Several authors have shown that VLSM suffers from limitations that may decrease the accuracy and reliability of the findings, and have proposed the use of multivariate methods to overcome these limitations. In this study, we propose a multivariate optimization technique known as sparse canonical correlation analysis for neuroimaging (SCCAN) for lesion to symptom mapping. To validate the method and compare it with mass-univariate results, we used data from 131 patients with chronic stroke lesions in the territory of the middle cerebral artery, and created synthetic behavioral scores based on the lesion load of 93 brain regions (putative functional units). LSM analyses were performed with univariate VLSM or SCCAN, and the accuracy of the two methods was compared in terms of both overlap and displacement from the simulated functional areas. Overall, SCCAN produced more accurate results - higher dice overlap and smaller average displacement - compared to VLSM. This advantage persisted at different sample sizes (N = 20-131) and different multiple comparison corrections (false discovery rate, FDR; Bonferroni; permutation-based family wise error rate, FWER). These findings were replicated with a fully automated SCCAN routine that relied on cross-validated predictive accuracy to find the optimal sparseness value. Simulations of one, two, and three brain regions showed a systematic advantage of SCCAN over VLSM; under no circumstance could VLSM exceed the accuracy obtained with SCCAN. When considering functional units composed of multiple brain areas VLSM identified fewer areas than SCCAN. The investigation of real scores of aphasia severity (aphasia quotient and picture naming) showed that SCCAN could accurately identify known language-critical areas, while VLSM either produced diffuse maps (FDR correction) or few scattered voxels (FWER correction). Overall, this study shows that a multivariate method, such as, SCCAN, outperforms VLSM in a number of scenarios, including functional dependency on single or multiple areas, different sample sizes, different multi-area combinations, and different thresholding mechanisms (FWER, Bonferroni, FDR). These results support previous claims that multivariate methods are in general more accurate than mass-univariate approaches, and should be preferred over traditional VLSM approaches. All the methods described in this study are available in the newly developed LESYMAP package for R.

Enhanced estimations of post-stroke aphasia severity using stacked multimodal predictions.

The severity of post-stroke aphasia and the potential for recovery are highly variable and difficult to predict. Evidence suggests that optimal estimation of aphasia severity requires the integration of multiple neuroimaging modalities and the adoption of new methods that can detect multivariate brain-behavior relationships. We created and tested a multimodal framework that relies on three information sources (lesion maps, structural connectivity, and functional connectivity) to create an array of unimodal predictions which are then fed into a final model that creates "stacked multimodal predictions" (STAMP). Crossvalidated predictions of four aphasia scores (picture naming, sentence repetition, sentence comprehension, and overall aphasia severity) were obtained from 53 left hemispheric chronic stroke patients (age: 57.1 ± 12.3 yrs, post-stroke interval: 20 months, 25 female). Results showed accurate predictions for all four aphasia scores (correlation true vs. predicted: r = 0.79-0.88). The accuracy was slightly smaller but yet significant (r = 0.66) in a full split crossvalidation with each patient considered as new. Critically, multimodal predictions produced more accurate results that any single modality alone. Topological maps of the brain regions involved in the prediction were recovered and compared with traditional voxel-based lesion-to-symptom maps, revealing high spatial congruency. These results suggest that neuroimaging modalities carry complementary information potentially useful for the prediction of aphasia scores. More broadly, this study shows that the translation of neuroimaging findings into clinically useful tools calls for a shift in perspective from unimodal to multimodal neuroimaging, from univariate to multivariate methods, from linear to nonlinear models, and, conceptually, from inferential to predictive brain mapping. Hum Brain Mapp 38:5603-5615, 2017. © 2017 Wiley Periodicals, Inc.