Search

Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in stroke research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires neuroanatomical expertise. We previously released an open-source dataset of stroke T1w MRIs and manually-segmented lesion masks (ATLAS v1.2, N = 304) to encourage the development of better algorithms. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N = 1271), a larger dataset of T1w MRIs and manually segmented lesion masks that includes training (n = 655), test (hidden masks, n = 300), and generalizability (hidden MRIs and masks, n = 316) datasets. Algorithm development using this larger sample should lead to more robust solutions; the hidden datasets allow for unbiased performance evaluation via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke research.

As stroke mortality rates decrease, there has been a surge of effort to study poststroke dementia (PSD) to improve long‐term quality of life for stroke survivors. Hippocampal volume may be an important neuroimaging biomarker in poststroke dementia, as it has been associated with many other forms of dementia. However, studying hippocampal volume using MRI requires hippocampal segmentation. Advances in automated segmentation methods have allowed for studying the hippocampus on a large scale, which is important for robust results in the heterogeneous stroke population. However, most of these automated methods use a single atlas‐based approach and may fail in the presence of severe structural abnormalities common in stroke. Hippodeep, a new convolutional neural network‐based hippocampal segmentation method, does not rely solely on a single atlas‐based approach and thus may be better suited for stroke populations. Here, we compared quality control and the accuracy of segmentations generated by Hippodeep and two well‐accepted hippocampal segmentation methods on stroke MRIs (FreeSurfer 6.0 whole hippocampus and FreeSurfer 6.0 sum of hippocampal subfields). Quality control was performed using a stringent protocol for visual inspection of the segmentations, and accuracy was measured as volumetric correlation with manual segmentations. Hippodeep performed significantly better than both FreeSurfer methods in terms of quality control. All three automated segmentation methods had good correlation with manual segmentations and no one method was significantly more correlated than the others. Overall, this study suggests that both Hippodeep and FreeSurfer may be useful for hippocampal segmentation in stroke rehabilitation research, but Hippodeep may be more robust to stroke lesion anatomy., In this study, we compared three automated hippocampal segmentation methods in a large stroke population in terms of quality control and segmentation accuracy compared to manual segmentations. While all three methods yielded similar volumes, new convolutional neural network based segmentation method Hippodeep had the lowest method‐wise quality control fail rate, suggesting it may be the most robust to post‐stroke anatomical distortions.

Objective: 22q11.2 deletion syndrome (22q11DS) is among the strongest known genetic risk factors for schizophrenia. Previous studies have reported variable alterations in subcortical brain structures in 22q11DS. To better characterize subcortical alterations in 22q11DS, including modulating effects of clinical and genetic heterogeneity, the authors studied a large multicenter neuroimaging cohort from the ENIGMA 22q11.2 Deletion Syndrome Working Group. Methods: Subcortical structures were measured using harmonized protocols for gross volume and subcortical shape morphometry in 533 individualswith 22q11DS and 330matched healthy control subjects (age range, 6-56 years; 49% female). Results: Compared with the control group, the 22q11DS group showed lower intracranial volume (ICV) and thalamus, putamen, hippocampus, and amygdala volumes and greater lateral ventricle, caudate, and accumbens volumes (Cohen's d values, 20.90 to 0.93). Shape analysis revealed complex differences in the 22q11DS group across all structures. The larger A-D deletion was associated with more extensive shape alterations compared with the smaller A-B deletion. Participants with 22q11DS with psychosis showed lower ICV and hippocampus, amygdala, and thalamus volumes (Cohen's d values, 20.91 to 0.53) compared with participants with 22q11DS without psychosis. Shape analysis revealed lower thickness and surface area across subregions of these structures. Compared with subcortical findings from other neuropsychiatric disorders studied by the ENIGMA consortium, significant convergence was observed between participants with 22q11DS with psychosis and participants with schizophrenia, bipolar disorder, major depressive disorder, and obsessive-compulsive disorder. Conclusions: In the largest neuroimaging study of 22q11DS to date, the authors found widespread alterations to subcortical brain structures, which were affected by deletion size and psychotic illness. Findings indicate significant overlap between 22q11DS-associated psychosis, idiopathic schizophrenia, and other severe neuropsychiatric illnesses.

Special Issue: The ENIGMA Consortium: the first 10 years., Schizophrenia is associated with widespread alterations in subcortical brain structure. While analytic methods have enabled more detailed morphometric characterization, findings are often equivocal. In this meta-analysis, we employed the harmonized ENIGMA shape analysis protocols to collaboratively investigate subcortical brain structure shape differences between individuals with schizophrenia and healthy control participants. The study analyzed data from 2,833 individuals with schizophrenia and 3,929 healthy control participants contributed by 21 worldwide research groups participating in the ENIGMA Schizophrenia Working Group. Harmonized shape analysis protocols were applied to each site's data independently for bilateral hippocampus, amygdala, caudate, accumbens, putamen, pallidum, and thalamus obtained from T1-weighted structural MRI scans. Mass univariate meta-analyses revealed more-concave-than-convex shape differences in the hippocampus, amygdala, accumbens, and thalamus in individuals with schizophrenia compared with control participants, more-convex-than-concave shape differences in the putamen and pallidum, and both concave and convex shape differences in the caudate. Patterns of exaggerated asymmetry were observed across the hippocampus, amygdala, and thalamus in individuals with schizophrenia compared to control participants, while diminished asymmetry encompassed ventral striatum and ventral and dorsal thalamus. Our analyses also revealed that higher chlorpromazine dose equivalents and increased positive symptom levels were associated with patterns of contiguous convex shape differences across multiple subcortical structures. Findings from our shape meta-analysis suggest that common neurobiological mechanisms may contribute to gray matter reduction across multiple subcortical regions, thus enhancing our understanding of the nature of network disorganization in schizophrenia., Center for Integrated Healthcare, U.S. Department of Veterans Affairs, Grant/Award Number: I01 CX000497; Commonwealth Health Research Board, Grant/Award Number: HRA_POR/2011/100; Conselho Nacional de Desenvolvimento Científico e Tecnológico, Grant/Award Numbers: 478466/2009, 480370/2009; Department of Energy, Labor and Economic Growth, Grant/Award Number: DE-FG02-99ER62764; Forskningsrådet om Hälsa, Arbetsliv och Välfärd, Grant/Award Numbers: K2009-62X-15077-06-3, K2012-61X-15077-09-3, 523-2014-3467, 2009-7053, 2013-2838; Fundação Amazônia Paraense de Amparo à Pesquisa, Grant/Award Numbers: 2009/14891-9, 2010/18672-7, 2012/23796-2, 2013/039; Instituto de Salud Carlos III, Grant/Award Numbers: FIS 00/3095, 01/3129, PI020499, PI060507, PI10/001; National Health and Medical Research Council, Grant/Award Numbers: 1009064, 496682; National Institutes of Health, Grant/Award Numbers: 1RC1MH089257, MH 60722, MH019112, MH064045, MH085096, MH098130, MO1 RR025758, P41RR14075, P50 MH071616, R01 DA053028, R01 EB020062, R01 HD050735, R01 MH056584, R01 MH084803, R01 MH116147, R01 MH117601, R01EB005846, R01EB015611, R01MH074797, R21 MH097196, R21MH097196, R37MH43375, S10 OD023696, T32 AG058507, T32 MH073526, TR000153, U01 MH097435, U24 RR021382A, U24 RR021992, U24 RR025736, U24 RR21992, U24RR021992, U54 EB020403, U54EB020403, UL1 TR000153; National Science Foundation, Grant/Award Numbers: 1636893, 1734853; Norges Forskningsråd, Grant/Award Numbers: 213837, 217776, 223273; Science Foundation Ireland, Grant/Award Numbers: 08/IN.1/B1916, 12/IP/1359; Wellcome Trust, Grant/Award Number: 072894/2/03/Z.

Diffusion-weighted magnetic resonance imaging (dMRI) is sensitive to microstructural changes in the brain that occur with normal aging and Alzheimer’s disease (AD). There is much interest in which dMRI measures are most strongly correlated with clinical measures of AD severity, such as the clinical dementia rating (CDR), and biological processes that may be disrupted in AD, such as brain amyloid load measured using PET. Of these processes, some can be targeted using novel drugs. Since 2016, the Alzheimer’s Disease Neuroimaging Initiative (ADNI) has collected dMRI data from three scanner manufacturers across 58 sites using 7 different protocols that vary in angular resolution, scan duration, and in the number and distribution of diffusion-weighted gradients. Here, we assessed dMRI data from 730 of those individuals (447 cognitively normal controls, 214 with mild cognitive impairment, 69 with dementia; age: 74.1±7.9 years; 381 female/349 male). To harmonize data from different protocols, we applied ComBat, ComBat-GAM, and CovBat to dMRI metrics from 28 white matter regions of interest. We ranked all dMRI metrics in order of the strength of clinically relevant associations, and assessed how this depended on the harmonization methods employed. dMRI metrics were associated with age and clinical impairment, but also with amyloid positivity. All harmonization methods gave comparable results while enabling data integration across multiple scanners and protocols.

The goal of the Enhancing Neuroimaging Genetics through Meta‐Analysis (ENIGMA) Stroke Recovery working group is to understand brain and behavior relationships using well‐powered meta‐ and mega‐analytic approaches. ENIGMA Stroke Recovery has data from over 2,100 stroke patients collected across 39 research studies and 10 countries around the world, comprising the largest multisite retrospective stroke data collaboration to date. This article outlines the efforts taken by the ENIGMA Stroke Recovery working group to develop neuroinformatics protocols and methods to manage multisite stroke brain magnetic resonance imaging, behavioral and demographics data. Specifically, the processes for scalable data intake and preprocessing, multisite data harmonization, and large‐scale stroke lesion analysis are described, and challenges unique to this type of big data collaboration in stroke research are discussed. Finally, future directions and limitations, as well as recommendations for improved data harmonization through prospective data collection and data management, are provided.

The Alzheimer’s Disease Neuroimaging Initiative (phase 3; ADNI3) is collecting multisite diffusion MRI (dMRI) data using protocols optimized for different scanner vendors, including one multi-shell protocol, to better understand disease effects. Here, we analyzed multi-shell scans from 56 ADNI3 participants (age: $74.3 \pm 7.5$ yrs; 17F/49M). We evaluated whether multi-shell dMRI measures computed from neurite orientation dispersion and density imaging (NODDI) and diffusion kurtosis imaging (DKI) differentiated people with mild cognitive impairment from healthy controls with higher sensitivity than standard diffusion tensor imaging (DTI) measures. We also assessed the effects of various multi-shell derived dMRI samples on the sensitivity of DTI measures. While we did not identify large differences in effect sizes among tensor-based, NODDI, or DKI measures, we did detect greater effect sizes from DTI measures estimated using multi-shell data converted to single-shell HARDI compared to those fit using the subset of $48 b=1000s /$mm $^{2}$ volumes, typical of DTI.

Brain imaging with diffusion-weighted MRI (dMRI) is sensitive to microstructural white matter changes associated with brain aging and neurodegeneration. In its third phase, the Alzheimer’s Disease Neuroimaging Initiative (ADNI3) is collecting data across multiple sites and scanners using different dMRI acquisition protocols, to better understand disease effects. It is vital to understand when data can be pooled across scanners, and how the choice of dMRI protocol affects the sensitivity of extracted measures to differences in clinical impairment. Here, we analyzed ADNI3 data from 317 participants (mean age: 75.4±7.9 years; 143 men/174 women), who were each scanned at one of 47 sites with one of six dMRI protocols using scanners from three different manufacturers. We computed four standard diffusion tensor imaging (DTI) indices including fractional anisotropy (FADTI) and mean, radial, and axial diffusivity, and one FA index based on the tensor distribution function (FATDF), in 24 bilaterally averaged white matter regions of interest. We found that protocol differences significantly affected dMRI indices, in particular FADTI. We ranked the diffusion indices for their strength of association with four clinical assessments. In addition to diagnosis, we evaluated cognitive impairment as indexed by three commonly used screening tools for detecting dementia and Alzheimer’s disease: the Alzheimer’s Disease Assessment Scale (ADAS-cog), the Mini-Mental State Examination (MMSE), and the Clinical Dementia Rating scale sum-of-boxes (CDR-sob). Using a nested random-effects model to account for protocol and site, we found that across all dMRI indices and clinical measures, the hippocampal-cingulum and fornix (crus) / stria terminalis regions most consistently showed strong associations with clinical impairment. Overall, the greatest effect sizes were detected in the hippocampal-cingulum and uncinate fasciculus for associations between axial or mean diffusivity and CDR-sob. FATDF detected robust widespread associations with clinical measures, while FADTI was the weakest of the five indices for detecting associations. Ultimately, we were able to successfully pool dMRI data from multiple acquisition protocols from ADNI3 and detect consistent and robust associations with clinical impairment and age.

Diffusion-weighted MRI (dMRI) offers a range of measures that are sensitive to brain aging and neurodegeneration. Here we analyzed data from 318 participants (mean age: 75.4±7.9 years; 143 men/175 women) from the third phase of the Alzheimer’s Disease Neuroimaging Initiative (ADNI3), who were each scanned with one of six different diffusion MRI protocols using scanners from three different manufacturers. We computed 4 standard diffusion tensor imaging (DTI) anisotropy and diffusivity indices, and one advanced anisotropy index based on the tensor distribution function (TDF), in 24 white matter regions of interest. Modeling protocol effects, we ranked the diffusion indices for their strength of correlation with 3 standard clinical measures of cognitive impairment: the ADAS-Cog, MMSE, and sum-of-boxes Clinical Dementia Rating. Across all dMRI indices and cognitive measures, the cingulum-hippocampal region and the uncinate showed some of the strongest associations with cognitive impairment; largest effect sizes were detected with axial diffusivity (AxDDTI). While fractional anisotropy (FA) derived from the DTI model was the weakest in detecting associations with cognitive measures, FA derived from the TDF detected widespread, robust associations. Protocol differences affected dMRI indices; however by modeling protocol effects, we were able to pool dMRI data from multiple acquisition protocols and detect consistent associations with cognitive impairment and age. dMRI indices computed from the upgraded scanning protocols in ADNI3 were sensitive to cognitive impairment in brain aging, offering a benchmark to compare to future multi-shell or multi-compartment diffusion indices.

As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.

Purpose In diffusion MRI (dMRI), fractional anisotropy derived from the single-tensor model (FADTI) is the most widely used metric to characterize white matter (WM) microarchitecture, despite known limitations in regions with crossing fibers. Due to time constraints when scanning patients in clinical settings, high angular resolution diffusion imaging acquisition protocols, often used to overcome these limitations, are still rare in clinical population studies. However, the tensor distribution function (TDF) may be used to model multiple underlying fibers by representing the diffusion profile as a probabilistic mixture of tensors. Methods We compared the ability of standard FADTI and TDF-derived FA (FATDF), calculated from a range of dMRI angular resolutions (41, 30, 15, and 7 gradient directions), to profile WM deficits in 251 individuals from the Alzheimer's Disease Neuroimaging Initiative and to detect associations with 1) Alzheimer's disease diagnosis, 2) Clinical Dementia Rating scores, and 3) average hippocampal volume. Results Across angular resolutions and statistical tests, FATDF showed larger effect sizes than FADTI, particularly in regions preferentially affected by Alzheimer's disease, and was less susceptible to crossing fiber anomalies. Conclusion The TDF “corrected” form of FA may be a more sensitive and accurate alternative to the commonly used FADTI, even in clinical quality dMRI data. Magn Reson Med 78:2322–2333, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Outcomes after traumatic brain injury (TBI) are variable and only partially predicted by acute injury factors. With rich datasets, we can examine how numerous factors – cognitive scores, acute injury variables, demographic variables, and brain imaging variables – are interrelated and aid in outcome prediction. To help study this rich data, we applied CorEx, a novel method for unsupervised machine learning. CorEx decodes the hierarchical structure, identifying latent causes of dependence in the data. It groups predictor variables based on their joint information and inter-dependence. We examined 21 TBI patients 2-5 months post-injury along with healthy controls; both groups were assessed again 12 months later. Although we were limited in the number of participants, this tool for exploratory analysis found potential relationships between change in cognitive scores over the 12-month period and baseline brain volumes. Certain regional brain volumes measured post-injury could serve as predictors of patient recovery. As future planned analyses will examine greater sample sizes, we hope to perform follow-up statistical analysis of variables identified by CorEx in independent data.

Diffusion tensor imaging (DTI) has recently been added to several large-scale studies of Alzheimer's disease (AD), such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), to investigate white matter (WM) abnormalities not detectable on standard anatomical MRI. Disease effects can be widespread, and the profile of WM abnormalities across tracts is still not fully understood. Here we analyzed image-wide measures from DTI fractional anisotropy (FA) maps to classify AD patients (n=43), mild cognitive impairment (n=114) and cognitively healthy elderly controls (n=70). We used voxelwise maps of FA along with averages in WM regions of interest (ROI) to drive a Support Vector Machine. We further used the ReliefF algorithm to select the most discriminative WM voxels for classification. This improved accuracy for all classification tasks by up to 15%. We found several clusters formed by the ReliefF algorithm, highlighting specific pathways affected in AD but not always captured when analyzing ROIs.