Search

We introduce a strategy for learning image registration without acquired imaging data, producing powerful networks agnostic to contrast introduced by magnetic resonance imaging (MRI). While classical registration methods accurately estimate the spatial correspondence between images, they solve an optimization problem for every new image pair. Learning-based techniques are fast at test time but limited to registering images with contrasts and geometric content similar to those seen during training. We propose to remove this dependency on training data by leveraging a generative strategy for diverse synthetic label maps and images that exposes networks to a wide range of variability, forcing them to learn more invariant features. This approach results in powerful networks that accurately generalize to a broad array of MRI contrasts. We present extensive experiments with a focus on 3D neuroimaging, showing that this strategy enables robust and accurate registration of arbitrary MRI contrasts even if the target contrast is not seen by the networks during training. We demonstrate registration accuracy surpassing the state of the art both within and across contrasts, using a single model. Critically, training on arbitrary shapes synthesized from noise distributions results in competitive performance, removing the dependency on acquired data of any kind. Additionally, since anatomical label maps are often available for the anatomy of interest, we show that synthesizing images from these dramatically boosts performance, while still avoiding the need for real intensity images. Our code is available at https://w3id.org/synthmorph., 16 pages, 15 figures, 3 tables, deformable image registration, data independence, deep learning, MRI-contrast invariance, anatomy agnosticism, final published version

The use of multiple atlases is common in medical image segmentation. This typically requires deformable registration of the atlases (or the average atlas) to the new image, which is computationally expensive and susceptible to entrapment in local optima. We propose to instead consider the probability of all possible atlas-to-image transformations and compute the expected label value (ELV) , thereby not relying merely on the transformation deemed “optimal” by the registration method. Moreover, we do so without actually performing deformable registration, thus avoiding the associated computational costs. We evaluate our ELV computation approach by applying it to brain, liver, and pancreas segmentation on datasets of magnetic resonance and computed tomography images.

Background We sought to develop an automatable score to predict hospitalization, critical illness, or death for patients at risk for coronavirus disease 2019 (COVID-19) presenting for urgent care. Methods We developed the COVID-19 Acuity Score (CoVA) based on a single-center study of adult outpatients seen in respiratory illness clinics or the emergency department. Data were extracted from the Partners Enterprise Data Warehouse, and split into development (n = 9381, 7 March–2 May) and prospective (n = 2205, 3–14 May) cohorts. Outcomes were hospitalization, critical illness (intensive care unit or ventilation), or death within 7 days. Calibration was assessed using the expected-to-observed event ratio (E/O). Discrimination was assessed by area under the receiver operating curve (AUC). Results In the prospective cohort, 26.1%, 6.3%, and 0.5% of patients experienced hospitalization, critical illness, or death, respectively. CoVA showed excellent performance in prospective validation for hospitalization (expected-to-observed ratio [E/O]: 1.01; AUC: 0.76), for critical illness (E/O: 1.03; AUC: 0.79), and for death (E/O: 1.63; AUC: 0.93). Among 30 predictors, the top 5 were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate. Conclusions CoVA is a prospectively validated automatable score for the outpatient setting to predict adverse events related to COVID-19 infection., A coronavirus disease 2019 (COVID-19) outpatient screening score is developed and validated prospectively in a single-center setting. It predicts 7-day prognosis: hospitalization, intensive care/ventilation, or death, based on 30 predictors including demographics, COVID-19 status, vital signs, radiology report, and medical history.

A tool was developed to automatically segment several subcortical limbic structures (nucleus accumbens, basal forebrain, septal nuclei, hypothalamus without mammillary bodies, the mammillary bodies, and fornix) using only a T1-weighted MRI as input. This tool fills an unmet need as there are few, if any, publicly available tools to segment these clinically relevant structures. A U-Net with spatial, intensity, contrast, and noise augmentation was trained using 39 manually labeled MRI data sets. In general, the Dice scores, true positive rates, false discovery rates, and manual-automatic volume correlation were very good relative to comparable tools for other structures. A diverse data set of 698 subjects were segmented using the tool; evaluation of the resulting labelings showed that the tool failed in less than 1% of cases. Test-retest reliability of the tool was excellent. The automatically segmented volume of all structures except mammillary bodies showed effectiveness at detecting either clinical AD effects, age effects, or both. This tool will be publicly released with FreeSurfer (surfer.nmr.mgh.harvard.edu/fswiki/ScLimbic). Together with the other cortical and subcortical limbic segmentations, this tool will allow FreeSurfer to provide a comprehensive view of the limbic system in an automated way., Graphical Abstract

Joint registration of a stack of 2D histological sections to recover 3D structure (``3D histology reconstruction'') finds application in areas such as atlas building and validation of \emph{in vivo} imaging. Straightforward pairwise registration of neighbouring sections yields smooth reconstructions but has well-known problems such as ``banana effect'' (straightening of curved structures) and ``z-shift'' (drift). While these problems can be alleviated with an external, linearly aligned reference (e.g., Magnetic Resonance (MR) images), registration is often inaccurate due to contrast differences and the strong nonlinear distortion of the tissue, including artefacts such as folds and tears. In this paper, we present a probabilistic model of spatial deformation that yields reconstructions for multiple histological stains that that are jointly smooth, robust to outliers, and follow the reference shape. The model relies on a spanning tree of latent transforms connecting all the sections and slices of the reference volume, and assumes that the registration between any pair of images can be see as a noisy version of the composition of (possibly inverted) latent transforms connecting the two images. Bayesian inference is used to compute the most likely latent transforms given a set of pairwise registrations between image pairs within and across modalities. The framework is used for accurate 3D reconstruction of two stains (Nissl and parvalbumin) from the Allen human brain atlas, showing its benefits on real data with severe distortions. Moreover, we also provide the registration of the reconstructed volume to MNI space, bridging the gaps between two of the most widely used atlases in histology and MRI. The 3D reconstructed volumes and atlas registration can be downloaded from https://openneuro.org/datasets/ds003590. The code is freely available at https://github.com/acasamitjana/3dhirest., Comment: Medical Image Analysis (Accepted on 07/10/2021). 22 pages, 11 figures

BackgroundStructural brain connectivity has been shown to be sensitive to the changes that the brain undergoes during Alzheimer’s disease (AD) progression.MethodsIn this work, we used our recently proposed structural connectivity quantification measure derived from diffusion MRI, which accounts for both direct and indirect pathways, to quantify brain connectivity in dementia. We analyzed data from the ADNI-2 and OASIS-3 datasets to derive relevant information for the study of the changes that the brain undergoes in AD. We also compared these datasets to the HCP dataset, as a reference, and eventually validated externally on two cohorts of the EDSD database.ResultsOur analysis shows expected trends of mean conductance with respect to age and cognitive scores, significant age prediction values in aging data, and regional effects centered among sub-cortical regions, and cingulate and temporal cortices.DiscussionResults indicate that the conductance measure has prediction potential, especially for age, that age and cognitive scores largely overlap, and that this measure could be used to study effects such as anti-correlation in structural connections.Impact statementThis work presents a methodology and a set of analyses that open new possibilities in the study of healthy and pathological aging. The methodology used here is sensitive to direct and indirect pathways in deriving brain connectivity measures from dMRI, and therefore provides information that many state-of-the-art methods do not account for. As a result, this technique may provide the research community with ways to detect subtle effects of healthy aging and AD.

The neuropathology associated with cognitive decline in military personnel exposed to traumatic brain injury (TBI) and chronic stress is incompletely understood. Few studies have examined clinicopathologic correlations between phosphorylated-tau neurofibrillary tangles, β-amyloid neuritic plaques, neuroinflammation, or white matter (WM) lesions, and neuropsychiatric disorders in veterans. We describe clinicopathologic findings in 4 military veterans with early-onset dementia (EOD) who had varying histories of blunt- and blast-TBI, cognitive decline, behavioral abnormalities, post-traumatic stress disorder, suicidal ideation, and suicide. We found that pathologic lesions in these military-EOD cases could not be categorized as classic Alzheimer’s disease (AD), chronic traumatic encephalopathy, traumatic axonal injury, or other well-characterized clinicopathologic entities. Rather, we observed a mixture of polypathology with unusual patterns compared with pathologies found in AD or other dementias. Also, ultrahigh resolution ex vivo MRI in 2 of these 4 brains revealed unusual patterns of periventricular WM injury. These findings suggest that military-EOD cases are associated with atypical combinations of brain lesions and distribution rarely seen in nonmilitary populations. Future prospective studies that acquire neuropsychiatric data before and after deployments, as well as genetic and environmental exposure data, are needed to further elucidate clinicopathologic correlations in military-EOD.

Continued improvement in MRI acquisition technology has made functional MRI (fMRI) with small isotropic voxel sizes down to 1 mm and below more commonly available. Although many conventional fMRI studies seek to investigate regional patterns of cortical activation for which conventional voxel sizes of 3 mm and larger provide sufficient spatial resolution, smaller voxels can help avoid contamination from adjacent white matter (WM) and cerebrospinal fluid (CSF), and thereby increase the specificity of fMRI to signal changes within the gray matter. Unfortunately, temporal signal-to-noise ratio (tSNR), a metric of fMRI sensitivity, is reduced in high-resolution acquisitions, which offsets the benefits of small voxels. Here we introduce a framework that combines small, isotropic fMRI voxels acquired at 7 T field strength with a novel anatomically-informed, surface mesh-navigated spatial smoothing that can provide both higher detection power and higher resolution than conventional voxel sizes. Our smoothing approach uses a family of intracortical surface meshes and allows for kernels of various shapes and sizes, including curved 3D kernels that adapt to and track the cortical folding pattern. Our goal is to restrict smoothing to the cortical gray matter ribbon and avoid noise contamination from CSF and signal dilution from WM via partial volume effects. We found that the intracortical kernel that maximizes tSNR does not maximize percent signal change (ΔS/S), and therefore the kernel configuration that optimizes detection power cannot be determined from tSNR considerations alone. However, several kernel configurations provided a favorable balance between boosting tSNR and ΔS/S, and allowed a 1.1-mm isotropic fMRI acquisition to have higher performance after smoothing (in terms of both detection power and spatial resolution) compared to an unsmoothed 3.0-mm isotropic fMRI acquisition. Overall, the results of this study support the strategy of acquiring voxels smaller than the cortical thickness, even for studies not requiring high spatial resolution, and smoothing them down within the cortical ribbon with a kernel of an appropriate shape to achieve the best performance—thus decoupling the choice of fMRI voxel size from the spatial resolution requirements of the particular study. The improvement of this new intracortical smoothing approach over conventional surface-based smoothing is expected to be modest for conventional resolutions, however the improvement is expected to increase with higher resolutions. This framework can also be applied to anatomically-informed intracortical smoothing of higher-resolution data (e.g. along columns and layers) in studies with prior information about the spatial structure of activation.

Diffusion tractography MRI can infer changes in network connectivity in patients with traumatic brain injury (TBI), but pathological substrates of disconnected tracts have not been well-defined due to a lack of high-resolution imaging with histopathological validation. We developed an ex vivo MRI protocol to analyze tract terminations at 750 μm resolution, followed by histopathologic evaluation of white matter pathology, and applied these methods to a 60-year-old man who died 26 days after TBI. Analysis of 74 cerebral hemispheric white matter regions revealed a heterogeneous distribution of tract disruptions. Associated histopathology identified variable white matter injury with patchy deposition of amyloid precursor protein and loss of neurofilament-positive axonal processes, myelin dissolution, astrogliosis, microgliosis, and perivascular hemosiderin-laden macrophages. Multiple linear regression revealed that tract disruption strongly correlated with neurofilament loss. Ex vivo diffusion MRI can detect tract disruptions in the human brain that reflect axonal injury.

We introduce a strategy for learning image registration without acquired imaging data, producing powerful networks agnostic to magnetic resonance imaging (MRI) contrast. While classical methods accurately estimate the spatial correspondence between images, they solve an optimization problem for every new image pair. Learning methods are fast at test time but limited to images with contrasts and geometric content similar to those seen during training. We propose to remove this dependency using a generative strategy that exposes networks to a wide range of images synthesized from segmentations during training, forcing them to generalize across contrasts. We show that networks trained within this framework generalize to a broad array of unseen MRI contrasts and surpass classical state-of-the-art brain registration accuracy by up to 12.4 Dice points for a variety of tested contrast combinations. Critically, training on arbitrary shapes synthesized from noise distributions results in competitive performance, removing the dependency on acquired data of any kind. Additionally, since anatomical label maps are often available for the anatomy of interest, we show that synthesizing images from these dramatically boosts performance, while still avoiding the need for real intensity images during training.

The MarkVCID consortium was formed under cooperative agreements with the National Institute of Neurologic Diseases and Stroke (NINDS) and National Institute on Aging (NIA) in 2016 with the goals of developing and validating biomarkers for the cerebral small vessel diseases associated with the vascular contributions to cognitive impairment and dementia (VCID). Rigorously validated biomarkers have consistently been identified as crucial for multicenter studies to identify effective strategies to prevent and treat VCID, specifically to detect increased VCID risk, diagnose the presence of small vessel disease and its subtypes, assess prognosis for disease progression or response to treatment, demonstrate target engagement or mechanism of action for candidate interventions, and monitor disease progression during treatment. The seven project sites and central coordinating center comprising MarkVCID, working with NINDS and NIA, identified a panel of 11 candidate fluid- and neuroimaging-based biomarker kits and established harmonized multicenter study protocols (see companion paper "MarkVCID cerebral small vessel consortium: I. Enrollment, clinical, fluid protocols" for full details). Here we describe the MarkVCID neuroimaging protocols with specific focus on validating their application to future multicenter trials. MarkVCID procedures for participant enrollment; clinical and cognitive evaluation; and collection, handling, and instrumental validation of fluid samples are described in detail in a companion paper. Magnetic resonance imaging (MRI) has long served as the neuroimaging modality of choice for cerebral small vessel disease and VCID because of its sensitivity to a wide range of brain properties, including small structural lesions, connectivity, and cerebrovascular physiology. Despite MRI's widespread use in the VCID field, there have been relatively scant data validating the repeatability and reproducibility of MRI-based biomarkers across raters, scanner types, and time intervals (collectively defined as instrumental validity). The MRI protocols described here address the core MRI sequences for assessing cerebral small vessel disease in future research studies, specific sequence parameters for use across various research scanner types, and rigorous procedures for determining instrumental validity. Another candidate neuroimaging modality considered by MarkVCID is optical coherence tomography angiography (OCTA), a non-invasive technique for directly visualizing retinal capillaries as a marker of the cerebral capillaries. OCTA has theoretical promise as a unique opportunity to visualize small vessels derived from the cerebral circulation, but at a considerably earlier stage of development than MRI. The additional OCTA protocols described here address procedures for determining OCTA instrumental validity, evaluating sources of variability such as pupil dilation, and handling data to maintain participant privacy. MRI protocol and instrumental validation The core sequences selected for the MarkVCID MRI protocol are three-dimensional T1-weighted multi-echo magnetization-prepared rapid-acquisition-of-gradient-echo (ME-MPRAGE), three-dimensional T2-weighted fast spin echo fluid-attenuated-inversion-recovery (FLAIR), two-dimensional diffusion-weighted spin-echo echo-planar imaging (DWI), three-dimensional T2*-weighted multi-echo gradient echo (3D-GRE), three-dimensional T2 -weighted fast spin-echo imaging (T2w), and two-dimensional T2*-weighted gradient echo echo-planar blood-oxygenation-level-dependent imaging with brief periods of CO2 inhalation (BOLD-CVR). Harmonized parameters for each of these core sequences were developed for four 3 Tesla MRI scanner models in widespread use at academic medical centers. MarkVCID project sites are trained and certified for their instantiation of the consortium MRI protocols. Sites are required to perform image quality checks every 2 months using the Alzheimer's Disease Neuroimaging Initiative phantom. Instrumental validation for MarkVCID MRI-based biomarkers is operationally defined as inter-rater reliability, test-retest repeatability, and inter-scanner reproducibility. Assessments of these instrumental properties are performed on individuals representing a range of cerebral small vessel disease from mild to severe. Inter-rater reliability is determined by distribution of an independent dataset of MRI scans to each analysis site. Test-retest repeatability is determined by repeat MRI scans performed on individual participants on a single MRI scanner after a short (1- to 14-day) interval. Inter-scanner reproducibility is determined by repeat MRI scans performed on individuals performed across four MRI scanner models. OCTA protocol and instrumental validation The MarkVCID OCTA protocol uses a commercially available, Food and Drug Administration-approved OCTA apparatus. Imaging is performed on one dilated and one undilated eye to assess the need for dilation. Scans are performed in quadruplicate. MarkVCID project sites participating in OCTA validation are trained and certified by this biomarker's lead investigator. Inter-rater reliability for OCTA is assessed by distribution of OCTA datasets to each analysis site. Test-retest repeatability is assessed by repeat OCTA imaging on individuals on the same day as their baseline OCTA and a different-day repeat session after a short (1- to 14-day) interval. Methods were developed to allow the OCTA data to be de-identified by the sites before transmission to the central data management system. The MarkVCID neuroimaging protocols, like the other MarkVCID procedures, are designed to allow translation to multicenter trials and as a template for outside groups to generate directly comparable neuroimaging data. The MarkVCID neuroimaging protocols are available to the biomedical community and intended to be shared. In addition to the instrumental validation procedures described here, each of the neuroimaging MarkVCID kits will undergo biological validation to determine its ability to measure important aspects of VCID such as cognitive function. The analytic methods for the neuroimaging-based kits and the results of these validation studies will be published separately. The results will ultimately determine the neuroimaging kits' potential usefulness for multicenter interventional trials in small vessel disease-related VCID.

The vascular network in the human brain is universally involved in physiology and neural activity and the alteration is commonly associated with neurological disorders such as traumatic brain injury, stroke, multiple sclerosis, and Alzheimer’s disease. However, small arterioles, venules, and the capillary networks are beyond the resolution of in vivo MRI and optical microscopy only reveals the vasculature of cortex in small animals. We reported a vascular network reconstruction with an automatic serial sectioning polarization sensitive optical coherence tomography at 3.5 micrometer resolution in ex vivo human brain tissue. Pathological patterns surrounding the vessel walls were revealed as well.

We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training. Classical registration methods solve an optimization problem to find a set of spatial correspondences between two images, while learning-based methods leverage a training dataset to learn a function that generates these correspondences. The quality of the results for both types of techniques depends greatly on the choice of hyperparameters. Unfortunately, hyperparameter tuning is time-consuming and typically involves training many separate models with various hyperparameter values, potentially leading to suboptimal results. To address this inefficiency, we introduce amortized hyperparameter learning for image registration, a novel strategy to learn the effects of hyperparameters on deformation fields. The proposed framework learns a hypernetwork that takes in an input hyperparameter and modulates a registration network to produce the optimal deformation field for that hyperparameter value. In effect, this strategy trains a single, rich model that enables rapid, fine-grained discovery of hyperparameter values from a continuous interval at test-time. We demonstrate that this approach can be used to optimize multiple hyperparameters considerably faster than existing search strategies, leading to a reduced computational and human burden as well as increased flexibility. We also show several important benefits, including increased robustness to initialization and the ability to rapidly identify optimal hyperparameter values specific to a registration task, dataset, or even a single anatomical region, all without retraining the HyperMorph model. Our code is publicly available at http://voxelmorph.mit.edu.

Accurate and reliable whole-brain segmentation is critical to longitudinal neuroimaging studies. We undertake a comparative analysis of two subcortical segmentation methods, Automatic Segmentation (ASEG) and Sequence Adaptive Multimodal Segmentation (SAMSEG), recently provided in the open-source neuroimaging package FreeSurfer 7.1, with regard to reliability, bias, sensitivity to detect longitudinal change, and diagnostic sensitivity to Alzheimer’s disease. First, we assess intra- and inter-scanner reliability for eight bilateral subcortical structures: amygdala, caudate, hippocampus, lateral ventricles, nucleus accumbens, pallidum, putamen and thalamus. For intra-scanner analysis we use a large sample of participants (n = 1629) distributed across the lifespan (age range = 4–93 years) and acquired on a 1.5T Siemens Avanto (n = 774) and a 3T Siemens Skyra (n = 855) scanners. For inter-scanner analysis we use a sample of 24 participants scanned on the day with three models of Siemens scanners: 1.5T Avanto, 3T Skyra and 3T Prisma. Second, we test how each method detects volumetric age change using longitudinal follow up scans (n = 491 for Avanto and n = 245 for Skyra; interscan interval = 1–10 years). Finally, we test sensitivity to clinically relevant change. We compare annual rate of hippocampal atrophy in cognitively normal older adults (n = 20), patients with mild cognitive impairment (n = 20) and Alzheimer’s disease (n = 20). We find that both ASEG and SAMSEG are reliable and lead to the detection of within-person longitudinal change, although with notable differences between age-trajectories for most structures, including hippocampus and amygdala. In summary, SAMSEG yields significantly lower differences between repeated measures for intra- and inter-scanner analysis without compromising sensitivity to changes and demonstrating ability to detect clinically relevant longitudinal changes.

Significance: The optical properties of biological samples provide information about the structural characteristics of the tissue and any changes arising from pathological conditions. Optical coherence tomography (OCT) has proven to be capable of extracting tissue’s optical properties using a model that combines the exponential decay due to tissue scattering and the axial point spread function that arises from the confocal nature of the detection system, particularly for higher numerical aperture (NA) measurements. A weakness in estimating the optical properties is the inter-parameter cross-talk between tissue scattering and the confocal parameters defined by the Rayleigh range and the focus depth. Aim: In this study, we develop a systematic method to improve the characterization of optical properties with high-NA OCT. Approach: We developed a method that spatially parameterizes the confocal parameters in a previously established model for estimating the optical properties from the depth profiles of high-NA OCT. Results: The proposed parametrization model was first evaluated on a set of intralipid phantoms and then validated using a low-NA objective in which cross-talk from the confocal parameters is negligible. We then utilize our spatially parameterized model to characterize optical property changes introduced by a tissue index matching process using a simple immersion agent, 2,2’-thiodiethonal. Conclusions: Our approach improves the confidence of parameter estimation by reducing the degrees of freedom in the non-linear fitting model.

The use of multiple atlases is common in medical image segmentation. This typically requires deformable registration of the atlases (or the average atlas) to the new image, which is computationally expensive and susceptible to entrapment in local optima. We propose to instead consider the probability of all possible atlas-to-image transformations and compute the expected label value (ELV), thereby not relying merely on the transformation deemed “optimal” by the registration method. Moreover, we do so without actually performing deformable registration, thus avoiding the associated computational costs. We evaluate our ELV computation approach by applying it to brain, liver, and pancreas segmentation on datasets of magnetic resonance and computed tomography images.

Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human brain MRI scans, replicating FreeSurfer's anatomical segmentation including surface reconstruction and cortical parcellation. To this end, we introduce an advanced deep learning architecture capable of whole brain segmentation into 95 classes. The network architecture incorporates local and global competition via competitive dense blocks and competitive skip pathways, as well as multi-slice information aggregation that specifically tailor network performance towards accurate segmentation of both cortical and sub-cortical structures. Further, we perform fast cortical surface reconstruction and thickness analysis by introducing a spectral spherical embedding and by directly mapping the cortical labels from the image to the surface. This approach provides a full FreeSurfer alternative for volumetric analysis (in under 1 minute) and surface-based thickness analysis (within only around 1h runtime). For sustainability of this approach we perform extensive validation: we assert high segmentation accuracy on several unseen datasets, measure generalizability and demonstrate increased test-retest reliability, and high sensitivity to group differences in dementia., Comment: Submitted to NeuroImage

The development of automated tools for brain morphometric analysis in infants has lagged significantly behind analogous tools for adults. This gap reflects the greater challenges in this domain due to: 1) a smaller-scaled region of interest, 2) increased motion corruption, 3) regional changes in geometry due to heterochronous growth, and 4) regional variations in contrast properties corresponding to ongoing myelination and other maturation processes. Nevertheless, there is a great need for automated image-processing tools to quantify differences between infant groups and other individuals, because aberrant cortical morphologic measurements (including volume, thickness, surface area, and curvature) have been associated with neuropsychiatric, neurologic, and developmental disorders in children. In this paper we present an automated segmentation and surface extraction pipeline designed to accommodate clinical MRI studies of infant brains in a population 0-2 year-olds. The algorithm relies on a single channel of T1-weighted MR images to achieve automated segmentation of cortical and subcortical brain areas, producing volumes of subcortical structures and surface models of the cerebral cortex. We evaluated the algorithm both qualitatively and quantitatively using manually labeled datasets, relevant comparator software solutions cited in the literature, and expert evaluations. The computational tools and atlases described in this paper will be distributed to the research community as part of the FreeSurfer image analysis package., Comment: 49 pages, 25 figures, submitted to NeuroImage

Cortical volumetric analysis is widely used to study the anatomic basis of neurological deficits in patients with traumatic brain injury (TBI). However, patients with TBI-related lesions are often excluded from MRI analyses because cortical lesions may compromise the accuracy of reconstructed surfaces upon which volumetric measurements are based. We developed a FreeSurfer-based lesion correction method and tested its impact on cortical volume measures in 87 patients with chronic moderate-to-severe TBI. We reconstructed cortical surfaces from T1-weighted MRI scans, then manually labeled and removed vertices on the cortical surfaces where lesions caused inaccuracies. Next, we measured the surface area of lesion overlap with seven canonical brain networks and the percent volume of each network affected by lesions. • The lesion correction method revealed that cortical lesions in patients with TBI are preferentially located in the limbic and default mode networks (95.7% each), with the limbic network also having the largest average surface area (4.4+/−3.7%) and percent volume affected by lesions (12.7+/−9.7%). • The method has the potential to improve the accuracy of cortical volumetric measurements and permit inclusion of patients with lesioned brains in MRI analyses. • The method also provides new opportunities to elucidate network-based mechanisms of neurological deficits in patients with TBI.

BackgroundWe sought to develop an automatable score to predict hospitalization, critical illness, or death in patients at risk for COVID-19 presenting for urgent care during the Massachusetts outbreak.MethodsSingle-center study of adult outpatients seen in respiratory illness clinics (RICs) or the emergency department (ED), including development (n = 9381, March 7-May 2) and prospective (n = 2205, May 3-14) cohorts. Data was queried from Partners Enterprise Data Warehouse. Outcomes were hospitalization, critical illness or death within 7 days. We developed the COVID-19 Acuity Score (CoVA) using automatically extracted data from the electronic medical record and learning-to-rank ordinal logistic regression modeling. Calibration was assessed using predicted-to-observed ratio (E/O). Discrimination was assessed by C-statistics (AUC).ResultsIn the development cohort, 27.3%, 7.2%, and 1.1% of patients experienced hospitalization, critical illness, or death, respectively; and in the prospective cohort, 26.1%, 6.3%, and 0.5%. CoVA showed excellent performance in the development cohort (concurrent validation) for hospitalization (E/O: 1.00, AUC: 0.80); for critical illness (E/O: 1.00, AUC: 0.82); and for death (E/O: 1.00, AUC: 0.87). Performance in the prospective cohort (prospective validation) was similar for hospitalization (E/O: 1.01, AUC: 0.76); for critical illness (E/O 1.03, AUC: 0.79); and for death (E/O: 1.63, AUC=0.93). Among 30 predictors, the top five were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate.ConclusionsCoVA is a prospectively validated automatable score to assessing risk for adverse outcomes related to COVID-19 infection in the outpatient setting.

The human hippocampus is vulnerable to a range of degenerative conditions and as such, accurate in vivo measurement of the hippocampus and hippocampal substructures via neuroimaging is of great interest for understanding mechanisms of disease as well as for use as a biomarker in clinical trials of novel therapeutics. Although total hippocampal volume can be measured relatively reliably, it is critical to understand how this reliability is affected by acquisition on different scanners, as multiple scanning platforms would likely be utilized in large-scale clinical trials. This is particularly true for hippocampal subregional measurements, which have only relatively recently been measurable through common image processing platforms such as FreeSurfer. Accurate segmentation of these subregions is challenging due to their small size, magnetic resonance imaging (MRI) signal loss in medial temporal regions of the brain, and lack of contrast for delineation from standard neuroimaging procedures.Here, we assess the test-retest reliability of the FreeSurfer automated hippocampal subfield segmentation procedure using two Siemens model scanners (a Siemens Trio and Prismafit Trio upgrade). T1-weighted images were acquired for 11 generally healthy younger participants (two scans on the Trio and one scan on the Prismafit). Each scan was processed through the standard cross-sectional stream and the recently released longitudinal pipeline in FreeSurfer v6.0 for hippocampal segmentation. Test-retest reliability of the volumetric measures was examined for individual subfields as well as percent volume difference and Dice overlap among scans and intra-class correlation coefficients (ICC). Reliability was high in the molecular layer, dentate gyrus, and whole hippocampus with the inclusion of three time points with mean volume differences among scans less than 3%, overlap greater than 80%, and ICC >0.95. The parasubiculum and hippocampal fissure showed the least improvement in reliability with mean volume difference greater than 5%, overlap less than 70%, and ICC scores ranging from 0.78 to 0.89. Other subregions, including the CA regions, were stable in their mean volume difference and overlap (75% respectively) and showed improvement in reliability with the inclusion of three scans (ICC ​> ​0.9). Reliability was generally higher within scanner (Trio-Trio), however, Trio-Prismafit reliability was also high and did not exhibit an obvious bias. These results suggest that the FreeSurfer automated segmentation procedure is a reliable method to measure total as well as hippocampal subregional volumes and may be useful in clinical applications including as an endpoint for future clinical trials of conditions affecting the hippocampus.

Non-rigid cortical registration is an important and challenging task due to the geometric complexity of the human cortex and the high degree of inter-subject variability. A conventional solution is to use a spherical representation of surface properties and perform registration by aligning cortical folding patterns in that space. This strategy produces accurate spatial alignment but often requires a high computational cost. Recently, convolutional neural networks (CNNs) have demonstrated the potential to dramatically speed up volumetric registration. However, due to distortions introduced by projecting a sphere to a 2D plane, a direct application of recent learning-based methods to surfaces yields poor results. In this study, we present SphereMorph, a diffeomorphic registration framework for cortical surfaces using deep networks that addresses these issues. SphereMorph uses a UNet-style network associated with a spherical kernel to learn the displacement field and warps the sphere using a modified spatial transformer layer. We propose a resampling weight in computing the data fitting loss to account for distortions introduced by polar projection, and demonstrate the performance of our proposed method on two tasks, including cortical parcellation and group-wise functional area alignment. The experiments show that the proposed SphereMorph is capable of modeling the geometric registration problem in a CNN framework and demonstrate superior registration accuracy and computational efficiency. The source code of SphereMorph will be released to the public upon acceptance of this manuscript at https://github.com/voxelmorph/spheremorph., Comment: cortical surface registration, deep network, unsupervised learning, registration, deep learning, cortical, spherical, invertible

A systematic method was developed to parametrize confocal parameters for modeling the depth profile of optical coherence tomography images in highly scattering media. This approach enables improved quantification of optical properties of human brain tissue.

Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols – even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR .

There is great value to use of structural neuroimaging in the assessment of Alzheimer's disease (AD). However, to date, predictive value of structural imaging tend to range between 80% and 90% in accuracy and it is unclear why this is the case given that structural imaging should parallel the pathologic processes of AD. There is a possibility that clinical misdiagnosis relative to the gold standard pathologic diagnosis and/or additional brain pathologies are confounding factors contributing to reduced structural imaging classification accuracy. We examined potential factors contributing to misclassification of individuals with clinically diagnosed AD purely from cortical thickness measures. Correctly classified and incorrectly classified groups were compared across a range of demographic, biological, and neuropsychological data including cerebrospinal fluid biomarkers, amyloid imaging, white matter hyperintensity (WMH) volume, cognitive, and genetic factors. Individual subject analyses suggested that at least a portion of the control individuals misclassified as AD from structural imaging additionally harbor substantial AD biomarker pathology and risk, yet are relatively resistant to cognitive symptoms, likely due to "cognitive reserve," and therefore clinically unimpaired. In contrast, certain clinical control individuals misclassified as AD from cortical thickness had increased WMH volume relative to other controls in the sample, suggesting that vascular conditions may contribute to classification accuracy from cortical thickness measures. These results provide examples of factors that contribute to the accuracy of structural imaging in predicting a clinical diagnosis of AD, and provide important information about considerations for future work aimed at optimizing structural based diagnostic classifiers for AD.

Background White matter signal abnormalities (WMSA) (also known as 'hyperintensities') on MRI are commonly seen in normal aging and increases have been noted in Alzheimer's disease (AD), but whether there is a spatial specificity to these increases is unknown. Objective To discern whether or not there is a spatial pattern of WMSA in the brains of individuals with AD that differs from those who exhibit cognitively healthy aging. Method Structural MRI data from the Alzheimer's Disease Neuroimaging Initiative public database were used to quantify WMSA in 35 regions of interest (ROIs). Regional measures were compared between cognitively healthy older controls (OC; n = 107) and individuals with a clinical diagnosis of AD (n = 127). Regional WMSA volume was also assessed in individuals with mild cognitive impairment (MCI; n = 74) who were 6, 12, and 24 months away from AD conversion. Results WMSA volume was significantly greater in AD compared to OC in 24 out of 35 ROIs after controlling for age, and nine were significantly higher after normalizing for total WMSA. Regions with greater WMSA volume in AD included rostral frontal, inferior temporal, and inferior parietal WM. In MCI, frontal and temporal regions demonstrated significantly greater WMSA volume with decreasing time-to-AD-conversion. Discussion Individuals with AD have greater regional volume of WMSA compared to OC regardless of age or total WMSA volume. Accumulation of regional WMSA is linked to time to AD conversion in individuals with MCI. These findings indicate WMSA is an important pathological component of AD development.

Cortical volumetric analysis is widely used to study the anatomic basis of neurological deficits in patients with traumatic brain injury (TBI). However, patients with TBI-related lesions are often excluded from analysis, because cortical lesions may compromise the accuracy of reconstructed surfaces upon which volumetric measurements are based. Here, we propose a novel FreeSurfer-based lesion correction method and illustrate its impact on cortical volume measures in patients with chronic moderate-to-severe TBI. We performed MRI in 87 patients at mean+/−SD 10.9+/−9.1 years post-injury using a T1-weighted multi-echo MPRAGE sequence at 1 mm resolution. Following surface reconstruction, we parcellated the cerebral cortex into seven functional networks using FreeSurfer’s standard pipeline. Next, we manually labeled vertices on the cortical surface where lesions caused inaccuracies and removed them from network-based cortical volumetric measures. After performing this lesion correction procedure, we measured the surface area of lesion overlap with each network and the percent volume of each network affected by lesions. We identified 120 lesions that caused inaccuracies in the cortical surface in 46 patients. In these 46 patients, the most commonly lesioned networks were the limbic and default mode networks (95.7% each), followed by the executive control (78.3%), and salience (71.7%) networks. The limbic network had the largest average surface area of lesion overlap (4.4+/−3.7%) and the largest percent volume affected by lesions (12.7+/−9.7%). The lesion correction method has the potential to improve the accuracy of cortical volumetric measurements and permit inclusion of patients with lesioned brains in quantitative analyses, providing new opportunities to elucidate network-based mechanisms of neurological deficits in patients with TBI.

We present an ultra-high resolution MRI dataset of an ex vivo human brain specimen. The brain specimen was donated by a 58-year-old woman who had no history of neurological disease and died of non-neurological causes. After fixation in 10% formalin, the specimen was imaged on a 7 Tesla MRI scanner at 100 µm isotropic resolution using a custom-built 31-channel receive array coil. Single-echo multi-flip Fast Low-Angle SHot (FLASH) data were acquired over 100 hours of scan time (25 hours per flip angle), allowing derivation of synthesized FLASH volumes. This dataset provides an unprecedented view of the three-dimensional neuroanatomy of the human brain. To optimize the utility of this resource, we warped the dataset into standard stereotactic space. We now distribute the dataset in both native space and stereotactic space to the academic community via multiple platforms. We envision that this dataset will have a broad range of investigational, educational, and clinical applications that will advance understanding of human brain anatomy in health and disease., Measurement(s)nuclear magnetic resonance assayTechnology Type(s)MRI ScannerFactor Type(s)flip angleSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.9958688

With the advent of convolutional neural networks~(CNN), supervised learning methods are increasingly being used for whole brain segmentation. However, a large, manually annotated training dataset of labeled brain images required to train such supervised methods is frequently difficult to obtain or create. In addition, existing training datasets are generally acquired with a homogeneous magnetic resonance imaging~(MRI) acquisition protocol. CNNs trained on such datasets are unable to generalize on test data with different acquisition protocols. Modern neuroimaging studies and clinical trials are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is very difficult to standardize the gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input acquisition. Our approach relies on building approximate forward models of pulse sequences that produce a typical test image. For a given pulse sequence, we use its forward model to generate plausible, synthetic training examples that appear as if they were acquired in a scanner with that pulse sequence. Sampling over a wide variety of pulse sequences results in a wide variety of augmented training examples that help build an image contrast invariant model. Our method trains a single CNN that can segment input MRI images with acquisition parameters as disparate as $T_1$-weighted and $T_2$-weighted contrasts with only $T_1$-weighted training data. The segmentations generated are highly accurate with state-of-the-art results~(overall Dice overlap$=0.94$), with a fast run time~($\approx$ 45 seconds), and consistent across a wide range of acquisition protocols., Typo in author name corrected. Greves -> Greve

The use of multiple atlases is common in medical image segmentation. This typically requires deformable registration of the atlases (or the average atlas) to the new image, which is computationally expensive and susceptible to entrapment in local optima. We propose to instead consider the probability of all possible transformations and compute the expected label value (ELV), thereby not relying merely on the transformation resulting from the registration. Moreover, we do so without actually performing deformable registration, thus avoiding the associated computational costs. We evaluate our ELV computation approach by applying it to liver segmentation on a dataset of computed tomography (CT) images.

No abstract available.

Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learning-based segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU.

Diffusion magnetic resonance imaging (dMRI) is a unique technology that allows the noninvasive quantification of microstructural tissue properties of the human brain in healthy subjects as well as the probing of disease-induced variations. Population studies of dMRI data have been essential in identifying pathological structural changes in various conditions, such as Alzheimer's and Huntington's diseases (Salat et al., 2010; Rosas et al., 2006). The most common form of dMRI involves fitting a tensor to the underlying imaging data (known as diffusion tensor imaging, or DTI), then deriving parametric maps, each quantifying a different aspect of the underlying microstructure, e.g. fractional anisotropy and mean diffusivity. To date, the statistical methods utilized in most DTI population studies either analyzed only one such map or analyzed several of them, each in isolation. However, it is most likely that variations in the microstructure due to pathology or normal variability would affect several parameters simultaneously, with differing variations modulating the various parameters to differing degrees. Therefore, joint analysis of the available diffusion maps can be more powerful in characterizing histopathology and distinguishing between conditions than the widely used univariate analysis. In this article, we propose a multivariate approach for statistical analysis of diffusion parameters that uses partial least squares correlation (PLSC) analysis and permutation testing as building blocks in a voxel-wise fashion. Stemming from the common formulation, we present three different multivariate procedures for group analysis, regressing-out nuisance parameters and comparing effects of different conditions. We used the proposed procedures to study the effects of non-demented aging, Alzheimer's disease and mild cognitive impairment on the white matter. Here, we present results demonstrating that the proposed PLSC-based approach can differentiate between effects of different conditions in the same region as well as uncover spatial variations of effects across the white matter. The proposed procedures were able to answer questions on structural variations such as: "are there regions in the white matter where Alzheimer's disease has a different effect than aging or similar effect as aging?" and "are there regions in the white matter that are affected by both mild cognitive impairment and Alzheimer's disease but with differing multivariate effects?"

Recent work has demonstrated that subject motion produces systematic biases in the metrics computed by widely used morphometry software packages, even when the motion is too small to produce noticeable image artefacts. In the common situation where the control population exhibits different behaviours in the scanner when compared to the experimental population, these systematic measurement biases may produce significant confounds for between-group analyses, leading to erroneous conclusions about group differences. While previous work has shown that prospective motion correction can improve perceived image quality, here we demonstrate that, in healthy subjects performing a variety of directed motions, the use of the volumetric navigator (vNav) prospective motion correction system significantly reduces the motion-induced bias and variance in morphometry.

AbstaractConnectomics has proved promising in quantifying and understanding the effects of development, aging and an array of diseases on the brain. In this work, we propose a new structural connectivity measure from diffusion MRI that allows us to incorporate direct brain connections, as well as indirect ones that would not be otherwise accounted for by standard techniques and that may be key for the better understanding of function from structure. From our experiments on the Human Connectome Project dataset, we find that our measure of structural connectivity better correlates with functional connectivity than streamline tractography does, meaning that it provides new structural information related to function. Through additional experiments on the ADNI-2 dataset, we demonstrate the ability of this new measure to better discriminate different stages of Alzheimer’s disease. Our findings suggest that this measure is useful in the study of the normal brain structure, and for quantifying the effects of disease on the brain structure.

Image segmentation is a critical step in numerous medical imaging studies, which can be facilitated by automatic computational techniques. Supervised methods, although highly effective, require large training datasets of manually labeled images that are labor-intensive to produce. Unsupervised methods, on the contrary, can be used in the absence of training data to segment new images. We introduce a new approach to unsupervised image segmentation that is based on the computation of the local center of mass. We propose an efficient method to group the pixels of a one-dimensional signal, which we then use in an iterative algorithm for two- and three-dimensional image segmentation. We validate our method on a 2D X-ray image, a 3D abdominal magnetic resonance (MR) image and a dataset of 3D cardiovascular MR images.

PURPOSE: To integrate markerless head motion tracking with prospectively-corrected neuroanatomical MRI sequences and to investigate high-frequency motion correction during imaging echo-trains. METHODS: A commercial 3D surface tracking system, which estimates head motion by registering point cloud reconstructions of the face, was used to adapt the imaging field-of-view (FOV) based on head movement during MPRAGE and T2-SPACE (3D variable-flip-angle TSE) sequences. The FOV position and orientation were updated every 6 lines of k-space (

Epidemiological studies suggest that a single moderate-to-severe traumatic brain injury (TBI) is associated with an increased risk of neurodegenerative disease, including Alzheimer's disease (AD) and Parkinson's disease (PD). Histopathological studies describe complex neurodegenerative pathologies in individuals exposed to single moderate-to-severe TBI or repetitive mild TBI, including chronic traumatic encephalopathy (CTE). However, the clinicopathological links between TBI and post-traumatic neurodegenerative diseases such as AD, PD, and CTE remain poorly understood. Here, we describe the methodology of the Late Effects of TBI (LETBI) study, whose goals are to characterize chronic post-traumatic neuropathology and to identify in vivo biomarkers of post-traumatic neurodegeneration. LETBI participants undergo extensive clinical evaluation using National Institutes of Health TBI Common Data Elements, proteomic and genomic analysis, structural and functional magnetic resonance imaging (MRI), and prospective consent for brain donation. Selected brain specimens undergo ultra-high resolution ex vivo MRI and histopathological evaluation including whole–mount analysis. Co-registration of ex vivo and in vivo MRI data enables identification of ex vivo lesions that were present during life. In vivo signatures of postmortem pathology are then correlated with cognitive and behavioral data to characterize the clinical phenotype(s) associated with pathological brain lesions. We illustrate the study methods and demonstrate proof of concept for this approach by reporting results from the first LETBI participant, who despite the presence of multiple in vivo and ex vivo pathoanatomic lesions had normal cognition and was functionally independent until her mid-80s. The LETBI project represents a multidisciplinary effort to characterize post-traumatic neuropathology and identify in vivo signatures of postmortem pathology in a prospective study.

The results of most neuroimaging studies are reported in volumetric (e.g., MNI152) or surface (e.g., fsaverage) coordinate systems. Accurate mappings between volumetric and surface coordinate systems can facilitate many applications, such as projecting fMRI group analyses from MNI152/Colin27 to fsaverage for visualization, or projecting resting-state fMRI parcellations from fsaverage to MNI152/Colin27 for volumetric analysis of new data. However, there has been surprisingly little research on this topic. Here, we evaluated three approaches for mapping data between MNI152/Colin27 and fsaverage coordinate systems by simulating the above applications: projection of group-average data from MNI152/Colin27 to fsaverage and projection of fsaverage parcellations to MNI152/Colin27. Two of the approaches are currently widely used. A third approach (registration fusion) was previously proposed, but not widely adopted. Two implementations of the registration fusion (RF) approach were considered, with one implementation utilizing the Advanced Normalization Tools (ANTs). We found that RF-ANTs performed the best for mapping between fsaverage and MNI152/Colin27, even for new subjects registered to MNI152/Colin27 using a different software tool (FSL FNIRT). This suggests that RF-ANTs would be useful even for researchers not using ANTs. Finally, it is worth emphasizing that the most optimal approach for mapping data to a coordinate system (e.g., fsaverage) is to register individual subjects directly to the coordinate system, rather than via another coordinate system. Only in scenarios where the optimal approach is not possible (e.g., mapping previously published results from MNI152 to fsaverage), should the approaches evaluated in this manuscript be considered. In these scenarios, we recommend RF-ANTs (https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/registration/Wu2017_RegistrationFusion).

Accurate automatic segmentation of brain anatomy from \(T_1\)-weighted (\(T_1\)-w) magnetic resonance images (MRI) has been a computationally intensive bottleneck in neuroimaging pipelines, with state-of-the-art results obtained by unsupervised intensity modeling-based methods and multi-atlas registration and label fusion. With the advent of powerful supervised convolutional neural networks (CNN)-based learning algorithms, it is now possible to produce a high quality brain segmentation within seconds. However, the very supervised nature of these methods makes it difficult to generalize them on data different from what they have been trained on. Modern neuroimaging studies are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is not possible to standardize the whole gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input \(T_1\)-w acquisition. Our approach relies on building approximate forward models of \(T_1\)-w pulse sequences that produce a typical test image. We use the forward models to augment the training data with test data specific training examples. These augmented data can be used to update and/or build a more robust segmentation model that is more attuned to the test data imaging properties. Our method generates highly accurate, state-of-the-art segmentation results (overall Dice overlap = 0.94), within seconds and is consistent across a wide-range of protocols.

Recent advances in MR technology have enabled increased spatial resolution for routine functional and anatomical imaging, which has created demand for software tools that are able to process these data. The availability of high-resolution data also raises the question of whether higher resolution leads to substantial gains in accuracy of quantitative morphometric neuroimaging procedures, in particular the cortical surface reconstruction and cortical thickness estimation. In this study we adapted the FreeSurfer cortical surface reconstruction pipeline to process structural data at native submillimeter resolution. We then quantified the differences in surface placement between meshes generated from (0.75 mm)3 isotropic resolution data acquired in 39 volunteers and the same data downsampled to the conventional 1 mm3 voxel size. We find that when processed at native resolution, cortex is estimated to be thinner in most areas, but thicker around the Cingulate and the Calcarine sulci as well as in the posterior bank of the Central sulcus. Thickness differences are driven by two kinds of effects. First, the gray–white surface is found closer to the white matter, especially in cortical areas with high myelin content, and thus low contrast, such as the Calcarine and the Central sulci, causing local increases in thickness estimates. Second, the gray–CSF surface is placed more interiorly, especially in the deep sulci, contributing to local decreases in thickness estimates. We suggest that both effects are due to reduced partial volume effects at higher spatial resolution. Submillimeter voxel sizes can therefore provide improved accuracy for measuring cortical thickness.

We introduce BrainPrint, a compact and discriminative representation of brain morphology. BrainPrint captures shape information of an ensemble of cortical and subcortical structures by solving the eigenvalue problem of the 2D and 3D Laplace–Beltrami operator on triangular (boundary) and tetrahedral (volumetric) meshes. This discriminative characterization enables new ways to study the similarity between brains; the focus can either be on a specific brain structure of interest or on the overall brain similarity. We highlight four applications for BrainPrint in this article: (i) subject identification, (ii) age and sex prediction, (iii) brain asymmetry analysis, and (iv) potential genetic influences on brain morphology. The properties of BrainPrint require the derivation of new algorithms to account for the heterogeneous mix of brain structures with varying discriminative power. We conduct experiments on three datasets, including over 3000 MRI scans from the ADNI database, 436 MRI scans from the OASIS dataset, and 236 MRI scans from the VETSA twin study. All processing steps for obtaining the compact representation are fully automated, making this processing framework particularly attractive for handling large datasets., National Cancer Institute (U.S.) (1K25-CA181632-01), Athinoula A. Martinos Center for Biomedical Imaging (P41-RR014075), Athinoula A. Martinos Center for Biomedical Imaging (P41-EB015896), National Alliance for Medical Image Computing (U.S.) (U54-EB005149), Neuroimaging Analysis Center (U.S.) (P41-EB015902), National Center for Research Resources (U.S.) (U24 RR021382), National Institute of Biomedical Imaging and Bioengineering (U.S.) (5P41EB015896-15), National Institute of Biomedical Imaging and Bioengineering (U.S.) (R01EB006758), National Institute on Aging (AG022381), National Institute on Aging (5R01AG008122-22), National Institute on Aging (AG018344), National Institute on Aging (AG018386), National Center for Complementary and Alternative Medicine (U.S.) (RC1 AT005728-01), National Institute of Neurological Diseases and Stroke (U.S.) (R01 NS052585-01), National Institute of Neurological Diseases and Stroke (U.S.) (1R21NS072652-01), National Institute of Neurological Diseases and Stroke (U.S.) (1R01NS070963), National Institute of Neurological Diseases and Stroke (U.S.) (R01NS083534), National Institutes of Health (U.S.) ((5U01-MH093765)

In this paper we present a novel label fusion algorithm suited for scenarios in which different manual delineation protocols with potentially disparate structures have been used to annotate the training scans (hereafter referred to as "atlases"). Such scenarios arise when atlases have missing structures, when they have been labeled with different levels of detail, or when they have been taken from different heterogeneous databases. The proposed algorithm can be used to automatically label a novel scan with any of the protocols from the training data. Further, it enables us to generate new labels that are not present in any delineation protocol by defining intersections on the underling labels. We first use probabilistic models of label fusion to generalize three popular label fusion techniques to the multi-protocol setting: majority voting, semi-locally weighted voting and STAPLE. Then, we identify some shortcomings of the generalized methods, namely the inability to produce meaningful posterior probabilities for the different labels (majority voting, semi-locally weighted voting) and to exploit the similarities between the atlases (all three methods). Finally, we propose a novel generative label fusion model that can overcome these drawbacks. We use the proposed method to combine four brain MRI datasets labeled with different protocols (with a total of 102 unique labeled structures) to produce segmentations of 148 brain regions. Using cross-validation, we show that the proposed algorithm outperforms the generalizations of majority voting, semi-locally weighted voting and STAPLE (mean Dice score 83%, vs. 77%, 80% and 79%, respectively). We also evaluated the proposed algorithm in an aging study, successfully reproducing some well-known results in cortical and subcortical structures. (C) 2014 The Authors. Published by Elsevier Inc.

The choice of a reference image typically influences the results of deformable image registration, thereby making it asymmetric. This is a consequence of a spatially non-uniform weighting in the cost function integral that leads to general registration inaccuracy. The inhomogeneous integral measure – which is the local volume change in the transformation, thus varying through the course of the registration – causes image regions to contribute differently to the objective function. More importantly, the optimization algorithm is allowed to minimize the cost function by manipulating the volume change, instead of aligning the images. The approaches that restore symmetry to deformable registration successfully achieve inverse-consistency, but do not eliminate the regional bias that is the source of the error. In this work, we address the root of the problem: the non-uniformity of the cost function integral. We introduce a new quasi-volume-preserving constraint that allows for volume change only in areas with well-matching image intensities, and show that such a constraint puts a bound on the error arising from spatial non-uniformity. We demonstrate the advantages of adding the proposed constraint to standard (asymmetric and symmetrized) demons and diffeomorphic demons algorithms through experiments on synthetic images, and real X-ray and 2D/3D brain MRI data. Specifically, the results show that our approach leads to image alignment with more accurate matching of manually defined neuroanatomical structures, better tradeoff between image intensity matching and registration-induced distortion, improved native symmetry, and lower susceptibility to local optima. In summary, the inclusion of this space- and time-varying constraint leads to better image registration along every dimension that we have measured it.

Multimodal image registration facilitates the combination of complementary information from images acquired with different modalities. Most existing methods require computation of the joint histogram of the images, while some perform joint segmentation and registration in alternate iterations. In this work, we introduce a new non-information-theoretical method for pairwise multimodal image registration, in which the error of segmentation — using both images — is considered as the registration cost function. We empirically evaluate our method via rigid registration of multi-contrast brain magnetic resonance images, and demonstrate an often higher registration accuracy in the results produced by the proposed technique, compared to those by several existing methods.

Diffusion MRI tractography produces massive sets of streamlines that contain a wealth of information on brain connections. The size of these datasets creates a need for automated clustering methods to group the streamlines into meaningful bundles. Conventional clustering techniques group streamlines based on their spatial coordinates. Neuroanatomists, however, define white-matter bundles based on the anatomical structures that they go through or next to, rather than their spatial coordinates. Thus we propose a similarity measure for clustering streamlines based on their position relative to cortical and subcortical brain regions. We incorporate this measure into a hierarchical clustering algorithm and compare it to a measure that relies on Euclidean distance, using data from the Human Connectome Project. We show that the anatomical similarity measure leads to a 20% improvement in the overlap of clusters with manually labeled tracts. Importantly, this is achieved without introducing any prior information from a tract atlas into the clustering algorithm, therefore without imposing the existence of any named tracts.

We report the clinical, neuroimaging, and neuropathologic characteristics of 2 patients who developed early onset dementia after a moderate-severe traumatic brain injury (TBI). Neuropathological evaluation revealed abundant β-amyloid neuritic and cored plaques, diffuse β-amyloid plaques, and frequent hyperphosphorylated-tau neurofibrillary tangles (NFT) involving much of the cortex, including insula and mammillary bodies in both cases. Case 1 additionally showed NFTs in both the superficial and deep cortical layers, occasional perivascular and depth-of-sulci NFTs, and parietal white matter rarefaction, which corresponded with decreased parietal fiber tracts observed on ex vivo MRI. Case 2 additionally showed NFT predominance in the superficial layers of the cortex, hypothalamus and brainstem, diffuse Lewy bodies in the cortex, amygdala and brainstem, and intraneuronal TDP-43 inclusions. The neuropathologic diagnoses were atypical Alzheimer disease (AD) with features of chronic traumatic encephalopathy and white matter loss (Case 1), and atypical AD, dementia with Lewy bodies and coexistent TDP-43 pathology (Case 2). These findings support an epidemiological association between TBI and dementia and further characterize the variety of misfolded proteins that may accumulate after TBI. Analyses with comprehensive clinical, imaging, genetic, and neuropathological data are required to characterize the full clinicopathological spectrum associated with dementias occurring after moderate-severe TBI.

Population-level inferences and individual-level analyses are two important aspects in functional magnetic resonance imaging (fMRI) studies. Extracting reliable and informative features from fMRI data that capture biologically meaningful inter-subject variation is critical for aligning and comparing functional networks across subjects, and connecting the properties of functional brain organization with variations in behavior, cognition and genetics. In this study, we derive two new measures, which we term functional density map and edge map, and demonstrate their usefulness in characterizing the function of individual brains. Specifically, using data from the Human Connectome Project (HCP), we show that (1) both functional maps capture intrinsic properties of the functional connectivity pattern in individuals while exhibiting large variation across subjects; (2) functional maps derived from either resting-state or task-evoked fMRI can be used to accurately identify subjects from a population; and (3) cross-subject alignment using these functional maps considerably reduces functional variation and improves functional correspondence across subjects over state-of-the-art multimodal registration algorithms. Our results suggest that the proposed functional density and edge maps are promising features in characterizing the functional architecture in individuals and provide an alternative way to explore the functional variation across subjects.

BACKGROUND AND PURPOSE: The entorhinal cortex, a critical gateway between the neocortex and hippocampus, is one of the earliest regions affected by Alzheimer disease–associated neurofibrillary tangle pathology. Although our prior work has automatically delineated an MR imaging–based measure of the entorhinal cortex, whether antemortem entorhinal cortex thickness is associated with postmortem tangle burden within the entorhinal cortex is still unknown. Our objective was to evaluate the relationship between antemortem MRI measures of entorhinal cortex thickness and postmortem neuropathological measures. MATERIALS AND METHODS: We evaluated 50 participants from the Rush Memory and Aging Project with antemortem structural T1-weighted MR imaging and postmortem neuropathologic assessments. Here, we focused on thickness within the entorhinal cortex as anatomically defined by our previously developed MR imaging parcellation system (Desikan-Killiany Atlas in FreeSurfer). Using linear regression, we evaluated the association between entorhinal cortex thickness and tangles and amyloid-β load within the entorhinal cortex and medial temporal and neocortical regions. RESULTS: We found a significant relationship between antemortem entorhinal cortex thickness and entorhinal cortex (P = .006) and medial temporal lobe tangles (P = .002); we found no relationship between entorhinal cortex thickness and entorhinal cortex (P = .09) and medial temporal lobe amyloid-β (P = .09). We also found a significant association between entorhinal cortex thickness and cortical tangles (P = .003) and amyloid-β (P = .01). We found no relationship between parahippocampal gyrus thickness and entorhinal cortex (P = .31) and medial temporal lobe tangles (P = .051). CONCLUSIONS: Our findings indicate that entorhinal cortex–associated in vivo cortical thinning may represent a marker of postmortem medial temporal and neocortical Alzheimer disease pathology.