Superficial white matter across development, young adulthood, and aging: volume, thickness, and relationship with cortical features

Superficial white matter (SWM) represents a significantly understudied part of the human brain, despite comprising a large portion of brain volume and making up a majority of cortico-cortical white matter connections. Using multiple, high-quality datasets with large sample sizes (N = 2421, age range 5-100) in combination with methodological advances in tractography, we quantified features of SWM volume and thickness across the brain and across development, young adulthood, and aging. We had four primary aims: (1) characterize SWM thickness across brain regions (2) describe associations between SWM volume and age (3) describe associations between SWM thickness and age, and (4) quantify relationships between SWM thickness and cortical features. Our main findings are that (1) SWM thickness varies across the brain, with patterns robust across individuals and across the population at the region-level and vertex-level; (2) SWM volume shows unique volumetric trajectories with age that are distinct from gray matter and other white matter trajectories; (3) SWM thickness shows nonlinear cross-sectional changes across the lifespan that vary across regions; and (4) SWM thickness is associated with features of cortical thickness and curvature. For the first time, we show that SWM volume follows a similar trend as overall white matter volume, peaking at a similar time in adolescence, leveling off throughout adulthood, and decreasing with age thereafter. Notably, the relative fraction of total brain volume of SWM continuously increases with age, and consequently takes up a larger proportion of total white matter volume, unlike the other tissue types that decrease with respect to total brain volume. This study represents the first characterization of SWM features across the large portion of the lifespan and provides the background for characterizing normal aging and insight into the mechanisms associated with SWM development and decline.

Comprehensive shape analysis of the cortex in Huntington's disease

The striatum has traditionally been the focus of Huntington's disease research due to the primary insult to this region and its central role in motor symptoms. Beyond the striatum, evidence of cortical alterations caused by Huntington's disease has surfaced. However, findings are not coherent between studies which have used cortical thickness for Huntington's disease since it is the well-established cortical metric of interest in other diseases. In this study, we propose a more comprehensive approach to cortical morphology in Huntington's disease using cortical thickness, sulcal depth, and local gyrification index. Our results show consistency with prior findings in cortical thickness, including its limitations. Our comparison between cortical thickness and local gyrification index underscores the complementary nature of these two measures-cortical thickness detects changes in the sensorimotor and posterior areas while local gyrification index identifies insular differences. Since local gyrification index and cortical thickness measures detect changes in different regions, the two used in tandem could provide a clinically relevant measure of disease progression. Our findings suggest that differences in insular regions may correspond to earlier neurodegeneration and may provide a complementary cortical measure for detection of subtle early cortical changes due to Huntington's disease.

Hierarchical particle optimization for cortical shape correspondence in temporal lobe resection

BACKGROUND

Anterior temporal lobe resection is an effective treatment for temporal lobe epilepsy. The post-surgical structural changes could influence the follow-up treatment. Capturing post-surgical changes necessitates a well-established cortical shape correspondence between pre- and post-surgical surfaces. Yet, most cortical surface registration methods are designed for normal neuroanatomy. Surgical changes can introduce wide ranging artifacts in correspondence, for which conventional surface registration methods may not work as intended.

METHODS

In this paper, we propose a novel particle method for one-to-one dense shape correspondence between pre- and post-surgical surfaces with temporal lobe resection. The proposed method can handle partial structural abnormality involving non-rigid changes. Unlike existing particle methods using implicit particle adjacency, we consider explicit particle adjacency to establish a smooth correspondence. Moreover, we propose hierarchical optimization of particles rather than full optimization of all particles at once to avoid trappings of locally optimal particle update.

RESULTS

We evaluate the proposed method on 25 pairs of T1-MRI with pre- and post-simulated resection on the anterior temporal lobe and 25 pairs of patients with actual resection. We show improved accuracy over several cortical regions in terms of ROI boundary Hausdorff distance with 4.29 mm and Dice similarity coefficients with average value 0.841, compared to existing surface registration methods on simulated data. In 25 patients with actual resection of the anterior temporal lobe, our method shows an improved shape correspondence in qualitative and quantitative evaluation on parcellation-off ratio with average value 0.061 and cortical thickness changes. We also show better smoothness of the correspondence without self-intersection, compared with point-wise matching methods which show various degrees of self-intersection.

CONCLUSION

The proposed method establishes a promising one-to-one dense shape correspondence for temporal lobe resection. The resulting correspondence is smooth without self-intersection. The proposed hierarchical optimization strategy could accelerate optimization and improve the optimization accuracy. According to the results on the paired surfaces with temporal lobe resection, the proposed method outperforms the compared methods and is more reliable to capture cortical thickness changes.

Integrating the BIDS Neuroimaging Data Format and Workflow Optimization for Large-Scale Medical Image Analysis

A robust medical image computing infrastructure must host massive multimodal archives, perform extensive analysis pipelines, and execute scalable job management. An emerging data format standard, the Brain Imaging Data Structure (BIDS), introduces complexities for interfacing with XNAT archives. Moreover, workflow integration is combinatorically problematic when matching large amount of processing to large datasets. Historically, workflow engines have been focused on refining workflows themselves instead of actual job generation. However, such an approach is incompatible with data centric architecture that hosts heterogeneous medical image computing. Distributed automation for XNAT toolkit (DAX) provides large-scale image storage and analysis pipelines with an optimized job management tool. Herein, we describe developments for DAX that allows for integration of XNAT and BIDS standards. We also improve DAX's efficiencies of diverse containerized workflows in a high-performance computing (HPC) environment. Briefly, we integrate YAML configuration processor scripts to abstract workflow data inputs, data outputs, commands, and job attributes. Finally, we propose an online database-driven mechanism for DAX to efficiently identify the most recent updated sessions, thereby improving job building efficiency on large projects. We refer the proposed overall DAX development in this work as DAX-1 (DAX version 1). To validate the effectiveness of the new features, we verified (1) the efficiency of converting XNAT data to BIDS format and the correctness of the conversion using a collection of BIDS standard containerized neuroimaging workflows, (2) how YAML-based processor simplified configuration setup via a sequence of application pipelines, and (3) the productivity of DAX-1 on generating actual HPC processing jobs compared with earlier DAX baseline method. The empirical results show that (1) DAX-1 converting XNAT data to BIDS has similar speed as accessing XNAT data only; (2) YAML can integrate to the DAX-1 with shallow learning curve for users, and (3) DAX-1 reduced the job/assessor generation latency by finding recent modified sessions. Herein, we present approaches for efficiently integrating XNAT and modern image formats with a scalable workflow engine for the large-scale dataset access and processing.

Automated volumetric determination of high R2 * regions in substantia nigra: A feasibility study of quantifying substantia nigra atrophy in progressive supranuclear palsy

The establishment of an unbiased protocol for the automated volumetric measurement of iron-rich regions in the substantia nigra (SN) is clinically important for diagnosing neurodegenerative diseases exhibiting midbrain atrophy, such as progressive supranuclear palsy (PSP). This study aimed to automatically quantify the volume and surface properties of the iron-rich 3D regions in the SN using the quantitative MRI-R₂ ^* map. Three hundred and sixty-seven slices of R₂ ^* map and susceptibility-weighted imaging (SWI) at 3-T MRI from healthy control (HC) individuals and Parkinson's disease (PD) patients were used to train customized U-net++ convolutional neural network based on expert-segmented masks. Age- and sex-matched participants were selected from HC, PD, and PSP groups to automate the volumetric determination of iron-rich areas in the SN. Dice similarity coefficient values between expert-segmented and detected masks from the proposed network were 0.91 ± 0.07 for R₂ ^* maps and 0.89 ± 0.08 for SWI. Reductions in iron-rich SN volume from the R₂ ^* map (SWI) were observed in PSP with area under the receiver operating characteristic curve values of 0.96 (0.89) and 0.98 (0.92) compared with HC and PD, respectively. The mean curvature of the PSP showed SN deformation along the side closer to the red nucleus. We demonstrated the automated volumetric measurement of iron-rich regions in the SN using deep learning can quantify the SN atrophy in PSP compared with PD and HC.

SPHARM-Net: Spherical Harmonics-Based Convolution for Cortical Parcellation

We present a spherical harmonics-based convolutional neural network (CNN) for cortical parcellation, which we call SPHARM-Net. Recent advances in CNNs offer cortical parcellation on a fine-grained triangle mesh of the cortex. Yet, most CNNs designed for cortical parcellation employ spatial convolution that depends on extensive data augmentation and allows only predefined neighborhoods of specific spherical tessellation. On the other hand, a rotation-equivariant convolutional filter avoids data augmentation, and rotational equivariance can be achieved in spectral convolution independent of a neighborhood definition. Nevertheless, the limited resources of a modern machine enable only a finite set of spectral components that might lose geometric details. In this paper, we propose (1) a constrained spherical convolutional filter that supports an infinite set of spectral components and (2) an end-to-end framework without data augmentation. The proposed filter encodes all the spectral components without the full expansion of spherical harmonics. We show that rotational equivariance drastically reduces the training time while achieving accurate cortical parcellation. Furthermore, the proposed convolution is fully composed of matrix transformations, which offers efficient and fast spectral processing. In the experiments, we validate SPHARM-Net on two public datasets with manual labels: Mindboggle-101 (N=101) and NAMIC (N=39). The experimental results show that the proposed method outperforms the state-of-the-art methods on both datasets even with fewer learnable parameters without rigid alignment and data augmentation. Our code is publicly available at https://github.com/Shape-Lab/SPHARM-Net.

Uncovering a tripartite landmark in posterior cingulate cortex

Understanding brain structure-function relationships, and their development and evolution, is central to neuroscience research. Here, we show that morphological differences in posterior cingulate cortex (PCC), a hub of functional brain networks, predict individual differences in macroanatomical, microstructural, and functional features of PCC. Manually labeling 4511 sulci in 572 hemispheres, we found a shallow cortical indentation (termed the inframarginal sulcus; ifrms) within PCC that is absent from neuroanatomical atlases yet colocalized with a focal, functional region of the lateral frontoparietal network implicated in cognitive control. This structural-functional coupling generalized to meta-analyses consisting of hundreds of studies and thousands of participants. Additional morphological analyses showed that unique properties of the ifrms differ across the life span and between hominoid species. These findings support a classic theory that shallow, tertiary sulci serve as landmarks in association cortices. They also beg the question: How many other cortical indentations have we missed?

Incomplete Hippocampal Inversion: A Neurodevelopmental Mechanism for Hippocampal Shape Deformation in Schizophrenia

BACKGROUND

Shape analyses of patients with schizophrenia have revealed bilateral deformations of the anterolateral hippocampus, primarily localized to the CA1 subfield. Incomplete hippocampal inversion (IHI), an anatomical variant of the human hippocampus resulting from an arrest during neurodevelopment, is more prevalent and severe in patients with schizophrenia. We hypothesized that IHI would affect the shape of the hippocampus and contribute to hippocampal shape differences in schizophrenia.

METHODS

We studied 199 patients with schizophrenia and 161 healthy control participants with structural magnetic resonance imaging to measure the prevalence and severity of IHI. High-fidelity hippocampal surface reconstructions were generated with the SPHARM-PDM toolkit. We used general linear models in SurfStat to test for group shape differences, the impact of IHI on hippocampal shape variation, and whether IHI contributes to hippocampal shape abnormalities in schizophrenia.

RESULTS

Not including IHI as a main effect in our between-group comparison replicated well-established hippocampal shape differences in patients with schizophrenia localized to the CA1 subfield in the anterolateral hippocampus. Shape differences were also observed near the uncus and hippocampal tail. IHI was associated with outward displacements of the dorsal and ventral surfaces of the hippocampus and inward displacements of the medial and lateral surfaces. Including IHI as a main effect in our between-group comparison eliminated the bilateral shape differences in the CA1 subfield. Shape differences in the uncus persisted after including IHI.

CONCLUSIONS

IHI impacts hippocampal shape. Our results suggest IHI as a neurodevelopmental mechanism for the well-known shape differences, particularly in the CA1 subfield, in schizophrenia.

Ultra-high-resolution Mapping of Cortical Layers 3T-Guided 7T MRI

7T MRI provides unprecedented resolution for examining human brain anatomy in vivo. For example, 7T MRI enables deep thickness measurement of laminar subdivisions in the right fusiform area. Existing laminar thickness measurement on 7T is labor intensive, and error prone since the visual inspection of the image is typically along one of the three orthogonal planes (axial, coronal, or sagittal view). To overcome this, we propose a new analytics tool that allows flexible quantification of cortical thickness on a 2D plane that is orthogonal to the cortical surface (beyond axial, coronal, and sagittal views) based on the 3D computational surface reconstruction. The proposed method further distinguishes high quality 2D planes and the low-quality ones by automatically inspecting the angles between the surface normals and slice direction. In our approach, we acquired a pair of 3T and 7T scans (same subject). We extracted the brain surfaces from the 3T scan using MaCRUISE and projected the surface to the 7T scan's space. After computing the angles between the surface normals and axial direction vector, we found that 18.58% of surface points were angled at more than 80° with the axial direction vector and had 2D axial planes with visually distinguishable cortical layers. 15.12% of the surface points with normal vectors angled at 30° or lesser with the axial direction, had poor 2D axial slices for visual inspection of the cortical layers. This effort promises to dramatically extend the area of cortex that can be quantified with ultra-high resolution in-plane imaging methods.

Generalizing deep learning brain segmentation for skull removal and intracranial measurements

Total intracranial volume (TICV) and posterior fossa volume (PFV) are essential covariates for brain volumetric analyses with structural magnetic resonance imaging (MRI). Detailed whole brain segmentation provides a non-invasive way to measure brain regions. Furthermore, increasing neuroimaging data are distributed in a skull-stripped manner for privacy protection. Therefore, generalizing deep learning brain segmentation for skull removal and intracranial measurements is an appealing task. However, data availability is challenging due to a limited set of manually traced atlases with whole brain and TICV/PFV labels. In this paper, we employ U-Net tiles to achieve automatic TICV estimation and whole brain segmentation simultaneously on brains w/and w/o the skull. To overcome the scarcity of manually traced whole brain volumes, a transfer learning method is introduced to estimate additional TICV and PFV labels during whole brain segmentation in T1-weighted MRI. Specifically, U-Net tiles are first pre-trained using large-scale BrainCOLOR atlases without TICV and PFV labels, which are created by multi-atlas segmentation. Then the pre-trained models are refined by training the additional TICV and PFV labels using limited BrainCOLOR atlases. We also extend our method to handle skull-stripped brain MR images. From the results, our method provides promising whole brain segmentation and volume estimation results for both brains w/and w/o skull in terms of mean Dice similarity coefficients and mean surface distance and absolute volume similarity. This method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg_skullstripped).

Random Multi-Channel Image Synthesis for Multiplexed Immunofluorescence Imaging

Multiplex immunofluorescence (MxIF) is an emerging imaging technique that produces the high sensitivity and specificity of single-cell mapping. With a tenet of "seeing is believing", MxIF enables iterative staining and imaging extensive antibodies, which provides comprehensive biomarkers to segment and group different cells on a single tissue section. However, considerable depletion of the scarce tissue is inevitable from extensive rounds of staining and bleaching ("missing tissue"). Moreover, the immunofluorescence (IF) imaging can globally fail for particular rounds ("missing stain"). In this work, we focus on the "missing stain" issue. It would be appealing to develop digital image synthesis approaches to restore missing stain images without losing more tissue physically. Herein, we aim to develop image synthesis approaches for eleven MxIF structural molecular markers (i.e., epithelial and stromal) on real samples. We propose a novel multi-channel high-resolution image synthesis approach, called pixN2N-HD, to tackle possible missing stain scenarios via a high-resolution generative adversarial network (GAN). Our contribution is three-fold: (1) a single deep network framework is proposed to tackle missing stain in MxIF; (2) the proposed "N-to-N" strategy reduces theoretical four years of computational time to 20 hours when covering all possible missing stains scenarios, with up to five missing stains (e.g., "(N-1)-to-1", "(N-2)-to-2"); and (3) this work is the first comprehensive experimental study of investigating cross-stain synthesis in MxIF. Our results elucidate a promising direction of advancing MxIF imaging with deep image synthesis.

Pandora: 4-D White Matter Bundle Population-Based Atlases Derived from Diffusion MRI Fiber Tractography

Brain atlases have proven to be valuable neuroscience tools for localizing regions of interest and performing statistical inferences on populations. Although many human brain atlases exist, most do not contain information about white matter structures, often neglecting them completely or labelling all white matter as a single homogenous substrate. While few white matter atlases do exist based on diffusion MRI fiber tractography, they are often limited to descriptions of white matter as spatially separate "regions" rather than as white matter "bundles" or fascicles, which are well-known to overlap throughout the brain. Additional limitations include small sample sizes, few white matter pathways, and the use of outdated diffusion models and techniques. Here, we present a new population-based collection of white matter atlases represented in both volumetric and surface coordinates in a standard space. These atlases are based on 2443 subjects, and include 216 white matter bundles derived from 6 different automated state-of-the-art tractography techniques. This atlas is freely available and will be a useful resource for parcellation and segmentation.

Cortical Morphology in Autism: Findings from a Cortical Shape-Adaptive Approach to Local Gyrification Indexing

It has been challenging to elucidate the differences in brain structure that underlie behavioral features of autism. Prior studies have begun to identify patterns of changes in autism across multiple structural indices, including cortical thickness, local gyrification, and sulcal depth. However, common approaches to local gyrification indexing used in prior studies have been limited by low spatial resolution relative to functional brain topography. In this study, we analyze the aforementioned structural indices, utilizing a new method of local gyrification indexing that quantifies this index adaptively in relation to specific sulci/gyri, improving interpretation with respect to functional organization. Our sample included n = 115 autistic and n = 254 neurotypical participants aged 5-54, and we investigated structural patterns by group, age, and autism-related behaviors. Differing structural patterns by group emerged in many regions, with age moderating group differences particularly in frontal and limbic regions. There were also several regions, particularly in sensory areas, in which one or more of the structural indices of interest either positively or negatively covaried with autism-related behaviors. Given the advantages of this approach, future studies may benefit from its application in hypothesis-driven examinations of specific brain regions and/or longitudinal studies to assess brain development in autism.

Body Part Regression With Self-Supervision

Body part regression is a promising new technique that enables content navigation through self-supervised learning. Using this technique, the global quantitative spatial location for each axial view slice is obtained from computed tomography (CT). However, it is challenging to define a unified global coordinate system for body CT scans due to the large variabilities in image resolution, contrasts, sequences, and patient anatomy. Therefore, the widely used supervised learning approach cannot be easily deployed. To address these concerns, we propose an annotation-free method named blind-unsupervised-supervision network (BUSN). The contributions of the work are in four folds: (1) 1030 multi-center CT scans are used in developing BUSN without any manual annotation. (2) the proposed BUSN corrects the predictions from unsupervised learning and uses the corrected results as the new supervision; (3) to improve the consistency of predictions, we propose a novel neighbor message passing (NMP) scheme that is integrated with BUSN as a statistical learning based correction; and (4) we introduce a new pre-processing pipeline with inclusion of the BUSN, which is validated on 3D multi-organ segmentation. The proposed method is trained on 1,030 whole body CT scans (230,650 slices) from five datasets, as well as an independent external validation cohort with 100 scans. From the body part regression results, the proposed BUSN achieved significantly higher median R-squared score (=0.9089) than the state-of-the-art unsupervised method (=0.7153). When introducing BUSN as a preprocessing stage in volumetric segmentation, the proposed pre-processing pipeline using BUSN approach increases the total mean Dice score of the 3D abdominal multi-organ segmentation from 0.7991 to 0.8145.

Labeling lateral prefrontal sulci using spherical data augmentation and context-aware training

The inference of cortical sulcal labels often focuses on deep (primary and secondary) sulcal regions, whereas shallow (tertiary) sulcal regions are largely overlooked in the literature due to the scarcity of manual/well-defined annotations and their large neuroanatomical variability. In this paper, we present an automated framework for regional labeling of both primary/secondary and tertiary sulci of the dorsal portion of lateral prefrontal cortex (LPFC) using spherical convolutional neural networks. We propose two core components that enhance the inference of sulcal labels to overcome such large neuroanatomical variability: (1) surface data augmentation and (2) context-aware training. (1) To take into account neuroanatomical variability, we synthesize training data from the proposed feature space that embeds intermediate deformation trajectories of spherical data in a rigid to non-rigid fashion, which bridges an augmentation gap in conventional rotation data augmentation. (2) Moreover, we design a two-stage training process to improve labeling accuracy of tertiary sulci by informing the biological associations in neuroanatomy: inference of primary/secondary sulci and then their spatial likelihood to guide the definition of tertiary sulci. In the experiments, we evaluate our method on 13 deep and shallow sulci of human LPFC in two independent data sets with different age ranges: pediatric (N=60) and adult (N=36) cohorts. We compare the proposed method with a conventional multi-atlas approach and spherical convolutional neural networks without/with rotation data augmentation. In both cohorts, the proposed data augmentation improves labeling accuracy of deep and shallow sulci over the baselines, and the proposed context-aware training offers further improvement in the labeling of shallow sulci over the proposed data augmentation. We share our tools with the field and discuss applications of our results for understanding neuroanatomical-functional organization of LPFC and the rest of cortex (https://github.com/ilwoolyu/SphericalLabeling).

Anatomical texture patterns identify cerebellar distinctions between essential tremor and Parkinson's disease

Voxel-based morphometry is an established technique to study focal structural brain differences in neurologic disease. More recently, texture-based analysis methods have enabled a pattern-based assessment of group differences, at the patch level rather than at the voxel level, allowing a more sensitive localization of structural differences between patient populations. In this study, we propose a texture-based approach to identify structural differences between the cerebellum of patients with Parkinson's disease (n = 280) and essential tremor (n = 109). We analyzed anatomical differences of the cerebellum among patients using two features: T1-weighted MRI intensity, and a texture-based similarity feature. Our results show anatomical differences between groups that are localized to the inferior part of the cerebellar cortex. Both the T1-weighted intensity and texture showed differences in lobules VIII and IX, vermis VIII and IX, and middle peduncle, but the texture analysis revealed additional differences in the dentate nucleus, lobules VI and VII, vermis VI and VII. This comparison emphasizes how T1-weighted intensity and texture-based methods can provide a complementary anatomical structure analysis. While texture-based similarity shows high sensitivity for gray matter differences, T1-weighted intensity shows sensitivity for the detection of white matter differences.

Validation of Group-wise Registration for Surface-based Functional MRI Analysis

Resting-state functional MRI (rsfMRI) provides important information for studying and mapping the activities and functions of the brain. Conventionally, rsfMRIs are often registered to structural images in the Euclidean space without considering cortical surface geometry. Meanwhile, a surface-based representation offers a relaxed coordinate chart, but this still requires surface registration for group-wise data analysis. In this work, we investigate the performance of two existing surface registration methods in a surface-based rsfMRI analysis framework: FreeSurfer and Hierarchical Spherical Deformation (HSD). To minimize registration bias, we establish shape correspondence using both methods in a group-wise manner that estimates the unbiased average of a given cohort. To evaluate their performance, we focus on neuroanatomical alignment as well as the amount of distortion that can potentially bias surface tessellation for secondary level rsfMRI data analyses. In the pilot analysis, we examine a single timepoint of imaging data from 100 subjects out of an aging cohort. Overall, HSD establishes improved shape correspondence with reduced mean curvature deviation (10.94% less on average per subject, paired t-test: p <10-10) and reduced registration distortion (FreeSurfer: average 41.91% distortion per subject, HSD: 18.63%, paired t-test: p <10-10). Furthermore, HSD introduces less distortion than FreeSurfer in the areas identified in the individual components that were extracted by surface-based independent component analysis (ICA) after spatial smoothing and time series normalization. Consequently, we show that FreeSurfer capture individual components with globally similar but locally different patterns in ICA in visual inspection.

Establishing Surface Correspondence for Post-surgical Cortical Thickness Changes in Temporal Lobe Epilepsy

In pre- and post-surgical surface shape analysis, establishing shape correspondence is necessary to investigate the postoperative surface changes. However, structural absence after the operation accompanies focal non-rigid changes, which leads to challenges in existing surface registration methods. In this paper, we present a fully automatic particle-based method to establish surface correspondence that can handle partial structural abnormality in the temporal lobe resection. Our method optimizes the coordinates of points which are modeled as particles on surfaces in a hierarchical way to reduce a chance of being trapped in a local minimum during the optimization. In the experiments, we evaluate the effectiveness of our method in comparison with conventional spherical registration (FreeSurfer) on two scenarios: cortical thickness changes in healthy controls within a short scan-rescan time window and patients with temporal lobe resection. The post-surgical scan is acquired at least 1 year after the presurgical scan. In region of interest-wise (ROI-wise) analysis, no changes on cortical thickness are found in both methods on the healthy control group. In patients, since there is no ground truth available, we instead investigated the disagreement between our method and FreeSurfer. We see poorly matched ROIs and large cortical thickness changes using FreeSurfer. On the contrary, our method shows well-matched ROIs and subtle cortical thickness changes. This suggests that the proposed method can establish a stable shape correspondence, which is not fully captured in a conventional spherical registration.

Joint cortical surface and structural connectivity analysis of Alzheimer's Disease

Prior neuroimaging studies have demonstrated isolated structural and connectivity changes in the brain due to Alzheimer's Disease (AD). However, how these changes relate to each other is not well understood. We present a preliminary study to begin to fill this gap by leveraging joint independent component analysis (jICA). We explore how jICA performs in an analysis of T1 and diffusion weighted MRI by characterizing the joint changes of complex cortical surface and structural connectivity metrics in AD in subjects from the Baltimore Longitudinal Study of Aging. We calculate 588 region-based cortical metrics and 4,753 fractional anisotropy-based connectivity metrics and project them into a low-dimensional manifold with principal component analysis. We perform jICA on the manifold and subsequently backproject the independent components to the original data space. We demonstrate component stability with 3-fold cross validation and find differential component loadings between 776 cognitively unimpaired control subjects and 23 with AD that generalizes across folds. In addition, we perform the same analysis on the surface and connectivity metrics separately and find that the joint approach identifies both novel and similar components to the separate approaches. To illustrate the joint approach's primary utility, we provide an example hypothesis for how surface and connectivity components may vary together with AD. These preliminary results suggest jointly varying independent cortical surface and structural connectivity components can be consistently extracted from MRI data and provide a data-driven way for generating novel hypotheses about AD that may not be captured by separate analyses.

High-resolution 3D abdominal segmentation with random patch network fusion

Deep learning for three dimensional (3D) abdominal organ segmentation on high-resolution computed tomography (CT) is a challenging topic, in part due to the limited memory provide by graphics processing units (GPU) and large number of parameters and in 3D fully convolutional networks (FCN). Two prevalent strategies, lower resolution with wider field of view and higher resolution with limited field of view, have been explored but have been presented with varying degrees of success. In this paper, we propose a novel patch-based network with random spatial initialization and statistical fusion on overlapping regions of interest (ROIs). We evaluate the proposed approach using three datasets consisting of 260 subjects with varying numbers of manual labels. Compared with the canonical "coarse-to-fine" baseline methods, the proposed method increases the performance on multi-organ segmentation from 0.799 to 0.856 in terms of mean DSC score (p-value < 0.01 with paired t-test). The effect of different numbers of patches is evaluated by increasing the depth of coverage (expected number of patches evaluated per voxel). In addition, our method outperforms other state-of-the-art methods in abdominal organ segmentation. In conclusion, the approach provides a memory-conservative framework to enable 3D segmentation on high-resolution CT. The approach is compatible with many base network structures, without substantially increasing the complexity during inference. Given a CT scan with at high resolution, a low-res section (left panel) is trained with multi-channel segmentation. The low-res part contains down-sampling and normalization in order to preserve the complete spatial information. Interpolation and random patch sampling (mid panel) is employed to collect patches. The high-dimensional probability maps are acquired (right panel) from integration of all patches on field of views.

A bayesian approach to examining default mode network functional connectivity and cognitive performance in major depressive disorder

To reconcile the inconsistency of the association between the resting-state functional connectivity (RSFC) and cognitive performance in healthy and depressed groups due to high variance of both measures, we proposed a Bayesian spatio-temporal model to precisely and accurately estimate the RSFC in depressed and nondepressed participants. This model was employed to estimate spatially-adjusted functional connectivity (saFC) in the extended default mode network (DMN) that was hypothesized to correlate with cognitive performance in both depressed and nondepressed. Multiple linear regression models were used to study the relationship between DMN saFC and cognitive performance scores measured in the following four cognitive domains while adjusting for age, sex, and education. In ROI pairs including the posterior cingulate (PCC) and anterior cingulate (ACC) cortex regions, the relationship between connectivity and cognition was found only with the Bayesian approach. Moreover, only the Bayesian approach was able to detect a significant diagnostic difference in the association in ROI pairs, including both PCC and ACC regions, due to smaller variance for the saFC estimator. The results confirm that a reliable and precise saFC estimator, based on the Bayesian model, can foster scientific discovery that may not be feasible with the conventional ROI-based FC estimator (denoted as 'AVG-FC').

Fast Polynomial Approximation of Heat Kernel Convolution on Manifolds and Its Application to Brain Sulcal and Gyral Graph Pattern Analysis

Heat diffusion has been widely used in brain imaging for surface fairing, mesh regularization and cortical data smoothing. Motivated by diffusion wavelets and convolutional neural networks on graphs, we present a new fast and accurate numerical scheme to solve heat diffusion on surface meshes. This is achieved by approximating the heat kernel convolution using high degree orthogonal polynomials in the spectral domain. We also derive the closed-form expression of the spectral decomposition of the Laplace-Beltrami operator and use it to solve heat diffusion on a manifold for the first time. The proposed fast polynomial approximation scheme avoids solving for the eigenfunctions of the Laplace-Beltrami operator, which is computationally costly for large mesh size, and the numerical instability associated with the finite element method based diffusion solvers. The proposed method is applied in localizing the male and female differences in cortical sulcal and gyral graph patterns obtained from MRI in an innovative way. The MATLAB code is available at http://www.stat.wisc.edu/~mchung/chebyshev.

AUTOMATIC LABELING OF CORTICAL SULCI USING SPHERICAL CONVOLUTIONAL NEURAL NETWORKS IN A DEVELOPMENTAL COHORT

In this paper, we present the automatic labeling framework for sulci in the human lateral prefrontal cortex (PFC). We adapt an existing spherical U-Net architecture with our recent surface data augmentation technique to improve the sulcal labeling accuracy in a developmental cohort. Specifically, our framework consists of the following key components: (1) augmented geometrical features being generated during cortical surface registration, (2) spherical U-Net architecture to efficiently fit the augmented features, and (3) postrefinement of sulcal labeling by optimizing spatial coherence via a graph cut technique. We validate our method on 30 healthy subjects with manual labeling of sulcal regions within PFC. In the experiments, we demonstrate significantly improved labeling performance (0.7749) in mean Dice overlap compared to that of multi-atlas (0.6410) and standard spherical U-Net (0.7011) approaches, respectively (p < 0.05). Additionally, the proposed method achieves a full set of sulcal labels in 20 seconds in this developmental cohort.

Network localization of clinical, cognitive, and neuropsychiatric symptoms in Alzheimer's disease

There is both clinical and neuroanatomical variability at the single-subject level in Alzheimer's disease, complicating our understanding of brain-behaviour relationships and making it challenging to develop neuroimaging biomarkers to track disease severity, progression, and response to treatment. Prior work has shown that both group-level atrophy in clinical dementia syndromes and complex neurological symptoms in patients with focal brain lesions localize to brain networks. Here, we use a new technique termed 'atrophy network mapping' to test the hypothesis that single-subject atrophy maps in patients with a clinical diagnosis of Alzheimer's disease will also localize to syndrome-specific and symptom-specific brain networks. First, we defined single-subject atrophy maps by comparing cortical thickness in each Alzheimer's disease patient versus a group of age-matched, cognitively normal subjects across two independent datasets (total Alzheimer's disease patients = 330). No more than 42% of Alzheimer's disease patients had atrophy at any given location across these datasets. Next, we determined the network of brain regions functionally connected to each Alzheimer's disease patient's location of atrophy using seed-based functional connectivity in a large (n = 1000) normative connectome. Despite the heterogeneity of atrophied regions at the single-subject level, we found that 100% of patients with a clinical diagnosis of Alzheimer's disease had atrophy functionally connected to the same brain regions in the mesial temporal lobe, precuneus cortex, and angular gyrus. Results were specific versus control subjects and replicated across two independent datasets. Finally, we used atrophy network mapping to define symptom-specific networks for impaired memory and delusions, finding that our results matched symptom networks derived from patients with focal brain lesions. Our study supports atrophy network mapping as a method to localize clinical, cognitive, and neuropsychiatric symptoms to brain networks, providing insight into brain-behaviour relationships in patients with dementia.

Cortical Surface Parcellation using Spherical Convolutional Neural Networks

We present cortical surface parcellation using spherical deep convolutional neural networks. Traditional multi-atlas cortical surface parcellation requires inter-subject surface registration using geometric features with slow processing speed on a single subject (2-3 hours). Moreover, even optimal surface registration does not necessarily produce optimal cortical parcellation as parcel boundaries are not fully matched to the geometric features. In this context, a choice of training features is important for accurate cortical parcellation. To utilize the networks efficiently, we propose cortical parcellation-specific input data from an irregular and complicated structure of cortical surfaces. To this end, we align ground-truth cortical parcel boundaries and use their resulting deformation fields to generate new pairs of deformed geometric features and parcellation maps. To extend the capability of the networks, we then smoothly morph cortical geometric features and parcellation maps using the intermediate deformation fields. We validate our method on 427 adult brains for 49 labels. The experimental results show that our method outperforms traditional multi-atlas and naive spherical U-Net approaches, while achieving full cortical parcellation in less than a minute.

Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE

Intra-voxel models of the diffusion signal are essential for interpreting organization of the tissue environment at micrometer level with data at millimeter resolution. Recent advances in data driven methods have enabled direct comparison and optimization of methods for in-vivo data with externally validated histological sections with both 2-D and 3-D histology. Yet, all existing methods make limiting assumptions of either (1) model-based linkages between b-values or (2) limited associations with single shell data. We generalize prior deep learning models that used single shell spherical harmonic transforms to integrate the recently developed simple harmonic oscillator reconstruction (SHORE) basis. To enable learning on the SHORE manifold, we present an alternative formulation of the fiber orientation distribution (FOD) object using the SHORE basis while representing the observed diffusion weighted data in the SHORE basis. To ensure consistency of hyper-parameter optimization for SHORE, we present our Deep SHORE approach to learn on a data-optimized manifold. Deep SHORE is evaluated with eight-fold cross-validation of a preclinical MRI-histology data with four b-values. Generalizability of in-vivo human data is evaluated on two separate 3T MRI scanners. Specificity in terms of angular correlation (ACC) with the preclinical data improved on single shell: 0.78 relative to 0.73 and 0.73, multi-shell: 0.80 relative to 0.74 (p < 0.001). In the in-vivo human data, Deep SHORE was more consistent across scanners with 0.63 relative to other multi-shell methods 0.39, 0.52 and 0.57 in terms of ACC. In conclusion, Deep SHORE is a promising method to enable data driven learning with DW-MRI under conditions with varying b-values, number of diffusion shells, and gradient directions per shell.

Hierarchical spherical deformation for cortical surface registration

We present hierarchical spherical deformation for a group-wise shape correspondence to address template selection bias and to minimize registration distortion. In this work, we aim at a continuous and smooth deformation field to guide accurate cortical surface registration. In conventional spherical registration methods, a global rigid alignment and local deformation are independently performed. Motivated by the composition of precession and intrinsic rotation, we simultaneously optimize global rigid rotation and non-rigid local deformation by utilizing spherical harmonics interpolation of local composite rotations in a single framework. To this end, we indirectly encode local displacements by such local composite rotations as functions of spherical locations. Furthermore, we introduce an additional regularization term to the spherical deformation, which maximizes its rigidity while reducing registration distortion. To improve surface registration performance, we employ the second order approximation of the energy function that enables fast convergence of the optimization. In the experiments, we validate our method on healthy normal subjects with manual cortical surface parcellation in registration accuracy and distortion. We show an improved shape correspondence with high accuracy in cortical surface parcellation and significantly low registration distortion in surface area and edge length. In addition to validation, we discuss parameter tuning, optimization, and implementation design with potential acceleration.

Deep learning reveals untapped information for local white-matter fiber reconstruction in diffusion-weighted MRI

PURPOSE

Diffusion-weighted magnetic resonance imaging (DW-MRI) is of critical importance for characterizing in-vivo white matter. Models relating microarchitecture to observed DW-MRI signals as a function of diffusion sensitization are the lens through which DW-MRI data are interpreted. Numerous modern approaches offer opportunities to assess more complex intra-voxel structures. Nevertheless, there remains a substantial gap between intra-voxel estimated structures and ground truth captured by 3-D histology.

METHODS

Herein, we propose a novel data-driven approach to model the non-linear mapping between observed DW-MRI signals and ground truth structures using a sequential deep neural network regression using residual block deep neural network (ResDNN). Training was performed on two 3-D histology datasets of squirrel monkey brains and validated on a third. A second validation was performed using scan-rescan datasets of 12 subjects from Human Connectome Project. The ResDNN was compared with multiple micro-structure reconstruction methods and super resolved-constrained spherical deconvolution (sCSD) in particular as baseline for both the validations.

RESULTS

Angular correlation coefficient (ACC) is a correlation/similarity measure and can be interpreted as accuracy when compared with a ground truth. The median ACC of ResDNN is 0.82 and median ACC's of different variants of CSD are 0.75, 0.77, 0.79. The mean, median and std. of ResDNN & sCSD ACC across 12 subjects from HCP are 0.74, 0.88, 0.31 and 0.61, 0.71, 0.31 respectively.

CONCLUSION

This work highlights the ability of deep learning to capture linkages between ex-vivo ground truth data with feasible MRI sequences. The data-driven approach is applicable to human in-vivo data and results in intriguingly high reproducibility of orientation structure.

Towards Portable Large-Scale Image Processing with High-Performance Computing

High-throughput, large-scale medical image computing demands tight integration of high-performance computing (HPC) infrastructure for data storage, job distribution, and image processing. The Vanderbilt University Institute for Imaging Science (VUIIS) Center for Computational Imaging (CCI) has constructed a large-scale image storage and processing infrastructure that is composed of (1) a large-scale image database using the eXtensible Neuroimaging Archive Toolkit (XNAT), (2) a content-aware job scheduling platform using the Distributed Automation for XNAT pipeline automation tool (DAX), and (3) a wide variety of encapsulated image processing pipelines called “spiders.” The VUIIS CCI medical image data storage and processing infrastructure have housed and processed nearly half-million medical image volumes with Vanderbilt Advanced Computing Center for Research and Education (ACCRE), which is the HPC facility at the Vanderbilt University. The initial deployment was natively deployed (i.e., direct installations on a bare-metal server) within the ACCRE hardware and software environments, which lead to issues of portability and sustainability. First, it could be laborious to deploy the entire VUIIS CCI medical image data storage and processing infrastructure to another HPC center with varying hardware infrastructure, library availability, and software permission policies. Second, the spiders were not developed in an isolated manner, which has led to software dependency issues during system upgrades or remote software installation. To address such issues, herein, we describe recent innovations using containerization techniques with XNAT/DAX which are used to isolate the VUIIS CCI medical image data storage and processing infrastructure from the underlying hardware and software environments. The newly presented XNAT/DAX solution has the following new features: (1) multi-level portability from system level to the application level, (2) flexible and dynamic software development and expansion, and (3) scalable spider deployment compatible with HPC clusters and local workstations.

Improving human cortical sulcal curve labeling in large scale cross-sectional MRI using deep neural networks

BACKGROUND

Human cortical primary sulci are relatively stable landmarks and commonly observed across the population. Despite their stability, the primary sulci exhibit phenotypic variability.

NEW METHOD

We propose a fully automated pipeline that integrates both sulcal curve extraction and labeling. In this study, we use a large normal control population (n = 1424) to train neural networks for accurately labeling the primary sulci. Briefly, we use sulcal curve distance map, surface parcellation, mean curvature and spectral features to delineate their sulcal labels. We evaluate the proposed method with 8 primary sulcal curves in the left and right hemispheres compared to an established multi-atlas curve labeling method.

RESULTS

Sulcal labels by the proposed method reasonably well agree with manual labeling. The proposed method outperforms the existing multi-atlas curve labeling method.

COMPARISON WITH EXISTING METHOD

Significantly improved sulcal labeling results are achieved with over 12.5 and 20.6 percent improvement on labeling accuracy in the left and right hemispheres, respectively compared to that of a multi-atlas curve labeling method in eight curves (p≪0.001, two-sample t-test).

CONCLUSION

The proposed method offers a computationally efficient and robust labeling of major sulci.

Inter-Scanner Harmonization of High Angular Resolution DW-MRI using Null Space Deep Learning

Diffusion-weighted magnetic resonance imaging (DW-MRI) allows for non-invasive imaging of the local fiber architecture of the human brain at a millimetric scale. Multiple classical approaches have been proposed to detect both single (e.g., tensors) and multiple (e.g., constrained spherical deconvolution, CSD) fiber population orientations per voxel. However, existing techniques generally exhibit low reproducibility across MRI scanners. Herein, we propose a data-driven technique using a neural network design which exploits two categories of data. First, training data were acquired on three squirrel monkey brains using ex-vivo DW-MRI and histology of the brain. Second, repeated scans of human subjects were acquired on two different scanners to augment the learning of the network proposed. To use these data, we propose a new network architecture, the null space deep network (NSDN), to simultaneously learn on traditional observed/truth pairs (e.g., MRI-histology voxels) along with repeated observations without a known truth (e.g., scan-rescan MRI). The NSDN was tested on twenty percent of the histology voxels that were kept completely blind to the network. NSDN significantly improved absolute performance relative to histology by 3.87% over CSD and 1.42% over a recently proposed deep neural network approach. Moreover, it improved reproducibility on the paired data by 21.19% over CSD and 10.09% over a recently proposed deep approach. Finally, NSDN improved generalizability of the model to a third in vivo human scanner (which was not used in training) by 16.08% over CSD and 10.41% over a recently proposed deep learning approach. This work suggests that data-driven approaches for local fiber reconstruction are more reproducible, informative and precise and offers a novel, practical method for determining these models.

Registration-based image enhancement improves multi-atlas segmentation of the thalamic nuclei and hippocampal subfields

Magnetic resonance imaging (MRI) is an important tool for analysis of deep brain grey matter structures. However, analysis of these structures is limited due to low intensity contrast typically found in whole brain imaging protocols. Herein, we propose a big data registration-enhancement (BDRE) technique to augment the contrast of deep brain structures using an efficient large-scale non-rigid registration strategy. Direct validation is problematic given a lack of ground truth data. Rather, we validate the usefulness and impact of BDRE for multi-atlas (MA) segmentation on two sets of structures of clinical interest: the thalamic nuclei and hippocampal subfields. The experimental design compares algorithms using T1-weighted 3 T MRI for both structures (and additional 7 T MRI for the thalamic nuclei) with an algorithm using BDRE. As baseline comparisons, a recent denoising (DN) technique and a super-resolution (SR) method are used to preprocess the original 3 T MRI. The performance of each MA segmentation is evaluated by the Dice similarity coefficient (DSC). BDRE significantly improves mean segmentation accuracy over all methods tested for both thalamic nuclei (3 T imaging: 9.1%; 7 T imaging: 15.6%; DN: 6.9%; SR: 16.2%) and hippocampal subfields (3 T T1 only: 8.7%; DN: 8.4%; SR: 8.6%). We also present DSC performance for each thalamic nucleus and hippocampal subfield and show that BDRE can help MA segmentation for individual thalamic nuclei and hippocampal subfields. This work will enable large-scale analysis of clinically relevant deep brain structures from commonly acquired T1 images.

Harmonizing 1.5T/3T Diffusion Weighted MRI through Development of Deep Learning Stabilized Microarchitecture Estimators

Diffusion weighted magnetic resonance imaging (DW-MRI) is interpreted as a quantitative method that is sensitive to tissue microarchitecture at a millimeter scale. However, the sensitization is dependent on acquisition sequences (e.g., diffusion time, gradient strength, etc.) and susceptible to imaging artifacts. Hence, comparison of quantitative DW-MRI biomarkers across field strengths (including different scanners, hardware performance, and sequence design considerations) is a challenging area of research. We propose a novel method to estimate microstructure using DW-MRI that is robust to scanner difference between 1.5T and 3T imaging. We propose to use a null space deep network (NSDN) architecture to model DW-MRI signal as fiber orientation distributions (FOD) to represent tissue microstructure. The NSDN approach is consistent with histologically observed microstructure (on previously acquired ex vivo squirrel monkey dataset) and scan-rescan data. The contribution of this work is that we incorporate identical dual networks (IDN) to minimize the influence of scanner effects via scan-rescan data. Briefly, our estimator is trained on two datasets. First, a histology dataset was acquired on three squirrel monkeys with corresponding DW-MRI and confocal histology (512 independent voxels). Second, 37 control subjects from the Baltimore Longitudinal Study of Aging (67-95 y/o) were identified who had been scanned at 1.5T and 3T scanners (b-value of 700 s/mm2, voxel resolution at 2.2mm, 30-32 gradient volumes) with an average interval of 4 years (standard deviation 1.3 years). After image registration, we used paired white matter (WM) voxels for 17 subjects and 440 histology voxels for training and 20 subjects and 72 histology voxels for testing. We compare the proposed estimator with super-resolved constrained spherical deconvolution (CSD) and a previously presented regression deep neural network (DNN). NSDN outperformed CSD and DNN in angular correlation coefficient (ACC) 0.81 versus 0.28 and 0.46, mean squared error (MSE) 0.001 versus 0.003 and 0.03, and general fractional anisotropy (GFA) 0.05 versus 0.05 and 0.09. Further validation and evaluation with contemporaneous imaging are necessary, but the NSDN is promising avenue for building understanding of microarchitecture in a consistent and device-independent manner.

Hierarchical Spherical Deformation for Shape Correspondence

We present novel spherical deformation for a landmark-free shape correspondence in a group-wise manner. In this work, we aim at both addressing template selection bias and minimizing registration distortion in a single framework. The proposed spherical deformation yields a non-rigid deformation field without referring to any particular spherical coordinate system. Specifically, we extend a rigid rotation represented by well-known Euler angles to general non-rigid local deformation via spatial-varying Euler angles. The proposed method employs spherical harmonics interpolation of the local displacements to simultaneously solve rigid and non-rigid local deformation during the optimization. This consequently leads to a continuous, smooth, and hierarchical representation of the deformation field that minimizes registration distortion. In addition, the proposed method is group-wise registration that requires no specific template to establish a shape correspondence. In the experiments, we show an improved shape correspondence with high accuracy in cortical surface parcellation as well as significantly low registration distortion in surface area and edge length compared to the existing registration methods while achieving fast registration in 3 mins per subject.

TRACE: A Topological Graph Representation for Automatic Sulcal Curve Extraction

A proper geometric representation of the cortical regions is a fundamental task for cortical shape analysis and landmark extraction. However, a significant challenge has arisen due to the highly variable, convoluted cortical folding patterns. In this paper, we propose a novel topological graph representation for automatic sulcal curve extraction (TRACE). In practice, the reconstructed surface suffers from noise influences introduced during image acquisition/surface reconstruction. In the presence of noise on the surface, TRACE determines stable sulcal fundic regions by employing the line simplification method that prevents the sulcal folding pattern from being significantly smoothed out. The sulcal curves are then traced over the connected graph in the determined regions by the Dijkstra's shortest path algorithm. For validation, we used the state-of-the-art surface reconstruction pipelines on a reproducibility data set. The experimental results showed higher reproducibility and robustness to noise in TRACE than the existing method (Li et al. 2010) with over 20% relative improvement in error for both surface reconstruction pipelines. In addition, the extracted sulcal curves by TRACE were well-aligned with manually delineated primary sulcal curves. We also provided a choice of parameters to control quality of the extracted sulcal curves and showed the influences of the parameter selection on the resulting curves.

A cortical shape-adaptive approach to local gyrification index

The amount of cortical folding, or gyrification, is typically measured within local cortical regions covered by an equidistant geodesic or nearest neighborhood-ring kernel. However, without careful design, such a kernel can easily cover multiple sulcal and gyral regions that may not be functionally related. Furthermore, this can result in smoothing out details of cortical folding, which consequently blurs local gyrification measurements. In this paper, we propose a novel kernel shape to locally quantify cortical gyrification within sulcal and gyral regions. We adapt wavefront propagation to generate a spatially varying kernel shape that encodes cortical folding patterns: neighboring gyral crowns, sulcal fundi, and sulcal banks. For this purpose, we perform anisotropic wavefront propagation that runs fast along gyral crowns and sulcal fundi by solving a static Hamilton-Jacobi partial differential equation. The resulting kernel adaptively elongates along gyral crowns and sulcal fundi, while keeping a uniform shape over flat regions like sulcal banks. We then measure local gyrification within the proposed spatially varying kernel. The experimental results show that the proposed kernel-based gyrification measure achieves a higher reproducibility than the conventional method in a multi-scan dataset. We further apply the proposed kernel to a brain development study in the early postnatal phase from neonate to 2 years of age. In this study we find that our kernel yields both positive and negative associations of gyrification with age, whereas the conventional method only captures positive associations. In general, our method yields sharper and more detailed statistical maps that associate cortical folding with sex and gestational age.

Constructing Statistically Unbiased Cortical Surface Templates Using Feature-Space Covariance

The choice of surface template plays an important role in cross-sectional subject analyses involving cortical brain surfaces because there is a tendency toward registration bias given variations in inter-individual and inter-group sulcal and gyral patterns. In order to account for the bias and spatial smoothing, we propose a feature-based unbiased average template surface. In contrast to prior approaches, we factor in the sample population covariance and assign weights based on feature information to minimize the influence of covariance in the sampled population. The mean surface is computed by applying the weights obtained from an inverse covariance matrix, which guarantees that multiple representations from similar groups (e.g., involving imaging, demographic, diagnosis information) are down-weighted to yield an unbiased mean in feature space. Results are validated by applying this approach in two different applications. For evaluation, the proposed unbiased weighted surface mean is compared with un-weighted means both qualitatively and quantitatively (mean squared error and absolute relative distance of both the means with baseline). In first application, we validated the stability of the proposed optimal mean on a scan-rescan reproducibility dataset by incrementally adding duplicate subjects. In the second application, we used clinical research data to evaluate the difference between the weighted and unweighted mean when different number of subjects were included in control versus schizophrenia groups. In both cases, the proposed method achieved greater stability that indicated reduced impacts of sampling bias. The weighted mean is built based on covariance information in feature space as opposed to spatial location, thus making this a generic approach to be applicable to any feature of interest.

A Data Colocation Grid Framework for Big Data Medical Image Processing: Backend Design

When processing large medical imaging studies, adopting high performance grid computing resources rapidly becomes important. We recently presented a "medical image processing-as-a-service" grid framework that offers promise in utilizing the Apache Hadoop ecosystem and HBase for data colocation by moving computation close to medical image storage. However, the framework has not yet proven to be easy to use in a heterogeneous hardware environment. Furthermore, the system has not yet validated when considering variety of multi-level analysis in medical imaging. Our target design criteria are (1) improving the framework's performance in a heterogeneous cluster, (2) performing population based summary statistics on large datasets, and (3) introducing a table design scheme for rapid NoSQL query. In this paper, we present a heuristic backend interface application program interface (API) design for Hadoop & HBase for Medical Image Processing (HadoopBase-MIP). The API includes: Upload, Retrieve, Remove, Load balancer (for heterogeneous cluster) and MapReduce templates. A dataset summary statistic model is discussed and implemented by MapReduce paradigm. We introduce a HBase table scheme for fast data query to better utilize the MapReduce model. Briefly, 5153 T1 images were retrieved from a university secure, shared web database and used to empirically access an in-house grid with 224 heterogeneous CPU cores. Three empirical experiments results are presented and discussed: (1) load balancer wall-time improvement of 1.5-fold compared with a framework with built-in data allocation strategy, (2) a summary statistic model is empirically verified on grid framework and is compared with the cluster when deployed with a standard Sun Grid Engine (SGE), which reduces 8-fold of wall clock time and 14-fold of resource time, and (3) the proposed HBase table scheme improves MapReduce computation with 7 fold reduction of wall time compare with a naïve scheme when datasets are relative small. The source code and interfaces have been made publicly available.

Sulcal Depth-based Cortical Shape Analysis in Normal Healthy Control and Schizophrenia Groups

Sulcal depth is an important marker of brain anatomy in neuroscience/neurological function. Previously, sulcal depth has been explored at the region-of-interest (ROI) level to increase statistical sensitivity to group differences. In this paper, we present a fully automated method that enables inferences of ROI properties from a sulcal region-focused perspective consisting of two main components: 1) sulcal depth computation and 2) sulcal curve-based refined ROIs. In conventional statistical analysis, the average sulcal depth measurements are employed in several ROIs of the cortical surface. However, taking the average sulcal depth over the full ROI blurs overall sulcal depth measurements which may result in reduced sensitivity to detect sulcal depth changes in neurological and psychiatric disorders. To overcome such a blurring effect, we focus on sulcal fundic regions in each ROI by filtering out other gyral regions. Consequently, the proposed method results in more sensitive to group differences than a traditional ROI approach. In the experiment, we focused on a cortical morphological analysis to sulcal depth reduction in schizophrenia with a comparison to the normal healthy control group. We show that the proposed method is more sensitivity to abnormalities of sulcal depth in schizophrenia; sulcal depth is significantly smaller in most cortical lobes in schizophrenia compared to healthy controls (p < 0.05).

Group-wise Shape Correspondence of Variable and Complex Objects

We present a group-wise shape correspondence method for analyzing variable and complex objects in a population study. The proposed method begins with the standard spherical harmonics (SPHARM) point distribution models (PDM) with their spherical mappings. In case of complex and variable objects, the equal area spherical mapping based SPHARM correspondence is imperfect. For such objects, we present here a novel group-wise correspondence. As an example dataset, we use 12 second mandibular molars representing 6 living or fossil euarchontan species. To improve initial correspondence of the SPHARM-PDM representation, we first apply a rigid transformation on each subject using five well-known landmarks (molar cusps). We further enhance the correspondence by optimizing landmarks (local) and multidimensional geometric property (global) over each subject with spherical harmonic representation. The resulting average shape model better captures sharp landmark representation in quantitative evaluation as well as a nice separation of different species compared with that of the SPHARM-PDM method.

SHARD: Spherical Harmonic-based Robust Outlier Detection for HARDI Methods

High Angular Resolution Diffusion Imaging (HARDI) models are used to capture complex intra-voxel microarchitectures. The magnetic resonance imaging sequences that are sensitized to diffusion are often highly accelerated and prone to motion, physiologic, and imaging artifacts. In diffusion tensor imaging, robust statistical approaches have been shown to greatly reduce these adverse factors without human intervention. Similar approaches would be possible with HARDI methods, but robust versions of each distinct HARDI approach would be necessary. To avoid the computational and pragmatic burdens of creating individual robust HARDI analysis variants, we propose a robust outlier imputation model to mitigate outliers prior to traditional HARDI analysis. This model uses a weighted spherical harmonic fit of diffusion weighted magnetic resonance imaging scans to estimate the values which had been corrupted during acquisition to restore them. Briefly, spherical harmonics of 6th order were used to generate basis function which were weighted by diffusion signal for detection of outliers. For validation, a single healthy volunteer was scanned for a single session comprising of two scans one without head movement and the other with deliberate head movement at a b-value of 3000 s/mm2 with 64 diffusion weighted directions with a single b0 (5 averages) per scan. The deliberate motion from the volunteer created natural artifacts in the acquisition of one of the scans. The imputation model shows reduction in root mean squared error of the raw signal intensities and improvement for the HARDI method Q-ball in terms of the Angular Correlation Coefficient. The results reveal that there is quantitative and qualitative improvement. The proposed model can be used as general pre-processing model before implementing any HARDI model in general to restore the artifacts which are created because of the outlier diffusion signal in certain gradient volumes.

Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities.

Development of cortical shape in the human brain from 6 to 24months of age via a novel measure of shape complexity

The quantification of local surface morphology in the human cortex is important for examining population differences as well as developmental changes in neurodegenerative or neurodevelopmental disorders. We propose a novel cortical shape measure, referred to as the 'shape complexity index' (SCI), that represents localized shape complexity as the difference between the observed distributions of local surface topology, as quantified by the shape index (SI) measure, to its best fitting simple topological model within a given neighborhood. We apply a relatively small, adaptive geodesic kernel to calculate the SCI. Due to the small size of the kernel, the proposed SCI measure captures fine differences of cortical shape. With this novel cortical feature, we aim to capture comparatively small local surface changes that capture a) the widening versus deepening of sulcal and gyral regions, as well as b) the emergence and development of secondary and tertiary sulci. Current cortical shape measures, such as the gyrification index (GI) or intrinsic curvature measures, investigate the cortical surface at a different scale and are less well suited to capture these particular cortical surface changes. In our experiments, the proposed SCI demonstrates higher complexity in the gyral/sulcal wall regions, lower complexity in wider gyral ridges and lowest complexity in wider sulcal fundus regions. In early postnatal brain development, our experiments show that SCI reveals a pattern of increased cortical shape complexity with age, as well as sexual dimorphisms in the insula, middle cingulate, parieto-occipital sulcal and Broca's regions. Overall, sex differences were greatest at 6months of age and were reduced at 24months, with the difference pattern switching from higher complexity in males at 6months to higher complexity in females at 24months. This is the first study of longitudinal, cortical complexity maturation and sex differences, in the early postnatal period from 6 to 24months of age with fine scale, cortical shape measures. These results provide information that complement previous studies of gyrification index in early brain development.

Robust estimation of group-wise cortical correspondence with an application to macaque and human neuroimaging studies

We present a novel group-wise registration method for cortical correspondence for local cortical thickness analysis in human and non-human primate neuroimaging studies. The proposed method is based on our earlier template based registration that estimates a continuous, smooth deformation field via sulcal curve-constrained registration employing spherical harmonic decomposition of the deformation field. This pairwise registration though results in a well-known template selection bias, which we aim to overcome here via a group-wise approach. We propose the use of an unbiased ensemble entropy minimization following the use of the pairwise registration as an initialization. An individual deformation field is then iteratively updated onto the unbiased average. For the optimization, we use metrics specific for cortical correspondence though all of these are straightforwardly extendable to the generic setting: The first focused on optimizing the correspondence of automatically extracted sulcal landmarks and the second on that of sulcal depth property maps. We further propose a robust entropy metric and a hierarchical optimization by employing spherical harmonic basis orthogonality. We also provide the detailed methodological description of both our earlier work and the proposed method with a set of experiments on a population of human and non-human primate subjects. In the experiment, we have shown that our method achieves superior results on consistency through quantitative and visual comparisons as compared to the existing methods.

Automatic Sulcal Curve Extraction on the Human Cortical Surface

The recognition of sulcal regions on the cortical surface is an important task to shape analysis and landmark detection. However, it is challenging especially in a complex, rough human cortex. In this paper, we focus on the extraction of sulcal curves from the human cortical surface. The previous sulcal extraction methods are time-consuming in practice and often have a difficulty to delineate curves correctly along the sulcal regions in the presence of significant noise. Our pipeline is summarized in two main steps: 1) We extract candidate sulcal points spread over the sulcal regions. We further reduce the size of the candidate points by applying a line simplification method. 2) Since the candidate points are potentially located away from the exact valley regions, we propose a novel approach to connect candidate sulcal points so as to obtain a set of complete curves (line segments). We have shown in experiment that our method achieves high computational efficiency, improved robustness to noise, and high reliability in a test-retest situation as compared to a well-known existing method.

Multi-atlas segmentation with particle-based group-wise image registration

We propose a novel multi-atlas segmentation method that employs a group-wise image registration method for the brain segmentation on rodent magnetic resonance (MR) images. The core element of the proposed segmentation is the use of a particle-guided image registration method that extends the concept of particle correspondence into the volumetric image domain. The registration method performs a group-wise image registration that simultaneously registers a set of images toward the space defined by the average of particles. The particle-guided image registration method is robust with low signal-to-noise ratio images as well as differing sizes and shapes observed in the developing rodent brain. Also, the use of an implicit common reference frame can prevent potential bias induced by the use of a single template in the segmentation process. We show that the use of a particle guided-image registration method can be naturally extended to a novel multi-atlas segmentation method and improves the registration method to explicitly use the provided template labels as an additional constraint. In the experiment, we show that our segmentation algorithm provides more accuracy with multi-atlas label fusion and stability against pair-wise image registration. The comparison with previous group-wise registration method is provided as well.

Cortical Correspondence via Sulcal Curve-Constrained Spherical Registration with Application to Macaque Studies

In this work, we present a novel cortical correspondence method with application to the macaque brain. The correspondence method is based on sulcal curve constraints on a spherical deformable registration using spherical harmonics to parameterize the spherical deformation. Starting from structural MR images, we first apply existing preprocessing steps: brain tissue segmentation using the Automatic Brain Classification tool (ABC), as well as cortical surface reconstruction and spherical parametrization of the cortical surface via Constrained Laplacian-based Automated Segmentation with Proximities (CLASP). Then, initial correspondence between two cortical surfaces is automatically determined by a curve labeling method using sulcal landmarks extracted along sulcal fundic regions. Since the initial correspondence is limited to sulcal regions, we use spherical harmonics to extrapolate and regularize this correspondence to the entire cortical surface. To further improve the correspondence, we compute a spherical registration that optimizes the spherical harmonic parameterized deformation using a metric that incorporates the error over the sulcal landmarks as well as the normalized cross correlation of sulcal depth maps over the whole cortical surface. For evaluation, a normal 18-months-old macaque brain (for both left and right hemispheres) was matched to a prior macaque brain template with 9 manually labeled, major sulcal curves. The results show successful registration using the proposed registration approach. Evaluation results for optimal parameter settings are presented as well.

Geodesic distances to landmarks for dense correspondence on ensembles of complex shapes

Establishing correspondence points across a set of biomedical shapes is an important technology for a variety of applications that rely on statistical analysis of individual subjects and populations. The inherent complexity (e.g. cortical surface shapes) and variability (e.g. cardiac chambers) evident in many biomedical shapes introduce significant challenges in finding a useful set of dense correspondences. Application specific strategies, such as registration of simplified (e.g. inflated or smoothed) surfaces or relying on manually placed landmarks, provide some improvement but suffer from limitations including increased computational complexity and ambiguity in landmark placement. This paper proposes a method for dense point correspondence on shape ensembles using geodesic distances to a priori landmarks as features. A novel set of numerical techniques for fast computation of geodesic distances to point sets is used to extract these features. The proposed method minimizes the ensemble entropy based on these features, resulting in isometry invariant correspondences in a very general, flexible framework.

Spectral-based automatic labeling and refining of human cortical sulcal curves using expert-provided examples

We present a spectral-based method for automatically labeling and refining major sulcal curves of a human cerebral cortex. Given a set of input (unlabeled) sulcal curves automatically extracted from a cortical surface and a collection of expert-provided examples (labeled sulcal curves), our objective is to identify the input major sulcal curves and assign their neuroanatomical labels, and then refines these curves based on the expert-provided example data, without employing any atlas-based registration scheme as preprocessing. In order to construct the example data, neuroanatomists manually labeled a set of 24 major sulcal curves (12 each for the left and right hemispheres) for each individual subject according to a precise protocol. We collected 30 sets of such curves from 30 subjects. Given the raw input sulcal curve set of a subject, we choose the most similar example curve to each input curve in the set to label and refine the latter according to the former. We adapt a spectral matching algorithm to choose the example curve by exploiting the sulcal curve features and their relationship. The high dimensionality of sulcal curve data in spectral matching is addressed by using their multi-resolution representations, which greatly reduces time and space complexities. Our method provides consistent labeling and refining results even under high variability of cortical sulci across the subjects. Through experiments we show that the results are comparable in accuracy to those done manually. Most output curves exhibited accuracy values higher than 80%, and the mean accuracy values of the curves in the left and the right hemispheres were 84.69% and 84.58%, respectively.