Effects of registration regularization and atlas sharpness on segmentation accuracy

Imaging of Brain Structural and Functional Effects in People With Human Immunodeficiency Virus

Before the introduction of antiretroviral therapy, human immunodeficiency virus (HIV) infection was often accompanied by central nervous system (CNS) opportunistic infections and HIV encephalopathy marked by profound structural and functional alterations detectable with neuroimaging. Treatment with antiretroviral therapy nearly eliminated CNS opportunistic infections, while neuropsychiatric impairment and peripheral nerve and organ damage have persisted among virally suppressed people with HIV (PWH), suggesting ongoing brain injury. Neuroimaging research must use methods sensitive for detecting subtle HIV-associated brain structural and functional abnormalities, while allowing for adjustments for potential confounders, such as age, sex, substance use, hepatitis C coinfection, cardiovascular risk, and others. Here, we review existing and emerging neuroimaging tools that demonstrated promise in detecting markers of HIV-associated brain pathology and explore strategies to study the impact of potential confounding factors on these brain measures. We emphasize neuroimaging approaches that may be used in parallel to gather complementary information, allowing efficient detection and interpretation of altered brain structure and function associated with suboptimal clinical outcomes among virally suppressed PWH. We examine the advantages of each imaging modality and systematic approaches in study design and analysis. We also consider advantages of combining experimental and statistical control techniques to improve sensitivity and specificity of biotype identification and explore the costs and benefits of aggregating data from multiple studies to achieve larger sample sizes, enabling use of emerging methods for combining and analyzing large, multifaceted data sets. Many of the topics addressed in this article were discussed at the National Institute of Mental Health meeting "Biotypes of CNS Complications in People Living with HIV," held in October 2021, and are part of ongoing research initiatives to define the role of neuroimaging in emerging alternative approaches to identifying biotypes of CNS complications in PWH. An outcome of these considerations may be the development of a common neuroimaging protocol available for researchers to use in future studies examining neurological changes in the brains of PWH.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

The macaque brain ONPRC18 template with combined gray and white matter labelmap for multimodal neuroimaging studies of Nonhuman Primates

Macaques are the most common nonhuman primate (NHP) species used in neuroscience research. With the advancement of many neuroimaging techniques, new studies are beginning to apply multiple types of in vivo mag netic resonance imaging (MRI), such as structural imaging (sMRI) with T1 and T2 weighted contrasts alongside diffusion weighed (DW) imaging. In studies involving rhesus macaques, this approach can be used to better under stand micro-structural changes that occur during development, in various disease states or with normative aging. However, many of the available rhesus brain atlases have been designed for only one imaging modality, making it difficult to consistently define the same brain regions across multiple imaging modalities in the same subject. To address this, we created a brain atlas from 18 adult rhesus macaques that includes co-registered templates constructed from images frequently used to characterize macroscopic brain structure (T2/SPACE and T1/MP-RAGE), and a diffusion tensor imaging (DTI) template. The DTI template was up-sampled from 1 mm isotropic resolution to resolution match to the T1 and T2-weighted images (0.5 mm isotropic), and the parameter maps were derived for FA, AD, RD and MD. The labelmap volumes delineate 57 gray matter regions of interest (ROIs; 36 cortical regions and 21 subcortical structures), as well as 74 white matter tracts. Importantly, the labelmap overlays both the structural and diffusion templates, enabling the same regions to be consistently identified across imaging modalities. A specialized condensed version of the labelmap ROIs are also included to further extend the usefulness of this tool for imaging data with lower spatial resolution, such as functional MRI (fMRI) or positron emission tomography (PET).

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.

Altered Cortical Morphometry in Pre-manifest Huntington's Disease: Cross-sectional Data from the IMAGE-HD Study

Huntington's disease (HD) is an inherited progressive neurodegenerative disease mainly associated with subcortical striatal atrophy. There is also strong evidence showing cerebral atrophy and cortical thinning; however, limited research has investigated altered patterns of cortical folding in this disease. Here, we investigated cortical morphometry via both gyrification index (GI, a measure of cortical folding) and cortical thinning. The localized GI was examined using a novel GI, namely LB-GI. As part of a cross-sectional study, pre-manifest (pre-HD) individuals (n = 29) and matched controls (n = 29) underwent T1-MRI using data from the IMAGE-HD study. Compared to controls, pre-HD individuals demonstrated significantly lower GI in the left superior parietal and the right superior temporal regions and greater cortical thinning in the bilateral pre-central and the superior frontal gyri and left caudal middle frontal gyrus, as well as the superior parietal region. For the first time, we report evidence of abnormal localized cortical folding in pre-HD. We also provide evidence that cortical folding impacts different regions of the cortical surface more so than cortical thickness. As a result, we propose a potential new biological marker that may increase our understanding of the neuropathology of HD. Greater understanding of brain changes could inform new therapeutic approaches and target points for clinical trials.

Baby brain atlases

The baby brain is constantly changing due to its active neurodevelopment, and research into the baby brain is one of the frontiers in neuroscience. To help guide neuroscientists and clinicians in their investigation of this frontier, maps of the baby brain, which contain a priori knowledge about neurodevelopment and anatomy, are essential. "Brain atlas" in this review refers to a 3D-brain image with a set of reference labels, such as a parcellation map, as the anatomical reference that guides the mapping of the brain. Recent advancements in scanners, sequences, and motion control methodologies enable the creation of various types of high-resolution baby brain atlases. What is becoming clear is that one atlas is not sufficient to characterize the existing knowledge about the anatomical variations, disease-related anatomical alterations, and the variations in time-dependent changes. In this review, the types and roles of the human baby brain MRI atlases that are currently available are described and discussed, and future directions in the field of developmental neuroscience and its clinical applications are proposed. The potential use of disease-based atlases to characterize clinically relevant information, such as clinical labels, in addition to conventional anatomical labels, is also discussed.

Detail-preserving construction of neonatal brain atlases in space-frequency domain

Brain atlases are commonly utilized in neuroimaging studies. However, most brain atlases are fuzzy and lack structural details, especially in the cortical regions. This is mainly caused by the image averaging process involved in atlas construction, which often smoothes out high-frequency contents that capture fine anatomical details. Brain atlas construction for neonatal images is even more challenging due to insufficient spatial resolution and low tissue contrast. In this paper, we propose a novel framework for detail-preserving construction of population-representative atlases. Our approach combines spatial and frequency information to better preserve image details. This is achieved by performing atlas construction in the space-frequency domain given by wavelet transform. In particular, sparse patch-based atlas construction is performed in all frequency subbands, and the results are combined to give a final atlas. For enhancing anatomical details, tissue probability maps are also used to guide atlas construction. Experimental results show that our approach can produce atlases with greater structural details than existing atlases. Hum Brain Mapp 37:2133-2150, 2016. © 2016 Wiley Periodicals, Inc.

Subject Based Registration for Individualized Analysis of Diffusion Tensor MRI

Registration of subject and control brains to a common anatomical space or template is the basis for quantitatively delineating regions of abnormality in an individual brain. Normally, a brain atlas is chosen as the template. Limitations in the registration process result in persistent differences between individual subject brains and template, which can be a source of error in an analysis. We propose a new approach to the registration process where the subject of interest is the registration template. Through this change, we eliminate errors due to differences between a brain template and a subject’s brain. We applied this method to the analysis of FA values derived from DTI data of 20 individual mTBI patients as compared to 48 healthy controls. Subject-centered analysis resulted in identification of significantly fewer regions of abnormally low FA compared to two separate atlas-centered analyses, with subject-centered abnormalities essentially representing the common subset of abnormal low FA regions detected by the two atlas-centered methods. Whereas each atlas-centered approach demonstrated abnormalities in nearly every subject (19/20 and 20/20), the subject-centered approach demonstrated abnormalities in fewer than half the subjects (9/20). This reduction of diffusion abnormalities observed using the subject-centered approach is due to elimination of misregistration errors that occur when registering the subject of interest to a template. Evaluation of atlas-centered analyses demonstrated that 9.8% to 13.3% of subject GM and CSF was misregistered onto the WM of the brain atlas, resulting in the observation of additional low FA clusters compared to the subject-centered approach. Without careful evaluation, these misregistrations could be misinterpreted as pathology. An additional benefit of the subject-centered approach is that diffusion abnormalities can now be visualized directly in the subject’s anatomical space, rather than interpolating results from the brain atlas space, and can thereby enhance correlation with other components of an imaging protocol.

Construction of 4D high-definition cortical surface atlases of infants: Methods and applications

In neuroimaging, cortical surface atlases play a fundamental role for spatial normalization, analysis, visualization, and comparison of results across individuals and different studies. However, existing cortical surface atlases created for adults are not suitable for infant brains during the first two postnatal years, which is the most dynamic period of postnatal structural and functional development of the highly-folded cerebral cortex. Therefore, spatiotemporal cortical surface atlases for infant brains are highly desired yet still lacking for accurate mapping of early dynamic brain development. To bridge this significant gap, leveraging our infant-dedicated computational pipeline for cortical surface-based analysis and the unique longitudinal infant MRI dataset acquired in our research center, in this paper, we construct the first spatiotemporal (4D) high-definition cortical surface atlases for the dynamic developing infant cortical structures at seven time points, including 1, 3, 6, 9, 12, 18, and 24 months of age, based on 202 serial MRI scans from 35 healthy infants. For this purpose, we develop a novel method to ensure the longitudinal consistency and unbiasedness to any specific subject and age in our 4D infant cortical surface atlases. Specifically, we first compute the within-subject mean cortical folding by unbiased groupwise registration of longitudinal cortical surfaces of each infant. Then we establish longitudinally-consistent and unbiased inter-subject cortical correspondences by groupwise registration of the geometric features of within-subject mean cortical folding across all infants. Our 4D surface atlases capture both longitudinally-consistent dynamic mean shape changes and the individual variability of cortical folding during early brain development. Experimental results on two independent infant MRI datasets show that using our 4D infant cortical surface atlases as templates leads to significantly improved accuracy for spatial normalization of cortical surfaces across infant individuals, in comparison to the infant surface atlases constructed without longitudinal consistency and also the FreeSurfer adult surface atlas. Moreover, based on our 4D infant surface atlases, for the first time, we reveal the spatially-detailed, region-specific correlation patterns of the dynamic cortical developmental trajectories between different cortical regions during early brain development.

Geodesic Information Flows: Spatially-Variant Graphs and Their Application to Segmentation and Fusion

Clinical annotations, such as voxel-wise binary or probabilistic tissue segmentations, structural parcellations, pathological regions-of-interest and anatomical landmarks are key to many clinical studies. However, due to the time consuming nature of manually generating these annotations, they tend to be scarce and limited to small subsets of data. This work explores a novel framework to propagate voxel-wise annotations between morphologically dissimilar images by diffusing and mapping the available examples through intermediate steps. A spatially-variant graph structure connecting morphologically similar subjects is introduced over a database of images, enabling the gradual diffusion of information to all the subjects, even in the presence of large-scale morphological variability. We illustrate the utility of the proposed framework on two example applications: brain parcellation using categorical labels and tissue segmentation using probabilistic features. The application of the proposed method to categorical label fusion showed highly statistically significant improvements when compared to state-of-the-art methodologies. Significant improvements were also observed when applying the proposed framework to probabilistic tissue segmentation of both synthetic and real data, mainly in the presence of large morphological variability.

Multi-atlas segmentation of biomedical images: A survey

Multi-atlas segmentation (MAS), first introduced and popularized by the pioneering work of Rohlfing, et al. (2004), Klein, et al. (2005), and Heckemann, et al. (2006), is becoming one of the most widely-used and successful image segmentation techniques in biomedical applications. By manipulating and utilizing the entire dataset of "atlases" (training images that have been previously labeled, e.g., manually by an expert), rather than some model-based average representation, MAS has the flexibility to better capture anatomical variation, thus offering superior segmentation accuracy. This benefit, however, typically comes at a high computational cost. Recent advancements in computer hardware and image processing software have been instrumental in addressing this challenge and facilitated the wide adoption of MAS. Today, MAS has come a long way and the approach includes a wide array of sophisticated algorithms that employ ideas from machine learning, probabilistic modeling, optimization, and computer vision, among other fields. This paper presents a survey of published MAS algorithms and studies that have applied these methods to various biomedical problems. In writing this survey, we have three distinct aims. Our primary goal is to document how MAS was originally conceived, later evolved, and now relates to alternative methods. Second, this paper is intended to be a detailed reference of past research activity in MAS, which now spans over a decade (2003-2014) and entails novel methodological developments and application-specific solutions. Finally, our goal is to also present a perspective on the future of MAS, which, we believe, will be one of the dominant approaches in biomedical image segmentation.

Tract-based analysis of white matter degeneration in Alzheimer's disease

Although much prior work has focused on the known cortical pathology that defines Alzheimer's disease (AD) histologically, recent work has additionally demonstrated substantial damage to the cerebral white matter in this condition. While there is large evidence of diffuse damage to the white matter in AD, it is unclear whether specific white matter tracts exhibit a more accelerated pattern of damage and whether the damage is associated with the classical neurodegenerative changes of AD. In this study, we investigated microstructural differences in the large fascicular bundles of the cerebral white matter of individuals with AD and mild cognitive impairment (MCI), using recently developed automated diffusion tractography procedures in the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset. Eighteen major fiber bundles in a total of 36 individuals with AD, 81 MCI and 60 control participants were examined with the TRActs Constrained by UnderLying Anatomy (TRACULA) procedure available as part of the FreeSurfer image processing software package. For each fiber bundle, the mean fractional anisotropy (FA), and mean, radial and axial diffusivities were calculated. Individuals with AD had increased diffusivities in both left and right cingulum-angular bundles compared to control participants (p<0.001). Individuals with MCI also had increased axial and mean diffusivities and increased FA in both cingulum-angular bundles compared to control participants (p<0.05) and decreased radial diffusivity compared to individuals with AD (p<0.05). We additionally examined how white matter deterioration relates to hippocampal volume, a traditional imaging measure of AD pathology, and found the strongest negative correlations in AD patients between hippocampal volume and the diffusivities of the cingulum-angular and cingulum-cingulate gyrus bundles and of the corticospinal tracts (p<0.05). However, statistically controlling for hippocampal volume did not remove all group differences in white matter measures, suggesting a unique contribution of white matter damage to AD unexplained by this disease biomarker. These results suggest that (1) AD-associated deterioration of white matter fibers is greatest in tracts known to be connected to areas of pathology in AD and (2) lower white matter tract integrity is more diffusely associated with lower hippocampal volume indicating that the pathology in the white matter follows to some degree the neurodegenerative staging and progression of this condition.

AUTOMATIC PARCELLATION OF CORTICAL SURFACES USING RANDOM FORESTS

Automatic and accurate parcellation of cortical surfaces into anatomically and functionally meaningful regions is of fundamental importance in brain mapping. In this paper, we propose a new method leveraging random forests and graph cuts methods to parcellate cortical surfaces into a set of gyral-based regions, using multiple surface atlases with manual labels by experts. Specifically, our method first takes advantage of random forests and auto-context methods to learn the optimal utilization of cortical features for rough parcellation and then the graph cuts method to further refine the parcellation for improved accuracy and spatial consistency. Particularly, to capitalize on random forests, we propose a novel definition of Haar-like features on cortical surfaces based on spherical mapping. The proposed method has been validated on cortical surfaces from 39 adult brain MR images, each with 35 regions manually labeled by a neuroanatomist, achieving the average Dice ratio of 0.902, higher than the-state-of-art methods.

Simultaneous and consistent labeling of longitudinal dynamic developing cortical surfaces in infants

The human cerebral cortex develops extremely dynamically in the first 2years of life. Accurate and consistent parcellation of longitudinal dynamic cortical surfaces during this critical stage is essential to understand the early development of cortical structure and function in both normal and high-risk infant brains. However, directly applying the existing methods developed for the cross-sectional studies often generates longitudinally-inconsistent results, thus leading to inaccurate measurements of the cortex development. In this paper, we propose a new method for accurate, consistent, and simultaneous labeling of longitudinal cortical surfaces in the serial infant brain MR images. The proposed method is explicitly formulated as a minimization problem with an energy function that includes a data fitting term, a spatial smoothness term, and a temporal consistency term. Specifically, inspired by multi-atlas based label fusion, the data fitting term is designed to integrate the contributions from multi-atlas surfaces adaptively, according to the similarities of their local cortical folding with that of the subject cortical surface. The spatial smoothness term is then designed to adaptively encourage label smoothness based on the local cortical folding geometries, i.e., allowing label discontinuity at sulcal bottoms (which often are the boundaries of cytoarchitecturally and functionally distinct regions). The temporal consistency term is to adaptively encourage the label consistency among the temporally-corresponding vertices, based on their similarity of local cortical folding. Finally, the entire energy function is efficiently minimized by a graph cuts method. The proposed method has been applied to the parcellation of longitudinal cortical surfaces of 13 healthy infants, each with 6 serial MRI scans acquired at 0, 3, 6, 9, 12 and 18months of age. Qualitative and quantitative evaluations demonstrated both accuracy and longitudinal consistency of the proposed method. By using our method, for the first time, we reveal several hitherto unseen properties of the dynamic and regionally heterogeneous development of the cortical surface area in the first 18months of life.

Gauss-Newton inspired preconditioned optimization in large deformation diffeomorphic metric mapping

In this work, we propose a novel preconditioned optimization method in the paradigm of Large Deformation Diffeomorphic Metric Mapping (LDDMM). The preconditioned update scheme is formulated for the non-stationary and the stationary parameterizations of diffeomorphisms, yielding three different LDDMM methods. The preconditioning matrices are inspired in the Hessian approximation used in Gauss-Newton method. The derivatives are computed using Frechet differentials. Thus, optimization is performed in a Sobolev space, in contrast to optimization in L(2) commonly used in non-rigid registration literature. The proposed LDDMM methods have been evaluated and compared with their respective implementations of gradient descent optimization. Evaluation has been performed using real and simulated images from the Non-rigid Image Registration Evaluation Project (NIREP). The experiments conducted in this work reported that our preconditioned LDDMM methods achieved a performance similar or superior to well-established-in-literature gradient descent non-stationary LDDMM in the great majority of cases. Moreover, preconditioned optimization showed a substantial reduction in the execution time with an affordable increase of the memory usage per iteration. Additional experiments reported that optimization using Frechet differentials should be preferable to optimization using L(2) differentials.

A multiatlas segmentation using graph cuts with applications to liver segmentation in CT scans

An atlas-based segmentation approach is presented that combines low-level operations, an affine probabilistic atlas, and a multiatlas-based segmentation. The proposed combination provides highly accurate segmentation due to registrations and atlas selections based on the regions of interest (ROIs) and coarse segmentations. Our approach shares the following common elements between the probabilistic atlas and multiatlas segmentation: (a) the spatial normalisation and (b) the segmentation method, which is based on minimising a discrete energy function using graph cuts. The method is evaluated for the segmentation of the liver in computed tomography (CT) images. Low-level operations define a ROI around the liver from an abdominal CT. We generate a probabilistic atlas using an affine registration based on geometry moments from manually labelled data. Next, a coarse segmentation of the liver is obtained from the probabilistic atlas with low computational effort. Then, a multiatlas segmentation approach improves the accuracy of the segmentation. Both the atlas selections and the nonrigid registrations of the multiatlas approach use a binary mask defined by coarse segmentation. We experimentally demonstrate that this approach performs better than atlas selections and nonrigid registrations in the entire ROI. The segmentation results are comparable to those obtained by human experts and to other recently published results.

Optimizing the use of radiologist seed points for improved multiple sclerosis lesion segmentation

Many current methods for multiple sclerosis (MS) lesion segmentation require radiologist seed points as input, but do not necessarily allow the expert to work in an intuitive or efficient way. Ironically, most methods also assume that the points are placed optimally. This paper examines how seed points can be processed with intuitive heuristics, which provide improved segmentation accuracy while facilitating quick and natural point placement. Using a large set of MRIs from an MS clinical trial, two radiologists are asked to seed the lesions while unaware that the points would be fed into a classifier, based on Parzen windows, that automatically delineates each marked lesion. To evaluate the impact of the new heuristics, an interactive region-growing method is used to provide ground truth and the Dice coefficient (DC) and Spearman’s rank correlation are used as the primary measures of agreement. A stratified analysis is performed to determine the effect on scans with low-, medium-, and high lesion loads. Compared to the unenhanced classifier, the heuristics dramatically improve the DC (+32.91 pt.) and correlation (+0.50) for the scans with low lesion loads, and also improve the DC (+14.55 pt.) and correlation (+0.15) for the scans with medium lesion loads, while having aminimal effect for the scans with high lesion loads, which are already segmented accurately by Parzen windows.With the heuristics, the DC is close to 80% and the correlation is above 0.9 for all three load categories.

Neonatal atlas construction using sparse representation

Atlas construction generally includes first an image registration step to normalize all images into a common space and then an atlas building step to fuse the information from all the aligned images. Although numerous atlas construction studies have been performed to improve the accuracy of the image registration step, unweighted or simply weighted average is often used in the atlas building step. In this article, we propose a novel patch-based sparse representation method for atlas construction after all images have been registered into the common space. By taking advantage of local sparse representation, more anatomical details can be recovered in the built atlas. To make the anatomical structures spatially smooth in the atlas, the anatomical feature constraints on group structure of representations and also the overlapping of neighboring patches are imposed to ensure the anatomical consistency between neighboring patches. The proposed method has been applied to 73 neonatal MR images with poor spatial resolution and low tissue contrast, for constructing a neonatal brain atlas with sharp anatomical details. Experimental results demonstrate that the proposed method can significantly enhance the quality of the constructed atlas by discovering more anatomical details especially in the highly convoluted cortical regions. The resulting atlas demonstrates superior performance of our atlas when applied to spatially normalizing three different neonatal datasets, compared with other start-of-the-art neonatal brain atlases.

Unsupervised segmentation, clustering, and groupwise registration of heterogeneous populations of brain MR images

Population analysis of brain morphology from magnetic resonance images contributes to the study and understanding of neurological diseases. Such analysis typically involves segmentation of a large set of images and comparisons of these segmentations between relevant subgroups of images (e.g., "normal" versus "diseased"). The images of each subgroup are usually selected in advance in a supervised way based on clinical knowledge. Their segmentations are typically guided by one or more available atlases, assumed to be suitable for the images at hand. We present a data-driven probabilistic framework that simultaneously performs atlas-guided segmentation of a heterogeneous set of brain MR images and clusters the images in homogeneous subgroups, while constructing separate probabilistic atlases for each cluster to guide the segmentation. The main benefits of integrating segmentation, clustering and atlas construction in a single framework are that: 1) our method can handle images of a heterogeneous group of subjects and automatically identifies homogeneous subgroups in an unsupervised way with minimal prior knowledge, 2) the subgroups are formed by automatical detection of the relevant morphological features based on the segmentation, 3) the atlases used by our method are constructed from the images themselves and optimally adapted for guiding the segmentation of each subgroup, and 4) the probabilistic atlases represent the morphological pattern that is specific for each subgroup and expose the groupwise differences between different subgroups. We demonstrate the feasibility of the proposed framework and evaluate its performance with respect to image segmentation, clustering and atlas construction on simulated and real data sets including the publicly available BrainWeb and ADNI data. It is shown that combined segmentation and atlas construction leads to improved segmentation accuracy. Furthermore, it is demonstrated that the clusters generated by our unsupervised framework largely coincide with the clinically determined subgroups in case of disease-specific differences in brain morphology and that the differences between the cluster-specific atlases are in agreement with the expected disease-specific patterns, indicating that our method is capable of detecting the different modes in a population. Our method can thus be seen as a comprehensive image-driven population analysis framework that can contribute to the detection of novel subgroups and distinctive image features, potentially leading to new insights in the brain development and disease.

Local label learning (LLL) for subcortical structure segmentation: application to hippocampus segmentation

Automatic and reliable segmentation of subcortical structures is an important but difficult task in quantitative brain image analysis. Multi-atlas based segmentation methods have attracted great interest due to their promising performance. Under the multi-atlas based segmentation framework, using deformation fields generated for registering atlas images onto a target image to be segmented, labels of the atlases are first propagated to the target image space and then fused to get the target image segmentation based on a label fusion strategy. While many label fusion strategies have been developed, most of these methods adopt predefined weighting models that are not necessarily optimal. In this study, we propose a novel local label learning strategy to estimate the target image's segmentation label using statistical machine learning techniques. In particular, we use a L1-regularized support vector machine (SVM) with a k nearest neighbor (kNN) based training sample selection strategy to learn a classifier for each of the target image voxel from its neighboring voxels in the atlases based on both image intensity and texture features. Our method has produced segmentation results consistently better than state-of-the-art label fusion methods in validation experiments on hippocampal segmentation of over 100 MR images obtained from publicly available and in-house datasets. Volumetric analysis has also demonstrated the capability of our method in detecting hippocampal volume changes due to Alzheimer's disease.

Improved inference in Bayesian segmentation using Monte Carlo sampling: application to hippocampal subfield volumetry

Many segmentation algorithms in medical image analysis use Bayesian modeling to augment local image appearance with prior anatomical knowledge. Such methods often contain a large number of free parameters that are first estimated and then kept fixed during the actual segmentation process. However, a faithful Bayesian analysis would marginalize over such parameters, accounting for their uncertainty by considering all possible values they may take. Here we propose to incorporate this uncertainty into Bayesian segmentation methods in order to improve the inference process. In particular, we approximate the required marginalization over model parameters using computationally efficient Markov chain Monte Carlo techniques. We illustrate the proposed approach using a recently developed Bayesian method for the segmentation of hippocampal subfields in brain MRI scans, showing a significant improvement in an Alzheimer's disease classification task. As an additional benefit, the technique also allows one to compute informative "error bars" on the volume estimates of individual structures.

Evaluation of group-specific, whole-brain atlas generation using Volume-based Template Estimation (VTE): application to normal and Alzheimer's populations

MRI-based human brain atlases, which serve as a common coordinate system for image analysis, play an increasingly important role in our understanding of brain anatomy, image registration, and segmentation. Study-specific brain atlases are often obtained from one of the subjects in a study or by averaging the images of all participants after linear or non-linear registration. The latter approach has the advantage of providing an unbiased anatomical representation of the study population. But, the image contrast is influenced by both inherent MR contrasts and residual anatomical variability after the registration; in addition, the topology of the brain structures cannot reliably be preserved. In this study, we demonstrated a population-based template-creation approach, which is based on Bayesian template estimation on a diffeomorphic random orbit model. This approach attempts to define a population-representative template without the cross-subject intensity averaging; thus, the topology of the brain structures is preserved. It has been tested for segmented brain structures, such as the hippocampus, but its validity on whole-brain MR images has not been examined. This paper validates and evaluates this atlas generation approach, i.e., Volume-based Template Estimation (VTE). Using datasets from normal subjects and Alzheimer's patients, quantitative measurements of sub-cortical structural volumes, metric distance, displacement vector, and Jacobian were examined to validate the group-averaged shape features of the VTE. In addition to the volume-based quantitative analysis, the preserved brain topology of the VTE allows surface-based analysis within the same atlas framework. This property was demonstrated by analyzing the registration accuracy of the pre- and post-central gyri. The proposed method achieved registration accuracy within 1mm for these population-preserved cortical structures in an elderly population.

A unified framework for cross-modality multi-atlas segmentation of brain MRI

Multi-atlas label fusion is a powerful image segmentation strategy that is becoming increasingly popular in medical imaging. A standard label fusion algorithm relies on independently computed pairwise registrations between individual atlases and the (target) image to be segmented. These registrations are then used to propagate the atlas labels to the target space and fuse them into a single final segmentation. Such label fusion schemes commonly rely on the similarity between intensity values of the atlases and target scan, which is often problematic in medical imaging - in particular, when the atlases and target images are obtained via different sensor types or imaging protocols. In this paper, we present a generative probabilistic model that yields an algorithm for solving the atlas-to-target registrations and label fusion steps simultaneously. The proposed model does not directly rely on the similarity of image intensities. Instead, it exploits the consistency of voxel intensities within the target scan to drive the registration and label fusion, hence the atlases and target image can be of different modalities. Furthermore, the framework models the joint warp of all the atlases, introducing interdependence between the registrations. We use variational expectation maximization and the Demons registration framework in order to efficiently identify the most probable segmentation and registrations. We use two sets of experiments to illustrate the approach, where proton density (PD) MRI atlases are used to segment T1-weighted brain scans and vice versa. Our results clearly demonstrate the accuracy gain due to exploiting within-target intensity consistency and integrating registration into label fusion.

Multiple Atlas construction from a heterogeneous brain MR image collection

In this paper, we propose a novel framework for computing single or multiple atlases (templates) from a large population of images. Unlike many existing methods, our proposed approach is distinguished by its emphasis on the sharpness of the computed atlases and the requirement of rotational invariance. In particular, we argue that sharp atlas images that retain crucial and important anatomical features with high fidelity are more useful for many medical imaging applications when compared with the blurry and fuzzy atlas images computed by most existing methods. The geometric notion that underlies our approach is the idea of manifold learning in a quotient space, the quotient space of the image space by the rotations. We present an extension of the existing manifold learning approach to quotient spaces by using invariant metrics, and utilizing the manifold structure for partitioning the images into more homogeneous sub-collections, each of which can be represented by a single atlas image. Specifically, we propose a three-step algorithm. First, we partition the input images into subgroups using unsupervised or semi-supervised learning methods on manifolds. Then we formulate a convex optimization problem in each subgroup to locate the atlases and determine the crucial neighbors that are used in the realization step to form the template images. We have evaluated our algorithm using whole brain MR volumes from OASIS database. Experimental results demonstrate that the atlases computed using the proposed algorithm not only discover the brain structural changes in different age groups but also preserve important structural details and generally enjoy better image quality.

The INIA19 Template and NeuroMaps Atlas for Primate Brain Image Parcellation and Spatial Normalization

The INIA19 is a new, high-quality template for imaging-based studies of non-human primate brains, created from high-resolution, T₁-weighted magnetic resonance (MR) images of 19 rhesus macaque (Macaca mulatta) animals. Combined with the comprehensive cortical and sub-cortical label map of the NeuroMaps atlas, the INIA19 is equally suitable for studies requiring both spatial normalization and atlas label propagation. Population-averaged template images are provided for both the brain and the whole head, to allow alignment of the atlas with both skull-stripped and unstripped data, and thus to facilitate its use for skull stripping of new images. This article describes the construction of the template using freely available software tools, as well as the template itself, which is being made available to the scientific community (http://nitrc.org/projects/inia19/).

Discriminative segmentation-based evaluation through shape dissimilarity

Segmentation-based scores play an important role in the evaluation of computational tools in medical image analysis. These scores evaluate the quality of various tasks, such as image registration and segmentation, by measuring the similarity between two binary label maps. Commonly these measurements blend two aspects of the similarity: pose misalignments and shape discrepancies. Not being able to distinguish between these two aspects, these scores often yield similar results to a widely varying range of different segmentation pairs. Consequently, the comparisons and analysis achieved by interpreting these scores become questionable. In this paper, we address this problem by exploring a new segmentation-based score, called normalized Weighted Spectral Distance (nWSD), that measures only shape discrepancies using the spectrum of the Laplace operator. Through experiments on synthetic and real data we demonstrate that nWSD provides additional information for evaluating differences between segmentations, which is not captured by other commonly used scores. Our results demonstrate that when jointly used with other scores, such as Dice's similarity coefficient, the additional information provided by nWSD allows richer, more discriminative evaluations. We show for the task of registration that through this addition we can distinguish different types of registration errors. This allows us to identify the source of errors and discriminate registration results which so far had to be treated as being of similar quality in previous evaluation studies.

Non-local statistical label fusion for multi-atlas segmentation

Multi-atlas segmentation provides a general purpose, fully-automated approach for transferring spatial information from an existing dataset ("atlases") to a previously unseen context ("target") through image registration. The method to resolve voxelwise label conflicts between the registered atlases ("label fusion") has a substantial impact on segmentation quality. Ideally, statistical fusion algorithms (e.g., STAPLE) would result in accurate segmentations as they provide a framework to elegantly integrate models of rater performance. The accuracy of statistical fusion hinges upon accurately modeling the underlying process of how raters err. Despite success on human raters, current approaches inaccurately model multi-atlas behavior as they fail to seamlessly incorporate exogenous intensity information into the estimation process. As a result, locally weighted voting algorithms represent the de facto standard fusion approach in clinical applications. Moreover, regardless of the approach, fusion algorithms are generally dependent upon large atlas sets and highly accurate registration as they implicitly assume that the registered atlases form a collectively unbiased representation of the target. Herein, we propose a novel statistical fusion algorithm, Non-Local STAPLE (NLS). NLS reformulates the STAPLE framework from a non-local means perspective in order to learn what label an atlas would have observed, given perfect correspondence. Through this reformulation, NLS (1) seamlessly integrates intensity into the estimation process, (2) provides a theoretically consistent model of multi-atlas observation error, and (3) largely diminishes the need for large atlas sets and very high-quality registrations. We assess the sensitivity and optimality of the approach and demonstrate significant improvement in two empirical multi-atlas experiments.

"Nonparametric Local Smoothing" is not image registration

BACKGROUND

Image registration is one of the most important and universally useful computational tasks in biomedical image analysis. A recent article by Xing & Qiu (IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(10):2081-2092, 2011) is based on an inappropriately narrow conceptualization of the image registration problem as the task of making two images look alike, which disregards whether the established spatial correspondence is plausible. The authors propose a new algorithm, Nonparametric Local Smoothing (NLS) for image registration, but use image similarities alone as a measure of registration performance, although these measures do not relate reliably to the realism of the correspondence map.

RESULTS

Using data obtained from its authors, we show experimentally that the method proposed by Xing & Qiu is not an effective registration algorithm. While it optimizes image similarity, it does not compute accurate, interpretable transformations. Even judged by image similarity alone, the proposed method is consistently outperformed by a simple pixel permutation algorithm, which is known by design not to compute valid registrations.

CONCLUSIONS

This study has demonstrated that the NLS algorithm proposed recently for image registration, and published in one of the most respected journals in computer science, is not, in fact, an effective registration method at all. Our results also emphasize the general need to apply registration evaluation criteria that are sensitive to whether correspondences are accurate and mappings between images are physically interpretable. These goals cannot be achieved by simply reporting image similarities.

Formulating spatially varying performance in the statistical fusion framework

To date, label fusion methods have primarily relied either on global [e.g., simultaneous truth and performance level estimation (STAPLE), globally weighted vote] or voxelwise (e.g., locally weighted vote) performance models. Optimality of the statistical fusion framework hinges upon the validity of the stochastic model of how a rater errs (i.e., the labeling process model). Hitherto, approaches have tended to focus on the extremes of potential models. Herein, we propose an extension to the STAPLE approach to seamlessly account for spatially varying performance by extending the performance level parameters to account for a smooth, voxelwise performance level field that is unique to each rater. This approach, Spatial STAPLE, provides significant improvements over state-of-the-art label fusion algorithms in both simulated and empirical data sets.

A GENERATIVE MODEL FOR MULTI-ATLAS SEGMENTATION ACROSS MODALITIES

Current label fusion methods enhance multi-atlas segmentation by locally weighting the contribution of the atlases according to their similarity to the target volume after registration. However, these methods cannot handle voxel intensity inconsistencies between the atlases and the target image, which limits their application across modalities or even across MRI datasets due to differences in image contrast. Here we present a generative model for multi-atlas image segmentation, which does not rely on the intensity of the training images. Instead, we exploit the consistency of voxel intensities within regions in the target volume and their relation to the propagated labels. This is formulated in a probabilistic framework, where the most likely segmentation is obtained with variational expectation maximization (EM). The approach is demonstrated in an experiment where T₁-weighted MRI atlases are used to segment proton-density (PD) weighted brain MRI scans, a scenario in which traditional weighting schemes cannot be used. Our method significantly improves the results provided by majority voting and STAPLE.

A Generative Model for Probabilistic Label Fusion of Multimodal Data

The maturity of registration methods, in combination with the increasing processing power of computers, has made multi-atlas segmentation methods practical. The problem of merging the deformed label maps from the atlases is known as label fusion. Even though label fusion has been well studied for intramodality scenarios, it remains relatively unexplored when the nature of the target data is multimodal or when its modality is different from that of the atlases. In this paper, we review the literature on label fusion methods and also present an extension of our previously published algorithm to the general case in which the target data are multimodal. The method is based on a generative model that exploits the consistency of voxel intensities within the target scan based on the current estimate of the segmentation. Using brain MRI scans acquired with a multiecho FLASH sequence, we compare the method with majority voting, statistical-atlas-based segmentation, the popular package FreeSurfer and an adaptive local multi-atlas segmentation method. The results show that our approach produces highly accurate segmentations (Dice 86.3% across 22 brain structures of interest), outperforming the competing methods.

Diffeomorphic brain registration under exhaustive sulcal constraints

The alignment and normalization of individual brain structures is a prerequisite for group-level analyses of structural and functional neuroimaging data. The techniques currently available are either based on volume and/or surface attributes, with limited insight regarding the consistent alignment of anatomical landmarks across individuals. This article details a global, geometric approach that performs the alignment of the exhaustive sulcal imprints (cortical folding patterns) across individuals. This DIffeomorphic Sulcal-based COrtical (DISCO) technique proceeds to the automatic extraction, identification and simplification of sulcal features from T1-weighted Magnetic Resonance Image (MRI) series. These features are then used as control measures for fully-3-D diffeomorphic deformations. Quantitative and qualitative evaluations show that DISCO correctly aligns the sulcal folds and gray and white matter volumes across individuals. The comparison with a recent, iconic diffeomorphic approach (DARTEL) highlights how the absence of explicit cortical landmarks may lead to the misalignment of cortical sulci. We also feature DISCO in the automatic design of an empirical sulcal template from group data. We also demonstrate how DISCO can efficiently be combined with an image-based deformation (DARTEL) to further improve the consistency and accuracy of alignment performances. Finally, we illustrate how the optimized alignment of cortical folds across subjects improves sensitivity in the detection of functional activations in a group-level analysis of neuroimaging data.

Infant brain atlases from neonates to 1- and 2-year-olds

Background

Studies for infants are usually hindered by the insufficient image contrast, especially for neonates. Prior knowledge, in the form of atlas, can provide additional guidance for the data processing such as spatial normalization, label propagation, and tissue segmentation. Although it is highly desired, there is currently no such infant atlas which caters for all these applications. The reason may be largely due to the dramatic early brain development, image processing difficulties, and the need of a large sample size.

Methodology

To this end, after several years of subject recruitment and data acquisition, we have collected a unique longitudinal dataset, involving 95 normal infants (56 males and 39 females) with MRI scanned at 3 ages, i.e., neonate, 1-year-old, and 2-year-old. State-of-the-art MR image segmentation and registration techniques were employed, to construct which include the templates (grayscale average images), tissue probability maps (TPMs), and brain parcellation maps (i.e., meaningful anatomical regions of interest) for each age group. In addition, the longitudinal correspondences between age-specific atlases were also obtained. Experiments of typical infant applications validated that the proposed atlas outperformed other atlases and is hence very useful for infant-related studies.

Conclusions

We expect that the proposed infant 0–1–2 brain atlases would be significantly conducive to structural and functional studies of the infant brains. These atlases are publicly available in our website, http://bric.unc.edu/ideagroup/free-softwares/.

Cortical sulci recognition and spatial normalization

Brain mapping techniques pair similar anatomical information across individuals. In this context, spatial normalization is mainly used to reduce inter-subject differences to improve comparisons. These techniques may benefit from anatomically identified landmarks useful to drive the registration. Automatic labeling, classification or segmentation techniques provide such labels. Most of these approaches depend strongly on normalization, as much as normalization depends on landmark accuracy. We propose in this paper a coherent Bayesian framework to automatically identify approximately 60 sulcal labels per hemisphere based on a probabilistic atlas (a mixture of spam models: Statistical Probabilistic Anatomy Map) estimating simultaneously normalization parameters. This way, the labelization method provides also with no extra computational costs a new automatically constrained registration of sulcal structures. We have limited our study to global affine and piecewise affine registration. The suggested global affine approach outperforms significantly standard affine intensity-based normalization techniques in term of sulci alignments. Further, by combining global and local joint labeling, a final mean recognition rate of 86% has been obtained with much more reliable labeling posterior probabilities. The different methods described in this paper have been integrated since the release version 3.2.1 of the BrainVISA software platform (Riviére et al., 2009).

LoAd: a locally adaptive cortical segmentation algorithm

Thickness measurements of the cerebral cortex can aid diagnosis and provide valuable information about the temporal evolution of diseases such as Alzheimer's, Huntington's, and schizophrenia. Methods that measure the thickness of the cerebral cortex from in-vivo magnetic resonance (MR) images rely on an accurate segmentation of the MR data. However, segmenting the cortex in a robust and accurate way still poses a challenge due to the presence of noise, intensity non-uniformity, partial volume effects, the limited resolution of MRI and the highly convoluted shape of the cortical folds. Beginning with a well-established probabilistic segmentation model with anatomical tissue priors, we propose three post-processing refinements: a novel modification of the prior information to reduce segmentation bias; introduction of explicit partial volume classes; and a locally varying MRF-based model for enhancement of sulci and gyri. Experiments performed on a new digital phantom, on BrainWeb data and on data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) show statistically significant improvements in Dice scores and PV estimation (p<10(-3)) and also increased thickness estimation accuracy when compared to three well established techniques.

Multi-contrast human neonatal brain atlas: application to normal neonate development analysis

MRI is a sensitive method for detecting subtle anatomic abnormalities in the neonatal brain. To optimize the usefulness for neonatal and pediatric care, systematic research, based on quantitative image analysis and functional correlation, is required. Normalization-based image analysis is one of the most effective methods for image quantification and statistical comparison. However, the application of this methodology to neonatal brain MRI scans is rare. Some of the difficulties are the rapid changes in T1 and T2 contrasts and the lack of contrast between brain structures, which prohibits accurate cross-subject image registration. Diffusion tensor imaging (DTI), which provides rich and quantitative anatomical contrast in neonate brains, is an ideal technology for normalization-based neonatal brain analysis. In this paper, we report the development of neonatal brain atlases with detailed anatomic information derived from DTI and co-registered anatomical MRI. Combined with a diffeomorphic transformation, we were able to normalize neonatal brain images to the atlas space and three-dimensionally parcellate images into 122 regions. The accuracy of the normalization was comparable to the reliability of human raters. This method was then applied to babies of 37-53 post-conceptional weeks to characterize developmental changes of the white matter, which indicated a posterior-to-anterior and a central-to-peripheral direction of maturation. We expect that future applications of this atlas will include investigations of the effect of prenatal events and the effects of preterm birth or low birth weights, as well as clinical applications, such as determining imaging biomarkers for various neurological disorders.

Towards Effcient Label Fusion by Pre-Alignment of Training Data

Label fusion is a multi-atlas segmentation approach that explicitly maintains and exploits the entire training dataset, rather than a parametric summary of it. Recent empirical evidence suggests that label fusion can achieve significantly better segmentation accuracy over classical parametric atlas methods that utilize a single coordinate frame. However, this performance gain typically comes at an increased computational cost due to the many pairwise registrations between the novel image and training images. In this work, we present a modified label fusion method that approximates these pairwise warps by first pre-registering the training images via a diffeomorphic groupwise registration algorithm. The novel image is then only registered once, to the template image that represents the average training subject. The pairwise spatial correspondences between the novel image and training images are then computed via concatenation of appropriate transformations. Our experiments on cardiac MR data suggest that this strategy for nonparametric segmentation dramatically improves computational efficiency, while producing segmentation results that are statistically indistinguishable from those obtained with regular label fusion. These results suggest that the key benefit of label fusion approaches is the underlying nonparametric inference algorithm, and not the multiple pairwise registrations.

A generative model for image segmentation based on label fusion

We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between the test image and individual training images. The training labels are then transferred to the test image and fused to compute the final segmentation of the test subject. Such label fusion methods have been shown to yield accurate segmentation, since the use of multiple registrations captures greater inter-subject anatomical variability and improves robustness against occasional registration failures. To the best of our knowledge, this manuscript presents the first comprehensive probabilistic framework that rigorously motivates label fusion as a segmentation approach. The proposed framework allows us to compare different label fusion algorithms theoretically and practically. In particular, recent label fusion or multiatlas segmentation algorithms are interpreted as special cases of our framework. We conduct two sets of experiments to validate the proposed methods. In the first set of experiments, we use 39 brain MRI scans-with manually segmented white matter, cerebral cortex, ventricles and subcortical structures-to compare different label fusion algorithms and the widely-used FreeSurfer whole-brain segmentation tool. Our results indicate that the proposed framework yields more accurate segmentation than FreeSurfer and previous label fusion algorithms. In a second experiment, we use brain MRI scans of 282 subjects to demonstrate that the proposed segmentation tool is sufficiently sensitive to robustly detect hippocampal volume changes in a study of aging and Alzheimer's Disease.

Preserved subcortical volumes and cortical thickness in women with sexual abuse-related PTSD

Posttraumatic stress disorder (PTSD) has been frequently associated with volumetric reductions of grey matter structures (e.g. hippocampus and anterior cingulate), but these results remain controversial, especially in female non-combat-related samples. The present study aimed at exploring whole-brain structures in women with sexual abuse-related PTSD on the basis of cortical and subcortical structure comparisons to a matched pair sample that was well-controlled. Seventeen young women who had experienced sexual abuse and who had a diagnosis of chronic PTSD based on the Clinician Administered PTSD Scale for DSM-IV and 17 healthy controls individually matched for age and years of education were consecutively recruited. Both groups underwent structural magnetic resonance imaging and psychiatric assessment of the main disorders according to Axis I of DSM-IV. The resulting scans were analyzed using automated cortical and subcortical volumetric quantifications. Compared with controls, PTSD subjects displayed normal global and regional brain volumes and cortical thicknesses. Our results indicate preserved subcortical volumes and cortical thickness in a sample of female survivors of sexual abuse with PTSD. The authors discuss potential differences between neural mechanisms of sexual abuse-related PTSD and war-related PTSD.

Learning task-optimal registration cost functions for localizing cytoarchitecture and function in the cerebral cortex

Image registration is typically formulated as an optimization problem with multiple tunable, manually set parameters. We present a principled framework for learning thousands of parameters of registration cost functions, such as a spatially-varying tradeoff between the image dissimilarity and regularization terms. Our approach belongs to the classic machine learning framework of model selection by optimization of cross-validation error. This second layer of optimization of cross-validation error over and above registration selects parameters in the registration cost function that result in good registration as measured by the performance of the specific application in a training data set. Much research effort has been devoted to developing generic registration algorithms, which are then specialized to particular imaging modalities, particular imaging targets and particular postregistration analyses. Our framework allows for a systematic adaptation of generic registration cost functions to specific applications by learning the "free" parameters in the cost functions. Here, we consider the application of localizing underlying cytoarchitecture and functional regions in the cerebral cortex by alignment of cortical folding. Most previous work assumes that perfectly registering the macro-anatomy also perfectly aligns the underlying cortical function even though macro-anatomy does not completely predict brain function. In contrast, we learn 1) optimal weights on different cortical folds or 2) optimal cortical folding template in the generic weighted sum of squared differences dissimilarity measure for the localization task. We demonstrate state-of-the-art localization results in both histological and functional magnetic resonance imaging data sets.

Reliability and validity of MRI-based automated volumetry software relative to auto-assisted manual measurement of subcortical structures in HIV-infected patients from a multisite study

The automated volumetric output of FreeSurfer and Individual Brain Atlases using Statistical Parametric Mapping (IBASPM), two widely used and well published software packages, was examined for accuracy and consistency relative to auto-assisted manual (AAM) tracings (i.e., manual correction of automated output) when measuring the caudate, putamen, amygdala, and hippocampus in the baseline scans of 120 HIV-infected patients (86.7% male, 47.3+/-6.3y.o., mean HIV duration 12.0+/-6.3years) from the NIH-funded HIV Neuroimaging Consortium (HIVNC) cohort. The data was examined for accuracy and consistency relative to auto-assisted manual tracing, and construct validity was assessed by correlating automated and AAM volumetric measures with relevant clinical measures of HIV progression. When results were averaged across all patients in the eight structures examined, FreeSurfer achieved lower absolute volume difference in five, higher sensitivity in seven, and higher spatial overlap in all eight structures. Additionally, FreeSurfer results exhibited less variability in all measures. Output from both methods identified discrepant correlations with clinical measures of HIV progression relative to AAM segmented data. Overall, FreeSurfer proved more effective in the context of subcortical volumetry in HIV-patients, particularly in a multisite cohort study such as this. These findings emphasize that regardless of the automated method used, visual inspection of segmentation output, along with manual correction if necessary, remains critical to ensuring the validity of reported results.

Spherical demons: fast diffeomorphic landmark-free surface registration

We present the Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizors for the modified Demons objective function can be efficiently approximated on the sphere using iterative smoothing. Based on one parameter subgroups of diffeomorphisms, the resulting registration is diffeomorphic and fast. The Spherical Demons algorithm can also be modified to register a given spherical image to a probabilistic atlas. We demonstrate two variants of the algorithm corresponding to warping the atlas or warping the subject. Registration of a cortical surface mesh to an atlas mesh, both with more than 160 k nodes requires less than 5 min when warping the atlas and less than 3 min when warping the subject on a Xeon 3.2 GHz single processor machine. This is comparable to the fastest nondiffeomorphic landmark-free surface registration algorithms. Furthermore, the accuracy of our method compares favorably to the popular FreeSurfer registration algorithm. We validate the technique in two different applications that use registration to transfer segmentation labels onto a new image 1) parcellation of in vivo cortical surfaces and 2) Brodmann area localization in ex vivo cortical surfaces.

Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation

Neonatal brain MRI segmentation is a challenging problem due to its poor image quality. Atlas-based segmentation approaches have been widely used for guiding brain tissue segmentation. Existing brain atlases are usually constructed by equally averaging pre-segmented images in a population. However, such approaches diminish local inter-subject structural variability and thus lead to lower segmentation guidance capability. To deal with this problem, we propose a multi-region-multi-reference framework for atlas-based neonatal brain segmentation. For each region of a brain parcellation, a population of spatially normalized pre-segmented images is clustered into a number of sub-populations. Each sub-population of a region represents an independent distribution from which a regional probability atlas can be generated. A selection of these regional atlases, across different sub-regions, will in the end be adaptively combined to form an overall atlas specific to the query image. Given a query image, the determination of the appropriate set of regional atlases is achieved by comparing the query image regionally with the reference, or exemplar, of each sub-population. Upon obtaining an overall atlas, an atlas-based joint registration-segmentation strategy is employed to segment the query image. Since the proposed method generates an atlas which is significant more similar to the query image than the traditional average-shape atlas, better tissue segmentation results can be expected. This is validated by applying the proposed method on a large set of neonatal brain images available in our institute. Experimental results on a randomly selected set of 10 neonatal brain images indicate that the proposed method achieves higher tissue overlap rates and lower standard deviations (SDs) in comparison with manual segmentations, i.e., 0.86 (SD 0.02) for GM, 0.83 (SD 0.03) for WM, and 0.80 (SD 0.05) for CSF. The proposed method also outperforms two other average-shape atlas-based segmentation methods.

Construction of neuroanatomical shape complex atlas from 3D brain MRI

This paper proposes a novel technique for constructing a neuroanatomical shape complex atlas using an information geometry framework. A shape complex is a collection of shapes in a local neighborhood. We represent the boundary of the entire shape complex using the zero level set of a distance function S(x). The spatial relations between the different anatomical structures constituting the shape complex are captured via the distance transform. We then leverage the well known relationship between the stationary state wave function psi(x) of the Schrödinger equation -h2nabla2 psi + psi = 0 and the eikonal equation //nablaS// = 1 satisfied by any distance function S(x). This leads to a one-to-one map between psi(x) and S(x) and allows for recovery of S(x) from psi(x) through an explicit mathematical relationship. Since the wave function can be regarded as a square-root density function, we are able to exploit this connection and convert shape complex distance transforms into probability density functions. Furthermore, square-root density functions can be seen as points on a unit hypersphere whose Riemannian structure is fully known. A shape complex atlas is constructed by first computing the Karcher mean psi(x) of the wave functions, followed by an inverse mapping of the estimated mean back to the space of distance transforms in order to realize the atlas. We demonstrate the shape complex atlas computation via a set of experiments on a population of brain MRI scans. We also present modes of variation from the computed atlas for the control population to demonstrate the shape complex variability.

DT-REFinD: diffusion tensor registration with exact finite-strain differential

In this paper, we propose the DT-REFinD algorithm for the diffeomorphic nonlinear registration of diffusion tensor images. Unlike scalar images, deforming tensor images requires choosing both a reorientation strategy and an interpolation scheme. Current diffusion tensor registration algorithms that use full tensor information face difficulties in computing the differential of the tensor reorientation strategy and consequently, these methods often approximate the gradient of the objective function. In the case of the finite-strain (FS) reorientation strategy, we borrow results from the pose estimation literature in computer vision to derive an analytical gradient of the registration objective function. By utilizing the closed-form gradient and the velocity field representation of one parameter subgroups of diffeomorphisms, the resulting registration algorithm is diffeomorphic and fast. We contrast the algorithm with a traditional FS alternative that ignores the reorientation in the gradient computation. We show that the exact gradient leads to significantly better registration at the cost of computation time. Independently of the choice of Euclidean or Log-Euclidean interpolation and sum of squared differences dissimilarity measure, the exact gradient achieves better alignment over an entire spectrum of deformation penalties. Alignment quality is assessed with a battery of metrics including tensor overlap, fractional anisotropy, inverse consistency and closeness to synthetic warps. The improvements persist even when a different reorientation scheme, preservation of principal directions, is used to apply the final deformations.