Reconstruction of the human cerebral cortex from magnetic resonance images

Toward evaluation of multiresolution cortical thickness estimation with FreeSurfer, MaCRUISE, and BrainSuite

Advances in Magnetic Resonance Imaging hardware and methodologies allow for promoting the cortical morphometry with submillimeter spatial resolution. In this paper, we generated 3D self-enhanced high-resolution (HR) MRI imaging, by adapting 1 deep learning architecture, and 3 standard pipelines, FreeSurfer, MaCRUISE, and BrainSuite, have been collectively employed to evaluate the cortical thickness. We systematically investigated the differences in cortical thickness estimation for MRI sequences at multiresolution homologously originated from the native image. It has been revealed that there systematically exhibited the preferences in determining both inner and outer cortical surfaces at higher resolution, yielding most deeper cortical surface placements toward GM/WM or GM/CSF boundaries, which directs a consistent reduction tendency of mean cortical thickness estimation; on the contrary, the lower resolution data will most probably provide a more coarse and rough evaluation in cortical surface reconstruction, resulting in a relatively thicker estimation. Although the differences of cortical thickness estimation at the diverse spatial resolution varied with one another, almost all led to roughly one-sixth to one-fifth significant reduction across the entire brain at the HR, independent to the pipelines we applied, which emphasizes on generally coherent improved accuracy in a data-independent manner and endeavors to cost-efficiency with quantitative opportunities.

Multiple Relevant Feature Ensemble Selection Based on Multilayer Co-Evolutionary Consensus MapReduce

Although feature selection for large data has been intensively investigated in data mining, machine learning, and pattern recognition, the challenges are not just to invent new algorithms to handle noisy and uncertain large data in applications, but rather to link the multiple relevant feature sources, structured, or unstructured, to develop an effective feature reduction method. In this paper, we propose a multiple relevant feature ensemble selection (MRFES) algorithm based on multilayer co-evolutionary consensus MapReduce (MCCM). We construct an effective MCCM model to handle feature ensemble selection of large-scale datasets with multiple relevant feature sources, and explore the unified consistency aggregation between the local solutions and global dominance solutions achieved by the co-evolutionary memeplexes, which participate in the cooperative feature ensemble selection process. This model attempts to reach a mutual decision agreement among co-evolutionary memeplexes, which calls for the need for mechanisms to detect some noncooperative co-evolutionary behaviors and achieve better Nash equilibrium resolutions. Extensive experimental comparative studies substantiate the effectiveness of MRFES to solve large-scale dataset problems with the complex noise and multiple relevant feature sources on some well-known benchmark datasets. The algorithm can greatly facilitate the selection of relevant feature subsets coming from the original feature space with better accuracy, efficiency, and interpretability. Moreover, we apply MRFES to human cerebral cortex-based classification prediction. Such successful applications are expected to significantly scale up classification prediction for large-scale and complex brain data in terms of efficiency and feasibility.

Combined Use of MRI, fMRIand Cognitive Data for Alzheimer’s Disease: Preliminary Results

MRI can favor clinical diagnosis providing morphological and functional information of several neurological disorders. This paper deals with the problem of exploiting both data, in a combined way, to develop a tool able to support clinicians in the study and diagnosis of Alzheimer’s Disease (AD). In this work, 69 subjects from the ADNI open database, 33 AD patients and 36 healthy controls, were analyzed. The possible existence of a relationship between brain structure modifications and altered functions between patients and healthy controls was investigated performing a correlation analysis on brain volume, calculated from the MRI image, the clustering coefficient, derived from fRMI acquisitions, and the Mini Mental Score Examination (MMSE). A statistically-significant correlation was found only in four ROIs after Bonferroni’s correction. The correlation analysis alone was still not sufficient to provide a reliable and powerful clinical tool in AD diagnosis however. Therefore, a machine learning strategy was studied by training a set of support vector machine classifiers comparing different features. The use of a unimodal approach led to unsatisfactory results, whereas the multimodal approach, i.e., the synergistic combination of MRI, fMRI, and MMSE features, resulted in an accuracy of 95.65%, a specificity of 97.22%, and a sensibility of 93.93%.

Consistent cortical reconstruction and multi-atlas brain segmentation

Whole brain segmentation and cortical surface reconstruction are two essential techniques for investigating the human brain. Spatial inconsistences, which can hinder further integrated analyses of brain structure, can result due to these two tasks typically being conducted independently of each other. FreeSurfer obtains self-consistent whole brain segmentations and cortical surfaces. It starts with subcortical segmentation, then carries out cortical surface reconstruction, and ends with cortical segmentation and labeling. However, this "segmentation to surface to parcellation" strategy has shown limitations in various cohorts such as older populations with large ventricles. In this work, we propose a novel "multi-atlas segmentation to surface" method called Multi-atlas CRUISE (MaCRUISE), which achieves self-consistent whole brain segmentations and cortical surfaces by combining multi-atlas segmentation with the cortical reconstruction method CRUISE. A modification called MaCRUISE(+) is designed to perform well when white matter lesions are present. Comparing to the benchmarks CRUISE and FreeSurfer, the surface accuracy of MaCRUISE and MaCRUISE(+) is validated using two independent datasets with expertly placed cortical landmarks. A third independent dataset with expertly delineated volumetric labels is employed to compare segmentation performance. Finally, 200MR volumetric images from an older adult sample are used to assess the robustness of MaCRUISE and FreeSurfer. The advantages of MaCRUISE are: (1) MaCRUISE constructs self-consistent voxelwise segmentations and cortical surfaces, while MaCRUISE(+) is robust to white matter pathology. (2) MaCRUISE achieves more accurate whole brain segmentations than independently conducting the multi-atlas segmentation. (3) MaCRUISE is comparable in accuracy to FreeSurfer (when FreeSurfer does not exhibit global failures) while achieving greater robustness across an older adult population. MaCRUISE has been made freely available in open source.

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.

LOGISMOS-B: layered optimal graph image segmentation of multiple objects and surfaces for the brain

Automated reconstruction of the cortical surface is one of the most challenging problems in the analysis of human brain magnetic resonance imaging (MRI). A desirable segmentation must be both spatially and topologically accurate, as well as robust and computationally efficient. We propose a novel algorithm, LOGISMOS-B, based on probabilistic tissue classification, generalized gradient vector flows and the LOGISMOS graph segmentation framework. Quantitative results on MRI datasets from both healthy subjects and multiple sclerosis patients using a total of 16,800 manually placed landmarks illustrate the excellent performance of our algorithm with respect to spatial accuracy. Remarkably, the average signed error was only 0.084 mm for the white matter and 0.008 mm for the gray matter, even in the presence of multiple sclerosis lesions. Statistical comparison shows that LOGISMOS-B produces a significantly more accurate cortical reconstruction than FreeSurfer, the current state-of-the-art approach (p << 0.001). Furthermore, LOGISMOS-B enjoys a run time that is less than a third of that of FreeSurfer, which is both substantial, considering the latter takes 10 h/subject on average, and a statistically significant speedup.

Measuring the dynamic longitudinal cortex development in infants by reconstruction of temporally consistent cortical surfaces

Quantitative measurement of the dynamic longitudinal cortex development during early postnatal stages is of great importance to understand the early cortical structural and functional development. Conventional methods usually reconstruct the cortical surfaces of longitudinal images from the same subject independently, which often generate longitudinally-inconsistent cortical surfaces and thus lead to inaccurate measurement of cortical changes, especially for vertex-wise mapping of cortical development. This paper aims to address this problem by presenting a method to reconstruct temporally-consistent cortical surfaces from longitudinal infant brain MR images, for accurate and consistent measurement of the dynamic cortex development in infants. Specifically, the longitudinal development of the inner cortical surface is first modeled by a deformable growth sheet with elasto-plasticity property to establish longitudinally smooth correspondences of the inner cortical surfaces. Then, the modeled longitudinal inner cortical surfaces are jointly deformed to locate both inner and outer cortical surfaces with a spatial-temporal deformable surface method. The method has been applied to 13 healthy infants, each with 6 serial MR scans acquired at 2 weeks, 3 months, 6 months, 9 months, 12 months and 18 months of age. Experimental results showed that our method with the incorporated longitudinal constraints can reconstruct the longitudinally-dynamic cortical surfaces from serial infant MR images more consistently and accurately than the previously published methods. By using our method, for the first time, we can characterize the vertex-wise longitudinal cortical thickness development trajectory at multiple time points in the first 18 months of life. Specifically, we found the highly age-related and regionally-heterogeneous developmental trajectories of the cortical thickness during this period, with the cortical thickness increased most from 3 to 6 months (16.2%) and least from 9 to 12 months (less than 0.1%). Specifically, the central sulcus only underwent significant increase of cortical thickness from 6 to 9 months and the occipital cortex underwent significant increase from 0 to 9 months, while the frontal, temporal and parietal cortices grew continuously in this first 18 months of life. The adult-like spatial patterns of cortical thickness were generally present at 18 months of age. These results provided detailed insights into the dynamic trajectory of the cortical thickness development in infants.

A novel tool for segmenting 3D medical images based on generalized cylinders and active surfaces

Three-dimensional (3D) medical imaging has been incorporated in routine clinical practice, since the required infrastructure has become increasingly affordable. New algorithms and applications are needed to serve the additional image processing and analysis functions in 3D space. In this work we propose a system for semi-automatic modeling and segmentation of elongated salient and anatomical objects in 3D medical images. The proposed methodology is based on a novel mathematical formalization of a well-known class of geometric primitives, namely generalized cylinders (GCs), which exhibits advantages over the existing parametric definition. Since the anatomical objects have to be modeled by their intersection with the transverse image planes, the proposed methodology includes also a new seeded region growing (SRG) segmentation algorithm for ellipse detection in 2D images, based on a priori shape knowledge. Finally, the resulting GC model is used to initialize an active surface (AS) segmentation method, in order to accurately delineate the required object. In this work we present the proposed algorithms in detail, along with the evaluation of the accuracy of the model-based segmentation by experts. Results show that elongated objects like the aorta and the trachea may be segmented with sensitivity between 90% and 95%. The proposed SRG-ellipse detector requires minimal user-initialization and its executions requires only few seconds for each image slice on an average laptop. The evolution of the AS requires less than one second per iteration for a typical CT image. Comparisons are provided with state of the art semi-automatic medical image processing software, which validate the merit of the proposed work.

System for integrated neuroimaging analysis and processing of structure

Mapping brain structure in relation to neurological development, function, plasticity, and disease is widely considered to be one of the most essential challenges for opening new lines of neuro-scientific inquiry. Recent developments with MRI analysis of structural connectivity, anatomical brain segmentation, cortical surface parcellation, and functional imaging have yielded fantastic advances in our ability to probe the neurological structure-function relationship in vivo. To date, the image analysis efforts in each of these areas have typically focused on a single modality. Here, we extend the cortical reconstruction using implicit surface evolution (CRUISE) methodology to perform efficient, consistent, and topologically correct analyses in a natively multi-parametric manner. This effort combines and extends state-of-the-art techniques to simultaneously consider and analyze structural and diffusion information alongside quantitative and functional imaging data. Robust and consistent estimates of the cortical surface extraction, cortical labeling, diffusion-inferred contrasts, diffusion tractography, and subcortical parcellation are demonstrated in a scan-rescan paradigm. Accompanying this demonstration, we present a fully automated software system complete with validation data.

Mapping region-specific longitudinal cortical surface expansion from birth to 2 years of age

The human cerebral cortex develops rapidly and dynamically in the first 2 years of life. It has been shown that cortical surface expansion from term infant to adult is highly nonuniform in a cross-sectional study. However, little is known about the longitudinal cortical surface expansion during early postnatal stages. In this article, we generate the first longitudinal surface-based atlases of human cortical structures at 0, 1, and 2 years of age from 73 healthy subjects. On the basis of the surface-based atlases, we study the longitudinal cortical surface expansion in the first 2 years of life and find that cortical surface expansion is age related and region specific. In the first year, cortical surface expands dramatically, with an average expansion of 1.80 times. In particular, regions of superior and medial temporal, superior parietal, medial orbitofrontal, lateral anterior prefrontal, occipital cortices, and postcentral gyrus expand relatively larger than other regions. In the second year, cortical surface still expands substantially, with an average expansion of 1.20 times. In particular, regions of superior and middle frontal, orbitofrontal, inferior temporal, inferior parietal, and superior parietal cortices expand relatively larger than other regions. These region-specific patterns of cortical surface expansion are related to cognitive and functional development at these stages.

Cortical Surface Reconstruction from High-Resolution MR Brain Images

Reconstruction of the cerebral cortex from magnetic resonance (MR) images is an important step in quantitative analysis of the human brain structure, for example, in sulcal morphometry and in studies of cortical thickness. Existing cortical reconstruction approaches are typically optimized for standard resolution (~1 mm) data and are not directly applicable to higher resolution images. A new PDE-based method is presented for the automated cortical reconstruction that is computationally efficient and scales well with grid resolution, and thus is particularly suitable for high-resolution MR images with submillimeter voxel size. The method uses a mathematical model of a field in an inhomogeneous dielectric. This field mapping, similarly to a Laplacian mapping, has nice laminar properties in the cortical layer, and helps to identify the unresolved boundaries between cortical banks in narrow sulci. The pial cortical surface is reconstructed by advection along the field gradient as a geometric deformable model constrained by topology-preserving level set approach. The method's performance is illustrated on exvivo images with 0.25–0.35 mm isotropic voxels. The method is further evaluated by cross-comparison with results of the FreeSurfer software on standard resolution data sets from the OASIS database featuring pairs of repeated scans for 20 healthy young subjects.

Magnetic Resonance Image Analysis for Brain CAD Systems with Machine Learning

This chapter describes the image analysis for brain Computer-Aided Diagnosis (CAD) systems with machine learning techniques, which could assist radiologists in the detection of such brain diseases as asymptomatic unruptured aneurysms, Alzheimer’s Disease (AD), vascular dementia, and Multiple Sclerosis (MS) by magnetic resonance imaging. Image analysis in CAD systems consists of image enhancement, initial detection, and image feature extraction, including segmentation. In addition, the authors review the classification of true and false positives using machine learning techniques, as well as the evaluation methods and development cycle for CAD systems.

Longitudinally guided level sets for consistent tissue segmentation of neonates

Quantification of brain development as well as disease-induced pathologies in neonates often requires precise delineation of white matter, grey matter and cerebrospinal fluid. Unlike adults, tissue segmentation in neonates is significantly more challenging due to the inherently lower tissue contrast. Most existing methods take a voxel-based approach and are limited to working with images from a single time-point, even though longitudinal scans are available. We take a different approach by taking advantage of the fact that the pattern of the major sulci and gyri are already present in the neonates and generally preserved but fine-tuned during brain development. That is, the segmentation of late-time-point image can be used to guide the segmentation of neonatal image. Accordingly, we propose a novel longitudinally guided level-sets method for consistent neonatal image segmentation by combining local intensity information, atlas spatial prior, cortical thickness constraint, and longitudinal information into a variational framework. The minimization of the proposed energy functional is strictly derived from a variational principle. Validation performed on both simulated and in vivo neonatal brain images shows promising results.

NURBS-Based Segmentation of the Brain in Medical Images

Extracting the human brain from magnetic resonance head scans is difficult because of its highly convoluted and nonuniform geometry. A technique based on Non-Uniform Rational B-Splines (NURBS) surfaces and energy minimizing deformable models to extract and visualize the brain surface patterns accurately from magnetic resonance head scans is presented. The weighting parameter that comes with the NURBS definition is explored to attract the surface into regions showing high curvature. The weight at each control point is adjusted automatically according to the curvature properties of the evolving surface. This process facilitates a deformable model with increased local flexibility that adapts to complex geometrical features of the brain surface. The results show that the proposed model is capable of capturing the correct brain surface with a higher accuracy than the existing techniques.

Consistent reconstruction of cortical surfaces from longitudinal brain MR images

Accurate and consistent reconstruction of cortical surfaces from longitudinal human brain MR images is of great importance in studying longitudinal subtle change of the cerebral cortex. This paper presents a novel deformable surface method for consistent and accurate reconstruction of inner, central and outer cortical surfaces from longitudinal brain MR images. Specifically, the cortical surfaces of the group-mean image of all aligned longitudinal images of the same subject are first reconstructed by a deformable surface method, which is driven by a force derived from the Laplace's equation. And then the longitudinal cortical surfaces are consistently reconstructed by jointly deforming the cortical surfaces of the group-mean image to all longitudinal images. The proposed method has been successfully applied to two sets of longitudinal human brain MR images. Both qualitative and quantitative experimental results demonstrate the accuracy and consistency of the proposed method. Furthermore, the reconstructed longitudinal cortical surfaces are used to measure the longitudinal changes of cortical thickness in both normal and diseased groups, where the overall decline trend of cortical thickness has been clearly observed. Meanwhile, the longitudinal cortical thickness also shows its potential in distinguishing different clinical groups.

A computational growth model for measuring dynamic cortical development in the first year of life

Human cerebral cortex develops extremely fast in the first year of life. Quantitative measurement of cortical development during this early stage plays an important role in revealing the relationship between cortical structural and high-level functional development. This paper presents a computational growth model to simulate the dynamic development of the cerebral cortex from birth to 1 year old by modeling the cerebral cortex as a deformable elastoplasticity surface driven via a growth model. To achieve a high accuracy, a guidance model is also incorporated to estimate the growth parameters and cortical shapes at later developmental stages. The proposed growth model has been applied to 10 healthy subjects with longitudinal brain MR images acquired at every 3 months from birth to 1 year old. The experimental results show that our proposed method can capture the dynamic developmental process of the cortex, with the average surface distance error smaller than 0.6 mm compared with the ground truth surfaces, and the results also show that 1) the curvedness and sharpness decrease from 2 weeks to 12 months and 2) the frontal lobe shows rapidly increasing cortical folding during this period, with relatively slower increase of the cortical folding in the occipital and parietal lobes.

Automatic segmentation of neonatal images using convex optimization and coupled level sets

Accurate segmentation of neonatal brain MR images remains challenging mainly due to their poor spatial resolution, inverted contrast between white matter and gray matter, and high intensity inhomogeneity. Most existing methods for neonatal brain segmentation are atlas-based and voxel-wise. Although active contour/surface models with geometric information constraint have been successfully applied to adult brain segmentation, they are not fully explored in the neonatal image segmentation. In this paper, we propose a novel neonatal image segmentation method by combining local intensity information, atlas spatial prior, and cortical thickness constraint in a single level-set framework. Besides, we also provide a robust and reliable tissue surface initialization for the proposed method by using a convex optimization technique. Thus, tissue segmentation, as well as inner and outer cortical surface reconstruction, can be obtained simultaneously. The proposed method has been tested on a large neonatal dataset, and the validation on 10 neonatal brain images (with manual segmentations) shows very promising results.

Topological correction of brain surface meshes using spherical harmonics

Surface reconstruction methods allow advanced analysis of structural and functional brain data beyond what can be achieved using volumetric images alone. Automated generation of cortical surface meshes from 3D brain MRI often leads to topological defects and geometrical artifacts that must be corrected to permit subsequent analysis. Here, we propose a novel method to repair topological defects using a surface reconstruction that relies on spherical harmonics. First, during reparameterization of the surface using a tiled platonic solid, the original MRI intensity values are used as a basis to select either a "fill" or "cut" operation for each topological defect. We modify the spherical map of the uncorrected brain surface mesh, such that certain triangles are favored while searching for the bounding triangle during reparameterization. Then, a low-pass filtered alternative reconstruction based on spherical harmonics is patched into the reconstructed surface in areas that previously contained defects. Self-intersections are repaired using a local smoothing algorithm that limits the number of affected points to less than 0.1% of the total, and as a last step, all modified points are adjusted based on the T1 intensity. We found that the corrected reconstructions have reduced distance error metrics compared with a "gold standard" surface created by averaging 12 scans of the same brain. Ninety-three percent of the topological defects in a set of 10 scans of control subjects were accurately corrected. The entire process takes 6-8 min of computation time. Further improvements are discussed, especially regarding the use of the T1-weighted image to make corrections.

A comparison of voxel and surface based cortical thickness estimation methods

Cortical thickness estimation performed in-vivo via magnetic resonance imaging is an important technique for the diagnosis and understanding of the progression of neurodegenerative diseases. Currently, two different computational paradigms exist, with methods generally classified as either surface or voxel-based. This paper provides a much needed comparison of the surface-based method FreeSurfer and two voxel-based methods using clinical data. We test the effects of computing regional statistics using two different atlases and demonstrate that this makes a significant difference to the cortical thickness results. We assess reproducibility, and show that FreeSurfer has a regional standard deviation of thickness difference on same day scans that is significantly lower than either a Laplacian or Registration based method and discuss the trade off between reproducibility and segmentation accuracy caused by bending energy constraints. We demonstrate that voxel-based methods can detect similar patterns of group-wise differences as well as FreeSurfer in typical applications such as producing group-wise maps of statistically significant thickness change, but that regional statistics can vary between methods. We use a Support Vector Machine to classify patients against controls and did not find statistically significantly different results with voxel based methods compared to FreeSurfer. Finally we assessed longitudinal performance and concluded that currently FreeSurfer provides the most plausible measure of change over time, with further work required for voxel based methods.

On the EEG/MEG forward problem solution for distributed cortical sources

In studies of EEG/MEG problems involving cortical sources, the cortex may be modeled by a 2-D manifold inside the brain. In such cases the primary or impressed current density over this manifold is usually approximated by a set of dipolar sources located at the vertices of the cortical surface tessellation. In this study, we analyze the different errors induced by this approximation on the EEG/MEG forward problem. Our results show that in order to obtain more accurate solutions of the forward problems with the multiple dipoles approximation, the moments of the dipoles should be weighted by the area of the surrounding triangles, or using an alternative approximation of the primary current as a constant or linearly varying current density over plane triangular elements of the cortical surface tessellation. This should be taken into account when computing the lead field matrix for solving the EEG/MEG inverse problem in brain imaging methods.

Consistent sulcal parcellation of longitudinal cortical surfaces

Automated accurate and consistent sulcal parcellation of longitudinal cortical surfaces is of great importance in studying longitudinal morphological and functional changes of human brains, since longitudinal cortical changes are normally very subtle, especially in aging brains. However, applying the existing methods (which were typically developed for cortical sulcal parcellation of a single cortical surface) independently to longitudinal cortical surfaces might generate longitudinally-inconsistent results. To overcome this limitation, this paper presents a novel energy function based method for accurate and consistent sulcal parcellation of longitudinal cortical surfaces. Specifically, both spatial and temporal smoothness are imposed in the energy function to obtain consistent longitudinal sulcal parcellation results. The energy function is efficiently minimized by a graph cut method. The proposed method has been successfully applied to sulcal parcellation of both real and simulated longitudinal inner cortical surfaces of human brain MR images. Both qualitative and quantitative evaluation results demonstrate the validity of the proposed method.

Consistent reconstruction of cortical surfaces from longitudinal brain MR images

Accurate and consistent reconstruction of cortical surfaces from longitudinal human brain MR images is of great importance in studying subtle morphological changes of the cerebral cortex. This paper presents a new deformable surface method for consistent and accurate reconstruction of inner, central and outer cortical surfaces from longitudinal MR images. Specifically, the cortical surfaces of the group-mean image of all aligned longitudinal images of the same subject are first reconstructed by a deformable surface method driven by a force derived from the Laplace's equation. And then the longitudinal cortical surfaces are consistently reconstructed by jointly deforming the cortical surfaces from the group-mean image to all longitudinal images. The proposed method has been successfully applied to both simulated and real longitudinal images, demonstrating its validity.

CLADA: cortical longitudinal atrophy detection algorithm

Measurement of changes in brain cortical thickness is useful for the assessment of regional gray matter atrophy in neurodegenerative conditions. A new longitudinal method, called CLADA (cortical longitudinal atrophy detection algorithm), has been developed for the measurement of changes in cortical thickness in magnetic resonance images (MRI) acquired over time. CLADA creates a subject-specific cortical model which is longitudinally deformed to match images from individual time points. The algorithm was designed to work reliably for lower resolution images, such as the MRIs with 1×1×5 mm(3) voxels previously acquired for many clinical trials in multiple sclerosis (MS). CLADA was evaluated to determine reproducibility, accuracy, and sensitivity. Scan-rescan variability was 0.45% for images with 1mm(3) isotropic voxels and 0.77% for images with 1×1×5 mm(3) voxels. The mean absolute accuracy error was 0.43 mm, as determined by comparison of CLADA measurements to cortical thickness measured directly in post-mortem tissue. CLADA's sensitivity for correctly detecting at least 0.1mm change was 86% in a simulation study. A comparison to FreeSurfer showed good agreement (Pearson correlation=0.73 for global mean thickness). CLADA was also applied to MRIs acquired over 18 months in secondary progressive MS patients who were imaged at two different resolutions. Cortical thinning was detected in this group in both the lower and higher resolution images. CLADA detected a higher rate of cortical thinning in MS patients compared to healthy controls over 2 years. These results show that CLADA can be used for reliable measurement of cortical atrophy in longitudinal studies, even in lower resolution images.

A computational model of cerebral cortex folding

The geometric complexity and variability of the human cerebral cortex have long intrigued the scientific community. As a result, quantitative description of cortical folding patterns and the understanding of underlying folding mechanisms have emerged as important research goals. This paper presents a computational 3D geometric model of cerebral cortex folding initialized by MRI data of a human fetal brain and deformed under the governance of a partial differential equation modeling cortical growth. By applying different simulation parameters, our model is able to generate folding convolutions and shape dynamics of the cerebral cortex. The simulations of this 3D geometric model provide computational experimental support to the following hypotheses: (1) Mechanical constraints of the skull regulate the cortical folding process. (2) The cortical folding pattern is dependent on the global cell growth rate of the whole cortex. (3) The cortical folding pattern is dependent on relative rates of cell growth in different cortical areas. (4) The cortical folding pattern is dependent on the initial geometry of the cortex.

Brain MRI tissue classification based on local Markov random fields

A new method for tissue classification of brain magnetic resonance images (MRI) of the brain is proposed. The method is based on local image models where each models the image content in a subset of the image domain. With this local modeling approach, the assumption that tissue types have the same characteristics over the brain needs not to be evoked. This is important because tissue type characteristics, such as T1 and T2 relaxation times and proton density, vary across the individual brain and the proposed method offers improved protection against intensity non-uniformity artifacts that can hamper automatic tissue classification methods in brain MRI. A framework in which local models for tissue intensities and Markov Random Field (MRF) priors are combined into a global probabilistic image model is introduced. This global model will be an inhomogeneous MRF and it can be solved by standard algorithms such as iterative conditional modes. The division of the whole image domain into local brain regions possibly having different intensity statistics is realized via sub-volume probabilistic atlases. Finally, the parameters for the local intensity models are obtained without supervision by maximizing the weighted likelihood of a certain finite mixture model. For the maximization task, a novel genetic algorithm almost free of initialization dependency is applied. The algorithm is tested on both simulated and real brain MR images. The experiments confirm that the new method offers a useful improvement of the tissue classification accuracy when the basic tissue characteristics vary across the brain and the noise level of the images is reasonable. The method also offers better protection against intensity non-uniformity artifact than the corresponding method based on a global (whole image) modeling scheme.

Joint brain parametric T1-map segmentation and RF inhomogeneity calibration

We propose a constrained version of Mumford and Shah's (1989) segmentation model with an information-theoretic point of view in order to devise a systematic procedure to segment brain magnetic resonance imaging (MRI) data for parametric T(1)-Map and T(1)-weighted images, in both 2-D and 3D settings. Incorporation of a tuning weight in particular adds a probabilistic flavor to our segmentation method, and makes the 3-tissue segmentation possible. Moreover, we proposed a novel method to jointly segment the T(1)-Map and calibrate RF Inhomogeneity (JSRIC). This method assumes the average T(1) value of white matter is the same across transverse slices in the central brain region, and JSRIC is able to rectify the flip angles to generate calibrated T(1)-Maps. In order to generate an accurate T(1)-Map, the determination of optimal flip-angles and the registration of flip-angle images are examined. Our JSRIC method is validated on two human subjects in the 2D T(1)-Map modality and our segmentation method is validated by two public databases, BrainWeb and IBSR, of T(1)-weighted modality in the 3D setting.

A combined region growing and deformable model method for extraction of closed surfaces in 3D CT and MRI scans

Image segmentation of 3D medical images is a challenging problem with several still not totally solved practical issues, such as noise interference, variable object structures and image artifacts. This paper describes a hybrid 3D image segmentation method which combines region growing and deformable models to obtain accurate and topologically preserving surface structures of anatomical objects of interest. The proposed strategy starts by determining a rough but robust approximation of the objects using a region-growing algorithm. Then, the closed surface mesh that encloses the region is constructed and used as the initial geometry of a deformable model for the final refinement. This integrated strategy provides an alternative solution to one of the flaws of traditional deformable models, achieving good refinements of internal surfaces in few steps. Experimental segmentation results of complex anatomical structures on both simulated and real data from MRI scans are presented, and the method is assessed by comparing with standard reference segmentations of head MRI. The evaluation was mainly based on the average overlap measure, which was tested on the segmentation of white matter, corresponding to a simulated brain data set, showing excellent performance exceeding 90% accuracy. In addition, the algorithm was applied to the detection of anatomical head structures on two real MRI and one CT data set. The final reconstructions resulting from the deformable models produce high quality meshes suitable for 3D visualization and further numerical analysis. The obtained results show that the approach achieves high quality segmentations with low computational complexity.

Atlas-based segmentation of 3D cerebral structures with competitive level sets and fuzzy control

We propose a novel approach for the simultaneous segmentation of multiple structures with competitive level sets driven by fuzzy control. To this end, several contours evolve simultaneously toward previously defined anatomical targets. A fuzzy decision system combines the a priori knowledge provided by an anatomical atlas with the intensity distribution of the image and the relative position of the contours. This combination automatically determines the directional term of the evolution equation of each level set. This leads to a local expansion or contraction of the contours, in order to match the boundaries of their respective targets. Two applications are presented: the segmentation of the brain hemispheres and the cerebellum, and the segmentation of deep internal structures. Experimental results on real magnetic resonance (MR) images are presented, quantitatively assessed and discussed.

The emerging discipline of Computational Functional Anatomy

Computational Functional Anatomy (CFA) is the study of functional and physiological response variables in anatomical coordinates. For this we focus on two things: (i) the construction of bijections (via diffeomorphisms) between the coordinatized manifolds of human anatomy, and (ii) the transfer (group action and parallel transport) of functional information into anatomical atlases via these bijections. We review advances in the unification of the bijective comparison of anatomical submanifolds via point-sets including points, curves and surface triangulations as well as dense imagery. We examine the transfer via these bijections of functional response variables into anatomical coordinates via group action on scalars and matrices in DTI as well as parallel transport of metric information across multiple templates which preserves the inner product.

Segmentation of brain magnetic resonance images for measurement of gray matter atrophy in multiple sclerosis patients

Multiple sclerosis (MS) affects both white matter and gray matter (GM). Measurement of GM volumes is a particularly useful method to estimate the total extent of GM tissue damage because it can be done with conventional magnetic resonance images (MRI). Many algorithms exist for segmentation of GM, but none were specifically designed to handle issues associated with MS, such as atrophy and the effects that MS lesions may have on the classification of GM. A new GM segmentation algorithm has been developed specifically for calculation of GM volumes in MS patients. The new algorithm uses a combination of intensity, anatomical, and morphological probability maps. Several validation tests were performed to evaluate the algorithm in terms of accuracy, reproducibility, and sensitivity to MS lesions. The accuracy tests resulted in error rates of 1.2% and 3.1% for comparisons to BrainWeb and manual tracings, respectively. Similarity indices indicated excellent agreement with the BrainWeb segmentation (0.858-0.975, for various levels of noise and rf inhomogeneity). The scan-rescan reproducibility test resulted in a mean coefficient of variation of 1.1% for GM fraction. Tests of the effects of varying the size of MS lesions revealed a moderate and consistent dependence of GM volumes on T2 lesion volume, which suggests that GM volumes should be corrected for T2 lesion volumes using a simple scale factor in order to eliminate this technical artifact. The new segmentation algorithm can be used for improved measurement of GM volumes in MS patients, and is particularly applicable to retrospective datasets.

Automatic active model initialization via Poisson inverse gradient

Active models have been widely used in image processing applications. A crucial stage that affects the ultimate active model performance is initialization. This paper proposes a novel automatic initialization approach for parametric active models in both 2-D and 3-D. The PIG initialization method exploits a novel technique that essentially estimates the external energy field from the external force field and determines the most likely initial segmentation. Examples and comparisons with two state-of-the- art automatic initialization methods are presented to illustrate the advantages of this innovation, including the ability to choose the number of active models deployed, rapid convergence, accommodation of broken edges, superior noise robustness, and segmentation accuracy.

Reconstruction of central cortical surface from brain MRI images: method and application

Reconstruction of the central surface representation of the cerebral cortex is an important means to study the structure and function of the human brain. In this paper, we propose a novel method based on an elastic transform vector field to drive a deformable model for the reconstruction of the central cortical surface. Both simulated brain cortexes and real brain images are used to evaluate this approach. We applied the surface reconstruction method and a hybrid volumetric and surface registration algorithm to detect simulated brain atrophy. Experimental results show that the central cortical surface representation has better performance in detecting simulated atrophy than the traditionally used inner or outer cortical surface representations.

Automated method for identification of patients with Alzheimer's disease based on three-dimensional MR images

RATIONALE AND OBJECTIVES

An automated method for identification of patients with cerebral atrophy due to Alzheimer's disease (AD) was developed based on three-dimensional (3D) T1-weighted magnetic resonance (MR) images.

MATERIALS AND METHODS

Our proposed method consisted of determination of atrophic image features and identification of AD patients. The atrophic image features included white matter and gray matter volumes, cerebrospinal fluid (CSF) volume, and cerebral cortical thickness determined based on a level set method. The cortical thickness was measured with normal vectors on a voxel-by-voxel basis, which were determined by differentiating a level set function. The CSF spaces within cerebral sulci and lateral ventricles (LVs) were extracted by wrapping the brain tightly in a propagating surface determined with a level set method. Identification of AD cases was performed using a support vector machine (SVM) classifier, which was trained by the atrophic image features of AD and non-AD cases, and then an unknown case was classified into either AD or non-AD group based on an SVM model. We applied our proposed method to MR images of the whole brains obtained from 54 cases, including 29 clinically diagnosed AD cases (age range, 52-82 years; mean age, 70 years) and 25 non-AD cases (age range, 49-78 years; mean age, 62 years).

RESULTS

As a result, the area under a receiver operating characteristic (ROC) curve (Az value) obtained by our computerized method was 0.909 based on a leave-one-out test in identification of AD cases among 54 cases.

CONCLUSION

This preliminary result showed that our method may be promising for detecting AD patients.

A framework for in vivo quantification of regional brain folding in premature neonates

This paper describes and compares novel approaches to in vivo 3D measurement of brain surface folding in clinically acquired neonatal MR image data, which allows regional folding evaluation. Most of the current measures of folding are not independent of the area of the surface they are derived from. Therefore, applying them to whole-brain surfaces or subregions of different sizes results in differences which may or may not reflect true differences in folding. We address this problem by proposing new measures to quantify gyrification and two approaches to normalize previously defined measures. The method was applied to twelve premature infants (age 28-37 weeks) from which cerebrospinal fluid/gray matter and gray matter/white matter interface surfaces were extracted. Experimental results show that previous folding measures are sensitive to the area of the surface of analysis and that the area-independent measures proposed here provide significant improvements. Such a system provides a tool that facilitates the study of structural development in the neonatal brain within specific functional subregions, which may be critical in identifying later neurological impairment.

Detection of cortical thickness correlates of cognitive performance: Reliability across MRI scan sessions, scanners, and field strengths

In normal humans, relationships between cognitive test performance and cortical structure have received little study, in part, because of the paucity of tools for measuring cortical structure. Computational morphometric methods have recently been developed that enable the measurement of cortical thickness from MRI data, but little data exist on their reliability. We undertook this study to evaluate the reliability of an automated cortical thickness measurement method to detect correlates of interest between thickness and cognitive task performance. Fifteen healthy older participants were scanned four times at 2-week intervals on three different scanner platforms. The four MRI data sets were initially treated independently to investigate the reliability of the spatial localization of findings from exploratory whole-cortex analyses of cortical thickness-cognitive performance correlates. Next, the first data set was used to define cortical ROIs based on the exploratory results that were then applied to the remaining three data sets to determine whether the relationships between cognitive performance and regional cortical thickness were comparable across different scanner platforms and field strengths. Verbal memory performance was associated with medial temporal cortical thickness, while visuomotor speed/set shifting was associated with lateral parietal cortical thickness. These effects were highly reliable - in terms of both spatial localization and magnitude of absolute cortical thickness measurements - across the four scan sessions. Brain-behavior relationships between regional cortical thickness and cognitive task performance can be reliably identified using an automated data analysis system, suggesting that these measures may be useful as imaging biomarkers of disease or performance ability in multicenter studies in which MRI data are pooled.

Combining anatomical manifold information via diffeomorphic metric mappings for studying cortical thinning of the cingulate gyrus in schizophrenia

Spatial normalization is a crucial step in assessing patterns of neuroanatomical structure and function associated with health and disease. Errors that occur during spatial normalization can influence hypothesis testing due to the dimensionalities of mapping algorithms and anatomical manifolds (landmarks, curves, surfaces, volumes) used to drive the mapping algorithms. The primary aim of this paper is to improve statistical inference using multiple anatomical manifolds and large deformation diffeomorphic metric mapping (LDDMM) algorithms. We propose that combining information generated by the various manifolds and algorithms improves the reliability of hypothesis testing. We used this unified approach to assess variation in the thickness of the cingulate gyrus in subjects with schizophrenia and healthy comparison subjects. Three different LDDMM algorithms for mapping landmarks, curves and triangulated meshes were used to transform thickness maps of the cingulate surfaces into an atlas coordinate system. We then tested for group differences by combining the information from the three types of anatomical manifolds and LDDMM mapping algorithms. The unified approach provided reliable statistical results and eliminated ambiguous results due to surface mismatches. Subjects with schizophrenia had non-uniform cortical thinning over the left and right cingulate gyri, especially in the anterior portion, as compared to healthy comparison subjects.

Automatic segmentation and reconstruction of the cortex from neonatal MRI

Segmentation and reconstruction of cortical surfaces from magnetic resonance (MR) images are more challenging for developing neonates than adults. This is mainly due to the dynamic changes in the contrast between gray matter (GM) and white matter (WM) in both T1- and T2-weighted images (T1w and T2w) during brain maturation. In particular in neonatal T2w images WM typically has higher signal intensity than GM. This causes mislabeled voxels during cortical segmentation, especially in the cortical regions of the brain and in particular at the interface between GM and cerebrospinal fluid (CSF). We propose an automatic segmentation algorithm detecting these mislabeled voxels and correcting errors caused by partial volume effects. Our results show that the proposed algorithm corrects errors in the segmentation of both GM and WM compared to the classic expectation maximization (EM) scheme. Quantitative validation against manual segmentation demonstrates good performance (the mean Dice value: 0.758+/-0.037 for GM and 0.794+/-0.078 for WM). The inner, central and outer cortical surfaces are then reconstructed using implicit surface evolution. A landmark study is performed to verify the accuracy of the reconstructed cortex (the mean surface reconstruction error: 0.73 mm for inner surface and 0.63 mm for the outer). Both segmentation and reconstruction have been tested on 25 neonates with the gestational ages ranging from approximately 27 to 45 weeks. This preliminary analysis confirms previous findings that cortical surface area and curvature increase with age, and that surface area scales to cerebral volume according to a power law, while cortical thickness is not related to age or brain growth.

Active contour external force using vector field convolution for image segmentation

Snakes, or active contours, have been widely used in image processing applications. Typical roadblocks to consistent performance include limited capture range, noise sensitivity, and poor convergence to concavities. This paper proposes a new external force for active contours, called vector field convolution (VFC), to address these problems. VFC is calculated by convolving the edge map generated from the image with the user-defined vector field kernel. We propose two structures for the magnitude function of the vector field kernel, and we provide an analytical method to estimate the parameter of the magnitude function. Mixed VFC is introduced to alleviate the possible leakage problem caused by choosing inappropriate parameters. We also demonstrate that the standard external force and the gradient vector flow (GVF) external force are special cases of VFC in certain scenarios. Examples and comparisons with GVF are presented in this paper to show the advantages of this innovation, including superior noise robustness, reduced computational cost, and the flexibility of tailoring the force field.

Brain segmentation with competitive level sets and fuzzy control

We propose to segment 3D structures with competitive level sets driven by fuzzy control. To this end, several contours evolve simultaneously toward previously defined anatomical targets. A fuzzy decision system combines the a priori knowledge provided by an anatomical atlas with the intensity distribution of the image and the relative position of the contours. This combination automatically determines the directional term of the evolution equation of each level set. This leads to a local expansion or contraction of the contours, in order to match the borders of their respective targets. Two applications are presented: the segmentation of the brain hemispheres and the cerebellum, and the segmentation of deep internal structures. Experimental results on real MR images are presented, quantitatively assessed and discussed.