Search

Recent advances in MRI have made it easier to collect data for studying human structural and functional connectivity networks. Computational methods can reveal complex spatiotemporal dynamics of the human developing brain. In this paper, we propose a Developmental Meta-network Decomposition (DMD) method to decompose a series of longitudinal networks into a set of Developmental Meta-networks (DMs), which reveal the underlying changes in connectivity over development. DMD circumvents the limitations of traditional static network decomposition methods by providing a novel exploratory approach to capture the spatiotemporal dynamics of longitudinal networks. We apply this method to longitudinal structural correlation networks of cortical thickness across subjects at 3-20 years of age, and identify four DMs that smoothly evolve over three stages, i.e., 3-6, 7-12, and 13-20 years of age. We analyze and highlight the characteristic connections of each DM in relation to brain development.

A variety of algorithms have been proposed for brain tumor segmentation from multi-channel sequences, however, most of them require isotropic or pseudo-isotropic resolution of the MR images. Although co-registration and interpolation of low-resolution sequences, such as T2-weighted images, onto the space of the high-resolution image, such as T1-weighted image, can be performed prior to the segmentation, the results are usually limited by partial volume effects due to interpolation of low-resolution images. To improve the quality of tumor segmentation in clinical applications where low-resolution sequences are commonly used together with high-resolution images, we propose the algorithm based on Spatial accuracy-weighted Hidden Markov random field and Expectation maximization (SHE) approach for both automated tumor and enhanced-tumor segmentation. SHE incorporates the spatial interpolation accuracy of low-resolution images into the optimization procedure of the Hidden Markov Random Field (HMRF) to segment tumor using multi-channel MR images with different resolutions, e.g., high-resolution T1-weighted and low-resolution T2-weighted images. In experiments, we evaluated this algorithm using a set of simulated multi-channel brain MR images with known ground-truth tissue segmentation and also applied it to a dataset of MR images obtained during clinical trials of brain tumor chemotherapy. The results show that more accurate tumor segmentation results can be obtained by comparing with conventional multi-channel segmentation algorithms.

Reliable cell nuclei segmentation is an important yet unresolved problem in biological imaging studies. This paper presents a novel computerized method for robust cell nuclei segmentation based on gradient flow tracking. This method is composed of three key steps: (1) generate a diffused gradient vector flow field; (2) perform a gradient flow tracking procedure to attract points to the basin of a sink; and (3) separate the image into small regions, each containing one nucleus and nearby peripheral background, and perform local adaptive thresholding in each small region to extract the cell nucleus from the background. To show the generality of the proposed method, we report the validation and experimental results using microscopic image data sets from three research labs, with both over-segmentation and under-segmentation rates below 3%. In particular, this method is able to segment closely juxtaposed or clustered cell nuclei, with high sensitivity and specificity in different situations.

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.

The zebrafish has become an important vertebrate animal model for the study of developmental biology, functional genomics, and disease mechanisms. It is also being used for drug discovery. Computerized detection of blob objects has been one of the important tasks in quantitative phenotyping of zebrafish. We present a new automated method that is able to detect blob objects, such as nuclei or cells in microscopic zebrafish images. This method is composed of three key steps. The first step is to produce a diffused gradient vector field by a physical elastic deformable model. In the second step, the flux image is computed on the diffused gradient vector field. The third step performs thresholding and nonmaximum suppression based on the flux image. We report the validation and experimental results of this method using zebrafish image datasets from three independent research labs. Both sensitivity and specificity of this method are over 90%. This method is able to differentiate closely juxtaposed or connected blob objects, with high sensitivity and specificity in different situations. It is characterized by a good, consistent performance in blob object detection.

Accurate and consistent skull stripping of serial brain MR images is of great importance in longitudinal studies that aim to detect subtle brain morphological changes. To avoid inconsistency and the potential bias introduced by independently performing skull-stripping for each time-point image, we propose an effective method that is capable of skull-stripping serial brain MR images simultaneously. Specifically, all serial images of the same subject are first affine aligned in a groupwise manner to a common space to avoid any potential bias introduced by asymmetric transforms. A brain probability map, which encapsulates prior information gathered from a population of real brain MR images, is then warped to the aligned serial images for guiding skull-stripping via a deformable surface method. In particular, the same initial surface meshes representing the initial brain surfaces are first placed on all aligned serial images, and then all these surface meshes are simultaneously evolved to the respective target brain boundaries, driven by the intensity-based force, the force from the probability map, as well as the force from the spatial and temporal smoothness. Especially, imposing the temporal smoothness helps achieve longitudinally consistent results. Evaluations on 20 subjects, each with 4 time points, from the ADNI database indicate that our method gives more accurate and consistent result compared with 3D skull-stripping method. To better show the advantages of our 4D brain extraction method over the 3D method, we compute the Dice ratio in a ring area (±5mm) surrounding the ground-truth brain boundary, and our 4D method achieves around 3% improvement over the 3D method. In addition, our 4D method also gives smaller mean and maximal surface-to-surface distance measurements, with reduced variances.

Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the large-scale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surface-based approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55 approximately 90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18 approximately 96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5 approximately 18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness., published_or_final_version

Quantitative measurement of dynamic cortex development during early postnatal stages is of great importance to understand early cortical structural and functional development. Conventional methods usually independently reconstruct cortical surfaces of longitudinal images from the same infant, which often generates longitudinallyinconsistent cortical surfaces and leads to inconsistence in cortex development measurement. This paper aims to address this problem by presenting a method to reconstruct consistent cortical surfaces from longitudinal brain MR images in the first-year infants for accurate and consistent measurement of dynamic cortex development. Specifically, longitudinal development of the inner cortical surface is first modeled by a deformable sheet with elasto-plasticity property to establish longitudinally smooth correspondences of inner cortical surfaces. Then, the modeled longitudinal inner cortical surfaces are jointly deformed to locate inner and outer cortical surfaces with a spatial-temporal deformable surface. The method has been applied on 10 infants, each with 5 or 6 scans acquired at every 3 months from birth. Experimental results show that our method can accurately and consistently reconstruct dynamic cortical surfaces from longitudinal infant images, with the average surface distance as low as 0.2mm. By using our method, we can quantitatively characterize longitudinally dynamic cortical thickness development in the first-year infants.

We propose an automated multi-atlas and multi-ROI based segmentation method for both skull-stripping of mouse brain and the ROI-labeling of mouse brain structures from the three dimensional (3D) magnetic resonance images (MRI). Three main steps are involved in our method. First, a region of interest (ROI) guided warping algorithm is designed to register multi-atlas images to the subject space, by considering more on the matching of image contents around the ROI boundaries which are more important for ROI labeling. Then, a multi-atlas and multi-ROI based deformable segmentation method is adopted to refine the ROI labeling result by deforming each ROI surface via boundary recognizers (i.e., SVM classifiers) trained on local surface patches. Finally, a local-mutual-information (MI) based multi-label fusion technique is proposed for allowing the atlases with better local image similarity with the subject to have more contributions in label fusion. The experimental results show that our method works better than the conventional methods on both in vitro and in vivo mouse brain datasets.

Skull-stripping refers to the separation of brain tissue from nonbrain tissue, such as the scalp, skull, and dura. In large-scale studies involving a significant number of subjects, a fully automatic method is highly desirable, since manual skull-stripping requires tremendous human effort and can be inconsistent even after sufficient training. We propose in this paper a robust and effective method that is capable of skull-stripping a large number of images accurately with minimal dependence on the parameter setting. The key of our method involves an initial skull-stripping by co-registration of an atlas, followed by a refinement phase with a surface deformation scheme that is guided by prior information obtained from a set of real brain images. Evaluation based on a total of 831 images, consisting of normal controls (NC) and patients with mild cognitive impairment (MCI) or Alzheimer's Disease (AD), from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database indicates that our method performs favorably at a consistent overall overlap rate of approximately 98% when compared with expert results. The software package will be made available to the public to facilitate neuroimaging studies.

The direction field on cortical surface conveys important information. Diffusion of direction field, which aims to smooth noise and meanwhile preserve major geometric structures and inherent discontinuity in the direction field, is useful for cortical surface analysis. In this paper, we propose a novel method for tangential direction field diffusion on cortical surface, which is formulated as an energy minimization problem. To minimize the energy function, we first convert it to a discrete labeling problem, in which the space of solution is represented using a set of labels corresponding to a set of predefined diffused directions. Then we solve the labeling problem efficiently by the graph cuts method. At last, we project the labeled diffused directions to the tangential spaces of the cortical surface and normalize them in order to obtain the final diffused direction field. We validate the proposed direction field diffusion method on both synthesized surfaces and real cortical surfaces, and obtain promising results.

Human cortical folding pattern has been studied for decades. This paper proposes a gyrus scale folding pattern analysis technique via cortical surface profiling. Firstly, we sample the cortical surface into 2D profiles and model them using power function. This step provides both the flexibility of representing arbitrary shape by profiling and the compactness of representing shape by parametric modeling. Secondly, based on the estimated model parameters, we extract affine-invariant features on the cortical surface and apply the affinity propagation clustering algorithm to parcellate the cortex into regions with different shape patterns. Finally, a second-round surface profiling is performed on the parcellated cortical regions, and the number of hinges is detected to describe the gyral folding pattern. Experiments demonstrate that our method could successfully classify human gyri into 2-hinge, 3-hinge and 4-hinge gyri. The proposed method has the potential to significantly contribute to automatic segmentation and recognition of cortical gyri.

This paper presents a novel method for parcellation of the cortical surface of human brain into gyral based regions via coupled flow field tracking. The proposed method consists of two major steps. First, the cortical surface is automatically parcellated into sulcal based regions using several procedures: estimating principal curvatures and principal directions; applying the hidden Markov random field and the Expectation-Maximization (HMRF-EM) framework for sulcal region segmentation based on the maximum principal curvature; diffusing the maximum principal direction field in order to propagate reliable and informative principal directions at gyral crests and sulcal bottoms to other flat cortical regions with noisy principal directions by minimization of an energy function; tracking the flow field towards sulcal bottoms to parcellate the cortical surfaces into sulcal basins. The sulcal parcellation provides a very good initialization for the following steps of gyral parcellation on cortical surfaces. Second, based on the sulcal parcellation results, the cortical surface is further parcellated into gyral based regions using the following procedures: extracting gyral crest segments; dilating gyral crest segments; inverting the principal direction flow field and tracking the flow field towards gyral crests in order to partition the cortical surface into a collection of gyral patches; merging gyral patches to obtain gyral parcellation of the cortical surface. The proposed algorithm pipeline is applied to nine randomly selected cortical surfaces of normal brains and promising results are obtained. The accuracy of the semi-automatic gyral parcellation is comparable to that labeled manually by experts.

In this paper, we present an approach of predictive modeling of neuroanatomic structures for the detection of brain atrophy based on cross-sectional MRI image. The underlying premise of applying predictive modeling for atrophy detection is that brain atrophy is defined as significant deviation of part of the anatomy from what the remaining normal anatomy predicts for that part. The steps of predictive modeling are as follows. The central cortical surface under consideration is reconstructed from brain tissue map and Regions of Interests (ROI) on it are predicted from other reliable anatomies. The vertex pair-wise distance between the predicted vertex and the true one within the abnormal region is expected to be larger than that of the vertex in normal brain region. Change of white matter/gray matter ratio within a spherical region is used to identify the direction of vertex displacement. In this way, the severity of brain atrophy can be defined quantitatively by the displacements of those vertices. The proposed predictive modeling method has been evaluated by using both simulated atrophies and MRI images of Alzheimer's disease.

Folding is an essential shape characteristic of the human cerebral cortex. Descriptors of cortical folding patterns have been studied for decades. However, many previous studies are either based on local shape descriptors such as curvature, or based on global descriptors such as gyrification index or spherical wavelets. This paper proposes a gyrus-scale folding pattern analysis technique via cortical surface profiling. Firstly, we sample the cortical surface into 2D profiles and model them using a power function. This step provides both the flexibility of representing arbitrary shape by profiling and the compactness of representing shape by parametric modeling. Secondly, based on the estimated model parameters, we extract affine-invariant features on the cortical surface, and apply the affinity propagation clustering algorithm to parcellate the cortex into cortical regions with strict hierarchy and smooth transitions among them. Finally, a second-round surface profiling is performed on the parcellated cortical surface, and the number of hinges is detected to describe the gyral folding pattern. We have applied the surface profiling method to two normal brain datasets and a schizophrenia patient dataset. The experimental results demonstrate that the proposed method can accurately classify human gyri into 2-hinge, 3-hinge and 4-hinge patterns. The distribution of these folding patterns on brain lobes and the relationship between fiber density and gyral folding patterns are further investigated. Results from the schizophrenia dataset are consistent with commonly found abnormality in former studies by others, which demonstrates the potential clinical applications of the proposed technique.

Resting state fMRI (rsfMRI) has been demonstrated to be an effective modality by which to explore the functional networks of the human brain, as the low-frequency oscillations in rsfMRI time courses between spatially distant brain regions show the evidence of correlated activity patterns in the brain. This paper proposes a novel surface-based data-driven framework to explore these networks through the use of high resolution rsfMRI data. Guided by DTI defined fiber pathways and constrained by the gray matter, we map the rsfMRI BOLD signals onto the cortical surface generated by DTI-based tissue segmentation. We then use a data-driven affinity propagation clustering algorithm to identify these functional networks. Our experimental results demonstrate that the framework has high reproducibility and that several networks are detected reliably among individual subjects. Furthermore, our results exhibit that functional networks are highly correlated with structural connections. Finally, our framework is able to reveal visual sub-networks, indicating its potential role in sub-network exploration.

Quantitative descriptions of white matter (WM) fiber shape and cortical folding patterns are important for neuroscience research. This paper presents a novel computational method for WM fiber shape pattern analysis, that is, WM fibers are clustered into five primitive shape patterns: closed ‘U’, ‘M’, curved line, open ‘U’ and straight line, based on the automatic clustering of their shape features. We study the correlation between the fiber shape patterns and the folding patterns of cortical regions that the fibers connect, and find that these patterns are highly correlated. Also, we investigate the shape patterns of the WM fibers that connect different brain regions such as cortical lobes and subcortical regions, and find that the shape patterns of the fibers connecting different brain regions are quite specific. These results might provide insights into the structural and functional architecture of the human brain.

The mechanisms of human cerebral cortex folding and their interactions during brain development are largely unknown, partly due to the difficulties in biological experiments and data acquisition for the developing fetus brain. Computational modeling and simulation provide a novel approach to the understanding of cortex folding processes in normal or aberrant neurodevelopment. Based on our recently developed computational model of the cerebral cortex folding using neuronal growth model and mechanical skull constraint, this paper presents a computational dynamic model of the brain skull that regulates the cortical folding simulation. Our simulation results show that the dynamic skull model is more biologically realistic and significantly improves our cortical folding simulation results. This work provides further computational support to the hypothesis that skull is an important regulator of cortical folding.

Development of imaging predictor of brain cytoarchitecture has been of significant interest in neuroimaging. Cortical geometric characteristic has been shown to be a good predictor of cortical cytoarchitecture. In this paper, a novel method based on sulcal geometric features is proposed for the extraction of sulcal banks, which are the cortical regions bounded by sulcal fundi and adjacent gyral crest lines. Given parcellated sulcal basins, we apply two graph partition techniques including the normalized cuts and the graph cuts to partition a sulcal basin into two opposing sulcal banks. Particularly, we designed novel geometric similarity metrics and cost functions to adopt these two graph partition algorithms specifically for our applications. As a test bed application, we applied this method to extract the anterior and posterior sulcal banks of the central sulci on over 400 cortical surfaces and achieved promising results. In addition, we applied this method to study the cortical thickness of central sulci and found that the cortical thickness of the anterior sulcal bank is significantly thicker than that of the posterior sulcal bank, suggesting that the segmented sulcal banks can differentiate cortical thickness layout, which is believed to be an indicator of brain cytoarchitecture. Finally, the asymmetry and longitudinal changes of cortical thickness are analyzed using the OASIS database and reasonable results are obtained.

It is widely believed that the structural connectivity of a brain region largely determines its function. High resolution Diffusion Tensor Imaging (DTI) is now able to image the axonal fibers in vivo and the DTI tractography result provides rich connectivity information. In this paper, a novel method is proposed to employ fiber density information for automatic cortical parcellation based on the premise that fibers connecting to the same cortical region should be within the same functional brain network and their aggregation on the cortex can define a functionally coherent region. This method consists of three steps. Firstly, the fiber density is calculated on the cortical surface. Secondly, a flow field is obtained by calculating the fiber density gradient and a flow field tracking method is utilized for cortical parcellation. Finally, an atlas-based warping method is used to label the parcellated regions. Our method was applied to parcellate and label the cortical surfaces of eight healthy brain DTI images, and interesting results are obtained. In addition, the labeled regions are used as ROIs to construct structural networks for different brains, and the graph properties of these networks are measured.

Automatic parcellation of cortical surfaces into sulci or gyri based regions is of great importance in studying the structure and function of the human brain. This paper presents a novel method for automatic parcellation of cortical surfaces into gyri based regions. The method is composed of two major steps: data-driven gyral patch segmentation and model-driven gyral patch labeling. The gyral patch segmentation is achieved by several steps, including sulcal region segmentation, sulcal basin parcellation, gyral crest segments extraction and gyral patch segmentation. The gyral patch labeling is formulated as an energy minimization problem, in which a cortical probabilistic atlas and the curvature information on surfaces are used to define the energy function. The energy function is efficiently solved by the graph cuts method. A unique feature of the proposed method is that it does not require high dimensional spatial normalization on images or surfaces. The method has been successfully applied to cortical surfaces of 15 young healthy brain MR images. Quantitative and qualitative evaluation results demonstrate the validity of the proposed method.

The human cerebral cortex is a highly convoluted structure composed of sulci and gyri, corresponding to the valleys and ridges of the cortical surface respectively. Automatic parcellation of the cortical surface into sulcal regions is of great importance in structural and functional mapping of the human brain. In this paper, a novel method is proposed for automatic cortical sulcal parcellation based on the geometric characteristics of cortical surface including its principal curvatures and principal directions. This method is composed of two major steps: 1) employing the hidden Markov random field model (HMRF) and the expectation maximization (EM) algorithm on the maximum principal curvatures of the cortical surface for sulcal region segmentation, and 2) using a principal direction flow field tracking method on the cortical surface for sulcal basin segmentation. The flow field is obtained by diffusing the principal direction field on the cortical surface mesh. A unique feature of this method is that the automatic sulcal parcellation process is quite robust and efficient, and is independent of any external guidance such as atlas-based warping. The method has been successfully applied to the inner cortical surfaces of twelve healthy human brain MR images. Both quantitative and qualitative evaluation results demonstrate the validity and efficiency of the proposed method.

Folding of the human cerebral cortex has intrigued many people for many years. Quantitative description of cortical folding pattern and understanding of the underlying mechanisms have emerged as an important research goal. This paper presents a computational 3D geometric model of cerebral cortex folding that is initialized by MRI data of human fetus brain and deformed under the governance of partial differential equations modeling the cortical growth. The simulations of this 3D geometric model provide computational experiment support to the following hypotheses: (1) Mechanical constraints of the brain skull regulate the cortical folding process. (2) The cortical folding pattern is dependent on the global cell growth rate in the whole cortex. (3) The cortical folding pattern is dependent on relative degrees of tethering of different cortical areas and the initial geometry.

In this paper, we propose a novel automated pipeline for extraction of sulcal fundi from triangulated cortical surfaces. This method consists of four consecutive steps. Firstly, we adopt a finite difference method to estimate principal curvatures, principal directions and curvature derivatives, along the principal directions, for each vertex. Then, we detect the sulcal fundi segment in each triangle of the cortical surface based on curvatures and curvature derivatives. Afterwards, we link the sulcal fundi segments into continuous curves. Finally, we connect breaking sulcal fundi and smooth bumping sulcal fundi by using the fast marching method on the cortical surface. The proposed method can find the accurate sulcal fundi using curvatures and curvature derivatives without any manual interaction. The method was applied to 10 normal brain MR images on inner cortical surfaces. We quantitatively evaluated the accuracy of the sulcal fundi extraction method using manually labeled sulcal fundi by experts. The average difference between automatically extracted major sulcal fundi and the expert labeled results is consistently around 1.0 mm on 10 subject images, indicating the good performance of the proposed method.

Sulcal fundi are 3D curves along the bottom of sulcal regions of the human cerebral cortex. In this paper, we propose a novel automatic method for extraction of sulcal fundi from triangulated cortical surface. Compared to existing methods, the proposed method can find accurate sulcal fundi using curvatures and curvature derivatives without manual interaction. Given a triangulated cortical surface, our method is composed of four steps: estimating curvatures and curvature derivatives for each vertex, detecting the sulcal fundi segments in each triangle, linking the sulcal fundi segments and combining of adjacent sulcal fundi, and connecting breaking sulcal fundi and smoothing using the fast marching method on the cortical surface. The proposed sulcal fundi extraction method is applied to ten normal brain inner cortical surfaces. We quantitatively validated the proposed method of sulcal fundi extraction using manually labeled sulcal fundi by experts as the ground truth.

Since the mid of 1990s, functional connectivity study using fMRI (fcMRI) has drawn increasing attention of neuroscientists and computer scientists, since it opens a new window to explore functional network of human brain with relatively high resolution. A variety of methods for fcMRI study have been proposed. This paper intends to provide a technical review on computational methodologies developed for fcMRI analysis. From our perspective, these computational methods are classified into two general categories: model-driven methods and data-driven methods. Data-driven methods are a large family, and thus are further sub-classified into decomposition-based methods and clustering analysis methods. For each type of methods, principles, main contributors, and their advantages and drawbacks are discussed. Finally, potential applications of fcMRI are overviewed.

Sulcal fundi are 3D curves along the bottom of sulcal regions of the human cerebral cortex. In this paper, we propose a novel automatic method for extraction of sulcal fundi from triangulated cortical surface. Compared to existing methods, the proposed method can find accurate sulcal fundi using curvatures and curvature derivatives without manual interaction. Given a triangulated cortical surface, our method is composed of four steps: estimating curvatures and curvature derivatives for each vertex, detecting the sulcal fundi segments in each triangle, linking the sulcal fundi segments and combining of adjacent sulcal fundi, and connecting breaking sulcal fundi and smoothing using the fast marching method on the cortical surface. The proposed sulcal fundi extraction method is applied to ten normal brain inner cortical surfaces. We quantitatively validated the proposed method of sulcal fundi extraction using manually labeled sulcal fundi by experts as the ground truth.

BackgroundReliable segmentation of cell nuclei from three dimensional (3D) microscopic images is an important task in many biological studies. We present a novel, fully automated method for the segmentation of cell nuclei from 3D microscopic images. It was designed specifically to segment nuclei in images where the nuclei are closely juxtaposed or touching each other. The segmentation approach has three stages: 1) a gradient diffusion procedure, 2) gradient flow tracking and grouping, and 3) local adaptive thresholding.ResultsBoth qualitative and quantitative results on synthesized and original 3D images are provided to demonstrate the performance and generality of the proposed method. Both the over-segmentation and under-segmentation percentages of the proposed method are around 5%. The volume overlap, compared to expert manual segmentation, is consistently over 90%.ConclusionThe proposed algorithm is able to segment closely juxtaposed or touching cell nuclei obtained from 3D microscopy imaging with reasonable accuracy.

Reconstruction of the geometric central surface of the human cerebral cortex is an important means to study the structure and function of the brain cortex. In this paper, we propose a novel method based on an elastic deformable transform vector field to drive a deformable model for the reconstruction of the central surface of the brain cortex. In addition, simulated brain cortexes are generated to evaluate this method. We report the evaluation results obtained from ten subjects to show the effectiveness of our approach. We applied the central cortical surface reconstruction method and the hybrid cortical surface registration method to detect simulated brain atrophy. Our results indicate that the central cortical surface has much better sensitivity in detecting simulated atrophy than traditionally used inner or outer cortical surfaces

The development of automated and robust computational algorithms for 3D cell segmentation remains challenging in situations where the cells are touching each other or connected together. In this paper, we present a novel automated method that aims to tackle the aforementioned challenges in the segmentation of clustered or connected 3D cells. We first diffuse the gradient vector field with an elastic deformable transform. Then, a gradient flow tracking procedure is performed for each voxel to find the corresponding center that the point flows to. All points that flow to the same center are grouped as a region. In this way, the boundaries between touching cells are formed naturally, and the touched cells are divided. Evaluation results from 3D image data of zebrafish and C. Elegant indicate good performance of the proposed method