Automated sulcal segmentation using watersheds on the cortical surface.

The human cortical surface is a highly complex, folded structure. Sulci, the spaces between the folds, define location on the cortex and provide a parcellation into anatomically distinct areas. A topic that has recently received increased attention is the segmentation of these sulci from magnetic resonance images, with most work focusing on extracting either the sulcal spaces between the folds or curve representations of sulci. Unlike these methods, we propose a technique that extracts actual regions of the cortical surface that surround sulci, which we call "sulcal regions." The method is based on a watershed algorithm applied to a geodesic depth measure on the cortical surface. A well-known problem with the watershed algorithm is a tendency toward oversegmentation, meaning that a single region is segmented as several pieces. To address this problem, we propose a postprocessing algorithm that merges appropriate segments from the watershed algorithm. The sulcal regions are then manually labeled by simply selecting the appropriate regions with a mouse click and a preliminary study of sulcal depth is reported. Finally, a scheme is presented for computing a complete parcellation of the cortical surface.     

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.     

Brain tissue segmentation based on DTI data

We present a method for automated brain tissue segmentation based on the multi-channel fusion of diffusion tensor imaging (DTI) data. The method is motivated by the evidence that independent tissue segmentation based on DTI parametric images provides complementary information of tissue contrast to the tissue segmentation based on structural MRI data. This has important applications in defining accurate tissue maps when fusing structural data with diffusion data. In the absence of structural data, tissue segmentation based on DTI data provides an alternative means to obtain brain tissue segmentation. Our approach to the tissue segmentation based on DTI data is to classify the brain into two compartments by utilizing the tissue contrast existing in a single channel. Specifically, because the apparent diffusion coefficient (ADC) values in the cerebrospinal fluid (CSF) are more than twice that of gray matter (GM) and white matter (WM), we use ADC images to distinguish CSF and non-CSF tissues. Additionally, fractional anisotropy (FA) images are used to separate WM from non-WM tissues, as highly directional white matter structures have much larger fractional anisotropy values. Moreover, other channels to separate tissue are explored, such as eigenvalues of the tensor, relative anisotropy (RA), and volume ratio (VR). We developed an approach based on the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm that combines these two-class maps to obtain a complete tissue segmentation map of CSF, GM, and WM. Evaluations are provided to demonstrate the performance of our approach. Experimental results of applying this approach to brain tissue segmentation and deformable registration of DTI data and spoiled gradient-echo (SPGR) data are also provided.     

Shape-based cortical surface segmentation for visualization brain mapping

We describe a knowledge-based approach to cortical surface segmentation that uses learned knowledge of the overall shape and range of variation of the cortex (excluding the detailed gyri and sulci) to guide the search for the grey-CSF boundary in a structural MRI image volume. The shape knowledge is represented by a radial surface model, which is a type of geometric constraint network (GCN) that we hypothesize can represent shape by networks of locally interacting constraints. The shape model is used in a protocol for visualization-based mapping of cortical stimulation mapping (CSM) sites onto the brain surface, prior to integration with other mapping modalities or as input to existing surface analysis and reconfiguration programs. Example results are presented for CSM data related to language organization in the cortex, but the methods should be applicable to other situations where a realistic visualization of the brain surface, as seen at neurosurgery, is desired.     

LoAd: a locally adaptive cortical segmentation algorithm

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

Multi-stage segmentation of white matter hyperintensity, cortical and lacunar infarcts

Cerebral abnormalities such as white matter hyperintensity (WMH), cortical infarct (CI), and lacunar infarct (LI) are of clinical importance and frequently present in patients with stroke and dementia. Up to date, there are limited algorithms available to automatically delineate these cerebral abnormalities partially due to their complex appearance in MR images. In this paper, we describe an automated multi-stage segmentation approach for labeling the WMH, CI, and LI using multi-modal MR images. We first automatically segment brain tissues (white matter, gray matter, and CSF) based on the T1-weighted image and then identify hyperintense voxels based on the fluid attenuated inversion recovery (FLAIR) image. We finally label the WMH, CI, and LI based on the T1-weighted, T2-weighted, and FLAIR images. The segmentation accuracy is evaluated using a community-based sample of 272 old adults. Our results show that the automated segmentation of the WMH, CI, and LI is comparable with manual labeling in terms of spatial location, volume, and the number of lacunes. Additionally, the WMH volume is highly correlated with the visual grading score based on the Age-Related White Matter Changes (ARWMC) protocol. The evaluations against the manual labeling and ARWMC visual grading suggest that our algorithm provides reasonable segmentation accuracy for the WMH, CI, and LI.     

FCN-based approach for the automatic segmentation of bone surfaces in ultrasound images

Purpose

A new algorithm, based on fully convolutional networks (FCN), is proposed for the automatic localization of the bone interface in ultrasound (US) images. The aim of this paper is to compare and validate this method with (1) a manual segmentation and (2) a state-of-the-art method called confidence in phase symmetry (CPS).

Methods

The dataset used for this study was composed of 1738 US images collected from three volunteers and manually delineated by three experts. The inter- and intra-observer variabilities of this manual delineation were assessed. Images having annotations with an inter-observer variability higher than a confidence threshold were rejected, resulting in 1287 images. Both FCN-based and CPS approaches were studied and compared to the average inter-observer segmentation according to six criteria: recall, precision, F1 score, accuracy, specificity and root-mean-square error (RMSE).

Results

The intra- and inter-observer variabilities were inferior to 1 mm for 90% of manual annotations. The RMSE was 1.32?±?3.70  mm and 5.00?±?7.70 mm for, respectively, the FCN-based approach and the CPS algorithm. The mean recall, precision, F1 score, accuracy and specificity were, respectively, 62%, 64%, 57%, 80% and 83% for the FCN-based approach and 66%, 34%, 41%, 52% and 43% for the CPS algorithm.

Conclusion

The FCN-based approach outperforms the CPS algorithm, and the obtained RMSE is similar to the manual segmentation uncertainty.

     

High resolution histopathology image generation and segmentation through adversarial training

Semantic segmentation of histopathology images can be a vital aspect of computer-aided diagnosis, and deep learning models have been effectively applied to this task with varying levels of success. However, their impact has been limited due to the small size of fully annotated datasets. Data augmentation is one avenue to address this limitation. Generative Adversarial Networks (GANs) have shown promise in this respect, but previous work has focused mostly on classification tasks applied to MR and CT images, both of which have lower resolution and scale than histopathology images. There is limited research that applies GANs as a data augmentation approach for large-scale image semantic segmentation, which requires high-quality image-mask pairs. In this work, we propose a multi-scale conditional GAN for high-resolution, large-scale histopathology image generation and segmentation. Our model consists of a pyramid of GAN structures, each responsible for generating and segmenting images at a different scale. Using semantic masks, the generative component of our model is able to synthesize histopathology images that are visually realistic. We demonstrate that these synthesized images along with their masks can be used to boost segmentation performance, especially in the semi-supervised scenario.     

基于期望值最大化方法的磁共振图像人脑组织分割

目的利用期望值最大化方法进行磁共振图像的人脑组织分割。方法在分析当前常用的医学图像分割方法的基础上,提出一种基于统计理论的期望值最大化分割方法,并给出了相应的理论算法模型和实现步骤,最后用Visual C 6.0编程,并对磁共振大脑图像进行实验,并与应用SPM软件对同一幅图像的分割结果进行分析比较。结果本文分割方法与SPM软件的分割结果非常接近,大脑灰质、白质、脑脊液等组织之间边界清晰,总体不确定性较小。结论本文分割方法切实可行,分割效果较好,为进一步的磁共振图像分析和疾病研究提供了一种有效工具。     

A combined machine-learning and graph-based framework for the segmentation of retinal surfaces in SD-OCT volumes

Optical coherence tomography is routinely used clinically for the detection and management of ocular diseases as well as in research where the studies may involve animals. This routine use requires that the developed automated segmentation methods not only be accurate and reliable, but also be adaptable to meet new requirements. We have previously proposed the use of a graph-theoretic approach for the automated 3-D segmentation of multiple retinal surfaces in volumetric human SD-OCT scans. The method ensures the global optimality of the set of surfaces with respect to a cost function. Cost functions have thus far been typically designed by hand by domain experts. This difficult and time-consuming task significantly impacts the adaptability of these methods to new models. Here, we describe a framework for the automated machine-learning based design of the cost function utilized by this graph-theoretic method. The impact of the learned components on the final segmentation accuracy are statistically assessed in order to tailor the method to specific applications. This adaptability is demonstrated by utilizing the method to segment seven, ten and five retinal surfaces from SD-OCT scans obtained from humans, mice and canines, respectively. The overall unsigned border position errors observed when using the recommended configuration of the graph-theoretic method was 6.45 ± 1.87 μm, 3.35 ± 0.62 μm and 9.75 ± 3.18 μm for the human, mouse and canine set of images, respectively.OCIS codes: (100.0100) Image processing, (100.2000) Digital image processing, (100.4994) Pattern recognition, image transforms, (100.6890) Three-dimensional image processing, (110.4500) Optical coherence tomography     

Multi-manifold diffeomorphic metric mapping for aligning cortical hemispheric surfaces

Cortical surface-based analysis has been widely used in anatomical and functional studies because it is geometrically appropriate for the cortex. One of the main challenges in the cortical surface-based analysis is to optimize the alignment of the cortical hemispheric surfaces across individuals. In this paper, we introduce a multi-manifold large deformation diffeomorphic metric mapping (MM-LDDMM) algorithm that allows simultaneously carrying the cortical hemispheric surface and its sulcal curves from one to the other through a flow of diffeomorphisms. We present an algorithm based on recent derivation of a law of momentum conservation for the geodesics of diffeomorphic flow. Once a template is fixed, the space of initial momentum becomes an appropriate space for studying shape via geodesic flow since the flow at any point on curves and surfaces along the geodesic is completely determined by the momentum at the origin. We solve for trajectories (geodesics) of the kinetic energy by computing its variation with respect to the initial momentum and by applying a gradient descent scheme. The MM-LDDMM algorithm optimizes the initial momenta encoding the anatomical variation of each individual relative to a common coordinate system in a linear space, which provides a natural scheme for shape deformation average and template (or atlas) generation. We applied the MM-LDDMM algorithm for constructing the templates for the cortical surface and 14 sulcal curves of each hemisphere using a group of 40 subjects. The estimated template shape reflects regions which are highly variable across these subjects. Compared with existing single-manifold LDDMM algorithms, such as the LDDMM-curve mapping and the LDDMM-surface mapping, the MM-LDDMM mapping provides better results in terms of surface to surface distances in five predefined regions.     

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

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

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.     

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

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

Learning a cortical parcellation of the brain robust to the MRI segmentation with convolutional neural networks

The parcellation of the human cortex into meaningful anatomical units is a common step of various neuroimaging studies. There have been multiple successful efforts to process magnetic resonance (MR) brain images automatically and identify specific anatomical regions, following atlases defined from cortical landmarks. Those definitions usually rely first on a high-quality brain surface reconstruction. On the other hand, when high accuracy is not a requirement, simpler methods based on warping a probabilistic atlas have been widely adopted. Here, we develop a cortical parcellation method for MR brain images based on Convolutional Neural Networks (ConvNets), a machine-learning method, with the goal of automatically transferring the knowledge obtained from surface analyses onto something directly applicable on simpler volume data. We train a ConvNet on a large (thousand) set of cortical ribbons of multiple MRI cohorts, to reproduce parcellations obtained from a surface method, in this case FreeSurfer. Further, to make the model applicable in a broader context, we force the model to generalize to unseen segmentations. The model is evaluated on unseen data of unseen cohorts. We characterize the behavior of the model during learning, and quantify its reliance on the dataset itself, which tends to give support for the necessity of large training sets, augmentation, and multiple contrasts. Overall, ConvNets can provide an efficient way to parcel MRI images, following the guidance established within more complex methods, quickly and accurately. The trained model is embedded within a open-source parcellation tool available at https://github.com/bthyreau/parcelcortex.     

An efficient algorithm for topologically correct segmentation of the cortical sheet in anatomical mr volumes

Polygon-mesh representations of the cortices of individual subjects are of anatomical interest, aid visualization of functional imaging data and provide important constraints for their statistical analysis. Due to noise and partial volume sampling, however, conventional segmentation methods rarely yield a voxel object whose outer boundary represents the folded cortical sheet without topological errors. These errors, called handles, have particularly deleterious effects when the polygon mesh constructed from the segmented voxel representation is inflated or flattened. So far handles had to be removed by cumbersome manual editing, or the computationally more expensive method of reconstruction by morphing had to be used, incorporating the a priori constraint of simple topology into the polygon-mesh model. Here we describe a linear time complexity algorithm that automatically detects and removes handles in presegmentations of the cortex obtained by conventional methods. The algorithm's modifications reflect the true structure of the cortical sheet. The core component of our method is a region growing process that starts deep inside the object, is prioritized by the distance-to-surface of the voxels considered for inclusion and is selftouching-sensitive, i.e., voxels whose inclusion would add a handle are never included. The result is a binary voxel object identical to the initial object except for "cuts" located in the thinnest part of each handle. By applying the same method to the inverse object, an alternative set of solutions is determined, correcting the errors by addition instead of deletion of voxels. For each handle separately, the solution more consistent with the intensities of the original anatomical MR scan is chosen. The accuracy of the resulting polygon-mesh reconstructions has been validated by visual inspection, by quantitative comparison to an expert's manual corrections, and by crossvalidation between reconstructions from different scans of the same subject's cortex.     

Direct cortical mapping via solving partial differential equations on implicit surfaces

In this paper, we propose a novel approach for cortical mapping that computes a direct map between two cortical surfaces while satisfying constraints on sulcal landmark curves. By computing the map directly, we can avoid conventional intermediate parameterizations and help simplify the cortical mapping process. The direct map in our method is formulated as the minimizer of a flexible variational energy under landmark constraints. The energy can include both a harmonic term to ensure smoothness of the map and general data terms for the matching of geometric features. Starting from a properly designed initial map, we compute the map iteratively by solving a partial differential equation (PDE) defined on the source cortical surface. For numerical implementation, a set of adaptive numerical schemes are developed to extend the technique of solving PDEs on implicit surfaces such that landmark constraints are enforced. In our experiments, we show the flexibility of the direct mapping approach by computing smooth maps following landmark constraints from two different energies. We also quantitatively compare the metric preserving property of the direct mapping method with a parametric mapping method on a group of 30 subjects. Finally, we demonstrate the direct mapping method in the brain mapping applications of atlas construction and variability analysis.     

Brain tissue segmentation in MR images based on a hybrid of MRF and social algorithms

Effective abnormality detection and diagnosis in Magnetic Resonance Images (MRIs) requires a robust segmentation strategy. Since manual segmentation is a time-consuming task which engages valuable human resources, automatic MRI segmentations received an enormous amount of attention. For this goal, various techniques have been applied. However, Markov Random Field (MRF) based algorithms have produced reasonable results in noisy images compared to other methods. MRF seeks a label field which minimizes an energy function. The traditional minimization method, simulated annealing (SA), uses Monte Carlo simulation to access the minimum solution with heavy computation burden. For this reason, MRFs are rarely used in real time processing environments. This paper proposed a novel method based on MRF and a hybrid of social algorithms that contain an ant colony optimization (ACO) and a Gossiping algorithm which can be used for segmenting single and multispectral MRIs in real time environments. Combining ACO with the Gossiping algorithm helps find the better path using neighborhood information. Therefore, this interaction causes the algorithm to converge to an optimum solution faster. Several experiments on phantom and real images were performed. Results indicate that the proposed algorithm outperforms the traditional MRF and hybrid of MRF-ACO in speed and accuracy.     

Brain cortical activation during guitar-induced hand dystonia studied by functional MRI

Focal hand dystonia in musicians is a strongly task-related movement disorder. Typically, symptoms become apparent only when players execute specific overpracticed skilled exercises on their instrument. We therefore examined five guitarists with functional MRI during dystonic symptom provocation by means of an adapted guitar inside the magnet. The activation patterns obtained in comparable nondystonic guitarists and in the study patients when performing normal-hand exercise served as references. A 1.5-T system equipped with echo-speed gradients and single-shot echoplanar imaging software was used. Data acquisition was centered on the cortical motor system encompassed in eight contiguous slices. Dystonic musicians compared with both control situations showed a significantly larger activation of the contralateral primary sensorimotor cortex that contrasted with a conspicuous bilateral underactivation of premotor areas. Our results coincide with studies of other dystonia types in that they show an abnormal recruitment of cortical areas involved in the control of voluntary movement. However, they do suggest that the primary sensorimotor cortex, rather than being underactive in idiopathic dystonic patients, may be overactive when tested during full expression of the task-induced movement disorder.