Atlas Space Research Articles

Abstract WP90: Voxel-Based Lesion Symptom Mapping (VLSM) of NIH Stroke Scale Subscore Deficits

Background: Studies identifying brain regions required to preserve specific neurologic functions after stroke typically analyze infarct volume or location. Lesion topography studies have found that, independent of volume, involvement of specific regions have greater impact on clinical outcome than others, suggesting location-determined differences in eloquence. However, most anatomy-based studies define location broadly. VLSM is an imaging analysis technique that establishes a relationship between precise lesion location and clinical deficit. A group of patients with a symptom (e.g. aphasia) is analyzed; every voxel on each patient’s MRI is evaluated for lesion presence or absence. Each voxel is assigned a t-statistic, and a statistical map of all lesioned voxels is generated to pinpoint regions most strongly associated with the deficit; a high t-score indicates a lesion in that voxel has a significant effect on the specified symptom. We generated VLSM maps for 6 NIHSS subscores (aphasia, right- and left-limb weakness, and sensory loss) in a novel characterization to be used in future research. Methods: 172 acute ischemic stroke (AIS) patients with large vessel occlusions (LVOs) were analyzed. Binary masks of infarcts on D5 FLAIR sequences were created. Lesions were coregistered to standard MNI atlas space. VLSM V2.55 was used to generate statistical maps of lesion contribution to clinical deficit. Maps were thresholded to p<0.001 on basis of cluster size and permutation method. A symptom reference area was defined as a region on which voxels had a t-score >3.14. Results: VLSM maps with voxelwise thresholds of p<0.001 were generated for 6 NIHSS categories (examples in figure). Conclusions: VLSM successfully generated unique maps of 6 NIHSS subscore deficits. These maps will be used to study patients presenting with perfusion/diffusion mismatch to predict the potential for resolution of specific deficits with reperfusion therapy and aid in prognostication.

A novel extended phase correlation algorithm based on Log-Gabor filtering for multimodal remote sensing image registration

ABSTRACT Automatic registration of multimodal remote sensing images, which is a critical prerequisite in a range of applications (e.g. image fusion, image mosaic, and image analysis), continues to be a fundamental and challenging problem. In this paper, we propose a novel extended phase correlation algorithm based on Log-Gabor filtering (LGEPC) for the registration of images with nonlinear radiometric differences and geometric differences (e.g. rotation, scale, and translation). Our algorithm focuses on two problems that the traditional extended phase correlation algorithms cannot well handle: 1) significant nonlinear radiometric differences and 2) large-scale differences between image pairs. After an over-complete multi-scale atlas space of the original image is built based on the filtered magnitudes obtained by using Log-Gabor filters with different central frequencies, the phase correlation of the single scale images is extended by LGEPC to atlases phase correlation, which is conducive to solving the problem of large scale and rotation differences between the image pairs. Subsequently, LGEPC eliminates the interface of the significant nonlinear radiometric differences by superimposing multi-scale geometric structural spectra and carrying out the phase correlation module, so that the translation can be well determined. Our experiments on synthetic images demonstrated the rationality and effectiveness of LGEPC, and the experiments on a variety of multimodal images confirmed that LGEPC can ideally achieve pixel-wise registration accuracy for multimodal image pairs that conform to the similarity transformation model.

Rat brain digital stereotaxic white matter atlas with fine tract delineation in Paxinos space and its automated applications in DTI data analysis

PurposeTo automatically analyze diffusion tensor images of the rat brain via both voxel-based and ROI-based approaches, we constructed a new white matter atlas of the rat brain with fine tracts delineation in the Paxinos and Watson space. Materials and methodsUnlike in previous studies, we constructed a digital atlas image from the latest edition of the Paxinos and Watson. This atlas contains 111 carefully delineated white matter fibers. A white matter network of rat brain based on anatomy was constructed by locating the intersection of all these tracts and recording the nuclei on the pathway of each white matter tract. Moreover, a compatible rat brain template from DTI images was created and standardized into the atlas space. To evaluate the automated application of the atlas in DTI data analysis, a group of rats with right-side middle cerebral artery occlusion (MCAO) and those without were enrolled in this study. ResultsThe voxel-based analysis result shows that the brain region showing significant declines in signal in the MCAO rats was consistent with the occlusion position. ConclusionWe constructed a stereotaxic white matter atlas of the rat brain with fine tract delineation and a compatible template for the data analysis of DTI images of the rat brain.

3D Correlation Mapping between Changes in Cartilage T1ρ and Thickness Over 1-year after ACL Reconstruction using Atlas-based Methods

Purpose: Subjects with anterior cruciate ligament (ACL) injury are at risk for post-traumatic osteoarthritis (PTOA). T1ρ MRI has been used to detect early degeneration after ACL injury and reconstruction. Previous studies also revealed significant changes in cartilage thickness after ACL injury, with thickness increasing in some compartments while decreasing in other compartments. However, the correlation between the change in T1ρ and the change in cartilage thickness has not been demonstrated. A better understanding of these correlations will help with staging the cartilage degeneration status after ACL injury. Very recently, a novel atlas-based method was developed which permits voxel-based relaxometry analysis (VBR). The goal of this study was to apply the atlas-based method to evaluate the local voxel-by-voxel correlation between changes in T1ρ and changes in thickness from baseline to 6-months and 1-year after ACL reconstruction (ACLR). Methods: Bilateral knees were scanned using a 3T MRI scanner for twenty-five patients with ACL injuries prior to surgical reconstruction (baseline, BL), and 6-months (6M) and 1-year (1Y) after ACLR (age = 28.4 ± 8.2 years, BMI = 23.8± 2.7 kg/m2, 10 female). The imaging protocol included the 3D MAPSS T1ρ/T2 sequence used for cartilage relaxation times quantification and high-resolution 3D FSE (CUBE) used for WORMS grading and semi-automatic cartilage segmentation. Those segmentations were used to define a voxel based thickness map for each subject. An atlas based registration approach was then used to morph all the T1ρ-weighted images and the thickness maps to the same reference space, and T1ρ maps were computed in the atlas space allowing for voxel-by-voxel correspondence between T1ρ and thickness. Longitudinal changes in cartilage thickness and T1ρ, as well as the local Pearson correlation coefficients between changes in T1ρ and changes in thickness were calculated voxel-by-voxel. Both analyses were adjusted for age, gender and BMI. The level of significance was set at p<0.05. Percentage of significant voxel (PSV, %) with positive or negative correlation and the mean value of correlation coefficients (R) were calculated in each compartment. Results: Significant increases of T1ρ in MFC and trochlea, and significant decreases of T1ρ in patella were observed; while significant increases of cartilage thickness in patella and significant decreases of cartilage thickness in trochlea were observed (Fig. 1 A–B). The most significant correlation between changes in T1ρ and changes in thickness was observed in patella, LFC, trochlea and MFC (Fig. 1C). In the patella, significant negative correlation was found between changes in T1ρ and changes in thickness from BL to 6M (38.4% voxels, R=−0.536) and from BL to 1Y (15.1% voxels, R=−0.590) (Tab1). This correlation was primarily the result of a decrease in T1ρ and an increase in thickness, while in other compartments, the negative correlations primarily resulted from an increase in T1ρ and a decrease in thickness. From 6M to 1Y, in LFC, a large decrease of the positive correlation PSV (from 11.2% to 2.5%) and a slight increase of negative correlation PSV were observed. There is an increasing trend of the total cartilage WORMS scores from BL (2.0±2.1) to 6M (2.2±2.1) and 1Y (2.4±2.3), but the increase was not significant. Conclusions: In this study, the local correlation between changes in cartilage matrix composition and changes in cartilage thickness was analyzed voxel-by-voxel using a novel 3D atlas-based method. Significant correlations were observed between ΔT1ρ and ΔΤhickness from BL to 6M and 1Y after ACLR. A positive correlation with increase in T1ρ and thickness may suggest the cartilage is at very early stages of degeneration with tissue swelling; while a negative correlation with increase in T1ρ and decrease in thickness may suggest later stages that cartilage begins to experience tissue loss. From 6M to 1Y, there is a general trend of decreasing positive correlation percentage while an increasing negative correlation percentage (Figure 2) in the femoral condyles and trochlea, suggests a progression of cartilage degeneration, confirmed by change in WORMS. In patella, the negative correlation was driven by the decrease of T1ρ and increase of thickness, which may be associated with changes in loading to patella-femoral joint (PFJ) as well as changes in activities after ACLR. Longer follow-up analysis is warranted to better understand cartilage degeneration progression after ACL injury. Funding from NIH/NIAMS P50 AR060752.

4D Infant Cortical Surface Atlas Construction using Spherical Patch-based Sparse Representation.

The 4D infant cortical surface atlas with densely sampled time points is highly needed for neuroimaging analysis of early brain development. In this paper, we build the 4D infant cortical surface atlas firstly covering 6 postnatal years with 11 time points (i.e., 1, 3, 6, 9, 12, 18, 24, 36, 48, 60, and 72 months), based on 339 longitudinal MRI scans from 50 healthy infants. To build the 4D cortical surface atlas, first, we adopt a two-stage groupwise surface registration strategy to ensure both longitudinal consistency and unbiasedness. Second, instead of simply averaging over the co-registered surfaces, a spherical patch-based sparse representation is developed to overcome possible surface registration errors across different subjects. The central idea is that, for each local spherical patch in the atlas space, we build a dictionary, which includes the samples of current local patches and their spatially-neighboring patches of all co-registered surfaces, and then the current local patch in the atlas is sparsely represented using the built dictionary. Compared to the atlas built with the conventional methods, the 4D infant cortical surface atlas constructed by our method preserves more details of cortical folding patterns, thus leading to boosted accuracy in registration of new infant cortical surfaces.

Atlas-based segmentation technique incorporating inter-observer delineation uncertainty for whole breast

Accurate, efficient auto-segmentation methods are essential for the clinical efficacy of adaptive radiotherapy delivered with highly conformal techniques. Current atlas based auto-segmentation techniques are adequate in this respect, however fail to account for inter-observer variation. An atlas-based segmentation method that incorporates inter-observer variation is proposed. This method is validated for a whole breast radiotherapy cohort containing 28 CT datasets with CTVs delineated by eight observers. To optimise atlas accuracy, the cohort was divided into categories by mean body mass index and laterality, with atlas’ generated for each in a leave-one-out approach. Observer CTVs were merged and thresholded to generate an auto-segmentation model representing both inter-observer and inter-patient differences. For each category, the atlas was registered to the left-out dataset to enable propagation of the auto-segmentation from atlas space. Auto-segmentation time was recorded. The segmentation was compared to the gold-standard contour using the dice similarity coefficient (DSC) and mean absolute surface distance (MASD). Comparison with the smallest and largest CTV was also made. This atlas-based auto-segmentation method incorporating inter-observer variation was shown to be efficient (<4min) and accurate for whole breast radiotherapy, with good agreement (DSC>0.7, MASD <9.3mm) between the auto-segmented contours and CTV volumes.

A framework for combining a motion atlas with non-motion information to learn clinically useful biomarkers: Application to cardiac resynchronisation therapy response prediction

We present a framework for combining a cardiac motion atlas with non-motion data. The atlas represents cardiac cycle motion across a number of subjects in a common space based on rich motion descriptors capturing 3D displacement, velocity, strain and strain rate. The non-motion data are derived from a variety of sources such as imaging, electrocardiogram (ECG) and clinical reports. Once in the atlas space, we apply a novel supervised learning approach based on random projections and ensemble learning to learn the relationship between the atlas data and some desired clinical output. We apply our framework to the problem of predicting response to Cardiac Resynchronisation Therapy (CRT). Using a cohort of 34 patients selected for CRT using conventional criteria, results show that the combination of motion and non-motion data enables CRT response to be predicted with 91.2% accuracy (100% sensitivity and 62.5% specificity), which compares favourably with the current state-of-the-art in CRT response prediction.

Classification of Alzheimer Disease using Gabor Texture Feature of Hippocampus Region

The aim of this research is to propose a methodology to classify the subjects into Alzheimer disease and normal control on the basis of visual features from hippocampus region. All three dimensional MRI images were spatially normalized to the MNI/ICBM atlas space. Then, hippocampus region was extracted from brain structural MRI images, followed by application of two dimensional Gabor filter in three scales and eight orientations for texture computation. Texture features were represented on slice by slice basis by mean and standard deviation of magnitude of Gabor response. Classification between Alzheimer disease and normal control was performed with linear support vector machine. This study analyzes the performance of Gabor texture feature along each projection (axial, coronal and sagittal) separately as well as combination of all projections. The experimental results from both single projection (axial) as well as combination of all projections (axial, coronal and sagittal), demonstrated better classification performance over other existing method. Hence, this methodology could be used as diagnostic measure for the detection of Alzheimer disease.

Abstract WMP15: Hyperperfusion on Arterial Spin Labeling: Objective Decision Support Using Pattern Recognition

Background: Hyperperfusion detected on arterial spin labeling (ASL) images acquired after stroke onset has been shown to correlate with subsequent hemorrhagic transformation (HT). Presence of hyperperfusion is typically detected by visual review of arterial spin labeling cerebral blood flow (CBF). Such a review is subjective as it is challenged by inter-reader variability, noise, and lack of standard threshold. We present in this study a quantitative hyperperfusion detection model that can provide an objective decision support for the interpretation of ASL CBF maps and rapidly delineate hyperperfusion regions. Methods: ASL Cerebral blood flow (CBF) maps of acute stroke patients presenting with an occlusion in the MCA territory were coregistered to a standardized atlas space. To achieve reliable detection of ASL hyperperfusion, we formalize the problem as a nonlinear classification that relates regional voxel intensity values to the corresponding binary label (normal or hyperperfused). Our method takes into account the healthy contralateral hemisphere and its CBF intensity values during the determination of hyperperfusion of a voxel. Each input feature vector combines the regional intensity values at the voxel of interest, its contralateral matched region, and the distribution of the difference between them. Each input vector is associated to a label corresponding to the presence of hyperperfusion that was manually established by consensus between experts. The predicted hyperperfusion regions were compared to a groundtruth that manually established by two researchers. Results: A total of 361 ASL scans were collected from 221 patients (age=72±17 years; 45% males). Hyperperfusion was detected in 76 patients that were subsequently used in our analysis. An AUC of 83±5% was reached after a leave-one-out cross-validation, which corresponds to the accuracy in detecting hyperperfusion compared to manual delineation of hyperperfusion on ASL CBF maps. Conclusion: Pattern recognition based on a nonlinear regression can provide an accurate and objective measure of hyperperfusion on ASL CBF images and could therefore improve the detection of hemorrhagic transformation in acute stroke patients.

Inherent Structure-Guided Multi-view Learning for Alzheimer's Disease and Mild Cognitive Impairment Classification.

Multi-atlas based morphometric pattern analysis has been recently proposed for the automatic diagnosis of Alzheimer's disease (AD) and its early stage, i.e., mild cognitive impairment (MCI), where multi-view feature representations for subjects are generated by using multiple atlases. However, existing multi-atlas based methods usually assume that each class is represented by a specific type of data distribution (i.e., a single cluster), while the underlying distribution of data is actually a prior unknown. In this paper, we propose an inherent structure-guided multi-view leaning (ISML) method for AD/MCI classification. Specifically, we first extract multi-view features for subjects using multiple selected atlases, and then cluster subjects in the original classes into several sub-classes (i.e., clusters) in each atlas space. Then, we encode each subject with a new label vector, by considering both the original class labels and the coding vectors for those sub-classes, followed by a multi-task feature selection model in each of multi-atlas spaces. Finally, we learn multiple SVM classifiers based on the selected features, and fuse them together by an ensemble classification method. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrate that our method achieves better performance than several state-of-the-art methods in AD/MCI classification.

NI-54 * HYPERVASCULAR VOLUME ESTIMATED BY COMPARISON TO A LARGE-SCALE CEREBRAL BLOOD VOLUME (CBV) RADIOGRAPHIC ATLAS PREDICTS SURVIVAL IN RECURRENT GLIOBLASTOMA TREATED WITH BEVACIZUMAB

Background: Dynamic susceptibility contrast (DSC)-MRI is a well-established perfusion MR imaging technique for estimating relative cerebral blood volume (CBV) in primary brain tumors; however, tumors localized to regions with naturally elevated perfusion, including cortical tissue and common vascular territories, make evaluation of tumor vascularity difficult to assess. In the current study, we have constructed a large-scale radiographic atlas of CBV to assess treatment response to bevacizumab in individual patients with recurrent glioblastoma. Methods: Z-score normalized CBV maps were registered to stereotactic atlas space in 450 patients with brain tumors. A CBV atlas was created by calculating the voxel-wise mean and variability in CBV. MRI and CBV maps from 32 recurrent glioblastoma patients were then obtained prior to and following treatment with bevacizumab, registered to and compared with the CBV atlas. The volume of tumor tissue with elevated CBV, percentage of enhancing tumor with elevated CBV, and the mean and maximum change in normalized CBV intensity relative to the atlas were computed. Results: Voxel-wise comparison of individual patient CBV maps to the atlas allowed delineation of elevated tumor perfusion from artery and normal cortical tissue. An atlas-defined hypervascular tumor blood volume greater than 2.35 cc prior to treatment, 0.14 cc after treatment, and a decrease in atlas-defined hypervascular tumor volume less than 80% following treatment were characteristic of a shorter PFS and OS. Traditional measures of CBV were not predictive of PFS or OS. Conclusions: This study highlights the advantages of large-scale population maps to identify abnormal biological tissues.

A statistical parametric mapping toolbox used for voxel-wise analysis of FDG-PET images of rat brain.

PurposePET (positron emission tomography) imaging researches of functional metabolism using fluorodeoxyglucose (18F-FDG) of animal brain are important in neuroscience studies. FDG-PET imaging studies are often performed on groups of rats, so it is desirable to establish an objective voxel-based statistical methodology for group data analysis.Material and MethodsThis study establishes a statistical parametric mapping (SPM) toolbox (plug-ins) named spmratIHEP for voxel-wise analysis of FDG-PET images of rat brain, in which an FDG-PET template and an intracranial mask image of rat brain in Paxinos & Watson space were constructed, and the default settings were modified according to features of rat brain. Compared to previous studies, our constructed rat brain template comprises not only the cerebrum and cerebellum, but also the whole olfactory bulb which made the later cognitive studies much more exhaustive. And with an intracranial mask image in the template space, the brain tissues of individuals could be extracted automatically. Moreover, an atlas space is used for anatomically labeling the functional findings in the Paxinos & Watson space. In order to standardize the template image with the atlas accurately, a synthetic FDG-PET image with six main anatomy structures is constructed from the atlas, which performs as a target image in the co-registration.ResultsThe spatial normalization procedure is evaluated, by which the individual rat brain images could be standardized into the Paxinos & Watson space successfully and the intracranial tissues could also be extracted accurately. The practical usability of this toolbox is evaluated using FDG-PET functional images from rats with left side middle cerebral artery occlusion (MCAO) in comparison to normal control rats. And the two-sample t-test statistical result is almost related to the left side MCA.ConclusionWe established a toolbox of SPM8 named spmratIHEP for voxel-wise analysis of FDG-PET images of rat brain.

Automated workflow for mapping tracer injection studies of the common marmoset into a reference template

Event Abstract Back to Event Automated workflow for mapping tracer injection studies of the common marmoset into a reference template Piotr Majka1*, Tristan A. Chaplin2, 3, 4, Hsin-Hao Yu2, 3, Vadim Pinskiy5, Partha Mitra5, Marcello Rosa2, 3, 4 and Daniel K. Wójcik1 1 Nencki Institute of Experimental Biology, Poland 2 Department of Physiology, Monash University, Australia 3 Australian Research Council Centre of Excellence for Integrative Brain Function, Australia 4 Monash Vision Group, Monash University, Australia 5 Cold Spring Harbor Laboratories, United States The goal of the study is to establish an automated workflow for mapping common marmoset connectivity data obtained from tracer injection studies into reference template space of a stereotaxic atlas [1, 2]. Nine marmosets were injected with fluorescent retrograde tracers in the dorsolateral prefrontal cortex. Retrograde tracers label the cell bodies of neurons that send projections to the injection site, thus providing a map of neuronal inputs. Due to the limited number of distinguishable tracers, building a map of connectivity requires the registration of multiple specimens to a common atlas. Furthermore, registration to a common coordinate system will allow purely spatially based comparisons of connectivity unlike the traditional method relying on prior assignment of data to discrete anatomical structures. Several steps are required to map the data obtained from a single specimen into the atlas space. During the initial stage, the locations of stained cells marked on the fluorescence sections are transferred to the neighboring Nissl sections. Afterwards, the Nissl stained sections are stacked and reconstructed into volumetric form. The reconstruction is initially performed with affine transformations followed by deformable warping. The latter step removes section specific distortions and allows for more reliable subsequent deformable mapping [3] into the atlas space. The process yields a set of transformations which are then applied to the actual cells locations. In the final step the individual cells are assigned to a particular brain structure based on the atlas parcellation. The described process will be conducted for nine test cases and will result in a database of the cell's coordinates in the atlas space. The reliability of the workflow will be assessed by comparing the number of the cells in each cortical area indicated by the automated approach with the count determined manually by an anatomist. Once established, the workflow will allow the processing of the remaining cases to produce a spatially defined connectivity map of the marmoset cortex, independent of anatomical parcellation scheme [4]. Furthermore, this map can be used as a gold standard in DTI validation studies.

Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification.

In order to establish the correspondences between different brains for comparison, spatial normalization based morphometric measurements have been widely used in the analysis of Alzheimer's disease (AD). In the literature, different subjects are often compared in one atlas space, which may be insufficient in revealing complex brain changes. In this paper, instead of deploying one atlas for feature extraction and classification, we propose a maximum-margin based representation learning (MMRL) method to learn the optimal representation from multiple atlases. Unlike traditional methods that perform the representation learning separately from the classification, we propose to learn the new representation jointly with the classification model, which is more powerful in discriminating AD patients from normal controls (NC). We evaluated the proposed method on the ADNI database, and achieved 90.69% for AD/NC classification and 73.69% for p-MCI/s-MCI classification.

First generation Waxholm atlas of the Sprague-Dawley rat brain

Event Abstract Back to Event First generation Waxholm atlas of the Sprague-Dawley rat brain Eszter A. Papp1*, Trygve B. Leergaard1, G. Allan Johnson2 and Jan G. Bjaalie1 1 CMBN, Institute of Basic Medical Sciences, University of Oslo, Norway 2 Center for in vivo Microscopy, Dept Radiology, Duke University Medical Center, United States Standardized brain atlas spaces provide key anchoring points for comparing heterogeneous datasets from different experimental animals in the context of structure - function analysis. The usability of such an atlas space depends on common access to high quality reference material, including delineations of anatomical structures (labels), and underlying original images (templates). Analysis of microscopic data of 3D nature, e.g. gene expression distributions and connectivity patterns, can to advantage make use of high resolution non-distorted volumetric templates and associated atlas labels for the rat brain. We present a first generation of such reference material for the standard Waxholm Space in the Sprague-Dawley rat. Microscopic resolution ex vivo magnetic resonance images (MRI) were acquired from an 80 day old male Sprague-Dawley rat, including T2* anatomical images with 39 μm isotropic voxels, and diffusion tensor images (DTI) with 78 μm isotropic voxels. Anatomical structures, including nuclei, areas, and fiber tracts, were delineated based on image contrast using ITK-SNAP software, resulting in 67 distinct labels along with detailed delineation criteria. Labels representing cortical areas have been transferred from an existing atlas (Hjornevik et al., http://dx.doi.org/10.3389/neuro.11.004.2007 ), warped into the volumetric template, and manually adjusted for shape differences. Validation of atlas labels was aided by collections of histological images from brains of comparable animals, and delineations from other rat brain atlases. The volumetric template, as well as the atlas labels, will be made open access through the INCF Software Center. Spatial reference is provided by the application of Waxholm Space, a standard atlas space recently defined by the International Neuroinformatics Coordinating Facility (INCF). The use of Waxholm Space connects the atlas to a growing infrastructure of interoperable resources and services for multi-level data integration and analysis across reference spaces. The presented atlas serves as a basis for a library of individual volumetric templates for different applications, e.g. different strains, disease models, and developmental stages. The atlas is to be included in a server-based registration pipeline as part of the INCF Digital Atlasing Infrastructure, allowing registration of both experimental data and new suitable templates to the atlas. Keywords: digital atlasing, Sprague-Dawley rat brain, Waxholm Space, Neuroimaging, computational neuroscience Conference: 5th INCF Congress of Neuroinformatics, Munich, Germany, 10 Sep - 12 Sep, 2012. Presentation Type: Poster Topic: Neuroinformatics Citation: Papp E, Leergaard T, Johnson G and Bjaalie J (2014). First generation Waxholm atlas of the Sprague-Dawley rat brain. Front. Neuroinform. Conference Abstract: 5th INCF Congress of Neuroinformatics. doi: 10.3389/conf.fninf.2014.08.00072 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 21 Mar 2013; Published Online: 27 Feb 2014. * Correspondence: Dr. Eszter A. Papp, CMBN, Institute of Basic Medical Sciences, University of Oslo, Oslo, Norway, e.a.papp@medisin.uio.no Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Eszter A. Papp Trygve B. Leergaard G. Allan Johnson Jan G. Bjaalie Google Eszter A. Papp Trygve B. Leergaard G. Allan Johnson Jan G. Bjaalie Google Scholar Eszter A. Papp Trygve B. Leergaard G. Allan Johnson Jan G. Bjaalie PubMed Eszter A. Papp Trygve B. Leergaard G. Allan Johnson Jan G. Bjaalie Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

ACM-Based Automatic Liver Segmentation From 3-D CT Images by Combining Multiple Atlases and Improved Mean-Shift Techniques

In this paper, we present an autocontext model(ACM)-based automatic liver segmentation algorithm, which combines ACM, multiatlases, and mean-shift techniques to segment liver from 3-D CT images. Our algorithm is a learning-based method and can be divided into two stages. At the first stage, i.e., the training stage, ACM is performed to learn a sequence of classifiers in each atlas space (based on each atlas and other aligned atlases). With the use of multiple atlases, multiple sequences of ACM-based classifiers are obtained. At the second stage, i.e., the segmentation stage, the test image will be segmented in each atlas space by applying each sequence of ACM-based classifiers. The final segmentation result will be obtained by fusing segmentation results from all atlas spaces via a multiclassifier fusion technique. Specially, in order to speed up segmentation, given a test image, we first use an improved mean-shift algorithm to perform over-segmentation and then implement the region-based image labeling instead of the original inefficient pixel-based image labeling. The proposed method is evaluated on the datasets of MICCAI 2007 liver segmentation challenge. The experimental results show that the average volume overlap error and the average surface distance achieved by our method are 8.3% and 1.5 m, respectively, which are comparable to the results reported in the existing state-of-the-art work on liver segmentation.

Software-based Diffusion MR Human Brain Phantom for Evaluating Fiber-tracking Algorithms.

Fiber tracking provides insights into the brain white matter network and has become more and more popular in diffusion MR imaging. Hardware or software phantom provides an essential platform to investigate, validate and compare various tractography algorithms towards a "gold standard". Software phantoms excel due to their flexibility in varying imaging parameters, such as tissue composition, SNR, as well as potential to model various anatomies and pathologies. This paper describes a novel method in generating diffusion MR images with various imaging parameters from realistically appearing, individually varying brain anatomy based on predefined fiber tracts within a high-resolution human brain atlas. Specifically, joint, high resolution DWI and structural MRI brain atlases were constructed with images acquired from 6 healthy subjects (age 22-26) for the DWI data and 56 healthy subject (age 18-59) for the structural MRI data. Full brain fiber tracking was performed with filtered, two-tensor tractography in atlas space. A deformation field based principal component model from the structural MRI as well as unbiased atlas building was then employed to generate synthetic structural brain MR images that are individually varying. Atlas fiber tracts were accordingly warped into each synthetic brain anatomy. Diffusion MR images were finally computed from these warped tracts via a composite hindered and restricted model of diffusion with various imaging parameters for gradient directions, image resolution and SNR. Furthermore, an open-source program was developed to evaluate the fiber tracking results both qualitatively and quantitatively based on various similarity measures.

Longitudinal tracking of white matter connectivity in Huntington's disease: 30 month longitudinal data from the IMAGE-HD study

Event Abstract Back to Event Longitudinal tracking of white matter connectivity in Huntington's disease: 30 month longitudinal data from the IMAGE-HD study Govinda Poudel1*, Juan Dominguez1, Louisa Salmon1, Andrew Churchyard2, Phyllis Chua1, Julie Stout1, Gary F. Egan1 and Nellie Georgiou-Karistianis1 1 Monash University, School of Psychology and Psychiatry, Australia 2 Monash Medical Centre, Australia Background: Disruption of structural integrity of specific neural circuits has been proposed to be one of the possible mechanisms underlying progressive deterioration in cognitive and motor function in Huntington’s disease (HD). The aim of this study was to use an unbiased longitudinal diffusion tensor imaging (DTI) analysis approach to track the microstructural integrity of white matter connections in pre-manifest (pre-HD) and symptomatic HD (symp-HD) individuals. Methods: DTI data from 22 pre-HD, 19 symp-HD, and 22 healthy controls was collected at baseline, 18 months, and 30 months, from a cohort of participants in the IMAGE-HD study. DTI data were preprocessed to remove eddy-current and motion artefacts. For longitudinal analysis, we adopted a tensor-based registration pipeline that used full tensor information in DTI data to drive improved alignment over multiple time points and across groups. White matter tracts of interest were delineated by segmenting fractional anisotropy (FA) map of the group atlas using a locally adaptive segmentation algorithm. Body, genu, and splenium of corpus callosum fibre bundle were located by normalization in an atlas space. Microstructural integrity was assessed by statistical analysis of FA values. Results: We observed selective loss in integrity of corpus callosum fibre bundle in both pre-HD close to onset and symp-HD groups. Symp-HD showed significant reduction of FA in all parts of corpus callosum, whereas in pre-HD close to onset FA reduction was topographically selective and localized in the splenium and body of corpus callosum. Discussion: Given that the corpus callosum plays an important role in interhemispheric connectivity, our findings suggest for the first time, that there is a progressive disruption in cortico-cortical structural connectivity in HD. Keywords: Diffusion Tensor Imaging, Huntington's disease, Corpus Callosum, fractional anisotropy, connectivity Conference: ACNS-2013 Australasian Cognitive Neuroscience Society Conference, Clayton, Melbourne, Australia, 28 Nov - 1 Dec, 2013. Presentation Type: Poster Topic: Motor Citation: Poudel G, Dominguez J, Salmon L, Churchyard A, Chua P, Stout J, Egan GF and Georgiou-Karistianis N (2013). Longitudinal tracking of white matter connectivity in Huntington's disease: 30 month longitudinal data from the IMAGE-HD study. Conference Abstract: ACNS-2013 Australasian Cognitive Neuroscience Society Conference. doi: 10.3389/conf.fnhum.2013.212.00012 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 15 Oct 2013; Published Online: 25 Nov 2013. * Correspondence: Dr. Govinda Poudel, Monash University, School of Psychology and Psychiatry, Clayton, Australia, govinda.poudel@monash.edu Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Govinda Poudel Juan Dominguez Louisa Salmon Andrew Churchyard Phyllis Chua Julie Stout Gary F Egan Nellie Georgiou-Karistianis Google Govinda Poudel Juan Dominguez Louisa Salmon Andrew Churchyard Phyllis Chua Julie Stout Gary F Egan Nellie Georgiou-Karistianis Google Scholar Govinda Poudel Juan Dominguez Louisa Salmon Andrew Churchyard Phyllis Chua Julie Stout Gary F Egan Nellie Georgiou-Karistianis PubMed Govinda Poudel Juan Dominguez Louisa Salmon Andrew Churchyard Phyllis Chua Julie Stout Gary F Egan Nellie Georgiou-Karistianis Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Ensemble Learning Incorporating Uncertain Registration

This paper proposes a novel approach for improving the accuracy of statistical prediction methods in spatially normalized analysis. This is achieved by incorporating registration uncertainty into an ensemble learning scheme. A probabilistic registration method is used to estimate a distribution of probable mappings between subject and atlas space. This allows the estimation of the distribution of spatially normalized feature data, e.g., grey matter probability maps. From this distribution, samples are drawn for use as training examples. This allows the creation of multiple predictors, which are subsequently combined using an ensemble learning approach. Furthermore, extra testing samples can be generated to measure the uncertainty of prediction. This is applied to separating subjects with Alzheimer's disease from normal controls using a linear support vector machine on a region of interest in magnetic resonance images of the brain. We show that our proposed method leads to an improvement in discrimination using voxel-based morphometry and deformation tensor-based morphometry over bootstrap aggregating, a common ensemble learning framework. The proposed approach also generates more reasonable soft-classification predictions than bootstrap aggregating. We expect that this approach could be applied to other statistical prediction tasks where registration is important.

Registration workflows for the creation of INCF digital atlas hubs

Workflows are being developed around specific data sharing use cases (Figure 2a). At this time, the use cases focus on 2D brain slice images (some sparsely, others highly sampled) of various modalities. The goal is to create tools, recommendations, and standard operating procedures to aid in the registration of data to a known standard atlas space (Figure 2b) and ability to share that data through INCF atlas hubs or to create new hubs (Figures 2c and 3). More information can be found at http://atlasing.incf.org/wiki/Workflow.