Search

To develop and evaluate an automatic segmentation method that extracts the 3D configuration of the ablation zone, the iceball, from images acquired during the freezing phase of MRI-guided cryoablation.Intraprocedural images at 63 timepoints from 13 kidney tumor cryoablation procedures were examined retrospectively. The images were obtained using a 3 Tesla wide-bore MRI scanner and axial HASTE sequence. Initialized with semiautomatically localized cryoprobes, the iceball was segmented automatically at each timepoint using the graph cut (GC) technique with adapted shape priors.The average Dice Similarity Coefficients (DSC), compared with manual segmentations, were 0.88, 0.92, 0.92, 0.93, and 0.93 at 3, 6, 9, 12, and 15 min timepoints, respectively, and the average DSC of the total 63 segmentations was 0.92 ± 0.03. The proposed method improved the accuracy significantly compared with the approach without shape prior adaptation (P = 0.026). The number of probes involved in the procedure had no apparent influence on the segmentation results using our technique. The average computation time was 20 s, which was compatible with an intraprocedural setting.Our automatic iceball segmentation method demonstrated high accuracy and robustness for practical use in monitoring the progress of MRI-guided cryoablation.

International audience; The clustering of fibers into bundles is an important task in studying the structure and function of white matter. Existing technology mostly relies on geometrical features, such as the shape of fibers, and thus only provides very limited information about the neuroanatomical function of the brain. We advance this issue by proposing a multinomial representation of fibers decoding their connectivity to gray matter regions. We then simplify the clustering task by rst deriving a compact encoding of our representation via the logit transformation. Furthermore, we define a distance between fibers that is in theory invariant to parcellation biases and is equivalent to a family of Riemannian metrics on the simplex of multinomial probabilities. We apply our method to longitudinal scans of two healthy subjects showing high reproducibility of the resulting fiber bundles without needing to register the corresponding scans to a common coordinate system. We con firm these qualitative findings via a simple statistical analyse of the fiber bundles.

Transrectal ultrasound (TRUS) facilitates intra-treatment delineation of the prostate gland (PG) to guide insertion of brachytherapy seeds, but the prostate substructure and apex are not always visible which may make the seed placement sub-optimal. Based on an elastic model of the prostate created from MRI, where the prostate substructure and apex are clearly visible, we use a Bayesian approach to estimate the posterior distribution on deformations that aligns the pre-treatment MRI with intra-treatment TRUS. Without apex information in TRUS, the posterior prediction of the location of the prostate boundary, and the prostate apex boundary in particular, is mainly determined by the pseudo stiffness hyper-parameter of the prior distribution. We estimate the optimal value of the stiffness through likelihood maximization that is sensitive to the accuracy as well as the precision of the posterior prediction at the apex boundary. From a data-set of 10 pre- and intra-treatment prostate images with ground truth delineation of the total PG, 4 cases were used to establish an optimal stiffness hyper-parameter when 15% of the prostate delineation was removed to simulate lack of apex information in TRUS, while the remaining 6 cases were used to cross-validate the registration accuracy and uncertainty over the PG and in the apex.

This paper proposes a method for aligning image volumes acquired from different imaging modalities (e.g. MR, CT) based on 3D scale-invariant image features. A novel method for encoding invariant feature geometry and appearance is developed, based on the assumption of locally linear intensity relationships, providing a solution to poor repeatability of feature detection in different image modalities. The encoding method is incorporated into a probabilistic feature-based model for multi-modal image alignment. The model parameters are estimated via a group-wise alignment algorithm, that iteratively alternates between estimating a feature-based model from feature data, then realigning feature data to the model, converging to a stable alignment solution with few pre-processing or pre-alignment requirements. The resulting model can be used to align multi-modal image data with the benefits of invariant feature correspondence: globally optimal solutions, high efficiency and low memory usage. The method is tested on the difficult RIRE data set of CT, T1, T2, PD and MP-RAGE brain images of subjects exhibiting significant inter-subject variability due to pathology.

The segmentation of MRI scans of patients with white matter lesions (WML) is difficult because the MRI characteristics of WML are similar to those of gray matter. Intensity-based statistical classification techniques misclassify some WML as gray matter and some gray matter as WML.We developed a fast elastic matching algorithm that warps a reference data set containing information about the location of the gray matter into the approximate shape of the patient's brain. The region of white matter was segmented after segmenting the cortex and deep gray matter structures. The cortex was identified by using a three-dimensional, region-growing algorithm that was constrained by anatomical, intensity gradient, and tissue class parameters. White matter and WML were then segmented without interference from gray matter by using a two-class minimum-distance classifier.Analysis of double-echo spin-echo MRI scans of 16 patients with clinically determined multiple sclerosis (MS) was carried out. The segmentation of the c...

The segmentation of MRI scans of patients with white matter lesions (WML) is difficult because the MRI characteristics of WML are similar to those of gray matter. Intensity-based statistical classification techniques misclassify some WML as gray matter and some gray matter as WML. We developed a fast elastic matching algorithm that warps a reference data set containing information about the location of the gray matter into the approximate shape of the patient's brain. The region of white matter was segmented after segmenting the cortex and deep gray matter structures. The cortex was identified by using a three-dimensional, region-growing algorithm that was constrained by anatomical, intensity gradient, and tissue class parameters. White matter and WML were then segmented without interference from gray matter by using a two-class minimum-distance classifier. Analysis of double-echo spin-echo MRI scans of 16 patients with clinically determined multiple sclerosis (MS) was carried out. The segmentation of the cortex and deep gray matter structures provided anatomical context. This was found to improve the segmentation of MS lesions by allowing correct classification of the white matter region despite the overlapping tissue class distributions of gray matter and MS lesion.

The neural correlates of working memory (WM) in schizophrenia (SZ) have been extensively studied using the multi-site fMRI data acquired by the Functional Biomedical Informatics Research Network (fBIRN) consortium. Although univariate and multivariate analysis methods have been variously employed to localize brain responses under differing task conditions, important hypotheses regarding the representation of mental processes in the spatio-temporal patterns of neural recruitment and the differential organization of these mental processes in patients versus controls have not been addressed in this context. This paper uses a multivariate state-space model (SSM) to analyse the differential representation and organization of mental processes of controls and patients performing the Sternberg Item Recognition Paradigm (SIRP) WM task. The SSM is able to not only predict the mental state of the subject from the data, but also yield estimates of the spatial distribution and temporal ordering of neural activity, along with estimates of the hemodynamic response. The dynamical Bayesian modeling approach used in this study was able to find significant differences between the predictability and organization of the working memory processes of SZ patients versus healthy subjects. Prediction of some stimulus types from imaging data in the SZ group was significantly lower than controls, reflecting a greater level of disorganization/heterogeneity of their mental processes. Moreover, the changes in accuracy of predicting the mental state of the subject with respect to parametric modulations, such as memory load and task duration, may have important implications on the neuro-cognitive models for WM processes in both SZ and healthy adults. Additionally, the SSM was used to compare the spatio-temporal patterns of mental activity across subjects, in a holistic fashion and to derive a low-dimensional representation space for the SIRP task, in which subjects were found to cluster according to their diagnosis.

We propose a hierarchical Bayesian model for analyzing multi-site experimental fMRI studies. Our method takes the hierarchical structure of the data (subjects are nested within sites, and there are multiple observations per subject) into account and allows for modeling between-site variation. Using posterior predictive model checking and model selection based on the deviance information criterion (DIC), we show that our model provides a good fit to the observed data by sharing information across the sites. We also propose a simple approach for evaluating the efficacy of the multi-site experiment by comparing the results to those that would be expected in hypothetical single-site experiments with the same sample size.

The efficient extraction of the cryoablation iceball from a time series of 3D images is crucial during cryoablation to assist the interventionalist in determining the coverage of the tumor by the ablated volume. Conventional semi-automatic segmentation tools such as ITK-SNAP and 3D Slicer's Fast Marching Segmentation can attain accurate iceball segmentation in retrospective studies, however, they are not ideal for intraprocedure real time segmentation, as they require time-consuming manual operations, such as the input of fiducials and the extent of the segmented region growth. In this paper, we present an innovative approach for the segmentation of the iceball during cryoablation, that executes a fully automatic computation. Our approach is based on the graph cuts segmentation framework, and incorporates prior information of iceball shape evolving in time, modeled using experimentally-derived iceball growth parameters. Modeling yields a shape prior mask image at each timepoint of the imaging time series for use in the segmentation. Segmentation results of our method and the ITK-SNAP method are compared for 8 timepoints in 2 cases. The results indicate that our fully automatic approach is accurate, robust and highly efficient compared to manual and semi-automatic approaches.

This paper presents feature-based alignment (FBA), a general method for efficient and robust model-to-image alignment. Volumetric images, e.g. CT scans of the human body, are modeled probabilistically as a collage of 3D scale-invariant image features within a normalized reference space. Features are incorporated as a latent random variable and marginalized out in computing a maximum a posteriori alignment solution. The model is learned from features extracted in pre-aligned training images, then fit to features extracted from a new image to identify a globally optimal locally linear alignment solution. Novel techniques are presented for determining local feature orientation and efficiently encoding feature intensity in 3D. Experiments involving difficult magnetic resonance (MR) images of the human brain demonstrate FBA achieves alignment accuracy similar to widely-used registration methods, while requiring a fraction of the memory and computation resources and offering a more robust, globally optimal solution. Experiments on CT human body scans demonstrate FBA as an effective system for automatic human body alignment where other alignment methods break down.

We present what we believe to be the first investigation into unbiased multi-subject registration of whole brain diffusion tractography of the white matter. To our knowledge, this is also the first entropy-based objective function applied to fiber tract registration. To define the probability of fiber trajectories for the computation of entropy, we take advantage of a pairwise fiber distance used as the basis for a Gaussian-like kernel. By employing several values of the kernel's scale parameter, the method is inherently multi-scale. Results of experiments using synthetic and real datasets demonstrate the potential of the method for simultaneous joint registration of tractography.

Understanding and quantifying the uncertainty involved when registering images is an important problem in medical imaging, where clinical decisions are made based on the registered solution. This is especially important in non-rigid registration where the higher degrees of freedom may provide unwarranted confidence in the results, through over-fitting. The Bayesian approach, which defines uncertainty as the posterior distribution on deformations, requires a generative model of the image formation process where the fixed image is modeled as a deformed version of the moving image plus a noise term. As per this model, the likelihood term is equivalent to the sum-of-squared differences image matching metric and is therefore valid only for same-mode image registration. In this paper, we propose a general formalism to quantify Bayesian uncertainty in the registration of multi-modal images through an extended probability model that introduces and then marginalizes out a stochastic transfer function between moving and fixed image intensities.

The delivery of therapeutic prostate interventions can be improved by intraprocedural visualization of the tumor during ultrasound-guided procedures. To this end, ultrasound-based tissue classification and registration of the clinical target volume from preoperative multiparametric MR images to intraoperative ultrasound are suggested as two potential solutions. In this paper we report techniques to implement both of these solutions. In ultrasound-based tissue typing, we employ Laplacian eigenmaps for reducing the dimensionality of the spectral feature space formed by ultrasound RF power spectra. This is followed by support vector machine classification for separating cancer from normal prostate tissue. A classification accuracy of 78.3±4.8% is reported. We also present a deformable MR-US registration method which relies on transforming the binary label maps acquired by delineating the prostate gland in both MRI and ultrasound. This method is developed to transfer the diagnostic references from MRI to US for training and validation of the proposed ultrasound-based prostate tissue classification technique. It yields a target registration error of 3.5±2.1 mm. We also report its use for MR-based dose boosting during ultrasound-guided brachytherapy.

In this paper, anatomical development is modeled as a collection of distinctive image patterns localized in space and time. A Bayesian posterior probability is defined over a random variable of subject age, conditioned on data in the form of scale-invariant image features. The model is automatically learned from a large set of images exhibiting significant variation, used to discover anatomical structure related to age and development, and fit to new images to predict age. The model is applied to a set of 230 infant structural MRIs of 92 subjects acquired at multiple sites over an age range of 8-590 days. Experiments demonstrate that the model can be used to identify age-related anatomical structure, and to predict the age of new subjects with an average error of 72 days.

The uncertainty in registration of medical images may contain important information in cases where clinical decisions are based on registered data. Posing the registration problem in a Bayesian framework allows characterization of the posterior distribution of the deformation parameters which represents the uncertainty of the registration. Uncertainty estimation approaches are complicated by the need to specify the values of hyper-parameters (HPs) of the underlying registration model, e.g. the regularization weight (tissue stiffness) and image noise variance, which have a significant effect on the shape of the posterior distribution. However, it is difficult to assign these HPs physical meaningful values and they are often specified on an ad-hoc basis. In a Bayesian framework, the marginalization of HPs under a suitable prior distribution is a principled alternative to manually tuning the HP values. This paper presents a fast method for marginalizing the HPs of an elastic registration model using local Laplace approximations. We show the feasibility and the advantage of this method in terms of robustness and convergence speed compared to alternative approaches on a clinical image data-set.

The overall goal of this research is the design of statistical atlas models that can be created from normal subjects, but may generalize to be applicable to abnormal brains. We present a new style of joint modeling of fMRI, DTI, and structural MRI. Motivated by the fact that a white matter tract and related cortical areas are likely to displace together in the presence of a mass lesion (brain tumor), in this work we propose a rotation and translation invariant model that represents the spatial relationship between fiber tracts and anatomic and functional landmarks. This landmark distance model provides a new basis for representation of fiber tracts and can be used for detection and prediction of fiber tracts based on landmarks. Our results indicate that the measured model is consistent across normal subjects, and thus suitable for atlas building. Our experiments demonstrate that the model is robust to displacement and missing data, and can be successfully applied to a small group of patients with mass lesions.

In addition to functional localization and integration, the problem of determining whether the data encode some information about the mental state of the subject, and if so, how this information is represented has become an important research agenda in functional neuroimaging. Multivariate classifiers, commonly used for brain state decoding, are restricted to simple experimental paradigms with a fixed number of alternatives and are limited in their representation of the temporal dimension of the task. Moreover, they learn a mapping from the data to experimental conditions and therefore do not explain the intrinsic patterns in the data. In this paper, we present a data–driven approach to building a spatio–temporal representation of mental processes using a state–space formalism, without reference to experimental conditions. Efficient Monte Carlo algorithms for estimating the parameters of the model along with a method for model–size selection are developed. The advantages of such a model in determining the mental–state of the subject over pattern classifiers are demonstrated using an fMRI study of mental arithmetic.

We present a probabilistic framework to estimate the accumulated radiation dose and the corresponding dose uncertainty that is delivered to important anatomical structures, e.g. the primary tumor and healthy surrounding organs, during radiotherapy. The dose uncertainty we report is a direct result of uncertainties in the estimates of the deformation which aligns the daily cone-beam CT images with the planning CT. The accumulated radiation dose is an important measure to monitor during treatment, in particular to see if it significantly deviates from the planned dose which might indicate that either the patient was not properly positioned before treatment or that the anatomy has changed due to the treatment. In the case of the latter, the treatment plan should be adaptively changed to align with the current patient anatomy. We estimate the accumulated dose distribution, and its uncertainty, retrospectively on a dataset acquired during treatment of cancer in the neck and show the dose distributions in the form of dose volume histograms.

We formulate registration-based elastography in a probabilistic framework and apply it to study lung elasticity in the presence of emphysematous and fibrotic tissue. The elasticity calculations are based on a Finite Element discretization of a linear elastic biomechanical model. We marginalize over the boundary conditions (deformation) of the biomechanical model to determine the posterior distribution over elasticity parameters. Image similarity is included in the likelihood, an elastic prior is included to constrain the boundary conditions, while a Markov model is used to spatially smooth the inhomogeneous elasticity. We use a Markov Chain Monte Carlo (MCMC) technique to characterize the posterior distribution over elasticity from which we extract the most probable elasticity as well as the uncertainty of this estimate. Even though registration-based lung elastography with inhomogeneous elasticity is challenging due the problem's highly underdetermined nature and the sparse image information available in lung CT, we show promising preliminary results on estimating lung elasticity contrast in the presence of emphysematous and fibrotic tissue.

Registration uncertainty may be important information to convey to a surgeon when surgical decisions are taken based on registered image data. However, conventional non-rigid registration methods only provide the most likely deformation. In this paper we show how to determine the registration uncertainty, as well as the most likely deformation, by using an elastic Bayesian registration framework that generates a dense posterior distribution on deformations. We model both the likelihood and the elastic prior on deformations with Boltzmann distributions and characterize the posterior with a Markov Chain Monte Carlo algorithm. We introduce methods that summarize the high-dimensional uncertainty information and show how these summaries can be visualized in a meaningful way. Based on a clinical neurosurgical dataset, we demonstrate the importance that uncertainty information could have on neurosurgical decision making.

This paper proposes a novel information theoretic scale-space for salient feature detection, based on the mutual information (MI) of image measurement and location. The MI scale-space is designed to identify image regions whose measurements are maximally informative regarding spatial location. A framework for computing the MI scale-space is proposed, based on combining information theory with Gaussian scale-space theory, where uncertainty in spatial location is explicitly defined by the heat equation. Experiments investigate the use of MI features for feature-based classification of Alzheimer's subjects in volumetric magnetic resonance imagery from a public data set, where MI features result in higher classification accuracy than features selected according to the established difference-of-Gaussian (DOG) criterion [15].

Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. Instead, a latent atlas, initialized by a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The proposed method is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method by segmenting 50 brain MR volumes. Segmentation accuracy for cortical and subcortical structures approaches the quality of state-of-the-art atlas-based segmentation results, suggesting that the latent atlas method is a reasonable alternative when existing atlases are not compatible with the data to be processed.

Objective To quantify size and localization differences between tumors presenting with seizures vs nonseizure neurological symptoms. Design Retrospective imaging survey. We performed magnetic resonance imaging–based morphometric analysis and nonparametric mapping in patients with brain tumors. Setting University-affiliated teaching hospital. Patients or Other Participants One hundred twenty-four patients with newly diagnosed supratentorial glial tumors. Main Outcome Measures Volumetric and mapping methods were used to evaluate differences in size and location of the tumors in patients who presented with seizures as compared with patients who presented with other symptoms. Results In high-grade gliomas, tumors presenting with seizures were smaller than tumors presenting with other neurological symptoms, whereas in low-grade gliomas, tumors presenting with seizures were larger. Tumor location maps revealed that in high-grade gliomas, deep-seated tumors in the pericallosal regions were more likely to present with nonseizure neurological symptoms. In low-grade gliomas, tumors of the temporal lobe as well as the insular region were more likely to present with seizures. Conclusions The influence of size and location of the tumors on their propensity to cause seizures varies with the grade of the tumor. In high-grade gliomas, rapidly growing tumors, particularly those situated in deeper structures, present with non–seizure-related symptoms. In low-grade gliomas, lesions in the temporal lobe or the insula grow large without other symptoms and eventually cause seizures. Quantitative image analysis allows for the mapping of regions in each group that are more or less susceptible to seizures.

SummaryComputer-assisted 3D planning, navigation and the possibilities ottered by intra-operative imaging updates have made a large impact on neurological surgery. Three-dimensional rendering of complex medical image information, as well as co-registration of multimodal sources has reached a highly sophisticated level. When introduced into surgical navigation however, this pre-operative data is unable to account for intra-operative changes, (‘brain-shift’). To update structural information during surgery, an open-configured, intra-operative MRI (Signa SP, 0.5 T) was realised at our institution in 1995. The design, advantages, limitations and current applications of this system are discussed, with emphasis on the integration of imaging into procedures. We also introduce our integrated platform for intra-operative visualisation and navigation, the 3D Slicer.

In this paper, we analyze Markov Random Field (MRF) as a spatial regularizer in fMRI detection. The low signal-to-noise ratio (SNR) in fMRI images presents a serious challenge for detection algorithms, making regularization necessary to achieve good detection accuracy. Gaussian smoothing, traditionally employed to boost SNR, often produces over-smoothed activation maps. Recently, the use of MRF priors has been suggested as an alternative regularization approach. However, solving for an optimal configuration of the MRF is NP-hard in general. In this work, we investigate fast inference algorithms based on the Mean Field approximation in application to MRF priors for fMRI detection. Furthermore, we propose a novel way to incorporate anatomical information into the MRF-based detection framework and into the traditional smoothing methods. Intuitively speaking, the anatomical evidence increases the likelihood of activation in the gray matter and improves spatial coherency of the resulting activation maps within each tissue type. Validation using the receiver operating characteristic (ROC) analysis and the confusion matrix analysis on simulated data illustrates substantial improvement in detection accuracy using the anatomically guided MRF spatial regularizer. We further demonstrate the potential benefits of the proposed method in real fMRI signals of reduced length. The anatomically guided MRF regularizer enables significant reduction of the scan length while maintaining the quality of the resulting activation maps., National Institutes of Health (U.S.) (National Institute for Biomedical Imaging and Bioengineering (U.S.)/National Alliance for Medical Image Computing (U.S.) Grant U54-EB005149), National Science Foundation (U.S.) (Grant IIS 9610249), National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Biomedical Informatics Research Network Grant U24-RR021382), National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Neuroimaging Analysis Center (U.S.) Grant P41-RR13218), National Institutes of Health (U.S.) (National Institute of Neurological Disorders and Stroke (U.S.) Grant R01-NS051826), National Science Foundation (U.S.) (CAREER Grant 0642971), National Science Foundation (U.S.). Graduate Research Fellowship, National Center for Research Resources (U.S.) (FIRST-BIRN Grant), Neuroimaging Analysis Center (U.S.)

BACKGROUND: Change detection is a critical component in the diagnosis and monitoring of many slowly evolving pathologies. OBJECTIVE: This article describes a semiautomatic monitoring approach using longitudinal medical images. We test the method on brain scans of patients with meningioma, which experts have found difficult to monitor because the tumor evolution is very slow and may be obscured by artifacts related to image acquisition. METHODS: We describe a semiautomatic procedure targeted toward identifying difficult-to-detect changes in brain tumor imaging. The tool combines input from a medical expert with state-of-the-art technology. The software is easy to calibrate and, in less than 5 minutes, returns the total volume of tumor change in mm 3 . We test the method on postgadolinium, T1-weighted magnetic resonance images of 10 patients with meningioma and compare our results with experts’ findings. We also perform benchmark testing with synthetic data. RESULTS: Our experiments indicated that experts’ visual inspections are not sensitive enough to detect subtle growth. Measurements based on experts’ manual segmentations were highly accurate but also labor intensive. The accuracy of our approach was comparable to the experts’ results. However, our approach required far less user input and generated more consistent measurements. CONCLUSION: The sensitivity of experts’ visual inspection is often too low to detect subtle growth of meningiomas from longitudinal scans. Measurements based on experts’ segmentation are highly accurate but generally too labor intensive for standard clinical settings. We described an alternative metric that provides accurate and robust measurements of subtle tumor changes while requiring a minimal amount of user input.

Elastic deformation models are frequently used when solving non-rigid registration problems that are associated with neurosurgical image guidance, however, establishing precise values for the material parameters of brain tissue remains challenging. In this work we include elastography in the registration process by formulating these parameters as unknown random variables with associated priors that may be broad or sharp, depending on the situation. A Bayesian registration model is introduced where the deformation probability is formulated by way of Boltzmann's equation and the linear elastic deformation and similarity energies. The full joint posterior on deformation and elastic random variables is characterized with a Markov Chain Monte Carlo method and can provide useful information beyond the usual "point estimates"; e.g. deformation uncertainty. Hard deformation constraints are easily accommodated in this framework which allows us to constrain the deformation of the brain to the intra-cranial space. We describe preliminary experiments with synthetic 3D brain images for which ground truth is known for the elastic and deformation parameters. We compare a model with separate elastic parameters for three compartments (white matter, gray matter, and CSF), to a single compartment model, and show convergence, improved deformation estimates for the three compartment model and that plausible posteriors on the elastic parameters are obtained from the elastography process.

Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented., National Institutes of Health (U.S.) (National Institute for Biomedical Imaging and Bioengineering (U.S.)/National Alliance for Medical Image Computing (U.S.) U54-EB005149), National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Neuroimaging Analysis Center (U.S.) P41-RR13218), National Institutes of Health (U.S.) (National Institute of Neurological Disorders and Stroke (U.S.) R01-NS051826), National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Biomedical Informatics Research Network U24-RR021382), National Science Foundation (U.S.) (CAREER Award 0642971), German Academy of Sciences Leopoldina (Fellowship LPDS 2009-10), Academy of Finland (Grant 133611)

We model images and the anatomy that they are derived from as stationary and jointly ergodic random processes. Using an empirically-observed property of anatomy, and data processing inequality arguments, we arrive at optimality criteria for mutual information in the ensemble domain. Using ergodicity, we transfer the criteria to single pairs of images in the spatial domain, where it applies to the popular mutual information-based registration approach that is used in practice.

Traditional non-rigid registration algorithms are incapable of accurately registering intra-operative with pre-operative images whenever tissue has been resected or retracted. In this work we present methods for detecting and handling retraction and resection. The registration framework is based on the bijective Demons algorithm using an anisotropic diffusion smoother. Retraction is detected at areas of the deformation field with high internal strain and the estimated retraction boundary is integrated as a diffusion boundary in the smoother to allow discontinuities to develop across the resection boundary. Resection is detected by a level set method evolving in the space where image intensities disagree. The estimated resection is integrated into the smoother as a diffusion sink to restrict image forces originating inside the resection from being diffused to surrounding areas. In addition, the deformation field is continuous across the diffusion sink boundary which allow us to move the boundary of the diffusion sink without changing values in the deformation field (no interpolation or extrapolation is needed). We present preliminary results on both synthetic and clinical data which clearly shows the added value of explicitly modeling these processes in a registration framework.

We describe a neuroimaging protocol that utilizes an anatomical atlas of the human head to guide diffuse optical tomography of human brain activation. The protocol is demonstrated by imaging the hemodynamic response to median-nerve stimulation in three healthy subjects, and comparing the images obtained using a head atlas with the images obtained using the subject-specific head anatomy. The results indicate that using the head atlas anatomy it is possible to reconstruct the location of the brain activation to the expected gyrus of the brain, in agreement with the results obtained with the subject-specific head anatomy. The benefits of this novel method derive from eliminating the need for subject-specific head anatomy and thus obviating the need for a subject-specific MRI to improve the anatomical interpretation of diffuse optical tomography images of brain activation., National Institutes of Health (U.S.) (U54-EB-005149), National Institutes of Health (U.S.) (P41-RR14075), National Institutes of Health (U.S.) (P41-RR13218)

This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-rank) descriptors outperform other state-of-the-art descriptors in terms of precision-recall, including standard SIFT and GLOH.

We describe a method for atlas-based segmentation of structural MRI for calculation of magnetic fieldmaps. CT data sets are used to construct a probabilistic atlas of the head and corresponding MR is used to train a classifier that segments soft tissue, air, and bone. Subject-specific fieldmaps are computed from the segmentations using a perturbation field model. Previous work has shown that distortion in echo-planar images can be corrected using predicted fieldmaps. We obtain results that agree well with acquired fieldmaps: 90% of voxel shifts from predicted fieldmaps show subvoxel disagreement with those computed from acquired fieldmaps. In addition, our fieldmap predictions show statistically significant improvement following inclusion of the atlas.

In this work, we describe a white matter trajectory clustering algorithm that allows for incorporating and appropriately weighting anatomical information. The influence of the anatomical prior reflects confidence in its accuracy and relevance. It can either be defined by the user or it can be inferred automatically. After a detailed description of our novel clustering framework, we demonstrate its properties through a set of preliminary experiments.

Change detection is a critical task in the diagnosis of many slowly evolving pathologies. This paper describes an approach that semi-automatically performs this task using longitudinal medical images. We are specifically interested in meningiomas, which experts often find difficult to monitor as the tumor evolution can be obscured by image artifacts. We test the method on synthetic data with known tumor growth as well as ten clinical data sets. We show that the results of our approach highly correlate with expert findings but seem to be less impacted by inter- and intra-rater variability.

We propose a Bayesian approach to incorporate anatomical information in the clustering of fiber trajectories. An expectation-maximization (EM) algorithm is used to cluster the trajectories, in which an atlas serves as the prior on the labels. The atlas guides the clustering algorithm and makes the resulting bundles anatomically meaningful. In addition, it provides the seed points for the tractography and initial settings of the EM algorithm. The proposed approach provides a robust and automated tool for tract-oriented analysis both in a single subject and over a population.

This paper presents a tract-oriented analysis of diffusion tensor (DT) images of the human brain. We demonstrate that unlike the commonly used ROI-based methods for population studies, our technique is sensitive to the local variation of diffusivity parameters along the fiber tracts. We show the strength of the proposed approach in identifying the differences in schizophrenic data compared to controls. Statistically significant drops in fractional anisotropy are observed along the genu and bilaterally in the splenium, as well as an increase in principal eigenvalue in uncinate fasciculus. This is the first tract-oriented clinical study in which an anatomical atlas is used to guide the algorithm.

We describe a method for correcting the distortions present in echo planar images (EPI) and registering the EPI to structural MRI. A fieldmap is predicted from an air / tissue segmentation of the MRI using a perturbation method and subsequently used to unwarp the EPI data. Shim and other missing parameters are estimated by registration. We obtain results that are similar to those obtained using fieldmaps, however neither fieldmaps, nor knowledge of shim coefficients is required.

We present an algorithm to generate samples from probability distributions on the space of curves. We view a traditional curve evolution energy functional as a negative log probability distribution and sample from it using a Markov chain Monte Carlo (MCMC) algorithm. We define a proposal distribution by generating smooth perturbations to the normal of the curve and show how to compute the transition probabilities to ensure that the samples come from the posterior distribution. We demonstrate some advantages of sampling methods such as robustness to local minima, better characterization of multi-modal distributions, access to some measures of estimation error, and ability to easily incorporate constraints on the curve.

Mapping functional areas of the brain is important for planning tumour resections. With the increased use of functional magnetic resonance imaging (fMRI) for presurgical planning, there is a need to validate that fMRI activation mapping is consistent with the mapping obtained during surgery using direct electrocortical stimulation (DECS).A quantitative comparison of DECS and fMRI mapping techniques was performed, using a patient-specific conductivity model to find the current distribution resulting from each stimulation site. The resulting DECS stimulation map was compared to the fMRI activation map, using the maximal Dice similarity coefficient (MDSC).Our results show some agreement between these two mapping techniques--the stimulation site with the largest MOSC was the only site that demonstrated intra-operative effect.There is a substantial effort to improve the techniques used to map functional areas, particularly using fMRI. It seems likely that fMRI will eventually provide a valid non-invasive means for functional mapping.

The logarithm of the odds ratio (LogOdds) is frequently used in areas such as artificial neural networks, economics, and biology, as an alternative representation of probabilities. Here, we use LogOdds to place probabilistic atlases in a linear vector space. This representation has several useful properties for medical imaging. For example, it not only encodes the shape of multiple anatomical structures but also captures some information concerning uncertainty. We demonstrate that the resulting vector space operations of addition and scalar multiplication have natural probabilistic interpretations. We discuss several examples for placing label maps into the space of LogOdds. First, we relate signed distance maps, a widely used implicit shape representation, to LogOdds and compare it to an alternative that is based on smoothing by spatial Gaussians. We find that the LogOdds approach better preserves shapes in a complex multiple object setting. In the second example, we capture the uncertainty of boundary locations by mapping multiple label maps of the same object into the LogOdds space. Third, we define a framework for non-convex interpolations among atlases that capture different time points in the aging process of a population. We evaluate the accuracy of our representation by generating a deformable shape atlas that captures the variations of anatomical shapes across a population. The deformable atlas is the result of a principal component analysis within the LogOdds space. This atlas is integrated into an existing segmentation approach for MR images. We compare the performance of the resulting implementation in segmenting 20 test cases to a similar approach that uses a more standard shape model that is based on signed distance maps. On this data set, the Bayesian classification model with our new representation outperformed the other approaches in segmenting subcortical structures.

A hierarchical model based on the Multivariate Autoregessive (MAR) process is proposed to jointly model neurological time-series collected from multiple subjects, and to characterize the distribution of MAR coefficients across the population from which those subjects were drawn. Thus, inference about effective connectivity between brain regions may be generalized beyond those subjects studied. The posterior on population- and subject-level connectivity parameters are estimated in a Variational Bayesian (VB) framework, and structural model parameters are chosen by the corresponding evidence criteria. The significance of resulting connectivity statistics are evaluated by permutation-based approximations to the null distribution. The method is demonstrated on simulated data and on actual multi-subject neurological time-series.

Regional investigations of newborn MRI are important to understand the appearance and consequences of early brain injury. Previously, regionalization in neonates has been achieved with a Talairach parcellation, using internal landmarks of the brain. Non-synostotic dolichocephaly defines a bi-temporal narrowing of the preterm infant's head caused by pressure on the immature skull. The impact of dolichocephaly on brain shape and regional brain shift, which may compromise the validity of the parcellation scheme, has not yet been investigated. Twenty-four preterm and 20 fullterm infants were scanned at term equivalent. Skull shapes were investigated by cephalometric measurements and population registration. Brain tissue volumes were calculated to rule out brain injury underlying skull shape differences. The position of Talairach landmarks was evaluated. Cortical structures were segmented to determine a positional shift between both groups. The preterm group displayed dolichocephalic head shapes and had similar brain volumes compared to the mesocephalic fullterm group. In preterm infants, Talairach landmarks were consistently positioned relative to each other and to the skull base, but were displaced with regard to the calvarium. The frontal and superior region was enlarged; central and temporal gyri and sulci were shifted comparing preterm and fullterm infants. We found that, in healthy preterm infants, dolichocephaly led to a shift of cortical structures, but did not influence deep brain structures. We concluded that the validity of a Talairach parcellation scheme is compromised and may lead to a miscalculation of regional brain volumes and inconsistent parcel contents when comparing infant populations with divergent head shapes.

We formalize the pair-wise registration problem in a maximum a posteriori (MAP) framework that employs a multinomial model of joint intensities with parameters for which we only have a prior distribution. To obtain an MAP estimate of the aligning transformation alone, we treat the multinomial parameters as nuisance parameters, and marginalize them out. If the prior on those is uninformative, the marginalization leads to registration by minimization of joint entropy. With an informative prior, the marginalization leads to minimization of the entropy of the data pooled with pseudo observations from the prior. In addition, we show that the marginalized objective function can be optimized by the Expectation-Maximization (EM) algorithm, which yields a simple and effective iteration for solving entropy-based registration problems. Experimentally, we demonstrate the effectiveness of the resulting EM iteration for rapidly solving a challenging intra-operative registration problem.

A novel framework for joint clustering and point-by-point mapping of white matter fiber pathways is presented. Accurate clustering of the trajectories into fiber bundles requires point correspondence determined along the fiber pathways. This knowledge is also crucial for any tract-oriented quantitative analysis. We employ an expectation-maximization (EM) algorithm to cluster the trajectories in a Gamma mixture model context. The result of clustering is the probabilistic assignment of the fiber trajectories to each cluster, an estimate of the cluster parameters, and point correspondences along the trajectories. Point-by-point correspondence of the trajectories within a bundle is obtained by constructing a distance map and a label map from each cluster center at every iteration of the EM algorithm. This offers a time-efficient alternative to pairwise curve matching of all trajectories with respect to each cluster center. Probabilistic assignment of the trajectories to clusters is controlled by imposing a minimum threshold on the membership probabilities, to remove outliers in a principled way. The presented results confirm the efficiency and effectiveness of the proposed framework for quantitative analysis of diffusion tensor MRI.

We describe a new approach for estimating the posterior probability of tissue labels. Conventional likelihood models are combined with a curve length prior on boundaries, and an approximate posterior distribution on labels is sought via the Mean Field approach. Optimizing the resulting estimator by gradient descent leads to a level set style algorithm where the level set functions are the logarithm-of-odds encoding of the posterior label probabilities in an unconstrained linear vector space. Applications with more than two labels are easily accommodated. The label assignment is accomplished by the Maximum A Posteriori rule, so there are no problems of "overlap" or "vacuum". We test the method on synthetic images with additive noise. In addition, we segment a magnetic resonance scan into the major brain compartments and subcortical structures.

We present an algorithm to generate samples from probability distributions on the space of curves. We view a traditional curve evolution energy functional as a negative log probability distribution and sample from it using a Markov chain Monte Carlo (MCMC) algorithm. We define a proposal distribution by generating smooth perturbations to the normal of the curve and show how to compute the transition probabilities to ensure that the samples come from the posterior distribution. We demonstrate some advantages of sampling methods such as robustness to local minima, better characterization of multi-modal distributions, access to some measures of estimation error, and ability to easily incorporate constraints on the curve.

Clinical and research neurosurgical studies involving the use of intracranial electroencephalography and cortical stimulation depend critically on accurate localization of electrodes. Neuronavigation tracking probes enable surgeons to record the position of exposed electrodes, but they cannot be used to reliably measure subdural contacts placed under the dura and beyond the extent of the craniotomy. We describe an algorithm to estimate the position of these inaccessible sites using the patient's preoperative structural MRI data. After generating a model of the cortical surface, our algorithm estimates surface normals at the sites of accessible electrodes, establishes the orientation of the electrode strips, and then extrapolates the position of adjacent contacts based on the known inter-electrode distance. We performed validation using a patient dataset consisting of 37 electrodes placed on the cortical surface during surgery.

We present a new objective function for the registration of multi-modal medical images. Our novel similarity metric incorporates both knowledge about the current observations and information gained from previous registration results and combines the relative influence of these two types of information in a principled way. We show that in the absence of prior information, the method reduces approximately to the popular entropy minimization approach of registration and we provide a theoretical comparison of incorporating prior information in our and other currently existing methods. We also demonstrate experimental results on real images.

The concept of the Logarithm of the Odds (LogOdds) is frequently used in areas such as artificial neural networks, economics, and biology. Here, we utilize LogOdds for a shape representation that demonstrates desirable properties for medical imaging. For example, the representation encodes the shape of an anatomical structure as well as the variations within that structure. These variations are embedded in a vector space that relates to a probabilistic model. We apply our representation to a voxel based segmentation algorithm. We do so by embedding the manifold of Signed Distance Maps (SDM) into the linear space of LogOdds. The LogOdds variant is superior to the SDM model in an experiment segmenting 20 subjects into subcortical structures. We also use LogOdds in the non-convex interpolation between space conditioned distributions. We apply this model to a longitudinal schizophrenia study using quadratic splines. The resulting time-continuous simulation of the schizophrenic aging process has a higher accuracy then a model based on convex interpolation.