Tumor location and neurocognitive function-Unravelling the association and identifying relevant anatomical substrates in intra-axial brain tumors.

Background: Neurocognitive function is a key outcome indicator of therapy in brain tumors. Understanding the underlying anatomical substrates involved in domain function and the pathophysiological basis of dysfunction can help ameliorate the effects of therapy and tailor directed rehabilitative strategies. Methods: Hundred adult diffuse gliomas were co-registered onto a common demographic-specific brain template to create tumor localization maps. Voxel-based lesion symptom (VLSM) technique was used to assign an association between individual voxels and neuropsychological dysfunction in various domains (attention and executive function (A & EF), language, memory, visuospatial/constructive abilities, and visuomotor speed). The probability maps thus generated were further co-registered to cortical and subcortical atlases. A permutation-based statistical testing method was used to evaluate the statistically and clinically significant anatomical parcels associated with domain dysfunction and to create heat maps. Results: Neurocognition was affected in a high proportion of subjects (93%), with A & EF and memory being the most affected domains. Left-sided networks were implicated in patients with A & EF, memory, and language deficits with the perisylvian white matter tracts being the most common across domains. Visuospatial dysfunction was associated with lesions involving the right perisylvian cortical regions, whereas deficits in visuomotor speed were associated with lesions involving primary visual and motor output pathways. Conclusions: Significant baseline neurocognitive deficits are prevalent in gliomas. These are multidomain and the perisylvian network especially on the left side seems to be very important, being implicated in dysfunction of many domains.

Mixed-dictionary models and variational inference in task fMRI for shorter scans and better image quality.

The propensity of task-based functional magnetic resonance imaging (T-fMRI) to large physiological fluctuations, measurement noise, and imaging artifacts entail longer scans and higher temporal resolution (trading off spatial resolution) to alleviate the effects of degradation. This paper focuses on methods towards reducing scan times and enabling higher spatial resolution in T-fMRI. We propose a novel mixed-dictionary model combining (i) the task-based design matrix, (ii) a learned dictionary from resting-state fMRI, and (iii) an analytically-defined wavelet frame. For model fitting, we propose a novel adaptation of the inference framework relying on variational Bayesian expectation maximization with nested minorization. We leverage the mixed-dictionary model coupled with variational inference to enable 2×shorter scan times in T-fMRI, improving activation-map estimates towards the same quality as those resulting from longer scans. We also propose a scheme with potential to increase spatial resolution through temporally undersampled acquisition. Results on motor-task fMRI and gambling-task fMRI show that our framework leads to improved activation-map estimates over the state of the art.

Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data.

Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, such DNN methods focus on applications involving test data that match the statistical characteristics of the training data very closely and give little attention to evaluating the performance of these DNNs on new out-of-distribution (OOD) acquisitions. We propose a novel DNN formulation that models the (i) underlying sinogram-based physics of the PET imaging system and (ii) the uncertainty in the DNN output through the per-voxel heteroscedasticity of the residuals between the predicted and the high-quality reference images. Our sinogram-based uncertainty-aware DNN framework, namely, suDNN, estimates a standard-dose PET image using multimodal input in the form of (i) a low-dose/low-count PET image and (ii) the corresponding multi-contrast MRI images, leading to improved robustness of suDNN to OOD acquisitions. Results on in vivo simultaneous PET-MRI, and various forms of OOD data in PET-MRI, show the benefits of suDNN over the current state of the art, quantitatively and qualitatively.

Incorporation of anatomical MRI knowledge for enhanced mapping of brain metabolism using functional PET.

Functional positron emission tomography (fPET) imaging using continuous infusion of [18F]-fluorodeoxyglucose (FDG) is a novel neuroimaging technique to track dynamic glucose utilization in the brain. In comparison to conventional static or dynamic bolus PET, fPET maintains a sustained supply of glucose in the blood plasma which improves sensitivity to measure dynamic glucose changes in the brain, and enables mapping of dynamic brain activity in task-based and resting-state fPET studies. However, there is a trade-off between temporal resolution and spatial noise due to the low concentration of FDG and the limited sensitivity of multi-ring PET scanners. Images from fPET studies suffer from partial volume errors and residual scatter noise that may cause the cerebral metabolic functional maps to be biased. Gaussian smoothing filters used to denoise the fPET images are suboptimal, as they introduce additional partial volume errors. In this work, a post-processing framework based on a magnetic resonance (MR) Bowsher-like prior was used to improve the spatial and temporal signal to noise characteristics of the fPET images. The performance of the MR guided method was compared with conventional denosing methods using both simulated and in vivo task fPET datasets. The results demonstrate that the MR-guided fPET framework denoises the fPET images and improves the partial volume correction, consequently enhancing the sensitivity to identify brain activation, and improving the anatomical accuracy for mapping changes of brain metabolism in response to a visual stimulation task. The framework extends the use of functional PET to investigate the dynamics of brain metabolic responses for faster presentation of brain activation tasks, and for applications in low dose PET imaging.

R-fMRI reconstruction from k-t undersampled data using a subject-invariant dictionary model and VB-EM with nested minorization.

Higher spatial resolution in resting-state functional magnetic resonance imaging (R-fMRI) can give reliable information about the functional networks in the cerebral cortex. Typical methods can achieve higher spatial or temporal resolution by speeding up scans using either (i) complex pulse-sequence designs or (ii) k-space undersampling coupled with priors on the signal. We propose to undersample the R-fMRI acquisition in k-space and time to speedup scans in order to improve spatial resolution. We propose a novel model-based R-fMRI reconstruction framework using a robust, subject-invariant, spatially regularized dictionary prior on the signal. Furthermore, we propose a novel inference framework based on variational Bayesian expectation maximization with nested minorization (VB-EM-NM). Our inference framework allows us to provide an estimate of uncertainty of the reconstruction, unlike typical reconstruction methods. Empirical evaluation of (i) simulated R-fMRI reconstruction and (ii) functional-network estimates from brain R-fMRI reconstructions demonstrate that our framework improves over the state of the art, and, additionally, enables significantly higher spatial resolution.

Joint PET-MRI image reconstruction using a patch-based joint-dictionary prior.

For simultaneous positron-emission-tomography and magnetic-resonance-imaging (PET-MRI) systems, while early methods relied on independently reconstructing PET and MRI images, recent works have demonstrated improvement in image reconstructions of both PET and MRI using joint reconstruction methods. The current state-of-the-art joint reconstruction priors rely on fine-scale PET-MRI dependencies through the image gradients at corresponding spatial locations in the PET and MRI images. In the general context of image restoration, compared to gradient-based models, patch-based models (e.g., sparse dictionaries) have demonstrated better performance by modeling image texture better. Thus, we propose a novel joint PET-MRI patch-based dictionary prior that learns inter-modality higher-order dependencies together with intra-modality textural patterns in the images. We model the joint-dictionary prior as a Markov random field and propose a novel Bayesian framework for joint reconstruction of PET and accelerated-MRI images, using expectation maximization for inference. We evaluate all methods on simulated brain datasets as well as on in vivo datasets. We compare our joint dictionary prior with the recently proposed joint priors based on image gradients, as well as independently applied patch-based priors. Our method demonstrates qualitative and quantitative improvement over the state of the art in both PET and MRI reconstructions.

Estimating uncertainty in MRF-based image segmentation: A perfect-MCMC approach.

Typical methods for image segmentation, or labeling, formulate and solve an optimization problem to produce a single optimal solution. For applications in clinical decision support relying on automated medical image segmentation, it is also desirable for methods to inform about (i) the uncertainty in label assignments or object boundaries or (ii) alternate close-to-optimal solutions. However, typical methods fail to do so. To estimate uncertainty, while some Bayesian methods rely on simplified prior models and approximate variational inference schemes, others rely on sampling segmentations from the associated posterior model using (i) traditional Markov chain Monte Carlo (MCMC) methods based on Gibbs sampling or (ii) approximate perturbation models. However, in such typical approaches, in practice, the resulting inference or generated sample set are approximations that deviate significantly from those indicated by the true posterior. To estimate uncertainty, we propose the modern paradigm of perfect MCMC sampling to sample multi-label segmentations from generic Bayesian Markov random field (MRF) models, in finite time for exact inference. Furthermore, for exact sampling in generic Bayesian MRFs, we extend the theory underlying Fill's algorithm to generic MRF models by proposing a novel bounding-chain algorithm. On several classic problems in medical image analysis, and several modeling and inference schemes, results on simulated data and clinical brain magnetic resonance images show that our uncertainty estimates gain accuracy over several state-of-the-art inference methods.

Kernel Methods for Riemannian Analysis of Robust Descriptors of the Cerebral Cortex.

Typical cerebral cortical analyses rely on spatial normalization and are sensitive to misregistration arising from partial homologies between subject brains and local optima in nonlinear registration. In contrast, we use a descriptor of the 3D cortical sheet (jointly modeling folding and thickness) that is robust to misregistration. Our histogram-based descriptor lies on a Riemannian manifold. We propose new regularized nonlinear methods for (i) detecting group differences, using a Mercer kernel with an implicit lifting map to a reproducing kernel Hilbert space, and (ii) regression against clinical variables, using kernel density estimation. For both methods, we employ kernels that exploit the Riemannian structure. Results on simulated and clinical data shows the improved accuracy and stability of our approach in cortical-sheet analysis.

Riemannian Statistical Analysis of Cortical Geometry with Robustness to Partial Homology and Misalignment.

Typical studies of the geometry of the cerebral cortical structure focus on either cortical folding or thickness. They rely on spatial normalization, but use cortical descriptors that are sensitive to misregistration arising from the well-known problems of partial homologies between subject brains and local optima in nonlinear registration. In contrast to these approaches, we propose a novel framework for studying the geometry of the entire cortical sheet, subsuming its folding and thickness characteristics. We propose a novel descriptor of local cortical geometry to increase robustness to partial homology and misregistration. The proposed descriptor lies on a Riemannian manifold, and we describe a method for hypothesis testing on manifolds for cross-sectional studies. Results on simulated and clinical data show the benefits of the proposed approach for detecting between-group differences with greater accuracy and consistency.

Colocalization Estimation Using Graphical Modeling and Variational Bayesian Expectation Maximization: Towards a Parameter-Free Approach.

In microscopy imaging, colocalization between two biological entities (e.g., protein-protein or protein-cell) refers to the (stochastic) dependencies between the spatial locations of the two entities in the biological specimen. Measuring colocalization between two entities relies on fluorescence imaging of the specimen using two fluorescent chemicals, each of which indicates the presence/absence of one of the entities at any pixel location. State-of-the-art methods for estimating colocalization rely on post-processing image data using an adhoc sequence of algorithms with many free parameters that are tuned visually. This leads to loss of reproducibility of the results. This paper proposes a brand-new framework for estimating the nature and strength of colocalization directly from corrupted image data by solving a single unified optimization problem that automatically deals with noise, object labeling, and parameter tuning. The proposed framework relies on probabilistic graphical image modeling and a novel inference scheme using variational Bayesian expectation maximization for estimating all model parameters, including colocalization, from data. Results on simulated and real-world data demonstrate improved performance over the state of the art.

Hierarchical bayesian modeling, estimation, and sampling for multigroup shape analysis.

This paper proposes a novel method for the analysis of anatomical shapes present in biomedical image data. Motivated by the natural organization of population data into multiple groups, this paper presents a novel hierarchical generative statistical model on shapes. The proposed method represents shapes using pointsets and defines a joint distribution on the population's (i) shape variables and (ii) object-boundary data. The proposed method solves for optimal (i) point locations, (ii) correspondences, and (iii) model-parameter values as a single optimization problem. The optimization uses expectation maximization relying on a novel Markov-chain Monte-Carlo algorithm for sampling in Kendall shape space. Results on clinical brain images demonstrate advantages over the state of the art.

A functional network estimation method of resting-state fMRI using a hierarchical Markov random field.

We propose a hierarchical Markov random field model for estimating both group and subject functional networks simultaneously. The model takes into account the within-subject spatial coherence as well as the between-subject consistency of the network label maps. The statistical dependency between group and subject networks acts as a regularization, which helps the network estimation on both layers. We use Gibbs sampling to approximate the posterior density of the network labels and Monte Carlo expectation maximization to estimate the model parameters. We compare our method with two alternative segmentation methods based on K-Means and normalized cuts, using synthetic and real fMRI data. The experimental results show that our proposed model is able to identify both group and subject functional networks with higher accuracy on synthetic data, more robustness, and inter-session consistency on the real data.

Multiatlas segmentation as nonparametric regression.

This paper proposes a novel theoretical framework to model and analyze the statistical characteristics of a wide range of segmentation methods that incorporate a database of label maps or atlases; such methods are termed as label fusion or multiatlas segmentation. We model these multiatlas segmentation problems as nonparametric regression problems in the high-dimensional space of image patches. We analyze the nonparametric estimator's convergence behavior that characterizes expected segmentation error as a function of the size of the multiatlas database. We show that this error has an analytic form involving several parameters that are fundamental to the specific segmentation problem (determined by the chosen anatomical structure, imaging modality, registration algorithm, and label-fusion algorithm). We describe how to estimate these parameters and show that several human anatomical structures exhibit the trends modeled analytically. We use these parameter estimates to optimize the regression estimator. We show that the expected error for large database sizes is well predicted by models learned on small databases. Thus, a few expert segmentations can help predict the database sizes required to keep the expected error below a specified tolerance level. Such cost-benefit analysis is crucial for deploying clinical multiatlas segmentation systems.

PROPER ORDERED MESHING OF COMPLEX SHAPES AND OPTIMAL GRAPH CUTS APPLIED TO ATRIAL-WALL SEGMENTATION FROM DE-MRI.

Segmentation of the left atrium wall from delayed enhancement MRI is challenging because of inconsistent contrast combined with noise and high variation in atrial shape and size. This paper presents a method for left-atrium wall segmentation by using a novel sophisticated mesh-generation strategy and graph cuts on a proper ordered graph. The mesh is part of a template/model that has an associated set of learned intensity features. When this mesh is overlaid onto a test image, it produces a set of costs on the graph vertices which eventually leads to an optimal segmentation. The novelty also lies in the construction of proper ordered graphs on complex shapes and for choosing among distinct classes of base shapes/meshes for automatic segmentation. We evaluate the proposed segmentation framework quantitatively on simulated and clinical cardiac MRI.

Modeling 4D Changes in Pathological Anatomy using Domain Adaptation: Analysis of TBI Imaging using a Tumor Database.

Analysis of 4D medical images presenting pathology (i.e., lesions) is significantly challenging due to the presence of complex changes over time. Image analysis methods for 4D images with lesions need to account for changes in brain structures due to deformation, as well as the formation and deletion of new structures (e.g., edema, bleeding) due to the physiological processes associated with damage, intervention, and recovery. We propose a novel framework that models 4D changes in pathological anatomy across time, and provides explicit mapping from a healthy template to subjects with pathology. Moreover, our framework uses transfer learning to leverage rich information from a known source domain, where we have a collection of completely segmented images, to yield effective appearance models for the input target domain. The automatic 4D segmentation method uses a novel domain adaptation technique for generative kernel density models to transfer information between different domains, resulting in a fully automatic method that requires no user interaction. We demonstrate the effectiveness of our novel approach with the analysis of 4D images of traumatic brain injury (TBI), using a synthetic tumor database as the source domain.

Bayesian segmentation of atrium wall using globally-optimal graph cuts on 3D meshes.

Efficient segmentation of the left atrium (LA) wall from delayed enhancement MRI is challenging due to inconsistent contrast, combined with noise, and high variation in atrial shape and size. We present a surface-detection method that is capable of extracting the atrial wall by computing an optimal a-posteriori estimate. This estimation is done on a set of nested meshes, constructed from an ensemble of segmented training images, and graph cuts on an associated multi-column, proper-ordered graph. The graph/mesh is a part of a template/model that has an associated set of learned intensity features. When this mesh is overlaid onto a test image, it produces a set of costs which lead to an optimal segmentation. The 3D mesh has an associated weighted, directed multi-column graph with edges that encode smoothness and inter-surface penalties. Unlike previous graph-cut methods that impose hard constraints on the surface properties, the proposed method follows from a Bayesian formulation resulting in soft penalties on spatial variation of the cuts through the mesh. The novelty of this method also lies in the construction of proper-ordered graphs on complex shapes for choosing among distinct classes of base shapes for automatic LA segmentation. We evaluate the proposed segmentation framework on simulated and clinical cardiac MRI.

Group analysis of resting-state fMRI by hierarchical Markov random fields.

Identifying functional networks from resting-state functional MRI is a challenging task, especially for multiple subjects. Most current studies estimate the networks in a sequential approach, i.e., they identify each individual subject's network independently to other subjects, and then estimate the group network from the subjects networks. This one-way flow of information prevents one subject's network estimation benefiting from other subjects. We propose a hierarchical Markov random field model, which takes into account both the within-subject spatial coherence and between-subject consistency of the network label map. Both population and subject network maps are estimated simultaneously using a Gibbs sampling approach in a Monte Carlo expectation maximization framework. We compare our approach to two alternative groupwise fMRI clustering methods, based on K-means and normalized Cuts, using both synthetic and real fMRI data. We show that our method is able to estimate more consistent subject label maps, as well as a stable group label map.

SEGMENTATION OF SERIAL MRI OF TBI PATIENTS USING PERSONALIZED ATLAS CONSTRUCTION AND TOPOLOGICAL CHANGE ESTIMATION.

Traumatic brain injury (TBI) due to falls, car accidents, and warfare affects millions of people annually. Determining personalized therapy and assessment of treatment efficacy can substantially benefit from longitudinal (4D) magnetic resonance imaging (MRI). In this paper, we propose a method for segmenting longitudinal brain MR images with TBI using personalized atlas construction. Longitudinal images with TBI typically present topological changes over time due to the effect of the impact force on tissue, skull, and blood vessels and the recovery process. We address this issue by defining a novel atlas construction scheme that explicitly models the effect of topological changes. Our method automatically estimates the probability of topological changes jointly with the personalized atlas. We demonstrate the effectiveness of this approach on MR images with TBI that also have been segmented by human raters, where our method that integrates 4D information yields improved validation measures compared to temporally independent segmentations.

How Many Templates Does It Take for a Good Segmentation?: Error Analysis in Multiatlas Segmentation as a Function of Database Size.

This paper proposes a novel formulation to model and analyze the statistical characteristics of some types of segmentation problems that are based on combining label maps / templates / atlases. Such segmentation-by-example approaches are quite powerful on their own for several clinical applications and they provide prior information, through spatial context, when combined with intensity-based segmentation methods. The proposed formulation models a class of multiatlas segmentation problems as nonparametric regression problems in the high-dimensional space of images. The paper presents a systematic analysis of the nonparametric estimation's convergence behavior (i.e. characterizing segmentation error as a function of the size of the multiatlas database) and shows that it has a specific analytic form involving several parameters that are fundamental to the specific segmentation problem (i.e. chosen anatomical structure, imaging modality, registration method, label-fusion algorithm, etc.). We describe how to estimate these parameters and show that several brain anatomical structures exhibit the trends determined analytically. The proposed framework also provides per-voxel confidence measures for the segmentation. We show that the segmentation error for large database sizes can be predicted using small-sized databases. Thus, small databases can be exploited to predict the database sizes required ("how many templates") to achieve "good" segmentations having errors lower than a specified tolerance. Such cost-benefit analysis is crucial for designing and deploying multiatlas segmentation systems.

Building Spatiotemporal Anatomical Models using Joint 4-D Segmentation, Registration, and Subject-Specific Atlas Estimation.

Longitudinal analysis of anatomical changes is a vital component in many personalized-medicine applications for predicting disease onset, determining growth/atrophy patterns, evaluating disease progression, and monitoring recovery. Estimating anatomical changes in longitudinal studies, especially through magnetic resonance (MR) images, is challenging because of temporal variability in shape (e.g. from growth/atrophy) and appearance (e.g. due to imaging parameters and tissue properties affecting intensity contrast, or from scanner calibration). This paper proposes a novel mathematical framework for constructing subject-specific longitudinal anatomical models. The proposed method solves a generalized problem of joint segmentation, registration, and subject-specific atlas building, which involves not just two images, but an entire longitudinal image sequence. The proposed framework describes a novel approach that integrates fundamental principles that underpin methods for image segmentation, image registration, and atlas construction. This paper presents evaluation on simulated longitudinal data and on clinical longitudinal brain MRI data. The results demonstrate that the proposed framework effectively integrates information from 4-D spatiotemporal data to generate spatiotemporal models that allow analysis of anatomical changes over time.