A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity

Brain connectivity alterations associated with mental disorders have been widely reported in both functional MRI (fMRI) and diffusion MRI (dMRI). However, extracting useful information from the vast amount of information afforded by brain networks remains a great challenge. Capturing network topology, graph convolutional networks (GCNs) have demonstrated to be superior in learning network representations tailored for identifying specific brain disorders. Existing graph construction techniques generally rely on a specific brain parcellation to define regions-of-interest (ROIs) to construct networks, often limiting the analysis into a single spatial scale. In addition, most methods focus on the pairwise relationships between the ROIs and ignore high-order associations between subjects. In this letter, we propose a mutual multi-scale triplet graph convolutional network (MMTGCN) to analyze functional and structural connectivity for brain disorder diagnosis. We first employ several templates with different scales of ROI parcellation to construct coarse-to-fine brain connectivity networks for each subject. Then, a triplet GCN (TGCN) module is developed to learn functional/structural representations of brain connectivity networks at each scale, with the triplet relationship among subjects explicitly incorporated into the learning process. Finally, we propose a template mutual learning strategy to train different scale TGCNs collaboratively for disease classification. Experimental results on 1,160 subjects from three datasets with fMRI or dMRI data demonstrate that our MMTGCN outperforms several state-of-the-art methods in identifying three types of brain disorders.

Image analysis by Krawtchouk moments

In this paper, a new set of orthogonal moments based on the discrete classical Krawtchouk polynomials is introduced. The Krawtchouk polynomials are scaled to ensure numerical stability, thus creating a set of weighted Krawtchouk polynomials. The set of proposed Krawtchouk moments is then derived from the weighted Krawtchouk polynomials. The orthogonality of the proposed moments ensures minimal information redundancy. No numerical approximation is involved in deriving the moments, since the weighted Krawtchouk polynomials are discrete. These properties make the Krawtchouk moments well suited as pattern features in the analysis of two-dimensional images. It is shown that the Krawtchouk moments can be employed to extract local features of an image, unlike other orthogonal moments, which generally capture the global features. The computational aspects of the moments using the recursive and symmetry properties are discussed. The theoretical framework is validated by an experiment on image reconstruction using Krawtchouk moments and the results are compared to that of Zernike, pseudo-Zernike, Legendre, and Tchebyscheff moments. Krawtchouk moment invariants are constructed using a linear combination of geometric moment invariants; an object recognition experiment shows Krawtchouk moment invariants perform significantly better than Hu's moment invariants in both noise-free and noisy conditions.

View-aligned hypergraph learning for Alzheimer's disease diagnosis with incomplete multi-modality data

Effectively utilizing incomplete multi-modality data for the diagnosis of Alzheimer's disease (AD) and its prodrome (i.e., mild cognitive impairment, MCI) remains an active area of research. Several multi-view learning methods have been recently developed for AD/MCI diagnosis by using incomplete multi-modality data, with each view corresponding to a specific modality or a combination of several modalities. However, existing methods usually ignore the underlying coherence among views, which may lead to sub-optimal learning performance. In this paper, we propose a view-aligned hypergraph learning (VAHL) method to explicitly model the coherence among views. Specifically, we first divide the original data into several views based on the availability of different modalities and then construct a hypergraph in each view space based on sparse representation. A view-aligned hypergraph classification (VAHC) model is then proposed, by using a view-aligned regularizer to capture coherence among views. We further assemble the class probability scores generated from VAHC, via a multi-view label fusion method for making a final classification decision. We evaluate our method on the baseline ADNI-1 database with 807 subjects and three modalities (i.e., MRI, PET, and CSF). Experimental results demonstrate that our method outperforms state-of-the-art methods that use incomplete multi-modality data for AD/MCI diagnosis.

4D multi-modality tissue segmentation of serial infant images

Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6-8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).

Deep Multi-Scale Mesh Feature Learning for Automated Labeling of Raw Dental Surfaces From 3D Intraoral Scanners

Precisely labeling teeth on digitalized 3D dental surface models is the precondition for tooth position rearrangements in orthodontic treatment planning. However, it is a challenging task primarily due to the abnormal and varying appearance of patients' teeth. The emerging utilization of intraoral scanners (IOSs) in clinics further increases the difficulty in automated tooth labeling, as the raw surfaces acquired by IOS are typically low-quality at gingival and deep intraoral regions. In recent years, some pioneering end-to-end methods (e.g., PointNet) have been proposed in the communities of computer vision and graphics to consume directly raw surface for 3D shape segmentation. Although these methods are potentially applicable to our task, most of them fail to capture fine-grained local geometric context that is critical to the identification of small teeth with varying shapes and appearances. In this paper, we propose an end-to-end deep-learning method, called MeshSegNet, for automated tooth labeling on raw dental surfaces. Using multiple raw surface attributes as inputs, MeshSegNet integrates a series of graph-constrained learning modules along its forward path to hierarchically extract multi-scale local contextual features. Then, a dense fusion strategy is applied to combine local-to-global geometric features for the learning of higher-level features for mesh cell annotation. The predictions produced by our MeshSegNet are further post-processed by a graph-cut refinement step for final segmentation. We evaluated MeshSegNet using a real-patient dataset consisting of raw maxillary surfaces acquired by 3D IOS. Experimental results, performed 5-fold cross-validation, demonstrate that MeshSegNet significantly outperforms state-of-the-art deep learning methods for 3D shape segmentation.

Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion

In this work, we are interested in predicting the diagnostic statuses of potentially neurodegenerated patients using feature values derived from multi-modality neuroimaging data and biological data, which might be incomplete. Collecting the feature values into a matrix, with each row containing a feature vector of a sample, we propose a framework to predict the corresponding associated multiple target outputs (e.g., diagnosis label and clinical scores) from this feature matrix by performing matrix shrinkage following matrix completion. Specifically, we first combine the feature and target output matrices into a large matrix and then partition this large incomplete matrix into smaller submatrices, each consisting of samples with complete feature values (corresponding to a certain combination of modalities) and target outputs. Treating each target output as the outcome of a prediction task, we apply a 2-step multi-task learning algorithm to select the most discriminative features and samples in each submatrix. Features and samples that are not selected in any of the submatrices are discarded, resulting in a shrunk version of the original large matrix. The missing feature values and unknown target outputs of the shrunk matrix is then completed simultaneously. Experimental results using the ADNI dataset indicate that our proposed framework achieves higher classification accuracy at a greater speed when compared with conventional imputation-based classification methods and also yields competitive performance when compared with the state-of-the-art methods.

Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning based Registration

This paper introduces an unsupervised adversarial similarity network for image registration. Unlike existing deep learning registration frameworks, our approach does not require ground-truth deformations and specific similarity metrics. We connect a registration network and a discrimination network with a deformable transformation layer. The registration network is trained with feedback from the discrimination network, which is designed to judge whether a pair of registered images are sufficiently similar. Using adversarial training, the registration network is trained to predict deformations that are accurate enough to fool the discrimination network. Experiments on four brain MRI datasets indicate that our method yields registration performance that is promising in both accuracy and efficiency compared with state-of-the-art registration methods, including those based on deep learning.

TIMER: tensor image morphing for elastic registration

We propose a novel diffusion tensor imaging (DTI) registration algorithm, called Tensor Image Morphing for Elastic Registration (TIMER), which leverages the hierarchical guidance of regional distributions and local boundaries, both extracted directly from the tensors. Currently available DTI registration methods generally extract tensor scalar features from each tensor to construct scalar maps. Subsequently, regional integration and other operations such as edge detection are performed to extract more features to guide the registration. However, there are two major limitations with these approaches. First, the computed regional features might not reflect the actual regional tensor distributions. Second, by the same token, gradient maps calculated from the tensor-derived scalar feature maps might not represent the actual tissue tensor boundaries. To overcome these limitations, we propose a new approach which extracts regional and edge information directly from a tensor neighborhood. Regional tensor distribution information, such as mean and variance, is computed in a multiscale fashion directly from the tensors by taking into account the voxel neighborhood of different sizes, and hence capturing tensor information at different scales, which in turn can be employed to hierarchically guide the registration. Such multiscale scheme can help alleviate the problem of local minimum and is also more robust to noise since one can better determine the statistical properties of each voxel by taking into account the properties of its surrounding. Also incorporated in our method is edge information extracted directly from the tensors, which is crucial to facilitate registration of tissue boundaries. Experiments involving real subjects, simulated subjects, fiber tracking, and atrophy detection indicate that TIMER performs better than the other methods (Yang et al., 2008; Zhang et al., 2006).

Diagnosis of Autism Spectrum Disorders Using Temporally Distinct Resting-State Functional Connectivity Networks

INTRODUCTION

Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis.

AIMS

We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network.

RESULTS

The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers.

CONCLUSIONS

By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.

Multi-site MRI harmonization via attention-guided deep domain adaptation for brain disorder identification

Structural magnetic resonance imaging (MRI) has shown great clinical and practical values in computer-aided brain disorder identification. Multi-site MRI data increase sample size and statistical power, but are susceptible to inter-site heterogeneity caused by different scanners, scanning protocols, and subject cohorts. Multi-site MRI harmonization (MMH) helps alleviate the inter-site difference for subsequent analysis. Some MMH methods performed at imaging level or feature extraction level are concise but lack robustness and flexibility to some extent. Even though several machine/deep learning-based methods have been proposed for MMH, some of them require a portion of labeled data in the to-be-analyzed target domain or ignore the potential contributions of different brain regions to the identification of brain disorders. In this work, we propose an attention-guided deep domain adaptation (AD2A) framework for MMH and apply it to automated brain disorder identification with multi-site MRIs. The proposed framework does not need any category label information of target data, and can also automatically identify discriminative regions in whole-brain MR images. Specifically, the proposed AD2A is composed of three key modules: (1) an MRI feature encoding module to extract representations of input MRIs, (2) an attention discovery module to automatically locate discriminative dementia-related regions in each whole-brain MRI scan, and (3) a domain transfer module trained with adversarial learning for knowledge transfer between the source and target domains. Experiments have been performed on 2572 subjects from four benchmark datasets with T1-weighted structural MRIs, with results demonstrating the effectiveness of the proposed method in both tasks of brain disorder identification and disease progression prediction.

Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion

In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84% and time prediction correlation of 0.665.

TPS-HAMMER: improving HAMMER registration algorithm by soft correspondence matching and thin-plate splines based deformation interpolation

We present an improved MR brain image registration algorithm, called TPS-HAMMER, which is based on the concepts of attribute vectors and hierarchical landmark selection scheme proposed in the highly successful HAMMER registration algorithm. We demonstrate that TPS-HAMMER algorithm yields better registration accuracy, robustness, and speed over HAMMER owing to (1) the employment of soft correspondence matching and (2) the utilization of thin-plate splines (TPS) for sparse-to-dense deformation field generation. These two aspects can be integrated into a unified framework to refine the registration iteratively by alternating between soft correspondence matching and dense deformation field estimation. Compared with HAMMER, TPS-HAMMER affords several advantages: (1) unlike the Gaussian propagation mechanism employed in HAMMER, which can be slow and often leaves unreached blotches in the deformation field, the deformation interpolation in the non-landmark points can be obtained immediately with TPS in our algorithm; (2) the smoothness of deformation field is preserved due to the nice properties of TPS; (3) possible misalignments can be alleviated by allowing the matching of the landmarks with a number of possible candidate points and enforcing more exact matches in the final stages of the registration. Extensive experiments have been conducted, using the original HAMMER as a comparison baseline, to validate the merits of TPS-HAMMER. The results show that TPS-HAMMER yields significant improvement in both accuracy and speed, indicating high applicability for the clinical scenario.

CENTS: cortical enhanced neonatal tissue segmentation

The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-to-noise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions.

Non-Negative Spherical Deconvolution (NNSD) for estimation of fiber Orientation Distribution Function in single-/multi-shell diffusion MRI

Spherical Deconvolution (SD) is commonly used for estimating fiber Orientation Distribution Functions (fODFs) from diffusion-weighted signals. Existing SD methods can be classified into two categories: 1) Continuous Representation based SD (CR-SD), where typically Spherical Harmonic (SH) representation is used for convenient analytical solutions, and 2) Discrete Representation based SD (DR-SD), where the signal profile is represented by a discrete set of basis functions uniformly oriented on the unit sphere. A feasible fODF should be non-negative and should integrate to unity throughout the unit sphere S(2). However, to our knowledge, most existing SH-based SD methods enforce non-negativity only on discretized points and not the whole continuum of S(2). Maximum Entropy SD (MESD) and Cartesian Tensor Fiber Orientation Distributions (CT-FOD) are the only SD methods that ensure non-negativity throughout the unit sphere. They are however computational intensive and are susceptible to errors caused by numerical spherical integration. Existing SD methods are also known to overestimate the number of fiber directions, especially in regions with low anisotropy. DR-SD introduces additional error in peak detection owing to the angular discretization of the unit sphere. This paper proposes a SD framework, called Non-Negative SD (NNSD), to overcome all the limitations above. NNSD is significantly less susceptible to the false-positive peaks, uses SH representation for efficient analytical spherical deconvolution, and allows accurate peak detection throughout the whole unit sphere. We further show that NNSD and most existing SD methods can be extended to work on multi-shell data by introducing a three-dimensional fiber response function. We evaluated NNSD in comparison with Constrained SD (CSD), a quadratic programming variant of CSD, MESD, and an L1-norm regularized non-negative least-squares DR-SD. Experiments on synthetic and real single-/multi-shell data indicate that NNSD improves estimation performance in terms of mean difference of angles, peak detection consistency, and anisotropy contrast between isotropic and anisotropic regions.

Two-dimensional polar harmonic transforms for invariant image representation

This paper introduces a set of 2D transforms, based on a set of orthogonal projection bases, to generate a set of features which are invariant to rotation. We call these transforms Polar Harmonic Transforms (PHTs). Unlike the well-known Zernike and pseudo-Zernike moments, the kernel computation of PHTs is extremely simple and has no numerical stability issue whatsoever. This implies that PHTs encompass the orthogonality and invariance advantages of Zernike and pseudo-Zernike moments, but are free from their inherent limitations. This also means that PHTs are well suited for application where maximal discriminant information is needed. Furthermore, PHTs make available a large set of features for further feature selection in the process of seeking for the best discriminative or representative features for a particular application.

Denoising Magnetic Resonance Images Using Collaborative Non-Local Means

Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. It is thus often desirable to remove such artifacts beforehand for more robust and effective quantitative analysis. It is important to preserve the integrity of relevant image information while removing noise in MR images. A variety of approaches have been developed for this purpose, and the non-local means (NLM) filter has been shown to be able to achieve state-of-the-art denoising performance. For effective denoising, NLM relies heavily on the existence of repeating structural patterns, which however might not always be present within a single image. This is especially true when one considers the fact that the human brain is complex and contains a lot of unique structures. In this paper we propose to leverage the repeating structures from multiple images to collaboratively denoise an image. The underlying assumption is that it is more likely to find repeating structures from multiple scans than from a single scan. Specifically, to denoise a target image, multiple images, which may be acquired from different subjects, are spatially aligned to the target image, and an NLM-like block matching is performed on these aligned images with the target image as the reference. This will significantly increase the number of matching structures and thus boost the denoising performance. Experiments on both synthetic and real data show that the proposed approach, collaborative non-local means (CNLM), outperforms the classic NLM and yields results with markedly improved structural details.

Synthesized 7T MRI from 3T MRI via deep learning in spatial and wavelet domains

Ultra-high field 7T MRI scanners, while producing images with exceptional anatomical details, are cost prohibitive and hence highly inaccessible. In this paper, we introduce a novel deep learning network that fuses complementary information from spatial and wavelet domains to synthesize 7T T1-weighted images from their 3T counterparts. Our deep learning network leverages wavelet transformation to facilitate effective multi-scale reconstruction, taking into account both low-frequency tissue contrast and high-frequency anatomical details. Our network utilizes a novel wavelet-based affine transformation (WAT) layer, which modulates feature maps from the spatial domain with information from the wavelet domain. Extensive experimental results demonstrate the capability of the proposed method in synthesizing high-quality 7T images with better tissue contrast and greater details, outperforming state-of-the-art methods.

Identification of progressive mild cognitive impairment patients using incomplete longitudinal MRI scans

Distinguishing progressive mild cognitive impairment (pMCI) from stable mild cognitive impairment (sMCI) is critical for identification of patients who are at risk for Alzheimer's disease (AD), so that early treatment can be administered. In this paper, we propose a pMCI/sMCI classification framework that harnesses information available in longitudinal magnetic resonance imaging (MRI) data, which could be incomplete, to improve diagnostic accuracy. Volumetric features were first extracted from the baseline MRI scan and subsequent scans acquired after 6, 12, and 18 months. Dynamic features were then obtained using the 18th month scan as the reference and computing the ratios of feature differences for the earlier scans. Features that are linearly or non-linearly correlated with diagnostic labels are then selected using two elastic net sparse learning algorithms. Missing feature values due to the incomplete longitudinal data are imputed using a low-rank matrix completion method. Finally, based on the completed feature matrix, we build a multi-kernel support vector machine (mkSVM) to predict the diagnostic label of samples with unknown diagnostic statuses. Our evaluation indicates that a diagnosis accuracy as high as 78.2 % can be achieved when information from the longitudinal scans is used-6.6 % higher than the case using only the reference time point image. In other words, information provided by the longitudinal history of the disease improves diagnosis accuracy.

SPHERE: SPherical Harmonic Elastic REgistration of HARDI data

In contrast to the more common Diffusion Tensor Imaging (DTI), High Angular Resolution Diffusion Imaging (HARDI) allows superior delineation of angular microstructures of brain white matter, and makes possible multiple-fiber modeling of each voxel for better characterization of brain connectivity. However, the complex orientation information afforded by HARDI makes registration of HARDI images more complicated than scalar images. In particular, the question of how much orientation information is needed for satisfactory alignment has not been sufficiently addressed. Low order orientation representation is generally more robust than high order representation, although the latter provides more information for correct alignment of fiber pathways. However, high order representation, when naïvely utilized, might not necessarily be conducive to improving registration accuracy since similar structures with significant orientation differences prior to proper alignment might be mistakenly taken as non-matching structures. We present in this paper a HARDI registration algorithm, called SPherical Harmonic Elastic REgistration (SPHERE), which in a principled means hierarchically extracts orientation information from HARDI data for structural alignment. The image volumes are first registered using robust, relatively direction invariant features derived from the Orientation Distribution Function (ODF), and the alignment is then further refined using spherical harmonic (SH) representation with gradually increasing orders. This progression from non-directional, single-directional to multi-directional representation provides a systematic means of extracting directional information given by diffusion-weighted imaging. Coupled with a template-subject-consistent soft-correspondence-matching scheme, this approach allows robust and accurate alignment of HARDI data. Experimental results show marked increase in accuracy over a state-of-the-art DTI registration algorithm.

Constrained sparse functional connectivity networks for MCI classification

Mild cognitive impairment (MCI) is difficult to diagnose due to its subtlety. Recent emergence of advanced network analysis techniques utilizing resting-state functional Magnetic Resonance Imaging (rs-fMRI) has made the understanding of neurological disorders more comprehensively at a whole-brain connectivity level. However, inferring effective brain connectivity from fMRI data is a challenging task, particularly when the ultimate goal is to obtain good control-patient classification performance. Incorporating sparsity into connectivity modeling can potentially produce results that are biologically more meaningful since most biologically networks are formed by a relatively few number of connections. However, this constraint, when applied at an individual level, will degrade classification performance due to inter-subject variability. To address this problem, we consider a constrained sparse linear regression model associated with the least absolute shrinkage and selection operator (LASSO). Specifically, we introduced sparsity into brain connectivity via l1-norm penalization, and ensured consistent non-zero connections across subjects via l2-norm penalization. Our results demonstrate that the constrained sparse network gives better classification performance than the conventional correlation-based network, indicating its greater sensitivity to early stage brain pathologies.

Application of neuroanatomical features to tractography clustering

Diffusion tensor imaging allows unprecedented insight into brain neural connectivity in vivo by allowing reconstruction of neuronal tracts via captured patterns of water diffusion in white matter microstructures. However, tractography algorithms often output hundreds of thousands of fibers, rendering subsequent data analysis intractable. As a remedy, fiber clustering techniques are able to group fibers into dozens of bundles and thus facilitate analyses. Most existing fiber clustering methods rely on geometrical information of fibers, by viewing them as curves in 3D Euclidean space. The important neuroanatomical aspect of fibers, however, is ignored. In this article, the neuroanatomical information of each fiber is encapsulated in the associativity vector, which functions as the unique "fingerprint" of the fiber. Specifically, each entry in the associativity vector describes the relationship between the fiber and a certain anatomical ROI in a fuzzy manner. The value of the entry approaches 1 if the fiber is spatially related to the ROI at high confidence; on the contrary, the value drops closer to 0. The confidence of the ROI is calculated by diffusing the ROI according to the underlying fibers from tractography. In particular, we have adopted the fast marching method for simulation of ROI diffusion. Using the associativity vectors of fibers, we further model fibers as observations sampled from multivariate Gaussian mixtures in the feature space. To group all fibers into relevant major bundles, an expectation-maximization clustering approach is employed. Experimental results indicate that our method results in anatomically meaningful bundles that are highly consistent across subjects.

Consistent Spatial-Temporal Longitudinal Atlas Construction for Developing Infant Brains

Brain atlases are an essential component in understanding the dynamic cerebral development, especially for the early postnatal period. However, longitudinal atlases are rare for infants, and the existing ones are generally limited by their fuzzy appearance. Moreover, since longitudinal atlas construction is typically performed independently over time, the constructed atlases often fail to preserve temporal consistency. This problem is further aggravated for infant images since they typically have low spatial resolution and insufficient tissue contrast. In this paper, we propose a novel framework for consistent spatial-temporal construction of longitudinal atlases for developing infant brain MR images. Specifically, for preserving structural details, the atlas construction is performed in spatial-temporal wavelet domain simultaneously. This is achieved by a patch-based combination of results from each frequency subband. Compared with the existing infant longitudinal atlases, our experimental results indicate that our approach is able to produce longitudinal atlases with richer structural details and also better longitudinal consistency, thus leading to higher performance when used for spatial normalization of a group of infant brain images.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Mitigating gyral bias in cortical tractography via asymmetric fiber orientation distributions

Diffusion tractography in brain connectomics often involves tracing axonal trajectories across gray-white matter boundaries in gyral blades of complex cortical convolutions. To date, gyral bias is observed in most tractography algorithms with streamlines predominantly terminating at gyral crowns instead of sulcal banks. This work demonstrates that asymmetric fiber orientation distribution functions (AFODFs), computed via a multi-tissue global estimation framework, can mitigate the effects of gyral bias, enabling fiber streamlines at gyral blades to make sharper turns into the cortical gray matter. We use ex-vivo data of an adult rhesus macaque and in-vivo data from the Human Connectome Project (HCP) to show that the fiber streamlines given by AFODFs bend more naturally into the cortex than the conventional symmetric FODFs in typical gyral blades. We demonstrate that AFODF tractography improves cortico-cortical connectivity and provides highly consistent outcomes between two different field strengths (3T and 7T).

Attribute vector guided groupwise registration

Groupwise registration has been recently introduced to simultaneously register a group of images by avoiding the selection of a particular template. To achieve this, several methods have been proposed to take advantage of information-theoretic entropy measures based on image intensity. However, simplistic utilization of voxelwise image intensity is not sufficient to establish reliable correspondences, since it lacks important contextual information. Therefore, we explore the notion of attribute vector as the voxel signature, instead of image intensity, to guide the correspondence detection in groupwise registration. In particular, for each voxel, the attribute vector is computed from its multi-scale neighborhoods, in order to capture the geometric information at different scales. The probability density function (PDF) of each element in the attribute vector is then estimated from the local neighborhood, providing a statistical summary of the underlying anatomical structure in that local pattern. Eventually, with the help of Jensen-Shannon (JS) divergence, a group of subjects can be aligned simultaneously by minimizing the sum of JS divergences across the image domain and all attributes. We have employed our groupwise registration algorithm on both real (NIREP NA0 data set) and simulated data (12 pairs of normal control and simulated atrophic data set). The experimental results demonstrate that our method yields better registration accuracy, compared with a popular groupwise registration method.