Fetal cortical surface atlas parcellation based on growth patterns.

Defining anatomically and functionally meaningful parcellation maps on cortical surface atlases is of great importance in surface-based neuroimaging analysis. The conventional cortical parcellation maps are typically defined based on anatomical cortical folding landmarks in adult surface atlases. However, they are not suitable for fetal brain studies, due to dramatic differences in brain size, shape, and properties between adults and fetuses. To address this issue, we propose a novel data-driven method for parcellation of fetal cortical surface atlases into distinct regions based on the dynamic "growth patterns" of cortical properties (e.g., surface area) from a population of fetuses. Our motivation is that the growth patterns of cortical properties indicate the underlying rapid changes of microstructures, which determine the molecular and functional principles of the cortex. Thus, growth patterns are well suitable for defining distinct cortical regions in development, structure, and function. To comprehensively capture the similarities of cortical growth patterns among vertices, we construct two complementary similarity matrices. One is directly based on the growth trajectories of vertices, and the other is based on the correlation profiles of vertices' growth trajectories in relation to a set of reference points. Then, we nonlinearly fuse these two similarity matrices into a single one, which can better capture both their common and complementary information than by simply averaging them. Finally, based on this fused similarity matrix, we perform spectral clustering to divide the fetal cortical surface atlases into distinct regions. By applying our method on 25 normal fetuses from 26 to 29 gestational weeks, we construct age-specific fetal cortical surface atlases equipped with biologically meaningful parcellation maps based on cortical growth patterns. Importantly, our generated parcellation maps reveal spatially contiguous, hierarchical and bilaterally relatively symmetric patterns of fetal cortical surface development.

Toward the automatic quantification of in utero brain development in 3D structural MRI: A review.

Investigating the human brain in utero is important for researchers and clinicians seeking to understand early neurodevelopmental processes. With the advent of fast magnetic resonance imaging (MRI) techniques and the development of motion correction algorithms to obtain high-quality 3D images of the fetal brain, it is now possible to gain more insight into the ongoing maturational processes in the brain. In this article, we present a review of the major building blocks of the pipeline toward performing quantitative analysis of in vivo MRI of the developing brain and its potential applications in clinical settings. The review focuses on T1- and T2-weighted modalities, and covers state of the art methodologies involved in each step of the pipeline, in particular, 3D volume reconstruction, spatio-temporal modeling of the developing brain, segmentation, quantification techniques, and clinical applications. Hum Brain Mapp 38:2772-2787, 2017. © 2017 Wiley Periodicals, Inc.

Hierarchical multi-atlas label fusion with multi-scale feature representation and label-specific patch partition.

Multi-atlas patch-based label fusion methods have been successfully used to improve segmentation accuracy in many important medical image analysis applications. In general, to achieve label fusion a single target image is first registered to several atlas images. After registration a label is assigned to each target point in the target image by determining the similarity between the underlying target image patch (centered at the target point) and the aligned image patch in each atlas image. To achieve the highest level of accuracy during the label fusion process it's critical for the chosen patch similarity measurement to accurately capture the tissue/shape appearance of the anatomical structure. One major limitation of existing state-of-the-art label fusion methods is that they often apply a fixed size image patch throughout the entire label fusion procedure. Doing so may severely affect the fidelity of the patch similarity measurement, which in turn may not adequately capture complex tissue appearance patterns expressed by the anatomical structure. To address this limitation, we advance state-of-the-art by adding three new label fusion contributions: First, each image patch is now characterized by a multi-scale feature representation that encodes both local and semi-local image information. Doing so will increase the accuracy of the patch-based similarity measurement. Second, to limit the possibility of the patch-based similarity measurement being wrongly guided by the presence of multiple anatomical structures in the same image patch, each atlas image patch is further partitioned into a set of label-specific partial image patches according to the existing labels. Since image information has now been semantically divided into different patterns, these new label-specific atlas patches make the label fusion process more specific and flexible. Lastly, in order to correct target points that are mislabeled during label fusion, a hierarchical approach is used to improve the label fusion results. In particular, a coarse-to-fine iterative label fusion approach is used that gradually reduces the patch size. To evaluate the accuracy of our label fusion approach, the proposed method was used to segment the hippocampus in the ADNI dataset and 7.0 T MR images, sub-cortical regions in LONI LBPA40 dataset, mid-brain regions in SATA dataset from MICCAI 2013 segmentation challenge, and a set of key internal gray matter structures in IXI dataset. In all experiments, the segmentation results of the proposed hierarchical label fusion method with multi-scale feature representations and label-specific atlas patches are more accurate than several well-known state-of-the-art label fusion methods.

Relation Between Sex, Menopause, and White Matter Hyperintensities: The Rhineland Study.

BACKGROUND AND OBJECTIVES: Mounting evidence implies that there are sex differences in white matter hyperintensity (WMH) burden in older people. Questions remain regarding possible differences in WMH burden between men and women of younger age, sex-specific age trajectories and effects of (un)controlled hypertension, and the effect of menopause on WMH. Therefore, our aim was to investigate these sex differences and age dependencies in WMH load across the adult life span and to examine the effect of menopause. METHODS: This cross-sectional analysis was based on participants of the population-based Rhineland Study (30-95 years) who underwent brain MRI. We automatically quantified WMH using T1-weighted, T2-weighted, and fluid-attenuated inversion recovery images. Menopausal status was self-reported. We examined associations of sex and menopause with WMH load (logit-transformed and z-standardized) using linear regression models while adjusting for age, age-squared, and vascular risk factors. We checked for an age × sex and (un)controlled hypertension × sex interaction and stratified for menopausal status comparing men with premenopausal women (persons aged 59 years or younger), men with postmenopausal women (persons aged 45 years or older), and premenopausal with postmenopausal women (age range 45-59 years). RESULTS: Of 3,410 participants with a mean age of 54.3 years (SD = 13.7), 1,973 (57.9%) were women, of which 1,167 (59.1%) were postmenopausal. We found that the increase in WMH load accelerates with age and in a sex-dependent way. Premenopausal women and men of similar age did not differ in WMH burden. WMH burden was higher and accelerated faster in postmenopausal women compared with men of similar age. In addition, we observed changes related to menopause, in that postmenopausal women had more WMH than premenopausal women of similar age. Women with uncontrolled hypertension had a higher WMH burden compared with men, which was unrelated to menopausal status. DISCUSSION: After menopause, women displayed a higher burden of WMH than contemporary premenopausal women and men and an accelerated increase in WMH. Sex-specific effects of uncontrolled hypertension on WMH were not related to menopause. Further studies are warranted to investigate menopause-related physiologic changes that may inform on causal mechanisms involved in cerebral small vessel disease progression.

A novel approach to multiple anatomical shape analysis: Application to fetal ventriculomegaly.

Fetal ventriculomegaly (VM) is a condition in which one or both lateral ventricles are enlarged, and is diagnosed as an atrial diameter larger than 10 mm. Evidence of altered cortical folding associated with VM has been shown in the literature. However, existing works use a single scalar value such as diagnosis or lateral ventricular volume to characterize VM and study its relationship with alterations in cortical folding, thus failing to reveal the spatially-heterogeneous associations. In this work, we propose a novel approach to identify fine-grained associations between cortical folding and ventricular enlargement by leveraging the vertex-wise correlations between their growth patterns in terms of area expansion and curvature. Our approach comprises three steps. In the first step, we define a joint graph Laplacian matrix using cortex-to-ventricle correlations. The joint Laplacian is built based on multiple cortical features. Next, we propose a spectral embedding of the cortex-to-ventricle graph into a common underlying space where its nodes are projected according to the joint ventricle-cortex growth patterns. In this low-dimensional joint ventricle-cortex space, associated growth patterns lie close to each other. In the final step, we perform hierarchical clustering in the joint embedded space to identify associated sub-regions between cortex and ventricle. Using a dataset of 25 healthy fetuses and 23 fetuses with isolated non-severe VM within the age range of 26-29 gestational weeks, our approach reveals clinically relevant and heterogeneous regional associations. Cortical regions forming these associations are further validated using statistical analysis, revealing regions with altered folding that are significantly associated with ventricular dilation.

Revealing heterogeneity of brain imaging phenotypes in Alzheimer's disease based on unsupervised clustering of blood marker profiles.

Alzheimer's disease (AD) affects millions of people and is a major rising problem in health care worldwide. Recent research suggests that AD could have different subtypes, presenting differences in how the disease develops. Characterizing those subtypes could be key to deepen the understanding of this complex disease. In this paper, we used a multivariate, non-supervised clustering method over blood-based markers to find subgroups of patients defined by distinctive blood marker profiles. Our analysis on ADNI database identified 4 possible subgroups, each with a different blood profile. More importantly, we show that subgroups with different profiles have a different relationship between brain phenotypes detected in magnetic resonance imaging and disease condition.

Patch spaces and fusion strategies in patch-based label fusion.

In the field of multi-atlas segmentation, patch-based approaches have shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation based on local appearance information encoded in form of patches. The registration step establishes spatial correspondence, which is important to obtain anatomical priors. Patch-based label fusion in the target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance (i.e., patches) and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. In this work, we revisit and extend the patch-based label fusion framework, exploring the role of extracting this information from the native space of both atlases and target images, thus avoiding interpolation artifacts, but at the same time, we do it in a way that it does not sacrifice the anatomical priors derived by registration. We further propose a common formulation for two widely-used label fusion strategies, i.e., similarity-based and a particular type of learning-based label fusion. The proposed framework is evaluated on subcortical structure segmentation in adult brains and tissue segmentation in fetal brain MRI. Our results indicate that using atlas patches in their native space yields superior performance than warping the atlases to the target image. The learning-based approach tends to outperform the similarity-based approach, with the particularity that using patches in native space lessens the computational requirements of learning. As conclusion, the combination of learning-based label fusion and native atlas patches yields the best performance with reduced test times than conventional similarity-based approaches.

Benchmark on Automatic 6-month-old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge.

Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is an indispensable foundation for early studying of brain growth patterns and morphological changes in neurodevelopmental disorders. Nevertheless, in the isointense phase (approximately 6-9 months of age), due to inherent myelination and maturation process, WM and GM exhibit similar levels of intensity in both T1-weighted (T1w) and T2-weighted (T2w) MR images, making tissue segmentation very challenging. Despite many efforts were devoted to brain segmentation, only few studies have focused on the segmentation of 6-month infant brain images. With the idea of boosting methodological development in the community, iSeg-2017 challenge (http://iseg2017.web.unc.edu) provides a set of 6-month infant subjects with manual labels for training and testing the participating methods. Among the 21 automatic segmentation methods participating in iSeg-2017, we review the 8 top-ranked teams, in terms of Dice ratio, modified Hausdorff distance and average surface distance, and introduce their pipelines, implementations, as well as source codes. We further discuss limitations and possible future directions. We hope the dataset in iSeg-2017 and this review article could provide insights into methodological development for the community.

Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation.

Segmentation of brain structures during the pre-natal and early post-natal periods is the first step for subsequent analysis of brain development. Segmentation techniques can be roughly divided into two families. The first, which we denote as registration-based techniques, rely on initial estimates derived by registration to one (or several) templates. The second family, denoted as learning-based techniques, relate imaging (and spatial) features to their corresponding anatomical labels. Each approach has its own qualities and both are complementary to each other. In this paper, we explore two ensembling strategies, namely, stacking and cascading to combine the strengths of both families. We present experiments on segmentation of 6-month infant brains and a cohort of fetuses with isolated non-severe ventriculomegaly (INSVM). INSVM is diagnosed when ventricles are mildly enlarged and no other anomalies are apparent. Prognosis is difficult based solely on the degree of ventricular enlargement. In order to find markers for a more reliable prognosis, we use the resulting segmentations to find abnormalities in the cortical folding of INSVM fetuses. Segmentation results show that either combination strategy outperform all of the individual methods, thus demonstrating the capability of learning systematic combinations that lead to an overall improvement. In particular, the cascading strategy outperforms the ensembling one, the former one obtaining top 5, 7 and 13 results (out of 21 teams) in the segmentation of white matter, gray matter and cerebro-spinal fluid in the iSeg2017 MICCAI Segmentation Challenge. The resulting segmentations reveal that INSVM fetuses have a less convoluted cortex. This points to cortical folding abnormalities as potential markers of later neurodevelopmental outcomes.

Cortical folding alterations in fetuses with isolated non-severe ventriculomegaly.

Neuroimaging of brain diseases plays a crucial role in understanding brain abnormalities and early diagnosis. Of great importance is the study of brain abnormalities in utero and the assessment of deviations in case of maldevelopment. In this work, brain magnetic resonance images from 23 isolated non-severe ventriculomegaly (INSVM) fetuses and 25 healthy controls between 26 and 29 gestational weeks were used to identify INSVM-related cortical folding deviations from normative development. Since these alterations may reflect abnormal neurodevelopment, our working hypothesis is that markers of cortical folding can provide cues to improve the prediction of later neurodevelopmental problems in INSVM subjects. We analyzed the relationship of ventricular enlargement with cortical folding alterations in a regional basis using several curvature-based measures describing the folding of each cortical region. Statistical analysis (global and hemispheric) and sparse linear regression approaches were then used to find the cortical regions whose folding is associated with ventricular dilation. Results from both approaches were in great accordance, showing a significant cortical folding decrease in the insula, posterior part of the temporal lobe and occipital lobe. Moreover, compared to the global analysis, stronger ipsilateral associations of ventricular enlargement with reduced cortical folding were encountered by the hemispheric analysis. Our findings confirm and extend previous studies by identifying various cortical regions and emphasizing ipsilateral effects of ventricular enlargement in altered folding. This suggests that INSVM is an indicator of altered cortical development, and moreover, cortical regions with reduced folding constitute potential prognostic biomarkers to be used in follow-up studies to decipher the outcome of INSVM fetuses.

FETAL CORTICAL PARCELLATION BASED ON GROWTH PATTERNS.

Dividing the human cerebral cortex into structurally and functionally distinct regions is important in many neuroimaging studies. Although many parcellations have been created for adults, they are not applicable for fetal studies, due to dramatic differences in brain size, shape and folding between adults and fetuses, as well as dynamic growth of fetal brains. To address this issue, we propose a novel method to divide a population of fetal cortical surfaces into distinct regions based on the dynamic growth patterns of cortical properties, which indicate the underlying changes of microstructures. As microstructures determine the molecular organization and functional principles of the cortex, growth patterns enable an accurate definition of distinct regions in development, microstructure, and function. To comprehensively capture the similarities of cortical growth patterns among vertices, we construct two complementary similarity matrices. One is directly based on the growth trajectories of vertices and the other is based on the correlation profiles of vertices' growth trajectories in relation to those of reference points. Then, we nonlinearly fuse these two similarity matrices into a single one, which can better captures both their common and complementary information than by simply averaging them. Finally, based on this fused matrix, we perform spectral clustering to divide fetal cortical surfaces into distinct regions. We have applied our method on 25 normal fetuses from 26 to 29 gestational weeks and generated biologically meaningful parcellations.

Learning non-linear patch embeddings with neural networks for label fusion.

In brain structural segmentation, multi-atlas strategies are increasingly being used over single-atlas strategies because of their ability to fit a wider anatomical variability. Patch-based label fusion (PBLF) is a type of such multi-atlas approaches that labels each target point as a weighted combination of neighboring atlas labels, where atlas points with higher local similarity to the target contribute more strongly to label fusion. PBLF can be potentially improved by increasing the discriminative capabilities of the local image similarity measurements. We propose a framework to compute patch embeddings using neural networks so as to increase discriminative abilities of similarity-based weighted voting in PBLF. As particular cases, our framework includes embeddings with different complexities, namely, a simple scaling, an affine transformation, and non-linear transformations. We compare our method with state-of-the-art alternatives in whole hippocampus and hippocampal subfields segmentation experiments using publicly available datasets. Results show that even the simplest versions of our method outperform standard PBLF, thus evidencing the benefits of discriminative learning. More complex transformation models tended to achieve better results than simpler ones, obtaining a considerable increase in average Dice score compared to standard PBLF.

Revealing Regional Associations of Cortical Folding Alterations with In Utero Ventricular Dilation Using Joint Spectral Embedding.

Fetal ventriculomegaly (VM) is a condition with dilation of one or both lateral ventricles, and is diagnosed as an atrial diameter larger than 10 mm. Evidence of altered cortical folding associated with VM has been shown in the literature. However, existing studies use a holistic approach (i.e., ventricle as a whole) based on diagnosis or ventricular volume, thus failing to reveal the spatially-heterogeneous association patterns between cortex and ventricle. To address this issue, we develop a novel method to identify spatially fine-scaled association maps between cortical development and VM by leveraging vertex-wise correlations between the growth patterns of both ventricular and cortical surfaces in terms of area expansion and curvature information. Our approach comprises multiple steps. In the first step, we define a joint graph Laplacian matrix using cortex-to-ventricle correlations. Next, we propose a spectral embedding of the cortex-to-ventricle graph into a common underlying space where their joint growth patterns are projected. More importantly, in the joint ventricle-cortex space, the vertices of associated regions from both cortical and ventricular surfaces would lie close to each other. In the final step, we perform clustering in the joint embedded space to identify associated sub-regions between cortex and ventricle. Using a dataset of 25 healthy fetuses and 23 fetuses with isolated non-severe VM within the age range of 26-29 gestational weeks, our results show that the proposed approach is able to reveal clinically relevant and meaningful regional associations.

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Automatic Cardiac Diagnosis Challenge" dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

Discriminative confidence estimation for probabilistic multi-atlas label fusion.

Quantitative neuroimaging analyses often rely on the accurate segmentation of anatomical brain structures. In contrast to manual segmentation, automatic methods offer reproducible outputs and provide scalability to study large databases. Among existing approaches, multi-atlas segmentation has recently shown to yield state-of-the-art performance in automatic segmentation of brain images. It consists in propagating the labelmaps from a set of atlases to the anatomy of a target image using image registration, and then fusing these multiple warped labelmaps into a consensus segmentation on the target image. Accurately estimating the contribution of each atlas labelmap to the final segmentation is a critical step for the success of multi-atlas segmentation. Common approaches to label fusion either rely on local patch similarity, probabilistic statistical frameworks or a combination of both. In this work, we propose a probabilistic label fusion framework based on atlas label confidences computed at each voxel of the structure of interest. Maximum likelihood atlas confidences are estimated using a supervised approach, explicitly modeling the relationship between local image appearances and segmentation errors produced by each of the atlases. We evaluate different spatial pooling strategies for modeling local segmentation errors. We also present a novel type of label-dependent appearance features based on atlas labelmaps that are used during confidence estimation to increase the accuracy of our label fusion. Our approach is evaluated on the segmentation of seven subcortical brain structures from the MICCAI 2013 SATA Challenge dataset and the hippocampi from the ADNI dataset. Overall, our results indicate that the proposed label fusion framework achieves superior performance to state-of-the-art approaches in the majority of the evaluated brain structures and shows more robustness to registration errors.

Learning and combining image neighborhoods using random forests for neonatal brain disease classification.

It is challenging to characterize and classify normal and abnormal brain development during early childhood. To reduce the complexity of heterogeneous data population, manifold learning techniques are increasingly applied, which find a low-dimensional representation of the data, while preserving all relevant information. The neighborhood definition used for constructing manifold representations of the population is crucial for preserving the similarity structure and it is highly application dependent. The recently proposed neighborhood approximation forests learn a neighborhood structure in a dataset based on a user-defined distance. We propose a framework to learn multiple pairwise distances in a population of brain images and to combine them in an unsupervised manner optimally in a manifold learning step. Unlike other methods that only use a univariate distance measure, our method allows for a natural combination of multiple distances from heterogeneous sources. As a result, it yields a representation of the population that preserves the multiple distances. Furthermore, our method also selects the most predictive features associated with the distances. We evaluate our method in neonatal magnetic resonance images of three groups (term controls, patients affected by intrauterine growth restriction and mild isolated ventriculomegaly). We show that combining multiple distances related to the condition improves the overall characterization and classification of the three clinical groups compared to the use of single distances and classical unsupervised manifold learning.

MSClique: Multiple Structure Discovery through the Maximum Weighted Clique Problem.

We present a novel approach for feature correspondence and multiple structure discovery in computer vision. In contrast to existing methods, we exploit the fact that point-sets on the same structure usually lie close to each other, thus forming clusters in the image. Given a pair of input images, we initially extract points of interest and extract hierarchical representations by agglomerative clustering. We use the maximum weighted clique problem to find the set of corresponding clusters with maximum number of inliers representing the multiple structures at the correct scales. Our method is parameter-free and only needs two sets of points along with their tentative correspondences, thus being extremely easy to use. We demonstrate the effectiveness of our method in multiple-structure fitting experiments in both publicly available and in-house datasets. As shown in the experiments, our approach finds a higher number of structures containing fewer outliers compared to state-of-the-art methods.

Building dynamic population graph for accurate correspondence detection.

In medical imaging studies, there is an increasing trend for discovering the intrinsic anatomical difference across individual subjects in a dataset, such as hand images for skeletal bone age estimation. Pair-wise matching is often used to detect correspondences between each individual subject and a pre-selected model image with manually-placed landmarks. However, the large anatomical variability across individual subjects can easily compromise such pair-wise matching step. In this paper, we present a new framework to simultaneously detect correspondences among a population of individual subjects, by propagating all manually-placed landmarks from a small set of model images through a dynamically constructed image graph. Specifically, we first establish graph links between models and individual subjects according to pair-wise shape similarity (called as forward step). Next, we detect correspondences for the individual subjects with direct links to any of model images, which is achieved by a new multi-model correspondence detection approach based on our recently-published sparse point matching method. To correct those inaccurate correspondences, we further apply an error detection mechanism to automatically detect wrong correspondences and then update the image graph accordingly (called as backward step). After that, all subject images with detected correspondences are included into the set of model images, and the above two steps of graph expansion and error correction are repeated until accurate correspondences for all subject images are established. Evaluations on real hand X-ray images demonstrate that our proposed method using a dynamic graph construction approach can achieve much higher accuracy and robustness, when compared with the state-of-the-art pair-wise correspondence detection methods as well as a similar method but using static population graph.

A transversal approach for patch-based label fusion via matrix completion.

Recently, multi-atlas patch-based label fusion has received an increasing interest in the medical image segmentation field. After warping the anatomical labels from the atlas images to the target image by registration, label fusion is the key step to determine the latent label for each target image point. Two popular types of patch-based label fusion approaches are (1) reconstruction-based approaches that compute the target labels as a weighted average of atlas labels, where the weights are derived by reconstructing the target image patch using the atlas image patches; and (2) classification-based approaches that determine the target label as a mapping of the target image patch, where the mapping function is often learned using the atlas image patches and their corresponding labels. Both approaches have their advantages and limitations. In this paper, we propose a novel patch-based label fusion method to combine the above two types of approaches via matrix completion (and hence, we call it transversal). As we will show, our method overcomes the individual limitations of both reconstruction-based and classification-based approaches. Since the labeling confidences may vary across the target image points, we further propose a sequential labeling framework that first labels the highly confident points and then gradually labels more challenging points in an iterative manner, guided by the label information determined in the previous iterations. We demonstrate the performance of our novel label fusion method in segmenting the hippocampus in the ADNI dataset, subcortical and limbic structures in the LONI dataset, and mid-brain structures in the SATA dataset. We achieve more accurate segmentation results than both reconstruction-based and classification-based approaches. Our label fusion method is also ranked 1st in the online SATA Multi-Atlas Segmentation Challenge.

Learning-Based Atlas Selection for Multiple-Atlas Segmentation.

Recently, multi-atlas segmentation (MAS) has achieved a great success in the medical imaging area. The key assumption of MAS is that multiple atlases encompass richer anatomical variability than a single atlas. Therefore, we can label the target image more accurately by mapping the label information from the appropriate atlas images that have the most similar structures. The problem of atlas selection, however, still remains unexplored. Current state-of-the-art MAS methods rely on image similarity to select a set of atlases. Unfortunately, this heuristic criterion is not necessarily related to segmentation performance and, thus may undermine segmentation results. To solve this simple but critical problem, we propose a learning-based atlas selection method to pick up the best atlases that would eventually lead to more accurate image segmentation. Our idea is to learn the relationship between the pairwise appearance of observed instances (a pair of atlas and target images) and their final labeling performance (in terms of Dice ratio). In this way, we can select the best atlases according to their expected labeling accuracy. It is worth noting that our atlas selection method is general enough to be integrated with existing MAS methods. As is shown in the experiments, we achieve significant improvement after we integrate our method with 3 widely used MAS methods on ADNI and LONI LPBA40 datasets.