Automated model-based tissue classification of MR images of the brain

A Novel Method for High-Dimensional Anatomical Mapping of Extra-Axial Cerebrospinal Fluid: Application to the Infant Brain

Cerebrospinal fluid (CSF) plays an essential role in early postnatal brain development. Extra-axial CSF (EA-CSF) volume, which is characterized by CSF in the subarachnoid space surrounding the brain, is a promising marker in the early detection of young children at risk for neurodevelopmental disorders. Previous studies have focused on global EA-CSF volume across the entire dorsal extent of the brain, and not regionally-specific EA-CSF measurements, because no tools were previously available for extracting local EA-CSF measures suitable for localized cortical surface analysis. In this paper, we propose a novel framework for the localized, cortical surface-based analysis of EA-CSF. The proposed processing framework combines probabilistic brain tissue segmentation, cortical surface reconstruction, and streamline-based local EA-CSF quantification. The quantitative analysis of local EA-CSF was applied to a dataset of typically developing infants with longitudinal MRI scans from 6 to 24 months of age. There was a high degree of consistency in the spatial patterns of local EA-CSF across age using the proposed methods. Statistical analysis of local EA-CSF revealed several novel findings: several regions of the cerebral cortex showed reductions in EA-CSF from 6 to 24 months of age, and specific regions showed higher local EA-CSF in males compared to females. These age-, sex-, and anatomically-specific patterns of local EA-CSF would not have been observed if only a global EA-CSF measure were utilized. The proposed methods are integrated into a freely available, open-source, cross-platform, user-friendly software tool, allowing neuroimaging labs to quantify local extra-axial CSF in their neuroimaging studies to investigate its role in typical and atypical brain development.

Classification of Alzheimer's Disease and Mild Cognitive Impairment Based on Cortical and Subcortical Features from MRI T1 Brain Images Utilizing Four Different Types of Datasets

Alzheimer's disease (AD) is one of the most common neurodegenerative illnesses (dementia) among the elderly. Recently, researchers have developed a new method for the instinctive analysis of AD based on machine learning and its subfield, deep learning. Recent state-of-the-art techniques consider multimodal diagnosis, which has been shown to achieve high accuracy compared to a unimodal prognosis. Furthermore, many studies have used structural magnetic resonance imaging (MRI) to measure brain volumes and the volume of subregions, as well as to search for diffuse changes in white/gray matter in the brain. In this study, T1-weighted structural MRI was used for the early classification of AD. MRI results in high-intensity visible features, making preprocessing and segmentation easy. To use this image modality, we acquired four types of datasets from each dataset's server. In this work, we downloaded 326 subjects from the National Research Center for Dementia homepage, 123 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) homepage, 121 subjects from the Alzheimer's Disease Repository Without Borders homepage, and 131 subjects from the National Alzheimer's Coordinating Center homepage. In our experiment, we used the multiatlas label propagation with expectation–maximization-based refinement segmentation method. We segmented the images into 138 anatomical morphometry images (in which 40 features belonged to subcortical volumes and the remaining 98 features belonged to cortical thickness). The entire dataset was split into a 70 : 30 (training and testing) ratio before classifying the data. A principal component analysis was used for dimensionality reduction. Then, the support vector machine radial basis function classifier was used for classification between two groups—AD versus health control (HC) and early mild cognitive impairment (MCI) (EMCI) versus late MCI (LMCI). The proposed method performed very well for all four types of dataset. For instance, for the AD versus HC group, the classifier achieved an area under curve (AUC) of more than 89% for each dataset. For the EMCI versus LMCI group, the classifier achieved an AUC of more than 80% for every dataset. Moreover, we also calculated Cohen kappa and Jaccard index statistical values for all datasets to evaluate the classification reliability. Finally, we compared our results with those of recently published state-of-the-art methods.

Partial-volume modeling reveals reduced gray matter in specific thalamic nuclei early in the time course of psychosis and chronic schizophrenia

The structural complexity of the thalamus, due to its mixed composition of gray and white matter, make it challenging to disjoint and quantify each tissue contribution to the thalamic anatomy. This work promotes the use of partial‐volume‐based over probabilistic‐based tissue segmentation approaches to better capture thalamic gray matter differences between patients at different stages of psychosis (early and chronic) and healthy controls. The study was performed on a cohort of 23 patients with schizophrenia, 41 with early psychosis and 69 age and sex‐matched healthy subjects. Six tissue segmentation approaches were employed to obtain the gray matter concentration/probability images. The statistical tests were applied at three different anatomical scales: whole thalamus, thalamic subregions and voxel‐wise. The results suggest that the partial volume model estimation of gray matter is more sensitive to detect atrophies within the thalamus of patients with psychosis. However all the methods detected gray matter deficit in the pulvinar, particularly in early stages of psychosis. This study demonstrates also that the gray matter decrease varies nonlinearly with age and between nuclei. While a gray matter loss was found in the pulvinar of patients in both stages of psychosis, reduced gray matter in the mediodorsal was only observed in early psychosis subjects. Finally, our analyses point to alterations in a sub‐region comprising the lateral posterior and ventral posterior nuclei. The obtained results reinforce the hypothesis that thalamic gray matter assessment is more reliable when the tissues segmentation method takes into account the partial volume effect.

Sparse Data-Driven Learning for Effective and Efficient Biomedical Image Segmentation

Sparsity is a powerful concept to exploit for high-dimensional machine learning and associated representational and computational efficiency. Sparsity is well suited for medical image segmentation. We present a selection of techniques that incorporate sparsity, including strategies based on dictionary learning and deep learning, that are aimed at medical image segmentation and related quantification.

Automated White Matter Hyperintensity Segmentation Using Bayesian Model Selection: Assessment and Correlations with Cognitive Change

Accurate, automated white matter hyperintensity (WMH) segmentations are needed for large-scale studies to understand contributions of WMH to neurological diseases. We evaluated Bayesian Model Selection (BaMoS), a hierarchical fully-unsupervised model selection framework for WMH segmentation. We compared BaMoS segmentations to semi-automated segmentations, and assessed whether they predicted longitudinal cognitive change in control, early Mild Cognitive Impairment (EMCI), late Mild Cognitive Impairment (LMCI), subjective/significant memory concern (SMC) and Alzheimer's (AD) participants. Data were downloaded from the Alzheimer's disease Neuroimaging Initiative (ADNI). Magnetic resonance images from 30 control and 30 AD participants were selected to incorporate multiple scanners, and were semi-automatically segmented by 4 raters and BaMoS. Segmentations were assessed using volume correlation, Dice score, and other spatial metrics. Linear mixed-effect models were fitted to 180 control, 107 SMC, 320 EMCI, 171 LMCI and 151 AD participants separately in each group, with the outcomes being cognitive change (e.g. mini-mental state examination; MMSE), and BaMoS WMH, age, sex, race and education used as predictors. There was a high level of agreement between BaMoS' WMH segmentation volumes and a consensus of rater segmentations, with a median Dice score of 0.74 and correlation coefficient of 0.96. BaMoS WMH predicted cognitive change in: control, EMCI, and SMC groups using MMSE; LMCI using clinical dementia rating scale; and EMCI using Alzheimer's disease assessment scale-cognitive subscale (p < 0.05, all tests). BaMoS compares well to semi-automated segmentation, is robust to different WMH loads and scanners, and can generate volumes which predict decline. BaMoS can be applicable to further large-scale studies.

Relative rate of change in cognitive score network dynamics via Bayesian hierarchical models reveal spatial patterns of neurodegeneration

The degeneration of the human brain is a complex process, which often affects certain brain regions due to healthy aging or disease. This degeneration can be evaluated on regions of interest (ROI) in the brain through probabilistic networks and morphological estimates. Current approaches for finding such networks are limited to analyses at discrete neuropsychological stages, which cannot appropriately account for connectivity dynamics over the onset of cognitive deterioration, and morphological changes are seldom unified with connectivity networks, despite known dependencies. To overcome these limitations, a probabilistic wombling model is proposed to simultaneously estimate ROI cortical thickness and covariance networks contingent on rates of change in cognitive decline. This proposed model was applied to analyze longitudinal data from healthy control (HC) and Alzheimer's disease (AD) groups and found connection differences pertaining to regions, which play a crucial role in lasting cognitive impairment, such as the entorhinal area and temporal regions. Moreover, HC cortical thickness estimates were significantly higher than those in the AD group across all ROIs. The analyses presented in this work will help practitioners jointly analyze brain tissue atrophy at the ROI-level conditional on neuropsychological networks, which could potentially allow for more targeted therapeutic interventions.

Early Detection of Alzheimer's Disease Using Magnetic Resonance Imaging: A Novel Approach Combining Convolutional Neural Networks and Ensemble Learning

Early detection is critical for effective management of Alzheimer's disease (AD) and screening for mild cognitive impairment (MCI) is common practice. Among several deep-learning techniques that have been applied to assessing structural brain changes on magnetic resonance imaging (MRI), convolutional neural network (CNN) has gained popularity due to its superb efficiency in automated feature learning with the use of a variety of multilayer perceptrons. Meanwhile, ensemble learning (EL) has shown to be beneficial in the robustness of learning-system performance via integrating multiple models. Here, we proposed a classifier ensemble developed by combining CNN and EL, i.e., the CNN-EL approach, to identify subjects with MCI or AD using MRI: i.e., classification between (1) AD and healthy cognition (HC), (2) MCIc (MCI patients who will convert to AD) and HC, and (3) MCIc and MCInc (MCI patients who will not convert to AD). For each binary classification task, a large number of CNN models were trained applying a set of sagittal, coronal, or transverse MRI slices; these CNN models were then integrated into a single ensemble. Performance of the ensemble was evaluated using stratified fivefold cross-validation method for 10 times. The number of the intersection points determined by the most discriminable slices separating two classes in a binary classification task among the sagittal, coronal, and transverse slice sets, transformed into the standard Montreal Neurological Institute (MNI) space, acted as an indicator to assess the ability of a brain region in which the points were located to classify AD. Thus, the brain regions with most intersection points were considered as those mostly contributing to the early diagnosis of AD. The result revealed an accuracy rate of 0.84 ± 0.05, 0.79 ± 0.04, and 0.62 ± 0.06, respectively, for classifying AD vs. HC, MCIc vs. HC, and MCIc vs. MCInc, comparable to previous reports and a 3D deep learning approach (3D-SENet) based on a more state-of-the-art and popular Squeeze-and-Excitation Networks model using channel attention mechanism. Notably, the intersection points accurately located the medial temporal lobe and several other structures of the limbic system, i.e., brain regions known to be struck early in AD. More interestingly, the classifiers disclosed multiple patterned MRI changes in the brain in AD and MCIc, involving these key regions. These results suggest that as a data-driven method, the combined CNN and EL approach can locate the most discriminable brain regions indicated by the trained ensemble model while the generalization ability of the ensemble model was maximized to successfully capture AD-related brain variations early in the disease process; it can also provide new insights into understanding the complex heterogeneity of whole-brain MRI changes in AD. Further research is needed to examine the clinical implication of the finding, capability of the advocated CNN-EL approach to help understand and evaluate an individual subject's disease status, symptom burden and progress, and the generalizability of the advocated CNN-EL approach to locate the most discriminable brain regions in the detection of other brain disorders such as schizophrenia, autism, and severe depression, in a data-driven way.

A 3D Spatially Weighted Network for Segmentation of Brain Tissue From MRI

The segmentation of brain tissue in MRI is valuable for extracting brain structure to aid diagnosis, treatment and tracking the progression of different neurologic diseases. Medical image data are volumetric and some neural network models for medical image segmentation have addressed this using a 3D convolutional architecture. However, this volumetric spatial information has not been fully exploited to enhance the representative ability of deep networks, and these networks have not fully addressed the practical issues facing the analysis of multimodal MRI data. In this paper, we propose a spatially-weighted 3D network (SW-3D-UNet) for brain tissue segmentation of single-modality MRI, and extend it using multimodality MRI data. We validate our model on the MRBrainS13 and MALC12 datasets. This unpublished model ranked first on the leaderboard of the MRBrainS13 Challenge.

Rates of age- and amyloid β-associated cortical atrophy in older adults with superior memory performance

INTRODUCTION

Superior cognitive performance in older adults may reflect underlying resistance to age-associated neurodegeneration. While elevated amyloid β (Aβ) deposition (Aβ+) has been associated with increased cortical atrophy, it remains unknown whether "SuperAgers" may be protected from Aβ-associated neurodegeneration.

METHODS

Neuropsychologically defined SuperAgers (n = 172) and cognitively normal for age (n = 172) older adults from the Australian Imaging, Biomarkers and Lifestyle study were case matched. Rates of cortical atrophy over 8 years were examined by SuperAger classification and Aβ status.

RESULTS

Of the case-matched SuperAgers and cognitively normal for age older adults, 40.7% and 40.1%, respectively, were Aβ+. Rates of age- and Aβ-associated atrophy did not differ between the groups on any measure. Aβ- individuals displayed the slowest rates of atrophy.

DISCUSSION

Maintenance of superior memory in late life does not reflect resistance to age- or Aβ-associated atrophy. However, those individuals who reached old age without cognitive impairment nor elevated Aβ deposition (i.e. Aβ-) displayed reduced rates of cortical atrophy.

Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images

The author proposes a method for simultaneous registration and segmentation of multi-source images, using the multivariate mixture model (MvMM) and maximum of log-likelihood (LL) framework. Specifically, the method is applied to the problem of myocardial segmentation combining the complementary information from multi-sequence (MS) cardiac magnetic resonance (CMR) images. For the image misalignment and incongruent data, the MvMM is formulated with transformations and is further generalized for dealing with the hetero-coverage multi-modality images (HC-MMIs). The segmentation of MvMM is performed in a virtual common space, to which all the images and misaligned slices are simultaneously registered. Furthermore, this common space can be divided into a number of sub-regions, each of which contains congruent data, thus the HC-MMIs can be modeled using a set of conventional MvMMs. Results show that MvMM obtained significantly better performance compared to the conventional approaches and demonstrated good potential for scar quantification as well as myocardial segmentation. The generalized MvMM has also demonstrated better robustness in the incongruent data, where some images may not fully cover the region of interest, and the full coverage can only be reconstructed combining the images from multiple sources.

Using deep learning for a diffusion-based segmentation of the dentate nucleus and its benefits over atlas-based methods

The dentate nucleus (DN) is a gray matter structure deep in the cerebellum involved in motor coordination, sensory input integration, executive planning, language, and visuospatial function. The DN is an emerging biomarker of disease, informing studies that advance pathophysiologic understanding of neurodegenerative and related disorders. The main challenge in defining the DN radiologically is that, like many deep gray matter structures, it has poor contrast in T1-weighted magnetic resonance (MR) images and therefore requires specialized MR acquisitions for visualization. Manual tracing of the DN across multiple acquisitions is resource-intensive and does not scale well to large datasets. We describe a technique that automatically segments the DN using deep learning (DL) on common imaging sequences, such as T1-weighted, T2-weighted, and diffusion MR imaging. We trained a DL algorithm that can automatically delineate the DN and provide an estimate of its volume. The automatic segmentation achieved higher agreement to the manual labels compared to template registration, which is the current common practice in DN segmentation or multiatlas segmentation of manual labels. Across all sequences, the FA maps achieved the highest mean Dice similarity coefficient (DSC) of 0.83 compared to T1 imaging ( DSC = 0.76 ), T2 imaging ( DSC = 0.79 ), or a multisequence approach ( DSC = 0.80 ). A single atlas registration approach using the spatially unbiased atlas template of the cerebellum and brainstem template achieved a DSC of 0.23, and multi-atlas segmentation achieved a DSC of 0.33. Overall, we propose a method of delineating the DN on clinical imaging that can reproduce manual labels with higher accuracy than current atlas-based tools.

Unsupervised Deep Learning for Bayesian Brain MRI Segmentation

Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learning-based segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU.

Quantitative assessment of myelination patterns in preterm neonates using T2-weighted MRI

Myelination is considered to be an important developmental process during human brain maturation and closely correlated with gestational age. Quantitative assessment of the myelination status requires dedicated imaging, but the conventional T₂-weighted scans routinely acquired during clinical imaging of neonates carry signatures that are thought to be associated with myelination. In this work, we develop a quatitative marker of progressing myelination for assessment preterm neonatal brain maturation based on novel automatic segmentation method for myelin-like signals on T₂-weighted magnetic resonance images. Firstly we define a segmentation protocol for myelin-like signals. We then develop an expectation-maximization framework to obtain the automatic segmentations of myelin-like signals with explicit class for partial volume voxels whose locations are configured in relation to the composing pure tissues via second-order Markov random fields. The proposed segmentation achieves high Dice overlaps of 0.83 with manual annotations. The automatic segmentations are then used to track volumes of myelinated tissues in the regions of the central brain structures and brainstem. Finally, we construct a spatio-temporal growth models for myelin-like signals, which allows us to predict gestational age at scan in preterm infants with root mean squared error 1.41 weeks.

Automatic Human Brain Tumor Detection in MRI Image Using Template-Based K Means and Improved Fuzzy C Means Clustering Algorithm

In recent decades, human brain tumor detection has become one of the most challenging issues in medical science. In this paper, we propose a model that includes the template-based K means and improved fuzzy C means (TKFCM) algorithm for detecting human brain tumors in a magnetic resonance imaging (MRI) image. In this proposed algorithm, firstly, the template-based K-means algorithm is used to initialize segmentation significantly through the perfect selection of a template, based on gray-level intensity of image; secondly, the updated membership is determined by the distances from cluster centroid to cluster data points using the fuzzy C-means (FCM) algorithm while it contacts its best result, and finally, the improved FCM clustering algorithm is used for detecting tumor position by updating membership function that is obtained based on the different features of tumor image including Contrast, Energy, Dissimilarity, Homogeneity, Entropy, and Correlation. Simulation results show that the proposed algorithm achieves better detection of abnormal and normal tissues in the human brain under small detachment of gray-level intensity. In addition, this algorithm detects human brain tumors within a very short time—in seconds compared to minutes with other algorithms.

f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks

Obtaining expert labels in clinical imaging is difficult since exhaustive annotation is time-consuming. Furthermore, not all possibly relevant markers may be known and sufficiently well described a priori to even guide annotation. While supervised learning yields good results if expert labeled training data is available, the visual variability, and thus the vocabulary of findings, we can detect and exploit, is limited to the annotated lesions. Here, we present fast AnoGAN (f-AnoGAN), a generative adversarial network (GAN) based unsupervised learning approach capable of identifying anomalous images and image segments, that can serve as imaging biomarker candidates. We build a generative model of healthy training data, and propose and evaluate a fast mapping technique of new data to the GAN's latent space. The mapping is based on a trained encoder, and anomalies are detected via a combined anomaly score based on the building blocks of the trained model - comprising a discriminator feature residual error and an image reconstruction error. In the experiments on optical coherence tomography data, we compare the proposed method with alternative approaches, and provide comprehensive empirical evidence that f-AnoGAN outperforms alternative approaches and yields high anomaly detection accuracy. In addition, a visual Turing test with two retina experts showed that the generated images are indistinguishable from real normal retinal OCT images. The f-AnoGAN code is available at https://github.com/tSchlegl/f-AnoGAN.

A Spatial Registration Toolbox for Structural MR Imaging of the Aging Brain

During aging the brain undergoes a series of structural changes, in size, shape as well as tissue composition. In particular, cortical atrophy and ventricular enlargement are often present in the brain of elderly individuals. This poses serious challenges in the spatial registration of structural MR images. In this study, we addressed this open issue by proposing an enhanced framework for MR registration and segmentation. Our solution was compared with other approaches based on the tools available in SPM12, a widely used software package. Performance of the different methods was assessed on 229 T1-weighted images collected in healthy individuals, with age ranging between 55 and 90 years old. Our method showed a consistent improvement as compared to other solutions, especially for subjects with enlarged lateral ventricles. It also provided a superior inter-subject alignment in cortical regions, with the most marked improvement in the frontal lobe. We conclude that our method is a valid alternative to standard approaches based on SPM12, and is particularly suitable for the processing of structural MR images of brains with cortical atrophy and ventricular enlargement. The method is integrated in our software toolbox MRTool, which is freely available to the scientific community.

An automatic restoration framework based on GPU-accelerated collateral filtering in brain MR images

BACKGROUND

Image restoration is one of the fundamental and essential tasks within image processing. In medical imaging, developing an effective algorithm that can automatically remove random noise in brain magnetic resonance (MR) images is challenging. The collateral filter has been shown a more powerful algorithm than many existing methods. However, the computation of the collateral filter is more time-consuming and the selection of the filter parameters is also laborious. This paper proposes an automatic noise removal system based on the accelerated collateral filter for brain MR images.

METHODS

To solve these problems, we first accelerated the collateral filter with parallel computing using the graphics processing unit (GPU) architecture. We adopted the compute unified device architecture (CUDA), an application programming interface for the GPU by NVIDIA, to hasten the computation. Subsequently, the optimal filter parameters were selected and the automation was achieved by artificial neural networks. Specifically, an artificial neural network system associated with image feature analysis was adopted to establish the automatic image restoration framework. The best feature combination was selected by the paired t-test and the sequential forward floating selection (SFFS) methods.

RESULTS

Experimental results indicated that not only did the proposed automatic image restoration algorithm perform dramatically faster than the traditional collateral filter, but it also effectively removed the noise in a wide variety of brain MR images. A speed up gain of 34 was attained to process an MR image, which completed within 0.1 s. Representative illustrations of brain tumor images demonstrated the capability of identifying lesion boundaries, which outperformed many existing methods.

CONCLUSIONS

We believe that our accelerated and automated restoration framework is promising for achieving robust filtering in many brain MR image restoration applications.

A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology

The human thalamus is a brain structure that comprises numerous, highly specific nuclei. Since these nuclei are known to have different functions and to be connected to different areas of the cerebral cortex, it is of great interest for the neuroimaging community to study their volume, shape and connectivity in vivo with MRI. In this study, we present a probabilistic atlas of the thalamic nuclei built using ex vivo brain MRI scans and histological data, as well as the application of the atlas to in vivo MRI segmentation. The atlas was built using manual delineation of 26 thalamic nuclei on the serial histology of 12 whole thalami from six autopsy samples, combined with manual segmentations of the whole thalamus and surrounding structures (caudate, putamen, hippocampus, etc.) made on in vivo brain MR data from 39 subjects. The 3D structure of the histological data and corresponding manual segmentations was recovered using the ex vivo MRI as reference frame, and stacks of blockface photographs acquired during the sectioning as intermediate target. The atlas, which was encoded as an adaptive tetrahedral mesh, shows a good agreement with previous histological studies of the thalamus in terms of volumes of representative nuclei. When applied to segmentation of in vivo scans using Bayesian inference, the atlas shows excellent test-retest reliability, robustness to changes in input MRI contrast, and ability to detect differential thalamic effects in subjects with Alzheimer's disease. The probabilistic atlas and companion segmentation tool are publicly available as part of the neuroimaging package FreeSurfer.

Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method.

White matter microstructural correlates of relapse in alcohol dependence

Identification of neural correlates of relapse to alcohol after treatment is clinically important as it may inform better substance abuse treatment. Few studies have specifically analyzed the white matter microstructure in treatment seekers as it might relate to relapse risk versus long-term abstinence. Using 4 Tesla diffusion tensor imaging, we compared two groups of one-month-abstinent treatment-seekers, who were classified based on their drinking status between six and nine months after treatment initiation. We hypothesized that subsequent relapsers had greater white matter microstructural deficits in specific brain regions than long-term abstainers. At one month of abstinence, 37 future relapsers versus 25 future abstainers had lower fractional anisotropy (a measure of axonal organization and membrane integrity) in the corpus callosum and right stria terminalis/fornix, higher diffusivity in the genu of the corpus callosum, left and right stria terminalis/fornix, and lower diffusivity in left anterior corona radiata. These differences existed despite similar lifetime and recent drinking and smoking histories in the groups. Longer smoking duration in relapsers was associated with lower fractional anisotropy in right stria terminalis/fornix. The study identified specific microstructural biomarkers of alcohol relapse risk in adults, contributing to the definition of a neurobiological relapse risk profile in alcohol use disorder.

fMRI data processing in MRTOOL: to what extent does anatomical registration affect the reliability of functional results?

Spatial registration is an essential step in the analysis of fMRI data because it enables between-subject analyses of brain activity, measured either during task performance or in the resting state. In this study, we investigated how anatomical registration with MRTOOL affects the reliability of task-related fMRI activity. We used as a benchmark the results from two other spatial registration methods implemented in SPM12: the Unified Segmentation algorithm and the DARTEL toolbox. Structural alignment accuracy and the impact on functional activation maps were assessed with high-resolution T1-weighted images and a set of task-related functional volumes acquired in 10 healthy volunteers. Our findings confirmed that anatomical registration is a crucial step in fMRI data processing, contributing significantly to the total inter-subject variance of the activation maps. MRTOOL and DARTEL provided greater registration accuracy than Unified Segmentation. Although DARTEL had superior gray matter and white matter tissue alignment than MRTOOL, there were no significant differences between DARTEL and MRTOOL in test-retest reliability. Likewise, we found only limited differences in BOLD activation morphology between MRTOOL and DARTEL. The test-retest reliability of task-related responses was comparable between MRTOOL and DARTEL, and both proved superior to Unified Segmentation. We conclude that MRTOOL, which is suitable for single-subject processing of structural and functional MR images, is a valid alternative to other SPM12-based approaches that are intended for group analysis. MRTOOL now includes a normalization module for fMRI data and is freely available to the scientific 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.

An efficient algorithm for estimating brain covariance networks

Often derived from partial correlations or many pairwise analyses, covariance networks represent the inter-relationships among regions and can reveal important topological structures in brain measures from healthy and pathological subjects. However both approaches are not consistent network estimators and are sensitive to the value of the tuning parameters. Here, we propose a consistent covariance network estimator by maximising the network likelihood (MNL) which is robust to the tuning parameter. We validate the consistency of our algorithm theoretically and via a simulation study, and contrast these results against two well-known approaches: the graphical LASSO (gLASSO) and Pearson pairwise correlations (PPC) over a range of tuning parameters. The MNL algorithm had a specificity equal to and greater than 0.94 for all sample sizes in the simulation study, and the sensitivity was shown to increase as the sample size increased. The gLASSO and PPC demonstrated a specificity-sensitivity trade-off over a range of values of tuning parameters highlighting the discrepancy in the results for misspecified values. Application of the MNL algorithm to the case study data showed a loss of connections between healthy and impaired groups, and improved ability to identify between lobe connectivity in contrast to gLASSO networks. In this work, we propose the MNL algorithm as an effective approach to find covariance brain networks, which can inform the organisational features in brain-wide analyses, particularly for large sample sizes.

Nonmonotonic recruitment of ventromedial prefrontal cortex during remote memory recall

Systems-level consolidation refers to the time-dependent reorganisation of memory traces in the neocortex, a process in which the ventromedial prefrontal cortex (vmPFC) has been implicated. Capturing the precise temporal evolution of this crucial process in humans has long proved elusive. Here, we used multivariate methods and a longitudinal functional magnetic resonance imaging (fMRI) design to detect, with high granularity, the extent to which autobiographical memories of different ages were represented in vmPFC and how this changed over time. We observed an unexpected time course of vmPFC recruitment during retrieval, rising and falling around an initial peak of 8-12 months, before reengaging for older 2- and 5-year-old memories. This pattern was replicated in 2 independent sets of memories. Moreover, it was further replicated in a follow-up study 8 months later with the same participants and memories, for which the individual memory representations had undergone their hypothesised strengthening or weakening over time. We conclude that the temporal engagement of vmPFC in memory retrieval seems to be nonmonotonic, revealing a complex relationship between systems-level consolidation and prefrontal cortex recruitment that is unaccounted for by current theories.

Accurate and Robust Non-rigid Point Set Registration using Student's-t Mixture Model with Prior Probability Modeling

A new accurate and robust non-rigid point set registration method, named DSMM, is proposed for non-rigid point set registration in the presence of significant amounts of missing correspondences and outliers. The key idea of this algorithm is to consider the relationship between the point sets as random variables and model the prior probabilities via Dirichlet distribution. We assign the various prior probabilities of each point to its correspondences in the Student's-t mixture model. We later incorporate the local spatial representation of the point sets by representing the posterior probabilities in a linear smoothing filter and get closed-form mixture proportions, leading to a computationally efficient registration algorithm comparing to other Student's-t mixture model based methods. Finally, by introducing the hidden random variables in the Bayesian framework, we propose a general mixture model family for generalizing the mixture-model-based point set registration, where the existing methods can be considered as members of the proposed family. We evaluate DSMM and other state-of-the-art finite mixture models based point set registration algorithms on both artificial point set and various 2D and 3D point sets, where DSMM demonstrates its statistical accuracy and robustness, outperforming the competing algorithms.

Multidimensional co-segmentation of longitudinal brain MRI ensembles in the presence of a neurodegenerative process

MRI Segmentation of a pathological brain poses a significant challenge, as the available anatomical priors that provide top-down information to aid segmentation are inadequate in the presence of abnormalities. This problem is further complicated for longitudinal data capturing impaired brain development or neurodegenerative conditions, since the dynamic of brain atrophies has to be considered as well. For these cases, the absence of compatible annotated training examples renders the commonly used multi-atlas or machine-learning approaches impractical. We present a novel segmentation approach that accounts for the lack of labeled data via multi-region multi-subject co-segmentation (MMCoSeg) of longitudinal MRI sequences. The underlying, unknown anatomy is learned throughout an iterative process, in which the segmentation of a region is supported both by the segmentation of the neighboring regions, which share common boundaries, and by the segmentation of corresponding regions, in the other jointly segmented images. A 4D multi-region atlas that models the spatio-temporal deformations and can be adapted to different subjects undergoing similar degeneration processes is reconstructed concurrently. An inducible mouse model of p25 accumulation (the CK-p25 mouse) that displays key pathological hallmarks of Alzheimer disease (AD) is used as a gold-standard to test the proposed algorithm by providing a conditional control of rapid neurodegeneration. Applying the MMCoSeg to a cohort of CK-p25 mice and littermate controls yields promising segmentation results that demonstrate high compatibility with expertise manual annotations. An extensive comparative analysis with respect to current well-established, atlas-based segmentation methods highlights the advantage of the proposed approach, which provides accurate segmentation of longitudinal brain MRIs in pathological conditions, where only very few annotated examples are available.

Myocardium Segmentation From DE MRI Using Multicomponent Gaussian Mixture Model and Coupled Level Set

Objective: In this paper, we propose a fully automatic framework for myocardium segmentation of delayed-enhancement (DE) MRI images without relying on prior patient-specific information. Methods: We employ a multicomponent Gaussian mixture model to deal with the intensity heterogeneity of myocardium caused by the infarcts. To differentiate the myocardium from other tissues with similar intensities, while at the same time maintain spatial continuity, we introduce a coupled level set (CLS) to regularize the posterior probability. The CLS, as a spatial regularization, can be adapted to the image characteristics dynamically. We also introduce an image intensity gradient based term into the CLS, adding an extra force to the posterior probability based framework, to improve the accuracy of myocardium boundary delineation. The prebuilt atlases are propagated to the target image to initialize the framework. Results: The proposed method was tested on datasets of 22 clinical cases, and achieved Dice similarity coefficients of 87.43 ± 5.62% (endocardium), 90.53 ± 3.20% (epicardium) and 73.58 ± 5.58% (myocardium), which have outperformed three variants of the classic segmentation methods. Conclusion: The results can provide a benchmark for the myocardial segmentation in the literature. Significance: DE MRI provides an important tool to assess the viability of myocardium. The accurate segmentation of myocardium, which is a prerequisite for further quantitative analysis of myocardial infarction (MI) region, can provide important support for the diagnosis and treatment management for MI patients.Objective: In this paper, we propose a fully automatic framework for myocardium segmentation of delayed-enhancement (DE) MRI images without relying on prior patient-specific information. Methods: We employ a multicomponent Gaussian mixture model to deal with the intensity heterogeneity of myocardium caused by the infarcts. To differentiate the myocardium from other tissues with similar intensities, while at the same time maintain spatial continuity, we introduce a coupled level set (CLS) to regularize the posterior probability. The CLS, as a spatial regularization, can be adapted to the image characteristics dynamically. We also introduce an image intensity gradient based term into the CLS, adding an extra force to the posterior probability based framework, to improve the accuracy of myocardium boundary delineation. The prebuilt atlases are propagated to the target image to initialize the framework. Results: The proposed method was tested on datasets of 22 clinical cases, and achieved Dice similarity coefficients of 87.43 ± 5.62% (endocardium), 90.53 ± 3.20% (epicardium) and 73.58 ± 5.58% (myocardium), which have outperformed three variants of the classic segmentation methods. Conclusion: The results can provide a benchmark for the myocardial segmentation in the literature. Significance: DE MRI provides an important tool to assess the viability of myocardium. The accurate segmentation of myocardium, which is a prerequisite for further quantitative analysis of myocardial infarction (MI) region, can provide important support for the diagnosis and treatment management for MI patients.

Multimodal Breast Parenchymal Patterns Correlation Using a Patient-Specific Biomechanical Model

In this paper, we aim to produce a realistic 2-D projection of the breast parenchymal distribution from a 3-D breast magnetic resonance image (MRI). To evaluate the accuracy of our simulation, we compare our results with the local breast density (i.e., density map) obtained from the complementary full-field digital mammogram. To achieve this goal, we have developed a fully automatic framework, which registers MRI volumes to X-ray mammograms using a subject-specific biomechanical model of the breast. The optimization step modifies the position, orientation, and elastic parameters of the breast model to perform the alignment between the images. When the model reaches an optimal solution, the MRI glandular tissue is projected and compared with the one obtained from the corresponding mammograms. To reduce the loss of information during the ray-casting, we introduce a new approach that avoids resampling the MRI volume. In the results, we focus our efforts on evaluating the agreement of the distributions of glandular tissue, the degree of structural similarity, and the correlation between the real and synthetic density maps. Our approach obtained a high-structural agreement regardless the glandularity of the breast, whilst the similarity of the glandular tissue distributions and correlation between both images increase in denser breasts. Furthermore, the synthetic images show continuity with respect to large structures in the density maps.

The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction

The Developing Human Connectome Project (dHCP) seeks to create the first 4-dimensional connectome of early life. Understanding this connectome in detail may provide insights into normal as well as abnormal patterns of brain development. Following established best practices adopted by the WU-MINN Human Connectome Project (HCP), and pioneered by FreeSurfer, the project utilises cortical surface-based processing pipelines. In this paper, we propose a fully automated processing pipeline for the structural Magnetic Resonance Imaging (MRI) of the developing neonatal brain. This proposed pipeline consists of a refined framework for cortical and sub-cortical volume segmentation, cortical surface extraction, and cortical surface inflation, which has been specifically designed to address considerable differences between adult and neonatal brains, as imaged using MRI. Using the proposed pipeline our results demonstrate that images collected from 465 subjects ranging from 28 to 45 weeks post-menstrual age (PMA) can be processed fully automatically; generating cortical surface models that are topologically correct, and correspond well with manual evaluations of tissue boundaries in 85% of cases. Results improve on state-of-the-art neonatal tissue segmentation models and significant errors were found in only 2% of cases, where these corresponded to subjects with high motion. Downstream, these surfaces will enhance comparisons of functional and diffusion MRI datasets, supporting the modelling of emerging patterns of brain connectivity.

Multi-atlas segmentation of the hydrocephalus brain using an adaptive ventricle atlas

Normal pressure hydrocephalus (NPH) is a brain disorder caused by disruption of the flow of cerebrospinal fluid (CSF). The dementia-like symptoms of NPH are often mistakenly attributed to Alzheimer's disease. However, if correctly diagnosed, NPH patients can potentially be treated and their symptoms reversed through surgery. Observing the dilated ventricles through magnetic resonance imaging (MRI) is one element in diagnosing NPH. Diagnostic accuracy therefore benefits from accurate, automatic parcellation of the ventricular system into its sub-compartments. We present an improvement to a whole brain segmentation approach designed for subjects with enlarged and deformed ventricles. Our method incorporates an adaptive ventricle atlas from an NPH-atlas-based segmentation as a prior and uses a more robust relaxation scheme for the multi-atlas label fusion approach that accurately labels the four sub-compartments of the ventricular system. We validated our method on NPH patients, demonstrating improvement over state-of-the-art segmentation techniques.

The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction

The Developing Human Connectome Project (dHCP) seeks to create the first 4-dimensional connectome of early life. Understanding this connectome in detail may provide insights into normal as well as abnormal patterns of brain development. Following established best practices adopted by the WU-MINN Human Connectome Project (HCP), and pioneered by FreeSurfer, the project utilises cortical surface-based processing pipelines. In this paper, we propose a fully automated processing pipeline for the structural Magnetic Resonance Imaging (MRI) of the developing neonatal brain. This proposed pipeline consists of a refined framework for cortical and sub-cortical volume segmentation, cortical surface extraction, and cortical surface inflation, which has been specifically designed to address considerable differences between adult and neonatal brains, as imaged using MRI. Using the proposed pipeline our results demonstrate that images collected from 465 subjects ranging from 28 to 45 weeks post-menstrual age (PMA) can be processed fully automatically; generating cortical surface models that are topologically correct, and correspond well with manual evaluations of tissue boundaries in 85% of cases. Results improve on state-of-the-art neonatal tissue segmentation models and significant errors were found in only 2% of cases, where these corresponded to subjects with high motion. Downstream, these surfaces will enhance comparisons of functional and diffusion MRI datasets, supporting the modelling of emerging patterns of brain connectivity.

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI

A wide range of segmentation approaches assumes that intensity histograms extracted from magnetic resonance images (MRI) have a distribution for each brain tissue that can be modeled by a Gaussian distribution or a mixture of them. Nevertheless, intensity histograms of White Matter and Gray Matter are not symmetric and they exhibit heavy tails. In this work, we present a hidden Markov random field model with expectation maximization (EM-HMRF) modeling the components using the α-stable distribution. The proposed model is a generalization of the widely used EM-HMRF algorithm with Gaussian distributions. We test the α-stable EM-HMRF model in synthetic data and brain MRI data. The proposed methodology presents two main advantages: Firstly, it is more robust to outliers. Secondly, we obtain similar results than using Gaussian when the Gaussian assumption holds. This approach is able to model the spatial dependence between neighboring voxels in tomographic brain MRI.

Comparison of image intensity, local, and multi-atlas priors in brain tissue classification

PURPOSE

Automated and accurate tissue classification in three-dimensional brain magnetic resonance images is essential in volumetric morphometry or as a preprocessing step for diagnosing brain diseases. However, noise, intensity in homogeneity, and partial volume effects limit the classification accuracy of existing methods. This paper provides a comparative study on the contributions of three commonly used image information priors for tissue classification in normal brains: image intensity, local, and multi-atlas priors.

METHODS

We compared the effectiveness of the three priors by comparing the four methods modeling them: K-Means (KM), KM combined with a Markov Random Field (KM-MRF), multi-atlas segmentation (MAS), and the combination of KM, MRF, and MAS (KM-MRF-MAS). The key parameters and factors in each of the four methods are analyzed, and the performance of all the models is compared quantitatively and qualitatively on both simulated and real data.

RESULTS

The KM-MRF-MAS model that combines the three image information priors performs best.

CONCLUSIONS

The image intensity prior is insufficient to generate reasonable results for a few images. Introducing local and multi-atlas priors results in improved brain tissue classification. This study provides a general guide on what image information priors can be used for effective brain tissue classification.

A panel of clinical and neuropathological features of cerebrovascular disease through the novel neuroimaging methods

The last decade has witnessed substantial progress in acquiring diagnostic biomarkers for the diagnostic workup of cerebrovascular disease (CVD). Advanced neuroimaging methods not only provide a strategic contribution for the differential diagnosis of vascular dementia (VaD) and vascular cognitive impairment (VCI), but also help elucidate the pathophysiological mechanisms ultimately leading to small vessel disease (SVD) throughout its course.

OBJECTIVE

In this review, the novel imaging methods, both structural and metabolic, were summarized and their impact on the diagnostic workup of age-related CVD was analysed. Methods: An electronic search between January 2010 and 2017 was carried out on PubMed/MEDLINE, Institute for Scientific Information Web of Knowledge and EMBASE.

RESULTS

The use of full functional multimodality in simultaneous Magnetic Resonance (MR)/Positron emission tomography (PET) may potentially improve the clinical characterization of VCI-VaD; for structural imaging, MRI at 3.0 T enables higher-resolution scanning with greater imaging matrices, thinner slices and more detail on the anatomical structure of vascular lesions.

CONCLUSION

Although the importance of most of these techniques in the clinical setting has yet to be recognized, there is great expectancy in achieving earlier and more refined therapeutic interventions for the effective management of VCI-VaD.

Primatologist: A modular segmentation pipeline for macaque brain morphometry

Because they bridge the genetic gap between rodents and humans, non-human primates (NHPs) play a major role in therapy development and evaluation for neurological disorders. However, translational research success from NHPs to patients requires an accurate phenotyping of the models. In patients, magnetic resonance imaging (MRI) combined with automated segmentation methods has offered the unique opportunity to assess in vivo brain morphological changes. Meanwhile, specific challenges caused by brain size and high field contrasts make existing algorithms hard to use routinely in NHPs. To tackle this issue, we propose a complete pipeline, Primatologist, for multi-region segmentation. Tissue segmentation is based on a modular statistical model that includes random field regularization, bias correction and denoising and is optimized by expectation-maximization. To deal with the broad variety of structures with different relaxing times at 7 T, images are segmented into 17 anatomical classes, including subcortical regions. Pre-processing steps insure a good initialization of the parameters and thus the robustness of the pipeline. It is validated on 10 T2-weighted MRIs of healthy macaque brains. Classification scores are compared with those of a non-linear atlas registration, and the impact of each module on classification scores is thoroughly evaluated.

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.

Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?

PURPOSE

To compare two methods of automatic breast segmentation with each other and with manual segmentation in a large subject cohort. To discuss the factors involved in selecting the most appropriate algorithm for automatic segmentation and, in particular, to investigate the appropriateness of overlap measures (e.g., Dice and Jaccard coefficients) as the primary determinant in algorithm selection.

METHODS

Two methods of breast segmentation were applied to the task of calculating MRI breast density in 200 subjects drawn from the Avon Longitudinal Study of Parents and Children, a large cohort study with an MRI component. A semiautomated, bias-corrected, fuzzy C-means (BC-FCM) method was combined with morphological operations to segment the overall breast volume from in-phase Dixon images. The method makes use of novel, problem-specific insights. The resulting segmentation mask was then applied to the corresponding Dixon water and fat images, which were combined to give Dixon MRI density values. Contemporaneously acquired T1 - and T2 -weighted image datasets were analyzed using a novel and fully automated algorithm involving image filtering, landmark identification, and explicit location of the pectoral muscle boundary. Within the region found, fat-water discrimination was performed using an Expectation Maximization-Markov Random Field technique, yielding a second independent estimate of MRI density.

RESULTS

Images are presented for two individual women, demonstrating how the difficulty of the problem is highly subject-specific. Dice and Jaccard coefficients comparing the semiautomated BC-FCM method, operating on Dixon source data, with expert manual segmentation are presented. The corresponding results for the method based on T1 - and T2 -weighted data are slightly lower in the individual cases shown, but scatter plots and interclass correlations for the cohort as a whole show that both methods do an excellent job in segmenting and classifying breast tissue.

CONCLUSIONS

Epidemiological results demonstrate that both methods of automated segmentation are suitable for the chosen application and that it is important to consider a range of factors when choosing a segmentation algorithm, rather than focus narrowly on a single metric such as the Dice coefficient.

Regional brain volume changes in alcohol-dependent individuals during early abstinence: associations with relapse following treatment

Cross-sectional structural magnetic resonance (MR) imaging studies of individuals with an alcohol use disorder (AUD) report that those who relapse after treatment, relative to individuals who maintain a period of extended abstinence, show greater morphological abnormalities in multiple brain regions near the inception of treatment, particularly in the frontal lobe. However, given the cross-sectional design of previous studies, it is unclear if the baseline morphological differences between future abstainers and relapsers were maintained over the course of early recovery. The primary goal of this study was to determine if frontal lobe tissue volume recovery during early abstinence is associated with long-term abstinence from alcohol. We compared frontal, parietal, temporal and occipital grey matter (GM) and white matter (WM) volumes, at 1 and 4 weeks of abstinence, among individuals who resumed alcohol consumption within 12 months of treatment (Relapsers) and those who showed sustained abstinence over 12 months following treatment (Abstainers). At 1 and 4 weeks of sobriety, both Abstainers and Relapsers demonstrated significantly smaller GM volumes than Controls in the majority of ROIs, but Relapsers exhibited significantly smaller bilateral frontal GM volumes than Abstainers. No significant group differences were observed for any WM region of interest. The persistent bilateral frontal GM volume deficits in Relapsers over 4 weeks from last alcohol use may represent an endophenotype that differentiates those who respond more favorably to the typical psychosocial and pharmacological interventions provided for AUD.