Search

Perivascular spaces (PVS) are compartments surrounding cerebral blood vessels that become visible on MRI when enlarged. Enlarged PVS (EPVS) are commonly seen in patients with cerebral small vessel disease (CSVD) and have been suggested to reflect dysfunctional perivascular clearance of soluble waste products from the brain. In this study, we investigated histopathological correlates of EPVS and how they relate to vascular amyloid-beta (A beta) in cerebral amyloid angiopathy (CAA), a form of CSVD that commonly co-exists with Alzheimer's disease (AD) pathology. We used ex vivo MRI, semi-automatic segmentation and validated deep-learning-based models to quantify EPVS and associated histopathological abnormalities. Severity of MRI-visible PVS during life was significantly associated with severity of MRI-visible PVS on ex vivo MRI in formalin fixed intact hemispheres and corresponded with PVS enlargement on histopathology in the same areas. EPVS were located mainly around the white matter portion of perforating cortical arterioles and their burden was associated with CAA severity in the overlying cortex. Furthermore, we observed markedly reduced smooth muscle cells and increased vascular A beta accumulation, extending into the WM, in individually affected vessels with an EPVS. Overall, these findings are consistent with the notion that EPVS reflect impaired outward flow along arterioles and have implications for our understanding of perivascular clearance mechanisms, which play an important role in the pathophysiology of CAA and AD.

The purpose of our study is to quantify the extent to which Virchow-Robin spaces (VRS) detected on in vivo MRI are reproducible by post-mortem MRI.Double Echo Steady State 3T MRIs were acquired post-mortem in 49 double- and 32 single-hemispheric formalin-fixed brain sections from 12 patients, who underwent conventional diagnostic 1.5 or 3T MRI in median 22 days prior to death (25% to 75%: 12 to 134 days). The overlap of in vivo and post-mortem VRS segmentations was determined accounting for potential confounding factors.The reproducibility of VRS found on in vivo MRI by post-mortem MRI, in the supratentorial white matter was in median 80% (25% to 75%: 60 to 100). A lower reproducibility was present in the basal ganglia, with a median of 47% (25% to 75%: 30 to 50).VRS segmentations were histologically confirmed in one double hemispheric section.Overall, the majority of VRS found on in vivo MRI was stable throughout death and formalin fixation, emphasizing the translational potential of post-mortem VRS studies.

This report presents an overview of how machine learning is rapidly advancing clinical translational imaging in ways that will aid in the early detection, prediction, and treatment of diseases that threaten brain health. Towards this goal, we aresharing the information presented at a symposium, “Neuroimaging Indicators of Brain Structure and Function - Closing the Gap Between Research and Clinical Application”, co-hosted by the McCance Center for Brain Health at Mass General Hospital and the MIT HST Neuroimaging Training Program on February 12, 2021. The symposium focused on the potential for machine learning approaches, applied to increasingly large-scale neuroimaging datasets, to transform healthcare delivery and change the trajectory of brain health by addressing brain care earlier in the lifespan. While not exhaustive, this overview uniquely addresses many of the technical challenges from image formation, to analysis and visualization, to synthesis and incorporation into the clinical workflow. Some of the ethical challenges inherent to this work are also explored, as are some of the regulatory requirements for implementation. We seek to educate, motivate, and inspire graduate students, postdoctoral fellows, and early career investigators to contribute to a future where neuroimaging meaningfully contributes to the maintenance of brain health.

Thalamic atrophy is a common feature across all forms of FTD but little is known about specific nuclei involvement. We aimed to investigate in vivo atrophy of the thalamic nuclei across the FTD spectrum. A cohort of 402 FTD patients (age: mean(SD) 64.3(8.2) years; disease duration: 4.8(2.8) years) was compared with 104 age‐matched controls (age: 62.5(10.4) years), using an automated segmentation of T1‐weighted MRIs to extract volumes of 14 thalamic nuclei. Stratification was performed by clinical diagnosis (180 behavioural variant FTD (bvFTD), 85 semantic variant primary progressive aphasia (svPPA), 114 nonfluent variant PPA (nfvPPA), 15 PPA not otherwise specified (PPA‐NOS), and 8 with associated motor neurone disease (FTD‐MND), genetic diagnosis (27 MAPT, 28 C9orf72, 18 GRN), and pathological confirmation (37 tauopathy, 38 TDP‐43opathy, 4 FUSopathy). The mediodorsal nucleus (MD) was the only nucleus affected in all FTD subgroups (16–33% smaller than controls). The laterodorsal nucleus was also particularly affected in genetic cases (28–38%), TDP‐43 type A (47%), tau‐CBD (44%), and FTD‐MND (53%). The pulvinar was affected only in the C9orf72 group (16%). Both the lateral and medial geniculate nuclei were also affected in the genetic cases (10–20%), particularly the LGN in C9orf72 expansion carriers. Use of individual thalamic nuclei volumes provided higher accuracy in discriminating between FTD groups than the whole thalamic volume. The MD is the only structure affected across all FTD groups. Differential involvement of the thalamic nuclei among FTD forms is seen, with a unique pattern of atrophy in the pulvinar in C9orf72 expansion carriers.

A tool was developed to automatically segment several subcortical limbic structures (nucleus accumbens, basal forebrain, septal nuclei, hypothalamus without mammillary bodies, the mammillary bodies, and fornix) using only a T1-weighted MRI as input. This tool fills an unmet need as there are few, if any, publicly available tools to segment these clinically relevant structures. A U-Net with spatial, intensity, contrast, and noise augmentation was trained using 39 manually labeled MRI data sets. In general, the Dice scores, true positive rates, false discovery rates, and manual-automatic volume correlation were very good relative to comparable tools for other structures. A diverse data set of 698 subjects were segmented using the tool; evaluation of the resulting labelings showed that the tool failed in less than 1% of cases. Test-retest reliability of the tool was excellent. The automatically segmented volume of all structures except mammillary bodies showed effectiveness at detecting either clinical AD effects, age effects, or both. This tool will be publicly released with FreeSurfer (surfer.nmr.mgh.harvard.edu/fswiki/ScLimbic). Together with the other cortical and subcortical limbic segmentations, this tool will allow FreeSurfer to provide a comprehensive view of the limbic system in an automated way., Graphical Abstract

Joint registration of a stack of 2D histological sections to recover 3D structure (``3D histology reconstruction'') finds application in areas such as atlas building and validation of \emph{in vivo} imaging. Straightforward pairwise registration of neighbouring sections yields smooth reconstructions but has well-known problems such as ``banana effect'' (straightening of curved structures) and ``z-shift'' (drift). While these problems can be alleviated with an external, linearly aligned reference (e.g., Magnetic Resonance (MR) images), registration is often inaccurate due to contrast differences and the strong nonlinear distortion of the tissue, including artefacts such as folds and tears. In this paper, we present a probabilistic model of spatial deformation that yields reconstructions for multiple histological stains that that are jointly smooth, robust to outliers, and follow the reference shape. The model relies on a spanning tree of latent transforms connecting all the sections and slices of the reference volume, and assumes that the registration between any pair of images can be see as a noisy version of the composition of (possibly inverted) latent transforms connecting the two images. Bayesian inference is used to compute the most likely latent transforms given a set of pairwise registrations between image pairs within and across modalities. The framework is used for accurate 3D reconstruction of two stains (Nissl and parvalbumin) from the Allen human brain atlas, showing its benefits on real data with severe distortions. Moreover, we also provide the registration of the reconstructed volume to MNI space, bridging the gaps between two of the most widely used atlases in histology and MRI. The 3D reconstructed volumes and atlas registration can be downloaded from https://openneuro.org/datasets/ds003590. The code is freely available at https://github.com/acasamitjana/3dhirest., Comment: Medical Image Analysis (Accepted on 07/10/2021). 22 pages, 11 figures

Manual segmentation of stacks of 2D biomedical images (e.g., histology) is a time-consuming task which can be sped up with semi-automated techniques. In this article, we present a suggestive deep active learning framework that seeks to minimise the annotation effort required to achieve a certain level of accuracy when labelling such a stack. The framework suggests, at every iteration, a specific region of interest (ROI) in one of the images for manual delineation. Using a deep segmentation neural network and a mixed cross-entropy loss function, we propose a principled strategy to estimate class probabilities for the whole stack, conditioned on heterogeneous partial segmentations of the 2D images, as well as on weak supervision in the form of image indices that bound each ROI. Using the estimated probabilities, we propose a novel active learning criterion based on predictions for the estimated segmentation performance and delineation effort, measured with average Dice scores and total delineated boundary length, respectively, rather than common surrogates such as entropy. The query strategy suggests the ROI that is expected to maximise the ratio between performance and effort, while considering the adjacency of structures that may have already been labelled - which decrease the length of the boundary to trace. We provide quantitative results on synthetically deformed MRI scans and real histological data, showing that our framework can reduce labelling effort by up to 60-70% without compromising accuracy.

Highlights • A publicly available deep learning tool to segment the hypothalamus and its subunits. • Our tool outperforms inter-rater accuracy and approaches intra-rater precision level. • It can robustly generalise to unseen heterogeneous datasets. • It yields a rejection rate of less than 1% in a QC analysis performed on 675 scans. • It detects subtle subunit-specific hypothalamic atrophy in Alzheimer’s Disease., Despite the crucial role of the hypothalamus in the regulation of the human body, neuroimaging studies of this structure and its nuclei are scarce. Such scarcity partially stems from the lack of automated segmentation tools, since manual delineation suffers from scalability and reproducibility issues. Due to the small size of the hypothalamus and the lack of image contrast in its vicinity, automated segmentation is difficult and has been long neglected by widespread neuroimaging packages like FreeSurfer or FSL. Nonetheless, recent advances in deep machine learning are enabling us to tackle difficult segmentation problems with high accuracy. In this paper we present a fully automated tool based on a deep convolutional neural network, for the segmentation of the whole hypothalamus and its subregions from T1-weighted MRI scans. We use aggressive data augmentation in order to make the model robust to T1-weighted MR scans from a wide array of different sources, without any need for preprocessing. We rigorously assess the performance of the presented tool through extensive analyses, including: inter- and intra-rater variability experiments between human observers; comparison of our tool with manual segmentation; comparison with an automated method based on multi-atlas segmentation; assessment of robustness by quality control analysis of a larger, heterogeneous dataset (ADNI); and indirect evaluation with a volumetric study performed on ADNI. The presented model outperforms multi-atlas segmentation scores as well as inter-rater accuracy level, and approaches intra-rater precision. Our method does not require any preprocessing and runs in less than a second on a GPU, and approximately 10 seconds on a CPU. The source code as well as the trained model are publicly available at https://github.com/BBillot/hypothalamus_seg, and will also be distributed with FreeSurfer.

Structural hippocampal abnormalities are common in many neurological and psychiatric disorders, and variation in hippocampal measures is related to cognitive performance and other complex phenotypes such as stress sensitivity. Hippocampal subregions are increasingly studied, as automated algorithms have become available for mapping and volume quantification. In the context of the Enhancing Neuro Imaging Genetics through Meta Analysis Consortium, several Disease Working Groups are using the FreeSurfer software to analyze hippocampal subregion (subfield) volumes in patients with neurological and psychiatric conditions along with data from matched controls. In this overview, we explain the algorithm's principles, summarize measurement reliability studies, and demonstrate two additional aspects (subfield autocorrelation and volume/reliability correlation) with illustrative data. We then explain the rationale for a standardized hippocampal subfield segmentation quality control (QC) procedure for improved pipeline harmonization. To guide researchers to make optimal use of the algorithm, we discuss how global size and age effects can be modeled, how QC steps can be incorporated and how subfields may be aggregated into composite volumes. This discussion is based on a synopsis of 162 published neuroimaging studies (01/2013–12/2019) that applied the FreeSurfer hippocampal subfield segmentation in a broad range of domains including cognition and healthy aging, brain development and neurodegeneration, affective disorders, psychosis, stress regulation, neurotoxicity, epilepsy, inflammatory disease, childhood adversity and posttraumatic stress disorder, and candidate and whole genome (epi‐)genetics. Finally, we highlight points where FreeSurfer‐based hippocampal subfield studies may be optimized., Hippocampal subfield analysis is increasingly performed with the availability of automated magnetic resonance imaging segmentation methods. We give a synopsis of the FreeSurfer hippocampal subfield segmentation algorithm, measurement reliability studies and application domains. We discuss how global size and age effects can be modeled and suggest a standardized hippocampal subfield segmentation quality control procedure for improved pipeline harmonization.

Accurate and reliable whole-brain segmentation is critical to longitudinal neuroimaging studies. We undertake a comparative analysis of two subcortical segmentation methods, Automatic Segmentation (ASEG) and Sequence Adaptive Multimodal Segmentation (SAMSEG), recently provided in the open-source neuroimaging package FreeSurfer 7.1, with regard to reliability, bias, sensitivity to detect longitudinal change, and diagnostic sensitivity to Alzheimer’s disease. First, we assess intra- and inter-scanner reliability for eight bilateral subcortical structures: amygdala, caudate, hippocampus, lateral ventricles, nucleus accumbens, pallidum, putamen and thalamus. For intra-scanner analysis we use a large sample of participants (n = 1629) distributed across the lifespan (age range = 4–93 years) and acquired on a 1.5T Siemens Avanto (n = 774) and a 3T Siemens Skyra (n = 855) scanners. For inter-scanner analysis we use a sample of 24 participants scanned on the day with three models of Siemens scanners: 1.5T Avanto, 3T Skyra and 3T Prisma. Second, we test how each method detects volumetric age change using longitudinal follow up scans (n = 491 for Avanto and n = 245 for Skyra; interscan interval = 1–10 years). Finally, we test sensitivity to clinically relevant change. We compare annual rate of hippocampal atrophy in cognitively normal older adults (n = 20), patients with mild cognitive impairment (n = 20) and Alzheimer’s disease (n = 20). We find that both ASEG and SAMSEG are reliable and lead to the detection of within-person longitudinal change, although with notable differences between age-trajectories for most structures, including hippocampus and amygdala. In summary, SAMSEG yields significantly lower differences between repeated measures for intra- and inter-scanner analysis without compromising sensitivity to changes and demonstrating ability to detect clinically relevant longitudinal changes.

The development of automated tools for brain morphometric analysis in infants has lagged significantly behind analogous tools for adults. This gap reflects the greater challenges in this domain due to: 1) a smaller-scaled region of interest, 2) increased motion corruption, 3) regional changes in geometry due to heterochronous growth, and 4) regional variations in contrast properties corresponding to ongoing myelination and other maturation processes. Nevertheless, there is a great need for automated image-processing tools to quantify differences between infant groups and other individuals, because aberrant cortical morphologic measurements (including volume, thickness, surface area, and curvature) have been associated with neuropsychiatric, neurologic, and developmental disorders in children. In this paper we present an automated segmentation and surface extraction pipeline designed to accommodate clinical MRI studies of infant brains in a population 0-2 year-olds. The algorithm relies on a single channel of T1-weighted MR images to achieve automated segmentation of cortical and subcortical brain areas, producing volumes of subcortical structures and surface models of the cerebral cortex. We evaluated the algorithm both qualitatively and quantitatively using manually labeled datasets, relevant comparator software solutions cited in the literature, and expert evaluations. The computational tools and atlases described in this paper will be distributed to the research community as part of the FreeSurfer image analysis package., Comment: 49 pages, 25 figures, submitted to NeuroImage

The human hippocampus is vulnerable to a range of degenerative conditions and as such, accurate in vivo measurement of the hippocampus and hippocampal substructures via neuroimaging is of great interest for understanding mechanisms of disease as well as for use as a biomarker in clinical trials of novel therapeutics. Although total hippocampal volume can be measured relatively reliably, it is critical to understand how this reliability is affected by acquisition on different scanners, as multiple scanning platforms would likely be utilized in large-scale clinical trials. This is particularly true for hippocampal subregional measurements, which have only relatively recently been measurable through common image processing platforms such as FreeSurfer. Accurate segmentation of these subregions is challenging due to their small size, magnetic resonance imaging (MRI) signal loss in medial temporal regions of the brain, and lack of contrast for delineation from standard neuroimaging procedures.Here, we assess the test-retest reliability of the FreeSurfer automated hippocampal subfield segmentation procedure using two Siemens model scanners (a Siemens Trio and Prismafit Trio upgrade). T1-weighted images were acquired for 11 generally healthy younger participants (two scans on the Trio and one scan on the Prismafit). Each scan was processed through the standard cross-sectional stream and the recently released longitudinal pipeline in FreeSurfer v6.0 for hippocampal segmentation. Test-retest reliability of the volumetric measures was examined for individual subfields as well as percent volume difference and Dice overlap among scans and intra-class correlation coefficients (ICC). Reliability was high in the molecular layer, dentate gyrus, and whole hippocampus with the inclusion of three time points with mean volume differences among scans less than 3%, overlap greater than 80%, and ICC >0.95. The parasubiculum and hippocampal fissure showed the least improvement in reliability with mean volume difference greater than 5%, overlap less than 70%, and ICC scores ranging from 0.78 to 0.89. Other subregions, including the CA regions, were stable in their mean volume difference and overlap (75% respectively) and showed improvement in reliability with the inclusion of three scans (ICC ​> ​0.9). Reliability was generally higher within scanner (Trio-Trio), however, Trio-Prismafit reliability was also high and did not exhibit an obvious bias. These results suggest that the FreeSurfer automated segmentation procedure is a reliable method to measure total as well as hippocampal subregional volumes and may be useful in clinical applications including as an endpoint for future clinical trials of conditions affecting the hippocampus.

Appendix A. Supplementary data: The following are the Supplementary data to this article: Supplementary data 1. Available at: https://ars.els-cdn.com/content/image/1-s2.0-S2213158222001498-mmc1.docx (Word document (15MB)). Copyright © 2022 The Author(s). Background: Frontotemporal dementia (FTD) is a spectrum of diseases characterised by language, behavioural and motor symptoms. Among the different subcortical regions implicated in the FTD symptomatology, the hypothalamus regulates various bodily functions, including eating behaviours which are commonly present across the FTD spectrum. The pattern of specific hypothalamic involvement across the clinical, pathological, and genetic forms of FTD has yet to be fully investigated, and its possible associations with abnormal eating behaviours have yet to be fully explored. Methods: Using an automated segmentation tool for volumetric T1-weighted MR images, we measured hypothalamic regional volumes in a cohort of 439 patients with FTD (197 behavioural variant FTD [bvFTD]; 7 FTD with associated motor neurone disease [FTD-MND]; 99 semantic variant primary progressive aphasia [svPPA]; 117 non-fluent variant PPA [nfvPPA]; 19 PPA not otherwise specified [PPA-NOS]) and 118 age-matched controls. We compared volumes across the clinical, genetic (29 MAPT, 32 C9orf72, 23 GRN), and pathological diagnoses (61 tauopathy, 40 TDP-43opathy, 4 FUSopathy). We correlated the volumes with presence of abnormal eating behaviours assessed with the revised version of the Cambridge Behavioural Inventory (CBI-R). Results: On average, FTD patients showed 14% smaller hypothalamic volumes than controls. The groups with the smallest hypothalamic regions were FTD-MND (20%), MAPT (25%) and FUS (33%), with differences mainly localised in the anterior and posterior regions. The inferior tuberal region was only significantly smaller in tauopathies (MAPT and Pick’s disease) and in TDP-43 type C compared to controls and was the only regions that did not correlate with eating symptoms. PPA-NOS and nfvPPA were the groups with the least frequent eating behaviours and the least hypothalamic involvement. Conclusions: Abnormal hypothalamic volumes are present in all the FTD forms, but different hypothalamic regions might play a different role in the development of abnormal eating behavioural and metabolic symptoms. These findings might therefore help in the identification of different underlying pathological mechanisms, suggesting the potential use of hypothalamic imaging biomarkers and the research of potential therapeutic targets within the hypothalamic neuropeptides. The Dementia Research Centre is supported by Alzheimer's Research UK, Alzheimer's Society, Brain Research UK, and The Wolfson Foundation. This work was supported by the NIHR UCL/H Biomedical Research Centre, the Leonard Wolfson Experimental Neurology Centre (LWENC) Clinical Research Facility, and the UK Dementia Research Institute, which receives its funding from UK DRI Ltd, funded by the UK Medical Research Council, Alzheimer's Society and Alzheimer's Research UK. JDR is supported by the Miriam Marks Brain Research UK Senior Fellowship and has received funding from an MRC Clinician Scientist Fellowship (MR/M008525/1) and the NIHR Rare Disease Translational Research Collaboration (BRC149/NS/MH). This work was also supported by the MRC UK GENFI grant (MR/M023664/1), the Bluefield Project and the JPND GENFI-PROX grant (2019-02248). MB is supported by a Fellowship award from the Alzheimer’s Society, UK (AS-JF-19a-004-517). MB’s work was also supported by the UK Dementia Research Institute which receives its funding from DRI Ltd, funded by the UK Medical Research Council, Alzheimer’s Society and Alzheimer’s Research UK. MB acknowledges the support of NVIDIA Corporation with the donation of the Titan V GPU used for part of the analyses in this research. JEI is supported by the European Research Council (Starting Grant 677697, project BUNGEE-TOOLS), Alzheimer’s Research UK (ARUK-IRG2019A003) and the NIH (1RF1MH123195-01 and 1R01AG070988). JDW receives grant support from the Alzheimer's Society, Alzheimer's Research UK, the NIHR UCL/UCLH Biomedical Research Centre and a Frontotemporal Dementia Research Studentship in Memory of David Blechner (funded through The National Brain Appeal).

Objective Subfield-specific measurements provide superior information in the early stages of neurodegenerative diseases compared to global hippocampal measurements. The overall goal was to systematically compare the performance of five representative manual and automated T1 and T2 based subfield labeling techniques in a sub-set of the ADNI2 population. Methods The high resolution T2 weighted hippocampal images (T2-HighRes) and the corresponding T1 images from 106 ADNI2 subjects (41 controls, 57 MCI, 8 AD) were processed as follows. A. T1-based: 1. Freesurfer + Large-Diffeomorphic-Metric-Mapping in combination with shape analysis. 2. FreeSurfer 5.1 subfields using in-vivo atlas. B. T2-HighRes: 1. Model-based subfield segmentation using ex-vivo atlas (FreeSurfer 6.0). 2. T2-based automated multi-atlas segmentation combined with similarity-weighted voting (ASHS). 3. Manual subfield parcellation. Multiple regression analyses were used to calculate effect sizes (ES) for group, amyloid positivity in controls, and associations with cognitive/memory performance for each approach. Results Subfield volumetry was better than whole hippocampal volumetry for the detection of the mild atrophy differences between controls and MCI (ES: 0.27 vs 0.11). T2-HighRes approaches outperformed T1 approaches for the detection of early stage atrophy (ES: 0.27 vs.0.10), amyloid positivity (ES: 0.11 vs 0.04), and cognitive associations (ES: 0.22 vs 0.19). Conclusions T2-HighRes subfield approaches outperformed whole hippocampus and T1 subfield approaches. None of the different T2-HghRes methods tested had a clear advantage over the other methods. Each has strengths and weaknesses that need to be taken into account when deciding which one to use to get the best results from subfield volumetry., Highlights • Comparison of 4 automated and 1 manual subfield labeling technique in common data set. • Subfield labeling approaches perform better than whole hippocampal approaches. • High resolution T2 based approaches perform better than T1 based approaches. • Different high res T2 approaches have different strengths/weaknesses.

The surface of the human cerebellar cortex is much more tightly folded than the cerebral cortex. Volumetric analysis of cerebellar morphometry in magnetic resonance imaging studies suffers from insufficient resolution, and therefore has had limited impact on disease assessment. Automatic serial polarization-sensitive optical coherence tomography (as-PSOCT) is an emerging technique that offers the advantages of microscopic resolution and volumetric reconstruction of large-scale samples. In this study, we reconstructed multiple cubic centimeters of ex vivo human cerebellum tissue using as-PSOCT. The morphometric and optical properties of the cerebellar cortex across five subjects were quantified. While the molecular and granular layers exhibited similar mean thickness in the five subjects, the thickness varied greatly in the granular layer within subjects. Layer-specific optical property remained homogenous within individual subjects but showed higher cross-subject variability than layer thickness. High-resolution volumetric morphometry and optical property maps of human cerebellar cortex revealed by as-PSOCT have great potential to advance our understanding of cerebellar function and diseases.

Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols – even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR .

Available online 7 September 2016 Quantitative analysis of magnetic resonance imaging (MRI) scans of the brain requires accurate automated segmentation of anatomical structures. A desirable feature for such segmentation methods is to be robust against changes in acquisition platform and imaging protocol. In this paper we validate the performance of a segmentation algorithm designed to meet these requirements, building upon generative parametric models previously used in tissue classification. The method is tested on four different datasets acquired with different scanners, field strengths and pulse sequences, demonstrating comparable accuracy to state-of-the-art methods on T1-weighted scans while being one to two orders of magnitude faster. The proposed algorithm is also shown to be robust against small training datasets, and readily handles images with different MRI contrast as well as multi-contrast data. This research was supported by the NIH NCRR (P41-RR14075, 1S10RR023043), NIBIB (R01EB013565), the Lundbeck foundation (R141-2013-13117) and financial contributions from the Technical University of Denmark. JEI acknowledges financial support from the Gipuzkoako Foru Aldundia (Fellows Gipuzkoa Program), the European Union's Horizon 2020 Research and innovation program under the Marie Sklodowska-Curie grant agreement No 654911, as well as from the Spanish Ministry of Economy and Competetiveness (MINECO, TEC2014-51882-P).

Online publication 15/07/2016 The hippocampal formation is a complex, heterogeneous structure that consists of a number of distinct, interacting subregions. Atrophy of these subregions is implied in a variety of neurodegenerative diseases, most prominently in Alzheimer’s disease (AD). Thanks to the increasing resolution ofMRimages and computational atlases, automatic segmentation of hippocampal subregions is becoming feasible in MRI scans. Here we introduce a generative model for dedicated longitudinal segmentation that relies on subject-specific atlases. The segmentations of the scans at the different time points are jointly computed using Bayesian inference. All time points are treated the same to avoid processing bias. We evaluate this approach using over 4700 scans from two publicly available datasets (ADNI and MIRIAD). In test–retest reliability experiments, the proposed method yielded significantly lower volume differences and significantly higher Dice overlaps than the cross-sectional approach for nearly every subregion (average across subregions: 4.5% vs. 6.5%, Dice overlap: 81.8% vs. 75.4%). The longitudinal algorithm also demonstrated increased sensitivity to group differences: in MIRIAD (69 subjects: 46 with AD and 23 controls), it found differences in atrophy rates between AD and controls that the cross sectional method could not detect in a number of subregions: right parasubiculum, left and right presubiculum, right subiculum, left dentate gyrus, left CA4, left HATA and right tail. In ADNI (836 subjects: 369 with AD, 215 with early cognitive impairment — eMCI — and 252 controls), all methods found significant differences between AD and controls, but the proposed longitudinal algorithm detected differences between controls and eMCI and differences between eMCI and AD that the cross sectional method could not find: left presubiculum, right subiculum, left and right parasubiculum, left and right HATA. Moreover, many of the differences that the cross-sectional method already found were detected with higher significance. The presented algorithm will be made available as part of the open-source neuroimaging package FreeSurfer. This project has received funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No.654911 (project “THALAMODEL”), and also from the Spanish Ministry of Economy and Competitiveness (MINECO, reference TEC2014-51882-P). Support for this research was also provided in part by the National Cancer Institute (1K25-CA181632-01), the Genentech Foundation (G-40819) and the Nvidia corporation, which donated a Titan X GPU. Further support was provided by the A.A. Martinos Center for Biomedical Imaging (P41RR014075, P41EB015896, U24RR021382), and was made possible by the resources provided by Shared Instrumentation Grants1S10RR023401, 1S10RR019307, and 1S10RR023043. Support was also provided by the National Institute for Biomedical Imaging and Bioengineering (R01EB006758, R21EB018907, R01EB019956), the National Institute on Aging (5R01AG008122, R01AG016495), the National Institute for Neurological Disorders and Stroke (R01NS0525851, R21NS072652, R01NS070963, R01NS083534, 5U01NS086625) and the Lundbeck Foundation (R141-2013-13117), Additional support was provided by the NIH Blueprint for Neuroscience Research (5U01-MH093765), as part of the multi-institutional Human Connectome Project. In addition, BF has a financial interest in CorticoMetrics, a company whose medical pursuits focus on brain imaging and measurement technologies. BF's interests were reviewed and are managed by Massachusetts General Hospital and Partners HealthCare in accordance with their conflict of interest policies. The collection and sharing of the MRI data used in the group study based on ADNI was funded by the Alzheimer's Disease Neuroimaging Initiative (National Institutes of Health Grant U01 AG024904) and DOD ADNI (U.S. Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: Alzheimer's Association; Alzheimer's Drug Discovery Foundation; BioClinica, Inc.; Biogen Idec Inc.; Bristol-Myers Squibb Company; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; GE Healthcare; Innogenetics, N.V.; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Medpace, Inc.; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Synarc Inc.; and Takeda Pharmaceutical Company. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Disease Cooperative Study at the University of California, San Diego. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

No abstract available.

Published: 04 March 2016 Background: Evidence suggests a link between the presence of subjective memory complaints (SMC) and lower volume of the hippocampus, one of the first regions to show neuropathological lesions in Alzheimer’s disease. However, it remains unknown whether this pattern of hippocampal atrophy is regionally specific and whether SMC are also paralleled by changes in peripheral levels of amyloid-beta (Aβ). Methods: The volume of hippocampal subregions and plasma Aβ levels were cross-sectionally compared between elderly individuals with (SMC + ; N = 47) and without SMC (SMC − ; N = 48). Significant volume differences in hippocampal subregions were further correlated with plasma Aβ levels and with objective memory performance. Results: Individuals with SMC exhibited significantly higher Aβ 1–42 concentrations and lower volumes of CA1, CA4, dentate gyrus, and molecular layer compared with SMC − participants. Regression analyses further showed significant associations between lower volume of the dentate gyrus and both poorer memory performance and higher plasma Aβ 1–42 levels in SMC + participants. Conclusions: The presence of SMC, lower volumes of specific hippocampal regions, and higher plasma Aβ 1–42 levels could be conditions associated with aging vulnerability. If such associations are confirmed in longitudinal studies, the combination may be markers recommending clinical follow-up in nondemented older adults. This work was supported by research grants from the Spanish Ministry of Economy and Competitiveness (SAF2011-25463 to J.L.C., PSI2014-55747-R to M.A.), the Regional Ministry of Innovation, Science and Enterprise, Junta de Andalucia (P12-CTS-2327 to J.L.C.), CIBERNED (CB06/05/1111 to J.L.C.), the Fellows Gipuzkoa Program to J.E.I., the National Institutes of Health, National Center for Research Resources (P41-RR14075 to K.V.L.), the National Institutes of Health, National Institute of Biomedical Imaging and Bioengineering (R01EB013565 to K.V.L.), and the Lundbeck Foundation (R141-2013-13117 to K.V.L.).

BackgroundSmaller hippocampal volume in patients with PTSD represents the most consistently reported structural alteration in the brain. Subfields of the hippocampus play distinct roles in encoding and processing of memories, which are disrupted in PTSD. We examined PTSD-associated alterations in 12 hippocampal subfields in relation to global hippocampal shape, and clinical features.MethodsCase-control cross-sectional study of US military veterans (n=282) from the Iraq and Afghanistan era were grouped into PTSD (n=142) and trauma-exposed controls (n=140). Participants underwent clinical evaluation for PTSD and associated clinical parameters followed by MRI at 3-Tesla. Segmentation with Free Surfer v6.0 produced hippocampal subfield volumes for the left and right CA1, CA3, CA4, DG, fimbria, fissure, hippocampus-amygdala transition area, molecular layer, parasubiculum, presubiculum, subiculum, and tail, as well as hippocampal meshes. Covariates included age, gender, trauma exposure, alcohol use, depressive symptoms, antidepressant medication use, total hippocampal volume, and MRI scanner model.ResultsSignificantly lower subfield volumes were associated with PTSD in left CA1 (p=.01; d=.21; uncorrected), CA3 (p=.04; d=.08; uncorrected), and right CA3 (p=.02; d=.07; uncorrected) only if ipsilateral whole hippocampal volume was included as a covariate. A trend level association of L-CA1 with PTSD [F4,221=3.32, p = 0.07] is present and the other subfield findings are non-significant if ipsilateral whole hippocampal volume is not included as a covariate. PTSD associated differences in global hippocampal shape were non-significant.ConclusionsThe present finding of smaller hippocampal CA1 in PTSD is consistent with model systems in rodents that exhibit increased anxiety-like behavior from repeated exposure to acute stress. Behavioral correlations with hippocampal subfield volume differences in PTSD will elucidate their relevance to PTSD, particularly behaviors of associative fear learning, extinction training, and formation of false memories.

Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction algorithms. This registration is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid deformations and artefacts produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesising one modality from the other and then using intra-modality registration metrics, rather than by using information theory based metrics to solve the problem directly. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology and MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for deformable registration and synthesis directly on the target images, without requiring any training data. The method is based on a probabilistic model in which the MRI slice is assumed to be a contrast-warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other's uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance and robustness. Experiments on a synthetic dataset of MRI slices show that, compared with mutual information based registration, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than mutual information: landmarks constrain the deformation field in both methods, but in our algorithm, it also has a positive effect on the synthesis - which further improves the registration. We also show results on two real, publicly available datasets: the Allen and BigBrain atlases. In both of them, the proposed method provides a clear improvement over mutual information based registration, both qualitatively (visual inspection) and quantitatively (registration error measured with pairs of manually annotated landmarks). ispartof: MEDICAL IMAGE ANALYSIS vol:50 pages:127-144 ispartof: location:Netherlands status: published

Histology permits the observation of otherwise invisible structures of the internal topography of a specimen. Although it enables the investigation of tissues at a cellular level, it is invasive and breaks topology due to cutting. Three-dimensional (3D) reconstruction was thus introduced to overcome the limitations of single-section studies in a dimensional scope. 3D reconstruction finds its roots in embryology, where it enabled the visualisation of spatial relationships of developing systems and organs, and extended to biomedicine, where the observation of individual, stained sections provided only partial understanding of normal and abnormal tissues. However, despite bringing visual awareness, recovering realistic reconstructions is elusive without prior knowledge about the tissue shape. 3D medical imaging made such structural ground truths available. In addition, combining non-invasive imaging with histology unveiled invaluable opportunities to relate macroscopic information to the underlying microscopic properties of tissues through the establishment of spatial correspondences; image registration is one technique that permits the automation of such a process and we describe reconstruction methods that rely on it. It is thereby possible to recover the original topology of histology and lost relationships, gain insight into what affects the signals used to construct medical images (and characterise them), or build high resolution anatomical atlases. This paper reviews almost three decades of methods for 3D histology reconstruction from serial sections, used in the study of many different types of tissue. We first summarise the process that produces digitised sections from a tissue specimen in order to understand the peculiarity of the data, the associated artefacts and some possible ways to minimise them. We then describe methods for 3D histology reconstruction with and without the help of 3D medical imaging, along with methods of validation and some applications. We finally attempt to identify the trends and challenges that the field is facing, many of which are derived from the cross-disciplinary nature of the problem as it involves the collaboration between physicists, histolopathologists, computer scientists and physicians.

Subcortical gray matter regions have been implicated in mood disorders, including Major Depressive Disorder (MDD) and Bipolar Disorder (BD). It is unclear, however, whether or how these regions differ among mood disorders and whether such abnormalities are state- or trait-like. In this study, we examined differences in subcortical gray matter volumes among euthymic BD, MDD, remitted MDD (RMD), and healthy (CTL) individuals. Using automated gray matter segmentation of T1-weighted MRI images, we estimated volumes of 16 major subcortical gray matter structures in 40 BD, 57 MDD, 35 RMD, and 61 CTL individuals. We used multivariate analysis of variance to examine group differences in these structures, and support vector machines (SVMs) to assess individual-by-individual classification. Analyses yielded significant group differences for caudate (p = 0.029) and ventral diencephalon (VD) volumes (p = 0.003). For the caudate, both the BD (p = 0.004) and the MDD (p = 0.037) participants had smaller volumes than did the CTL participants. For the VD, the MDD participants had larger volumes than did the BD and CTL participants (ps < 0.005). SVM distinguished MDD from BD with 59.5% accuracy. These findings indicate that mood disorders are characterized by anomalies in subcortical gray matter volumes and that the caudate and VD contribute uniquely to differential affective pathology. Identifying abnormalities in subcortical gray matter may prove useful for the prevention, diagnosis, and treatment of mood disorders.

In this paper we present a novel label fusion algorithm suited for scenarios in which different manual delineation protocols with potentially disparate structures have been used to annotate the training scans (hereafter referred to as "atlases"). Such scenarios arise when atlases have missing structures, when they have been labeled with different levels of detail, or when they have been taken from different heterogeneous databases. The proposed algorithm can be used to automatically label a novel scan with any of the protocols from the training data. Further, it enables us to generate new labels that are not present in any delineation protocol by defining intersections on the underling labels. We first use probabilistic models of label fusion to generalize three popular label fusion techniques to the multi-protocol setting: majority voting, semi-locally weighted voting and STAPLE. Then, we identify some shortcomings of the generalized methods, namely the inability to produce meaningful posterior probabilities for the different labels (majority voting, semi-locally weighted voting) and to exploit the similarities between the atlases (all three methods). Finally, we propose a novel generative label fusion model that can overcome these drawbacks. We use the proposed method to combine four brain MRI datasets labeled with different protocols (with a total of 102 unique labeled structures) to produce segmentations of 148 brain regions. Using cross-validation, we show that the proposed algorithm outperforms the generalizations of majority voting, semi-locally weighted voting and STAPLE (mean Dice score 83%, vs. 77%, 80% and 79%, respectively). We also evaluated the proposed algorithm in an aging study, successfully reproducing some well-known results in cortical and subcortical structures. (C) 2014 The Authors. Published by Elsevier Inc.

Subcortical structures play a critical role in brain function. However, options for assessing electrophysiological activity in these structures are limited. Electromagnetic fields generated by neuronal activity in subcortical structures can be recorded non-invasively using magnetoencephalography (MEG) and electroencephalography (EEG). However, these subcortical signals are much weaker than those due to cortical activity. In addition, we show here that it is difficult to resolve subcortical sources, because distributed cortical activity can explain the MEG and EEG patterns due to deep sources. We then demonstrate that if the cortical activity can be assumed to be spatially sparse, both cortical and subcortical sources can be resolved with M/EEG. Building on this insight, we develop a novel hierarchical sparse inverse solution for M/EEG. We assess the performance of this algorithm on realistic simulations and auditory evoked response data and show that thalamic and brainstem sources can be correctly estimated in the presence of cortical activity. Our analysis and method suggest new opportunities and offer practical tools for characterizing electrophysiological activity in the subcortical structures of the human brain., 12 pages with 6 figures

Aligning images in a mid-space is a common approach to ensuring that deformable image registration is symmetric - that it does not depend on the arbitrary ordering of the input images. The results are, however, generally dependent on the mathematical definition of the mid-space. In particular, the set of possible solutions is typically restricted by the constraints that are enforced on the transformations to prevent the mid-space from drifting too far from the native image spaces. The use of an implicit atlas has been proposed as an approach to mid-space image registration. In this work, we show that when the atlas is aligned to each image in the native image space, the data term of implicit-atlas-based deformable registration is inherently independent of the mid-space. In addition, we show that the regularization term can be reformulated independently of the mid-space as well. We derive a new symmetric cost function that only depends on the transformation morphing the images to each other, rather than to the atlas. This eliminates the need for anti-drift constraints, thereby expanding the space of allowable deformations. We provide an implementation scheme for the proposed framework, and validate it through diffeomorphic registration experiments on brain magnetic resonance images.

Most individuals identified as ultra-high-risk (UHR) for psychosis do not develop frank psychosis. They continue to exhibit subthreshold symptoms, or go on to fully remit. Prior work has shown that the volume of CA1, a subfield of the hippocampus, is selectively reduced in the early stages of schizophrenia. Here we aimed to determine whether patterns of volume change of CA1 are different in UHR individuals who do or do not achieve symptomatic remission. Structural MRI scans were acquired at baseline and at 1-2 follow-up time points (at 12-month intervals) from 147 UHR and healthy control subjects. An automated method (based on an ex vivo atlas of ultra-high-resolution hippocampal tissue) was used to delineate the hippocampal subfields. Over time, a greater decline in bilateral CA1 subfield volumes was found in the subgroup of UHR subjects whose subthreshold symptoms persisted (n=40) and also those who developed clinical psychosis (n=12), compared with UHR subjects who remitted (n=41) and healthy controls (n=54). No baseline differences in volumes of the overall hippocampus or its subfields were found among the groups. Moreover, the rate of volume decline of CA1, but not of other hippocampal subfields, in the non-remitters was associated with increasing symptom severity over time. Thus, these findings indicate that there is deterioration of CA1 volume in persistently symptomatic UHR individuals in proportion to symptomatic progression.

Many segmentation algorithms in medical image analysis use Bayesian modeling to augment local image appearance with prior anatomical knowledge. Such methods often contain a large number of free parameters that are first estimated and then kept fixed during the actual segmentation process. However, a faithful Bayesian analysis would marginalize over such parameters, accounting for their uncertainty by considering all possible values they may take. Here we propose to incorporate this uncertainty into Bayesian segmentation methods in order to improve the inference process. In particular, we approximate the required marginalization over model parameters using computationally efficient Markov chain Monte Carlo techniques. We illustrate the proposed approach using a recently developed Bayesian method for the segmentation of hippocampal subfields in brain MRI scans, showing a significant improvement in an Alzheimer’s disease classification task. As an additional benefit, the technique also allows one to compute informative “error bars” on the volume estimates of individual structures.

Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems.

Published online: 23 February 2016 Volume deficits of the hippocampus in schizophrenia have been consistently reported. However, the hippocampus is anatomically heterogeneous; it remains unclear whether certain portions of the hippocampus are affected more than others in schizophrenia. In this study, we aimed to determine whether volume deficits in schizophrenia are confined to specific subfields of the hippocampus and to measure the subfield volume trajectories over the course of the illness. Magnetic resonance imaging scans were obtained from Data set 1: 155 patients with schizophrenia (mean duration of illness of 7 years) and 79 healthy controls, and Data set 2: an independent cohort of 46 schizophrenia patients (mean duration of illness of 18 years) and 46 healthy controls. In addition, follow-up scans were collected for a subset of Data set 1. A novel, automated method based on an atlas constructed from ultra-high resolution, post-mortem hippocampal tissue was used to label seven hippocampal subfields. Significant cross-sectional volume deficits in the CA1, but not of the other subfields, were found in the schizophrenia patients of Data set 1. However, diffuse cross-sectional volume deficits across all subfields were found in the more chronic and ill schizophrenia patients of Data set 2. Consistent with this pattern, the longitudinal analysis of Data set 1 revealed progressive illness-related volume loss (~2–6% per year) that extended beyond CA1 to all of the other subfields. This decline in volume correlated with symptomatic worsening. Overall, these findings provide converging evidence for early atrophy of CA1 in schizophrenia, with extension to other hippocampal subfields and accompanying clinical sequelae over time. This study was supported by the National Medical Research Council under the Centre Grant Programme (Institute of Mental Health, Singapore) (NMRC/CG/004/2013) (NFH) and by the National Healthcare Group, Singapore (SIG/05004; SIG/05028), and the Singapore Bioimaging Consortium (RP C-009/2006) research grants awarded to KS, as well grants from the National Institute of Mental Health (DJH: K23MH076054; JLR: K23MH084059) and a Howard Hughes Medical Institute Physician Scientist Early Career Award and grant from Pamlab (JLR). This research was also supported by the Biomedical Research Council, Singapore (awarded to JZ, BMRC 04/1/36/372), the Agency for Science, Technology, and Research (A*STAR) and Duke-NUS Graduate Medical School Signature Research Program funded by Ministry of Health, Singapore.

Automatic whole-brain extraction from magnetic resonance images (MRI), also known as skull stripping, is a key component in most neuroimage pipelines. As the first element in the chain, its robustness is critical for the overall performance of the system. Many skull stripping methods have been proposed, but the problem is not considered to be completely solved yet. Many systems in the literature have good performance on certain datasets (mostly the datasets they were trained/tuned on), but fail to produce satisfactory results when the acquisition conditions or study populations are different. In this paper we introduce a robust, learning-based brain extraction system (ROBEX). The method combines a discriminative and a generative model to achieve the final result. The discriminative model is a Random Forest classifier trained to detect the brain boundary; the generative model is a point distribution model that ensures that the result is plausible. When a new image is presented to the system, the generative model is explored to find the contour with highest likelihood according to the discriminative model. Because the target shape is in general not perfectly represented by the generative model, the contour is refined using graph cuts to obtain the final segmentation. Both models were trained using 92 scans from a proprietary dataset but they achieve a high degree of robustness on a variety of other datasets. ROBEX was compared with six other popular, publicly available methods (BET, BSE, FreeSurfer, AFNI, BridgeBurner, and GCUT) on three publicly available datasets (IBSR, LPBA40, and OASIS, 137 scans in total) that include a wide range of acquisition hardware and a highly variable population (different age groups, healthy/diseased). The results show that ROBEX provides significantly improved performance measures for almost every method/dataset combination.

Many different probabilistic tractography methods have been proposed in the literature to overcome the limitations of classical deterministic tractography: (i) lack of quantitative connectivity information; and (ii) robustness to noise, partial volume effects and selection of seed region. However, these methods rely on Monte Carlo sampling techniques that are computationally very demanding. This study presents an approximate stochastic tractography algorithm (FAST) that can be used interactively, as opposed to having to wait several minutes to obtain the output after marking a seed region. In FAST, tractography is formulated as a Markov chain that relies on a transition tensor. The tensor is designed to mimic the features of a well-known probabilistic tractography method based on a random walk model and Monte-Carlo sampling, but can also accommodate other propagation rules. Compared to the baseline algorithm, our method circumvents the sampling process and provides a deterministic solution at the expense of partially sacrificing sub-voxel accuracy. Therefore, the method is strictly speaking not stochastic, but provides a probabilistic output in the spirit of stochastic tractography methods. FAST was compared with the random walk model using real data from 10 patients in two different ways: 1. the probability maps produced by the two methods on five well-known fiber tracts were directly compared using metrics from the image registration literature; and 2. the connectivity measurements between different regions of the brain given by the two methods were compared using the correlation coefficient ρ. The results show that the connectivity measures provided by the two algorithms are well-correlated (ρ = 0.83), and so are the probability maps (normalized cross correlation 0.818 ± 0.081). The maps are also qualitatively (i.e., visually) very similar. The proposed method achieves a 60x speed-up (7 s vs. 7 min) over the Monte Carlo sampling scheme, therefore enabling interactive probabilistic tractography: the user can quickly modify the seed region if he is not satisfied with the output without having to wait on average 7 min.

Multi-atlas segmentation (MAS), first introduced and popularized by the pioneering work of Rohlfing, Brandt, Menzel and Maurer Jr (2004), Klein, Mensh, Ghosh, Tourville and Hirsch (2005), and Heckemann, Hajnal, Aljabar, Rueckert and Hammers (2006), is becoming one of the most widely-used and successful image segmentation techniques in biomedical applications. By manipulating and utilizing the entire dataset of “atlases” (training images that have been previously labeled, e.g., manually by an expert), rather than some model-based average representation, MAS has the flexibility to better capture anatomical variation, thus offering superior segmentation accuracy. This benefit, however, typically comes at a high computational cost. Recent advancements in computer hardware and image processing software have been instrumental in addressing this challenge and facilitated the wide adoption of MAS. Today, MAS has come a long way and the approach includes a wide array of sophisticated algorithms that employ ideas from machine learning, probabilistic modeling, optimization, and computer vision, among other fields. This paper presents a survey of published MAS algorithms and studies that have applied these methods to various biomedical problems. In writing this survey, we have three distinct aims. Our primary goal is to document how MAS was originally conceived, later evolved, and now relates to alternative methods. Second, this paper is intended to be a detailed reference of past research activity in MAS, which now spans over a decade (2003 – 2014) and entails novel methodological developments and application-specific solutions. Finally, our goal is to also present a perspective on the future of MAS, which, we believe, will be one of the dominant approaches in biomedical image segmentation.

VK: Lampinen, J. In this paper we present a method to segment four brainstem structures (midbrain, pons, medulla oblongata and superior cerebellar peduncle) from 3D brain MRI scans. The segmentation method relies on a probabilistic atlas of the brainstem and its neighboring brain structures. To build the atlas, we combined a dataset of 39 scans with already existing manual delineations of the whole brainstem and a dataset of 10 scans in which the brainstem structures were manually labeled with a protocol that was specifically designed for this study. The resulting atlas can be used in a Bayesian framework to segment the brainstem structures in novel scans. Thanks to the generative nature of the scheme, the segmentation method is robust to changes in MRI contrast or acquisition hardware. Using cross validation, we show that the algorithm can segment the structures in previously unseen T1 and FLAIR scans with great accuracy (mean error under 1 mm) and robustness (no failures in 383 scans including 168 AD cases). We also indirectly evaluate the algorithm with a experiment in which we study the atrophy of the brainstem in aging. The results show that, when used simultaneously, the volumes of the midbrain, pons and medulla are significantly more predictive of age than the volume of the entire brainstem, estimated as their sum. The results also demonstrate that the method can detect atrophy patterns in the brainstem structures that have been previously described in the literature. Finally, we demonstrate that the proposed algorithm is able to detect differential effects of AD on the brainstem structures. The method will be implemented as part of the popular neuroimaging package FreeSurfer.

In this paper we propose a method for whole brain parcellation using the type of generative parametric models typically used in tissue classification. Compared to the non-parametric, multi-atlas segmentation techniques that have become popular in recent years, our method obtains state-of-the-art segmentation performance in both cortical and subcortical structures, while retaining all the benefits of generative parametric models, including high computational speed, automatic adaptiveness to changes in image contrast when different scanner platforms and pulse sequences are used, and the ability to handle multi-contrast (vector-valued intensities) MR data. We have validated our method by comparing its segmentations to manual delineations both within and across scanner platforms and pulse sequences, and show preliminary results on multi-contrast test-retest scans, demonstrating the feasibility of the approach.

Multi-atlas label fusion is a powerful image segmentation strategy that is becoming increasingly popular in medical imaging. A standard label fusion algorithm relies on independently computed pairwise registrations between individual atlases and the (target) image to be segmented. These registrations are then used to propagate the atlas labels to the target space and fuse them into a single final segmentation. Such label fusion schemes commonly rely on the similarity between intensity values of the atlases and target scan, which is often problematic in medical imaging – in particular, when the atlases and target images are obtained via different sensor types or imaging protocols. In this paper, we present a generative probabilistic model that yields an algorithm for solving the atlas-to-target registrations and label fusion steps simultaneously. The proposed model does not directly rely on the similarity of image intensities. Instead, it exploits the consistency of voxel intensities within the target scan to drive the registration and label fusion, hence the atlases and target image can be of different modalities. Furthermore, the framework models the joint warp of all the atlases, introducing interdependence between the registrations. We use variational expectation maximization and the Demons registration framework in order to efficiently identify the most probable segmentation and registrations. We use two sets of experiments to illustrate the approach, where proton density (PD) MRI atlases are used to segment T1-weighted brain scans and vice versa. Our results clearly demonstrate the accuracy gain due to exploiting within-target intensity consistency and integrating registration into label fusion.

Multi-atlas techniques are commonplace in medical image segmentation due to their high performance and ease of implementation. Locally weighting the contributions from the different atlases in the label fusion process can improve the quality of the segmentation. However, how to define these weights in a principled way in inter-modality scenarios remains an open problem. Here we propose a label fusion scheme that does not require voxel intensity consistency between the atlases and the target image to segment. The method is based on a generative model of image data in which each intensity in the atlases has an associated conditional distribution of corresponding intensities in the target. The segmentation is computed using variational expectation maximization (VEM) in a Bayesian framework. The method was evaluated with a dataset of eight proton density weighted brain MRI scans with nine labeled structures of interest. The results show that the algorithm outperforms majority voting and a recently published inter-modality label fusion algorithm.

Many successful segmentation algorithms are based on Bayesian models in which prior anatomical knowledge is combined with the available image information. However, these methods typically have many free parameters that are estimated to obtain point estimates only, whereas a faithful Bayesian analysis would also consider all possible alternate values these parameters may take. In this paper, we propose to incorporate the uncertainty of the free parameters in Bayesian segmentation models more accurately by using Monte Carlo sampling. We demonstrate our technique by sampling atlas warps in a recent method for hippocampal subfield segmentation, and show a significant improvement in an Alzheimer’s disease classification task. As an additional benefit, the method also yields informative “error bars” on the segmentation results for each of the individual sub-structures.

In this study, we present a system for Alzheimer's disease classification on the ADNI dataset. Our system is able to learn/fuse registration-based (matching) and overlap-based similarity measures, which are enhanced using a self-smoothing operator (SSO). From a matrix of pair-wise affinities between data points, our system uses a diffusion process to output an enhanced matrix. The diffusion propagates the affinity mass along the intrinsic data space without the need to explicitly learn the manifold. Using the enhanced metric in nearest neighborhood classification, we show significantly improved accuracy for Alzheimer's Disease over Diffusion Maps and a popular metric learning approach. State-of-the-art results are obtained in the classification of 120 brain MRIs from ADNI as normal, mild cognitive impairment, and Alzheimer's.

This paper presents a new supervised learning framework for the efficient recognition and segmentation of anatomical structures in 3D computed tomography (CT), with as little training data as possible. Training supervised classifiers to recognize organs within CT scans requires a large number of manually delineated exemplar 3D images, which are very expensive to obtain. In this study, we borrow ideas from the field of active learning to optimally select a minimum subset of such images that yields accurate anatomy segmentation. The main contribution of this work is in designing a combined generative-discriminative model which: i) drives optimal selection of training data; and ii) increases segmentation accuracy. The optimal training set is constructed by finding unlabeled scans which maximize the disagreement between our two complementary probabilistic models, as measured by a modified version of the Jensen-Shannon divergence. Our algorithm is assessed on a database of 196 labeled clinical CT scans with high variability in resolution, anatomy, pathologies, etc. Quantitative evaluation shows that, compared with randomly selecting the scans to annotate, our method decreases the number of training images by up to 45%. Moreover, our generative model of body shape substantially increases segmentation accuracy when compared to either using the discriminative model alone or a generic smoothness prior (e.g. via a Markov Random Field).

This work addresses the challenging problem of simultaneously segmenting multiple anatomical structures in highly varied CT scans. We propose the entangled decision forest (EDF) as a new discriminative classifier which augments the state of the art decision forest, resulting in higher prediction accuracy and shortened decision time. Our main contribution is two-fold. First, we propose entangling the binary tests applied at each tree node in the forest, such that the test result can depend on the result of tests applied earlier in the same tree and at image points offset from the voxel to be classified. This is demonstrated to improve accuracy and capture long-range semantic context. Second, during training, we propose injecting randomness in a guided way, in which node feature types and parameters are randomly drawn from a learned (nonuniform) distribution. This further improves classification accuracy. We assess our probabilistic anatomy segmentation technique using a labeled database of CT image volumes of 250 different patients from various scan protocols and scanner vendors. In each volume, 12 anatomical structures have been manually segmented. The database comprises highly varied body shapes and sizes, a wide array of pathologies, scan resolutions, and diverse contrast agents. Quantitative comparisons with state of the art algorithms demonstrate both superior test accuracy and computational efficiency.

Purpose: This work describes a spatially variant mixture model constrained by a Markov random field to model high angular resolution diffusion imaging (HARDI) data. Mixture models suit HARDI well because the attenuation by diffusion is inherently a mixture. The goal is to create a general model that can be used in different applications. This study focuses on image denoising and segmentation (primarily the former). Methods: HARDI signal attenuation data are used to train a Gaussian mixture model in which the mean vectors and covariance matrices are assumed to be independent of spatial locations, whereas the mixture weights are allowed to vary at different lattice positions. Spatial smoothness of the data is ensured by imposing a Markov random field prior on the mixture weights. The model is trained in an unsupervised fashion using the expectation maximization algorithm. The number of mixture components is determined using the minimum message length criterion from information theory. Once the model has been trained, it can be fitted to a noisy diffusion MRI volume by maximizing the posterior probability of the underlying noiseless data in a Bayesian framework, recovering a denoised version of the image. Moreover, the fitted probability maps of the mixture components can be used as features for posterior image segmentation. Results: The model-based denoising algorithm proposed here was compared on real data with three other approaches that are commonly used in the literature: Gaussian filtering, anisotropic diffusion, and Rician-adapted nonlocal means. The comparison shows that, at low signal-to-noise ratio, when these methods falter, our algorithm considerably outperforms them. When tractography is performed on the model-fitted data rather than on the noisy measurements, the quality of the output improves substantially. Finally, ventricle and caudate nucleus segmentation experiments also show the potential usefulness of the mixture probability maps for classification tasks. Conclusions: The presented spatially variant mixture model for diffusion MRI provides excellent denoising results at low signal-to-noise ratios. This makes it possible to restore data acquired with a fast (i.e., noisy) pulse sequence to acceptable noise levels. This is the case in diffusion MRI, where a large number of diffusion-weighted volumes have to be acquired under clinical time constraints.

Learning-based approaches have become increasingly practical in medical imaging. For a supervised learning strategy, the quality of the trained algorithm (usually a classifier) is heavily dependent on the amount, as well as quality, of the available training data. It is often very time-consuming to obtain the ground truth manual delineations. In this paper, we propose a semi-supervised learning algorithm and show its application to skull stripping in brain MRI. The resulting method takes advantage of existing state-of-the-art systems, such as BET and FreeSurfer, to sample unlabeled data in an agreement-based framework. Using just two labeled and a set of unlabeled MRI scans, a voxel-based random forest classifier is trained to perform the skull stripping. Our system is practical, and it displays significant improvement over supervised approaches, BET and FreeSurfer in two datasets (60 test images).

From the image analysis perspective, a disadvantage of MRI is the lack of image intensity standardization. Differences in coil sensitivity, pulse sequence and acquisition parameters lead to very different mappings from tissue properties to image intensity levels. This presents challenges for image analysis techniques because the distribution of image intensities for different brain regions can change substantially from scan to scan. Though intensity correction can sometimes alleviate this problem, it fails in more difficult scenarios in which different types of tissue are mapped to similar gray levels in one scan but different intensities in another. Here, we propose using multi-spectral data to create synthetic MRI scans matched to the intensity distribution of a given dataset using a physical model of acquisition. If the multi-spectral data are manually annotated, the labels can be transfered to the synthetic scans to build a dataset-tailored gold standard. The approach was tested on a multi-atlas based hippocampus segmentation framework using a publicly available database, significantly improving the results obtained with other intensity correction methods.

Contains fulltext : 81641.pdf (Publisher’s version ) (Closed access) Automated analysis of mammograms requires robust methods for pectoralis segmentation and nipple detection. Locating the nipple is especially important in multiview computer aided detection systems, in which findings are matched across images using the nipple-to-finding distance. Segmenting the pectoralis is a key preprocessing step to avoid false positives when detecting masses due to the similarity of the texture of mammographic parenchyma and the pectoral muscle. A multiatlas algorithm capable of providing very robust initial estimates of the nipple position and pectoral region in digitized mammograms is presented here. Ten full-field digital mammograms, which are easily annotated attributed to their excellent contrast, are robustly registered to the target digitized film-screen mammogram. The annotations are then propagated and fused into a final nipple position and pectoralis segmentation. Compared to other nipple detection methods in the literature, the system proposed here has the advantages that it is more robust and can provide a reliable estimate when the nipple is located outside the image. Our results show that the change in the correlation between nipple-to-finding distances in craniocaudal and mediolateral oblique views is not significant when the detected nipple positions replace the manual annotations. Moreover, the pectoralis segmentation is acceptable and can be used as initialization for a more complex algorithm to optimize the outline locally. A novel aspect of the method is that it is also capable of detecting and segmenting the pectoralis in craniocaudal views.

A patient's electronic medical record can consist of a large number of reports, especially for an elderly patient or for one affected by a chronic disease. It can thus be cumbersome for a physician to go through all of the reports to understand the patient's complete medical history. This paper describes work in progress towards tracking medications and their dosages through the course of a patient's medical history. 923 reports associated with 11 patients were obtained from a university hospital. Drug names were identified using a dictionary look-up approach. Dosages corresponding to these drugs were determined using regular expressions. The state of a drug (ON, OFF), which determines whether or not the drug was being taken, was identified using a support vector machine with features based on expert knowledge. Results were promising: prec. approximately recall approximately 87%. The output is a timeline display of the drugs which the patient has been taking.

Automated analysis of MRI data of the subregions of the hippocampus requires computational atlases built at a higher resolution than those that are typically used in current neuroimaging studies. Here we describe the construction of a statistical atlas of the hippocampal formation at the subregion level using ultra-high resolution, ex vivo MRI. Fifteen autopsy samples were scanned at 0.13 mm isotropic resolution (on average) using customized hardware. The images were manually segmented into 13 different hippocampal substructures using a protocol specifically designed for this study; precise delineations were made possible by the extraordinary resolution of the scans. In addition to the subregions, manual annotations for neighboring structures (e.g., amygdala, cortex) were obtained from a separate dataset of in vivo, T1-weighted MRI scans of the whole brain (1 mm resolution). The manual labels from the in vivo and ex vivo data were combined into a single computational atlas of the hippocampal formation with a novel atlas building algorithm based on Bayesian inference. The resulting atlas can be used to automatically segment the hippocampal subregions in structural MRI images, using an algorithm that can analyze multimodal data and adapt to variations in MRI contrast due to differences in acquisition hardware or pulse sequences. The applicability of the atlas, which we are releasing as part of FreeSurfer (version 6.0), is demonstrated with experiments on three different publicly available datasets with different types of MRI contrast. The results show that the atlas and companion segmentation method: 1) can segment T1 and T2 images, as well as their combination, 2) replicate findings on mild cognitive impairment based on high-resolution T2 data, and 3) can discriminate between Alzheimer's disease subjects and elderly controls with 88% accuracy in standard resolution (1 mm) T1 data, significantly outperforming the atlas in FreeSurfer version 5.3 (86% accuracy) and classification based on whole hippocampal volume (82% accuracy)., National Center for Research Resources (U.S.) (P41EB015896), National Center for Research Resources (U.S.) (BIRN002 U24 RR021382), National Institute for Biomedical Imaging and Bioengineering (U.S.) (R01EB013565), National Institute for Biomedical Imaging and Bioengineering (U.S.) (R01EB006758), National Institute on Aging (AG022381), National Institute on Aging (5R01AG008122-22), National Institute on Aging (K01AG028521), National Institute on Aging (P30AG13846), National Institute on Aging (R01AG1649), National Center for Complementary and Alternative Medicine (U.S.) (RC1 AT005728-01), National Institute of Neurological Diseases and Stroke (U.S.) (R01 NS052585-01), National Institute of Neurological Diseases and Stroke (U.S.) (1R21NS072652-01), National Institute of Neurological Diseases and Stroke (U.S.) (1R01NS070963), National Institute of Neurological Diseases and Stroke (U.S.) (R01NS083534), United States. Dept. of Health and Human Services. Shared Instrumentation Grant Program (1S10RR023401), United States. Dept. of Health and Human Services. Shared Instrumentation Grant Program (1S10RR019307), United States. Dept. of Health and Human Services. Shared Instrumentation Grant Program (1S10RR023043), Ellison Medical Foundation, National Institutes of Health (U.S.). Blueprint for Neuroscience Research (5U01-MH093765), United States. National Institutes of Health (P30-AG010129), United States. National Institutes of Health (K01-AG030514)

Fluorinert (perfluorocarbon) represents an inexpensive option for minimizing susceptibility artifacts in ex vivo brain MRI scanning, and provides an alternative to Fomblin. However, its impact on fixed tissue and histological analysis has not been rigorously and quantitatively validated. In this study, we excised tissue blocks from 2 brain regions (frontal pole and cerebellum) of 5 formalin-fixed specimens (2 progressive supranuclear palsy cases, 3 controls). We excised 2 blocks per region per case (20 blocks in total), one of which was subsequently immersed in Fluorinert for a week and then returned to a container with formalin. The other block from each region was kept in formalin for use as control. The tissue blocks were then sectioned and histological analysis was performed on each, including routine stains and immunohistochemistry. Visual inspection of the stained histological sections by an experienced neuropathologist through the microscope did not reveal any discernible differences between any of the samples. Moreover, quantitative analysis based on automated image patch classification showed that the samples were almost indistinguishable for a state-of-the-art classifier based on a deep convolutional neural network. The results showed that Fluorinert has no effect on subsequent histological analysis of the tissue even after a long (1 week) period of immersion, which is sufficient for even the lengthiest scanning protocols.

Ex vivo imaging enables analysis of the human brain at a level of detail that is not possible in vivo with MRI. In particular, histology can be used to study brain tissue at the microscopic level, using a wide array of different stains that highlight different microanatomical features. Complementing MRI with histology has important applications in ex vivo atlas building and in modeling the link between microstructure and macroscopic MR signal. However, histology requires sectioning tissue, hence distorting its 3D structure, particularly in larger human samples. Here, we present an open-source computational pipeline to produce 3D consistent histology reconstructions of the human brain. The pipeline relies on a volumetric MRI scan that serves as undistorted reference, and on an intermediate imaging modality (blockface photography) that bridges the gap between MRI and histology. We present results on 3D histology reconstruction of a whole human hemisphere.