scholarly journals Harmonization of large multi-site imaging datasets: Application to 10,232 MRIs for the analysis of imaging patterns of structural brain change throughout the lifespan

2019 ◽  
Author(s):  
Raymond Pomponio ◽  
Guray Erus ◽  
Mohamad Habes ◽  
Jimit Doshi ◽  
Dhivya Srinivasan ◽  
...  
Keyword(s):  
Brain Structure ◽  
Large Scale ◽  
Brain Mri ◽  
Big Data Analytics ◽  
Imaging Data ◽  
Mri Scans ◽  
Age Trends ◽  
Development And Aging ◽  
Structural Brain Change ◽  
Structural Brain

AbstractAs medical imaging enters its information era and presents rapidly increasing needs for big data analytics, robust pooling and harmonization of imaging data across diverse cohorts with varying acquisition protocols have become critical. We describe a comprehensive effort that merges and harmonizes a large-scale dataset of 10,232 structural brain MRI scans from participants without known neuropsychiatric disorder from 18 different studies that represent geographic diversity. We use this dataset and multi-atlas-based image processing methods to obtain a hierarchical partition of the brain from larger anatomical regions to individual cortical and deep structures and derive normative age trends of brain structure through the lifespan (3 to 96 years old). Critically, we present and validate a methodology for harmonizing this pooled dataset in the presence of nonlinear age trends. We provide a web-based visualization interface to generate and present the resulting age trends, enabling future studies of brain structure to compare their data with this normative reference of brain development and aging, and to examine deviations from normative ranges, potentially related to disease.

Structural Brain Imaging and the Prevention of Schizophrenia: Can We Identify Neuroanatomical Markers for Young People at Risk for the Development of Schizophrenia?

2000 ◽  
Vol 34 (1_suppl) ◽  
pp. A127-A130 ◽  
Author(s):  
Philip B. Ward
Keyword(s):  
At Risk ◽  
Brain Imaging ◽  
Brain Structure ◽  
Large Scale ◽  
Normal Volunteer ◽  
First Episode ◽  
Phenotypic Marker ◽  
Structural Brain Change ◽  
Structural Brain ◽  
Structural Brain Imaging

Objective To examine the potential role of measures derived from structural brain imaging as phenotypic markers for the development of schizophrenia. Method Literature review of results of MRI-based assessments of brain structure in patients with schizophrenia, their first-degree relatives and factors that affect interpretation of such results. Results Reliable differences in brain structure can be detected in patients with schizophrenia, including those experiencing a first episode of psychosis. Further research is required to determine whether these differences are progressive, how they relate to potential confounding factors such as comorbid substance abuse and the functional consequences of the relatively subtle changes observed. Conclusions Further research is needed before structural brain change can be considered as a phenotypic marker for those at risk of developing schizophrenia. Large-scale collaborative research in clinical and normal volunteer groups using standardised assessment protocols would enable the early identification of those findings with predictive power in at-risk populations.

scholarly journals Multidimensional Heritability Analysis of Neuroanatomical Shape

2015 ◽  
Author(s):  
Tian Ge ◽  
Martin Reuter ◽  
Anderson M. Winkler ◽  
Avram J. Holmes ◽  
Phil H. Lee ◽  
...  
Keyword(s):  
Brain Structure ◽  
Large Scale ◽  
Brain Mri ◽  
Brain Structures ◽  
Biomedical Data ◽  
Genetic Determinants ◽  
Genetic Studies ◽  
Genome Wide ◽  
Human Connectome Project ◽  
Mri Scans

In the dawning era of large-scale biomedical data, multidimensional phenotype vectors will play an increasing role in examining the genetic underpinnings of brain features, behavior and disease. For example, shape measurements derived from brain MRI scans are multidimensional geometric descriptions of brain structure and provide an alternate class of phenotypes that remains largely unexplored in genetic studies. Here we extend the concept of heritability to multidimensional traits, and present the first comprehensive analysis of the heritability of neuroanatomical shape measurements across an ensemble of brain structures based on genome-wide SNP and MRI data from 1,320 unrelated, young and healthy individuals. We replicate our findings in an extended twin sample from the Human Connectome Project (HCP). Our results demonstrate that neuroanatomical shape can be significantly heritable, above and beyond volume, and can serve as a complementary phenotype to study the genetic determinants and clinical relevance of brain structure.

Federated Learning on Structural Brain MRI Scans for the Diagnostic Classification of Major Depression

2021 ◽  
Vol 89 (9) ◽  
pp. S183
Author(s):  
Zhipeng Fan ◽  
Jianpo Su ◽  
Kai Gao ◽  
Limin Peng ◽  
Jian Qin ◽  
...  
Keyword(s):  
Major Depression ◽  
Brain Mri ◽  
Diagnostic Classification ◽  
Mri Scans ◽  
Structural Brain

scholarly journals Lack of evidence for interactions between APOE and Klotho genotypes on cognitive, dementia and brain imaging metrics in UK Biobank

2021 ◽  
Author(s):  
Rachana Tank ◽  
Joey Ward ◽  
Daniel J. Smith ◽  
Kristin E. Flegal ◽  
Donald M. Lyall
Keyword(s):  
Cognitive Impairment ◽  
Brain Imaging ◽  
Brain Structure ◽  
Cognitive Abilities ◽  
Large Scale ◽  
Cognitive Test ◽  
Uk Biobank ◽  
Type 1 Error ◽  
Structural Brain

AbstractImportanceRecent research has suggested that genetic variation in the Klotho (KL) locus may modify the association between apolipoprotein e (APOE) e4 genotype and cognitive impairment.ObjectiveLarge-scale testing for associations and interactions between KL and APOE genotypes vs. risk of dementia (n=1,570 cases), cognitive abilities (n=174,513) and brain structure (n = 13,158) in older (60+ years) participants.Design, setting and participantsCross-sectional and prospective data (UK Biobank).Main outcomes and measuresKL status was indexed with heterozygosity of the rs9536314 polymorphism (vs. not), in unrelated people with vs. without APOE e4 genotype, using regression and interaction tests. We assessed non-demented cognitive scores (processing speed; reasoning; memory; executive function), multiple structural brain imaging, and clinical dementia outcomes. All tests were corrected for age, sex, assessment centre, eight principal components for population stratification, genotypic array, smoking history, deprivation, and self-reported medication history.ResultsAPOE e4 presence (vs. not) was associated with increased risk of dementia, worse cognitive abilities and brain structure differences. KL heterozygosity was associated with less frontal lobe grey matter. There were no significant APOE/KL interactions for cognitive, dementia or brain imaging measures (all P>0.05).Conclusions and relevanceWe found no evidence of APOE/KL interactions on cognitive, dementia or brain imaging outcomes. This could be due to some degree of cognitive test imprecision, generally preserved participant health potentially due to relatively young age, type-1 error in prior studies, or indicative of a significant age-dependent KL effect only in the context of marked AD pathology.Key pointsQuestion: Klotho genotype has been previously shown to ‘offset’ a substantial amount of the APOE e4/cognitive impairment association. Is this modification effect apparent in large-scale independent data, in terms of non-demented cognitive abilities, brain structure and dementia prevalence?Findings: In aged 60 years and above participants from UK Biobank, we found significant associations of APOE and Klotho genotypes on cognitive, structural brain and dementia outcomes, but no significant interactions.Meaning: This could reflect somewhat healthy participants, prior type 1 error or cognitive/dementia ascertainment imprecision, and/or that Klotho genotypic effects are age and neuropathology dependent.

scholarly journals Morphometricity as a measure of the neuroanatomical signature of a trait

2016 ◽  
Vol 113 (39) ◽  
pp. E5749-E5756 ◽  
Author(s):  
Mert R. Sabuncu ◽  
Tian Ge ◽  
Avram J. Holmes ◽  
Jordan W. Smoller ◽  
Randy L. Buckner ◽  
...  
Keyword(s):  
Large Scale ◽  
Anatomical Variation ◽  
Brain Mri ◽  
Mixed Effects ◽  
Brain Morphology ◽  
Linear Mixed Effects Model ◽  
Linear Mixed Effects ◽  
Behavioral Traits ◽  
Clinical Diagnoses ◽  
Mri Scans

Complex physiological and behavioral traits, including neurological and psychiatric disorders, often associate with distributed anatomical variation. This paper introduces a global metric, called morphometricity, as a measure of the anatomical signature of different traits. Morphometricity is defined as the proportion of phenotypic variation that can be explained by macroscopic brain morphology. We estimate morphometricity via a linear mixed-effects model that uses an anatomical similarity matrix computed based on measurements derived from structural brain MRI scans. We examined over 3,800 unique MRI scans from nine large-scale studies to estimate the morphometricity of a range of phenotypes, including clinical diagnoses such as Alzheimer’s disease, and nonclinical traits such as measures of cognition. Our results demonstrate that morphometricity can provide novel insights about the neuroanatomical correlates of a diverse set of traits, revealing associations that might not be detectable through traditional statistical techniques.

scholarly journals Population-based body-brain mapping links brain morphology and body composition

2020 ◽  
Author(s):  
Tiril P Gurholt ◽  
Tobias Kaufmann ◽  
Oleksandr Frei ◽  
Dag Alnæs ◽  
Unn K Haukvik ◽  
...  
Keyword(s):  
Body Composition ◽  
Adipose Tissue ◽  
Brain Structure ◽  
Large Scale ◽  
Brain Mri ◽  
The Body ◽  
Liver Fat ◽  
Brain Morphology ◽  
Healthy Individuals ◽  
Insight Into

AbstractBackgroundUnderstanding complex body-brain processes, and putative interplay between adipose tissue and brain health, is of vital importance for brain and somatic disease prevention in the general population. We studied the link between body composition and brain structure through large-scale investigation in a healthy population without secondary disease effects.MethodsWe processed brain magnetic resonance imaging (MRI) data and extracted measures of brain morphometry from 19,330 healthy UK Biobank participants, of which a subset (n=2,703) had body MRI. We investigated associations between brain structure and (i) anthropometric body composition measures, and (ii) regional/specific body MRI measures of abdominal fat and muscle tissue.FindingsWe identified highly significant body-brain associations (p-values≤0·0002). Anthropometric measures showed negative, nonlinear, associations with cerebellar/cortical gray matter, and brain stem structures, negative associations with white matter, and positive associations with ventricular volumes. Subcortical structures exhibited mixed effect directionality, with strongest positive association for accumbens. Among body MRI measures, liver fat was negatively associated with thinner/lower cortical gray matter thickness/volume, and thigh muscle volume positively associated with accumbens volume.InterpretationWe demonstrate significant body-brain associations, and map individual differences in body composition to brain morphology in healthy individuals. Common measures of body composition correlated negatively with cerebellar and cortical structures and positively with the accumbens, a dopamine rich structure involved in reward processing. These findings of a relationship between brain anatomy and body composition provide new insight into body-brain processes and suggest shared mechanisms of cardiometabolic risk factors and brain disorders. This may form the foundation for a new type of prevention studies, and provides a framework for studies of underlying mechanisms related to unhealthy lifestyle and obesity, with implications for public health and prevention.FundingThe Research Council of Norway, South-Eastern Norway Regional Health Authority, European Union’s Horizon 2020 Research and Innovation Programme & European Research Council.Research in contextEvidence before this studyPrior studies have indicated an association between brain structure and both obesity and fitness levels - of opposing directionality. Despite this, normal body-brain association patterns in healthy individuals have not been established, and the causal mechanisms are unclear. To enhance our understanding and establish the link between the body and the brain, we saw the need for large-scale investigations in healthy populations. For the study, we searched the PubMed database from March 12th, 2019, through February 25th, 2020, for scientific literature related to adipose tissue, body composition, brain morphology, and body and brain MRI. Search terms included: body fat, adipose tissue, subcutaneous/visceral adipose tissue, liver fat, body composition, anthropometric measures, body mass index, waist circumference, waist-to-hip ratio, adiposity, obesity, metabolic syndrome, cardiovascular, cardiometabolic, disease/disorder, muscle volume, fitness, brain structure, brain morphology, brain MRI, and body MRI. We based the scientific foundation on review studies, meta-analyses, and other larger studies, but generally excluded smaller studies, and thereby lowering the risk of evidential bias such as winner’s curse, although this does not eliminate the risk of publication bias.Added value of this studyIn the largest study, to date, including 19,330 healthy participants without secondary disease effects, we provide insight into normal body-brain processes by identifying body-brain associations that map normally varying body composition to brain morphology.Implications of all the available evidenceWe identified body-brain associations that give insight into normal physiological body-brain processes in healthy individuals, providing a reference point for studies of underlying mechanisms related to unhealthy lifestyle, obesity, and disorders of the body and the brain. Whereas the directionality and causal chain is unknown, these findings have potential implications for public health and disease prevention.

scholarly journals MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction

2021 ◽  
Vol 22 (S2) ◽  
Author(s):  
Changhee Han ◽  
Leonardo Rundo ◽  
Kohei Murao ◽  
Tomoyuki Noguchi ◽  
Yuki Shimahara ◽  
...  
Keyword(s):  
Brain Metastases ◽  
Anomaly Detection ◽  
Late Stage ◽  
Large Scale ◽  
Early Stage ◽  
Brain Mri ◽  
Disease Diagnosis ◽  
Training Data ◽  
Mri Scans ◽  
Adjacent Brain

Abstract Background Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer’s disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. Results We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 $$\ell _1$$ ℓ 1 loss—trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones—reconstructs unseen healthy/abnormal scans; (Diagnosis) Average $$\ell _2$$ ℓ 2 loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. Conclusions Similar to physicians’ way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans.

scholarly journals Framework for large-scale automatic curation of heterogeneous cardiac MRI (ACUR MRI)

2021 ◽  
Vol 22 (Supplement_2) ◽  
Author(s):  
C Galazis ◽  
K Vimalesvaran ◽  
S Zaman ◽  
C Petri ◽  
J Howard ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cardiac Mri ◽  
Large Scale ◽  
Slice Thickness ◽  
Imaging Data ◽  
National Budget ◽  
Imaging Characteristics ◽  
Intelligence Models ◽  
Mri Scans ◽  
Artificial Intelligence Models

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): UKRI CDT in AI for Healthcare http://ai4health.io and British Heart Foundation Background  Data curation is an important process that structures and organises data, supporting research and the development of artificial intelligence models. However, manually curating a large volume of medical data is a time-consuming, repetitive and costly process that puts additional strain on clinical experts. The curation becomes more complex and demanding as more data sources are used. This leads to an introduction of disparity in the data structure and protocols.  Purpose  Here, we propose an automatic framework to curate large volumes of heterogenous cardiac MRI scans acquired across different sites and scanner vendors. Our framework requires minimal expert involvement throughout and works directly on DICOM images from the scanner or PACS.  The resulting structured standardised data allow for straightforward image analysis, hypothesis testing and the training and application of artificial intelligence models.  Methods  It is broken down into three main components anonymisation, cataloguing and outlier detection (see Figure 1). Anonymisation automatically removes any identifiable patient information from the DICOM image attributes. These data are replaced with anonymised labels, whilst maintaining relevant longitudinal information from each patient. DICOM attributes are also used to automatically group the different images according to imaging sequence (e.g. CINE, Delayed-Enhancement, T1 maps), acquisition geometry (e.g. short-axis, 2-chamber, 4-chamber) and imaging attributes (e.g. slice thickness, TE, TR), for easier querying. The sorting characteristics are flexible and can easily be defined by the user. Finally, we detect and flag, for subsequent manual inspection, any outliers within those groups, based on the similarity levels of chosen DICOM attributes. This framework additionally offers interactive image visualisation to allow users to assess its performance in real time.  Results  We tested the performance of ACUR CMRI on 26,668 CMR image series (723,531 images) from 858 patient examinations, which took place across two sites in four different scanners. With an average execution time per patient of 100 seconds, ACUR was able to sort imaging data with 1191 different sequence names into 43 categories. The framework can be freely downloaded from https://bitbucket.org/cmr-ai-working-group/acur/.  Conclusions  We present ACUR, an automatic framework to curate large volumes of heterogeneous cardiac MRI data. We show how it can quickly and automatically curate data, grouping it according to desired imaging characteristics defined in DICOM attributes. The proposed framework is flexible and ideally suited as a pre-processing tool for large biomedical imaging data studies.

scholarly journals Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions

2021 ◽  
Author(s):  
Pooja Prabhu ◽  
A. K. Karunakar ◽  
Sanjib Sinha ◽  
N. Mariyappa ◽  
G. K. Bhargava ◽  
...  
Keyword(s):  
Large Scale ◽  
Brain Mri ◽  
Similarity Measures ◽  
Principal Component ◽  
Brain Anatomy ◽  
Morphological Operations ◽  
Mr Images ◽  
Tilt Correction ◽  
Brain Mr Images ◽  
The Brain

AbstractIn a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

Sign in / Sign up

Export Citation Format

Share Document