Biology subjects

Thomopoulos, S. I.

Publications and source records attributed to Thomopoulos, S. I..

65 records · Page 4Linked to original sources

bioRxiv2021

Alzheimer's Disease Classification Accuracy is Improved by MRI Harmonization based on Attention-Guided Generative Adversarial Networks

Alzheimers disease (AD) accounts for 60% of dementia cases worldwide; patients with the disease typically suffer from irreversible memory loss and progressive decline in multiple cognitive domains. With brain imaging techniques such as magnetic resonance imaging (MRI), microscopic brain changes are detectable even before abnormal memory loss is detected clinically. Patterns of brain atrophy can be measured using MRI, which gives us an opportunity to facilitate AD detection using image classification techniques. Even so, MRI scanning protocols and scanners differ across studies. The resulting differences in image contrast and signal to noise make it important to train and test classification models on multiple datasets, and to handle shifts in image characteristics across protocols (also known as domain transfer or domain adaptation). Here, we examined whether adversarial domain adaptation can boost the performance of a Convolutional Neural Network (CNN) model designed to classify AD. To test this, we used an Attention-Guided Generative Adversarial Network (GAN) to harmonize images from three publicly available brain MRI datasets - ADNI, AIBL and OASIS - adjusting for scanner-dependent effects. Our AG-GAN optimized a joint objective function that included attention loss, pixel loss, cycle-consistency loss and adversarial loss; the model was trained bidirectionally in an end-to-end fashion. For AD classification, we adapted the popular 2D AlexNet CNN to handle 3D images. Classification based on harmonized MR images significantly outperformed classification based on the three datasets in non-harmonized form, motivating further work on image harmonization using adversarial techniques.

neuroscience↗

bioRxiv2021

3D Convolutional Neural Networks for Classification of Alzheimer's and Parkinson's Disease with T1-Weighted Brain MRI

Parkinsons disease (PD) and Alzheimers disease (AD) are progressive neurodegenerative disorders that affect millions of people worldwide. In this work, we propose a deep learning approach to classify these diseases based on 3D T1-weighted brain MRI. We analyzed several datasets including the Parkinsons Progression Markers Initiative (PPMI), an independent dataset from the University of Pennsylvania School of Medicine (UPenn), the Alzheimers Disease Neuroimaging Initiative (ADNI), and the Open Access Series of Imaging Studies (OASIS) dataset. The UPenn and OASIS datasets were used as independent test sets to evaluate the model performance during inference. We also implemented a random forest classifier as a baseline model by extracting key radiomics features from the same T1-weighted MRI scans. The proposed 3D convolutional neural network (CNN) model was trained from scratch for the classification tasks. For AD classification, the 3D CNN model achieved an ROC-AUC of 0.878 on the ADNI test set and an average ROC-AUC of 0.789 on the OASIS dataset. For PD classification, the proposed 3D CNN model achieved an ROC-AUC of 0.667 on the PPMI test set and an average ROC-AUC of 0.743 on the UPenn dataset. Model performance was largely maintained when using only 25% of the training dataset. The 3D CNN outperformed the random forest classifier for both the PD and AD tasks. The 3D CNN also generalized better on unseen MRI data from different imaging centers. These approaches show promise for screening of PD and AD patients using only T1-weighted brain MRI, which is relatively widely available. This model with additional validation could also be used to help differentiate between challenging cases of AD and PD when they present with similarly subtle motor and non-motor symptoms.

bioinformatics↗

bioRxiv2021

Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization

Large data initiatives and high-powered brain imaging analyses require the pooling of MR images acquired across multiple scanners, often using different protocols. Prospective cross-site harmonization often involves the use of a phantom or traveling subjects. However, as more datasets are becoming publicly available, there is a growing need for retrospective harmonization, pooling data from sites not originally coordinated together. Several retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most unsupervised methods cannot distinguish between image-acquisition based variability and cross-site population variability, so they require that datasets contain subjects or patient groups with similar clinical or demographic information. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a reference image directly, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our styleencoding model can harmonize MR images, and match intensity profiles, successfully, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. Moreover, we further demonstrated that if we included diverse enough images into the training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies.

neuroscience↗

bioRxiv2020

The ENIGMA Toolbox: Cross-disorder integration and multiscale neural contextualization of multisite neuroimaging datasets

Among big data initiatives, the ENIGMA (Enhancing NeuroImaging Genetics through Meta-Analysis) Consortium--a worldwide alliance of over 2,000 scientists diversified into over 50 Working Groups--has yielded some of the largest studies of the healthy and diseased brain. Integration of multisite datasets to assess transdiagnostic similarities and differences and to contextualize findings with respect to neural organization, however, have been limited. Here, we introduce the ENIGMA Toolbox, a Python/Matlab ecosystem for (i) accessing 100+ ENIGMA datasets, facilitating cross-disorder analysis, (ii) visualizing data on brain surfaces, and (iii) contextualizing findings at the microscale (postmortem cytoarchitecture and gene expression) and macroscale (structural and functional connectomes). Our Toolbox equips scientists with tutorials to explore molecular, histological, and network correlates of noninvasive neuroimaging markers of brain disorders. Moreover, our Toolbox bridges the gap between standardized data processing protocols and analytic workflows and facilitates cross-consortia initiatives. The Toolbox is documented and openly available at http://enigma-toolbox.readthedocs.io. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=63 SRC="FIGDIR/small/423838v3_ufig1.gif" ALT="Figure 1"> View larger version (16K): org.highwire.dtl.DTLVardef@183a3f3org.highwire.dtl.DTLVardef@180d368org.highwire.dtl.DTLVardef@b752a3org.highwire.dtl.DTLVardef@1928c53_HPS_FORMAT_FIGEXP M_FIG C_FIG

neuroscience↗

bioRxiv2020

Accurate brain age prediction using recurrent slice-based networks

BrainAge (a subjects apparent age predicted from neuroimaging data) is an important biomarker of brain aging. The deviation of BrainAge from true age has been associated with psychiatric and neurological disease, and has proven effective in predicting conversion from mild cognitive impairment (MCI) to dementia. Conventionally, 3D convolutional neural networks and their variants are used for brain age prediction. However, these networks have a larger number of parameters and take longer to train than their 2D counterparts. Here we propose a 2D slice-based recurrent neural network model, which takes in an ordered sequence of sagittal slices as input to predict the brain age. The model consists of two components: a 2D convolutional neural network (CNN), which encodes the relevant features from the slices, and a recurrent neural network (RNN) that learns the relationship between slices. We compare our method to other recently proposed methods, including 3D deep convolutional regression networks, information theoretic models, and bag-of-features (BoF) models (such as BagNet) - where the classification is based on the occurrences of local features, without taking into consideration their global spatial ordering. In our experiments, our proposed model performs comparably to, or better than, the current state of the art models, with nearly half the number of parameters and a lower convergence time.

neuroscience↗

bioRxiv2020

Dynamics of Brain Structure and its Genetic Architecture over the Lifespan

Human brain structure changes throughout our lives. Altered brain growth or rates of decline are implicated in a vast range of psychiatric, developmental, and neurodegenerative diseases. Here, we identified common genetic variants that affect rates of brain growth or atrophy, in the first genome-wide association meta-analysis of changes in brain morphology across the lifespan. Longitudinal MRI data from 15,640 individuals were used to compute rates of change for 15 brain structures. The most robustly identified genes GPR139, DACH1 and APOE are associated with metabolic processes. We demonstrate global genetic overlap with depression, schizophrenia, cognitive functioning, insomnia, height, body mass index and smoking. Gene-set findings implicate both early brain development and neurodegenerative processes in the rates of brain changes. Identifying variants involved in structural brain changes may help to determine biological pathways underlying optimal and dysfunctional brain development and ageing.

genetics↗

bioRxiv2018

Diffusion MRI Indices and their Relation to Cognitive Impairment in Brain Aging: The updated multi-protocol approach in ADNI3

Brain imaging with diffusion-weighted MRI (dMRI) is sensitive to microstructural white matter changes associated with brain aging and neurodegeneration. In its third phase, the Alzheimers Disease Neuroimaging Initiative (ADNI3) is collecting data across multiple sites and scanners using different dMRI acquisition protocols, to better understand disease effects. It is vital to understand when data can be pooled across scanners, and how the choice of dMRI protocol affects the sensitivity of extracted measures to differences in clinical impairment. Here, we analyzed ADNI3 data from 317 participants (mean age: 75.4{+/-}7.9 years; 143 men/174 women), who were each scanned at one of 47 sites with one of six dMRI protocols using scanners from three different manufacturers. We computed four standard diffusion tensor imaging (DTI) indices including fractional anisotropy (FADTI) and mean, radial, and axial diffusivity, and one FA index based on the tensor distribution function (FATDF), in 24 bilaterally averaged white matter regions of interest. We found that protocol differences significantly affected dMRI indices, in particular FADTI. We ranked the diffusion indices for their strength of association with four clinical assessments. In addition to diagnosis, we evaluated cognitive impairment as indexed by three commonly used screening tools for detecting dementia and Alzheimers disease: the Alzheimers Disease Assessment Scale (ADAS-cog), the Mini-Mental State Examination (MMSE), and the Clinical Dementia Rating scale sum-of-boxes (CDR-sob). Using a nested random-effects model to account for protocol and site, we found that across all dMRI indices and clinical measures, the hippocampal-cingulum and fornix (crus) / stria terminalis regions most consistently showed strong associations with clinical impairment. Overall, the greatest effect sizes were detected in the hippocampal-cingulum and uncinate fasciculus for associations between axial or mean diffusivity and CDR-sob. FATDF detected robust widespread associations with clinical measures, while FADTI was the weakest of the five indices for detecting associations. Ultimately, we were able to successfully pool dMRI data from multiple acquisition protocols from ADNI3 and detect consistent and robust associations with clinical impairment and age.

neuroscience↗

bioRxiv2018

Altered cortical brain structure and increased risk for disease seen decades after perinatal exposure to maternal smoking: A study of 9,000 adults in the UK Biobank

Secondhand smoke exposure is a major public health risk that is especially harmful to the developing brain, but it is unclear if early exposure affects brain structure during middle age and older adulthood. Here we analyzed brain MRI data from the UK Biobank in a population-based sample of individuals (ages 44-80) who were exposed (n=2,510) or unexposed (n=6,079) to smoking around birth. We used robust statistical models, including quantile regressions, to test the effect of perinatal smoke exposure (PSE) on cortical surface area (SA), thickness, and subcortical volume. We hypothesized that PSE would be associated with cortical disruption in primary sensory areas compared to unexposed (PSE-) adults. After adjusting for multiple comparisons, SA was significantly lower in the pericalcarine (PCAL), inferior parietal (IPL), and regions of the temporal and frontal cortex of PSE+ adults; these abnormalities were associated with increased risk for several diseases, including circulatory and endocrine conditions. Sensitivity analyses conducted in a hold-out group of healthy participants (exposed, n=109, unexposed, n=315) replicated the effect of PSE on SA in the PCAL and IPL. Collectively our results show a negative, long term effect of PSE on sensory cortices that may increase risk for disease later in life.

neuroscience↗

bioRxiv2017

White matter differences in Parkinson’s disease mapped using tractometry

Neurodegenerative disorders are characterized by a progressive loss of brain function. Improved precision in mapping the altered brain pathways can provide a deep understanding of the trajectory of decline. We propose a tractometry workflow for conducting group statistical analyses of point-wise microstructural measures along white matter fasciculi to identify patterns of abnormalities associated with disease. We combined state-of-the-art tools including fiber registration, tract simplification and fiber matching for accurate point-wise statistical analyses across populations. We test the utility of this method by identifying group differences between Parkinsons disease (PD) patients and healthy controls. We find statistically significant group differences in diffusion MRI derived measures along the anterior thalamic radiations (ATR), corticospinal tract (CST) and regions of the corpus callosum (CC). These pathways are essential for motor control systems within cortico-cortical and cortico-subcortical brain networks. Moreover, the reported pathological changes were not widespread but rather localized along several tracts. Point-wise tract analyses may therefore offer an advantage in anatomical specificity over traditional methods that assess mean microstructural measures across large regions of interest.

neuroscience↗

bioRxiv2017

FiberNet 2.0: An Automatic Neural Network Based Tool for Clustering White Matter Fibers in the Brain

The brains white matter fiber tracts are impaired in a range of common and devastating conditions, from Alzheimers disease to brain trauma, and in developmental disorders such as autism and neurogenetic syndromes. Many studies now examine the connectivity and microstructure of the brains neural pathways, spurring the development of algorithms to extract and measure tracts and fiber bundles. Clustering white matter (WM) fibers, from whole-brain tractography, into anatomically meaningful bundles is still a challenging problem. Existing tract segmentation methods use atlases or regions of interest (ROI) or unsupervised spectral clustering. Even so, atlas-based segmentation does not always partition the brain into a set of recognizable fiber bundles. Deep learning techniques can be applied to automatically segment and cluster white matter fibers. Here we propose a robust approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which we then exploit to cluster WM fibers into bundles. In a range of tests across diverse fiber bundles, we illustrate the accuracy of our method, and its ability to suppress false positive fibers.

neuroscience↗

bioRxiv2017

FiberNET: An ensemble deep learning framework for clustering white matter fibers

White matter tracts are commonly analyzed in studies of micro-structural integrity and anatomical connectivity in the brain. Over the last decade, it has been an open problem as to how best to cluster white matter fibers, extracted from whole-brain tractography, into anatomically meaningful groups. Some existing techniques use region of interest (ROI) based clustering, atlas-based labeling, or unsupervised spectral clustering. ROI-based clustering is popular for analyzing anatomical connectivity among a set of ROIs, but it does not always partition the brain into recognizable fiber bundles. Here we propose an approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which are then exploited to cluster white matter fibers. To achieve such clustering, we first need to re-parameterize the fibers in an intrinsic space. The clustering is performed in induced parameterized coordinates. To our knowledge, this is one of the first approaches for fiber clustering using deep learning techniques. The results show strong accuracy - on a par with or better than other state-of-the-art methods.

bioinformatics↗