A5047848421- Functional Brain Connectivity Studies
- Mental Health Research Topics
- Health, Environment, Cognitive Aging
- Advanced Software Engineering Methodologies
- Mobile and Web Applications
- Machine Learning in Healthcare
- Model-Driven Software Engineering Techniques
- Advanced MRI Techniques and Applications
- Cell Image Analysis Techniques
- Tryptophan and brain disorders
- Electroconvulsive Therapy Studies
- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Machine Learning and Data Classification
- Advanced Neural Network Applications
- Treatment of Major Depression
- Genomics and Rare Diseases
- Machine Learning and Algorithms
- Green IT and Sustainability
- Cognitive Abilities and Testing
- Image Processing and 3D Reconstruction
- Computational Physics and Python Applications
- Single-cell and spatial transcriptomics
- Radiomics and Machine Learning in Medical Imaging
- Service-Oriented Architecture and Web Services
University of Münster
2015-2025
Identifying neurobiological differences between patients with major depressive disorder (MDD) and healthy individuals has been a mainstay of clinical neuroscience for decades. However, recent meta-analyses have raised concerns regarding the replicability relevance brain alterations in depression.
Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one the most prevalent and disabling disorders, major depressive disorder (MDD), no informative biomarkers have been identified.
A network-based quantification of brain aging uncovers and fixes a fundamental problem all previous approaches.
PHOTONAI is a high-level Python API designed to simplify and accelerate machine learning model development. It functions as unifying framework allowing the user easily access combine algorithms from different toolboxes into custom algorithm sequences. especially support iterative development process automates repetitive training, hyperparameter optimization evaluation tasks. Importantly, workflow ensures unbiased performance estimates while still fully customize analysis. extends existing...
Abstract Many therapeutic interventions in psychiatry can be viewed as attempts to influence the brain’s large-scale, dynamic network state transitions. Building on connectome-based graph analysis and control theory, Network Control Theory is emerging a powerful tool quantify controllability—i.e., of one brain region over others regarding If how controllability related mental health remains elusive. Here, from Diffusion Tensor Imaging data, we inferred structural connectivity calculated...
Objective Acute kidney injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients the intensive care units. The lack standardized and open-source tools for applying Kidney Disease Improving Global Outcomes (KDIGO) criteria time series, requires researchers implement classification algorithms their own which resource might impact study quality by introducing different interpretations edge cases. This project introduces pyAKI, an pipeline addressing...
Abstract Background We investigated associations of the brain age gap (BAG), difference between actual and estimated derived from MRI scans, with disease course over nine years in patients affective disorders a long-term prospective design. Methods At two time-points, we acquired T 1 -weighted images (mean [SD] follow-up period 8.98 [2.20] years) Major Depressive Disorder (MDD; N=32) Bipolar (BD; N=6) healthy controls (HC; N = 37) at sites (Dublin, Münster). Using prediction model trained on...
Practitioners consider the focus of Agile Software Development and Enterprise Architecture Management as divergent. Following this view, two questions arise are answered by paper: whether how agile methods such Scrum can be used to create architecture deliverables enterprise architects collaborate with software development teams. Based on expert interviews in a major German consultancy, railway company, an automotive OEM integration TOGAF ADM has been developed evaluated following Design...
Abstract Motivation The application of next-generation sequencing in research and particularly clinical routine requires valid variant calling results. However, evaluation several commonly used tools has pointed out that not a single tool meets this requirement. False positive as well false negative calls necessitate additional experiments extensive manual work. Intelligent combination output filtration different could significantly improve the current situation. Results We developed...
Electroconvulsive Therapy (ECT) is arguably the most effective intervention for treatment-resistant depression. While large interindividual variability exists, a theory capable of explaining individual response to ECT remains elusive. To address this, we posit quantitative, mechanistic framework based on Network Control Theory (NCT). Then, empirically test our approach and employ it predict treatment response. this end, derive formal association between Postictal Suppression Index (PSI)-an...
Flow cytometry is a widely used technique for identifying cell populations in patient-derived fluids, such as peripheral blood (PB) or cerebrospinal fluid (CSF). Despite its ubiquity research and clinical practice, the process of gating, i.e., manually types, labor-intensive error-prone. The objective this study to address challenge by introducing GateNet, neural network architecture designed fully end-to-end automated gating without need correcting batch effects.
Abstract Background Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one the most prevalent and disabling disorders, Major Depressive Disorder (MDD), patients only marginally differ from healthy individuals on group-level. Whether Precision Psychiatry can solve this discrepancy provide specific, reliable biomarkers remains unclear as current Machine Learning (ML) studies suffer shortcomings pertaining methods data, which...
Background Controllability is a measure of the brain’s ability to orchestrate neural activity which can be quantified in terms properties network connectivity. Evidence from literature suggests that aging exert general effect on whole-brain controllability. Mounting evidence, other hand, parenthood and motherhood particular lead long-lasting changes brain architecture effectively slow down aging. We hypothesize might preserve controllability Methods In sample 814 healthy individuals (aged...
Within software product lines (SPL) similar products are created based on common features. We applied this versatile approach to cross-platform app development by extending the domain-specific language (DSL) of an established model-driven framework. The goal was support formulation coherent building blocks business use cases, referred as workflow elements. While former implementation already abstracted from technical details and provided possibility reuse low level features, it now enables...
Abstract Introduction Statistical effect sizes are systematically overestimated in small samples, leading to poor generalizability and replicability of findings all areas research. Due the large number variables, this is particularly problematic neuroimaging While cross-validation frequently used multivariate machine learning approaches assess model replicability, benefits for mass-univariate brain analysis yet unclear. We investigated impact on size estimation univariate voxel-based...
Introduction A required step for presenting results of clinical studies is the declaration participants demographic and baseline characteristics as claimed by FDAAA 801. The common workflow to accomplish this task export data from used electronic capture system import it into statistical software like SAS or IBM SPSS. This requires trained users, who have implement analysis individually each item. These expenditures may become an obstacle small studies. Objective work design, evaluate open...
Model-driven development techniques have been proposed for cross-platform app development. Typically, an individual domain-specific language (DSL) is used. The MD <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> framework consists of a DSL business apps and generators, which transform domain model to native platform code. Prior research on it focused general generator design, this paper accentuates the code generation stage. A reference...