Biology subjects

Dyrba, M.

Publications and source records attributed to Dyrba, M..

3 recordsLinked to original sources

bioRxiv2024

SMAS: Structural MRI-Based AD Score using Bayesian VAE

This study introduces the Structural MRI-based Alzheimers Disease Score (SMAS), a novel index intended to quantify Alzheimers Disease (AD)-related morphometric patterns using a deep learning Bayesian-supervised Variational Autoencoder (Bayesian-SVAE). SMAS index was constructed using baseline structural MRI data from the DELCODE study and evaluated longitudinally in two independent cohorts: DEL-CODE (n=415) and ADNI (n=190). Our findings indicate that SMAS has strong associations with cognitive performance (DELCODE: r=-0.83; ADNI: r=-0.62), age (DEL-CODE: r=0.50; ADNI: r=0.28), hippocampal volume (DEL-CODE: r=-0.44; ADNI: r=-0.66), and total grey matter volume (DELCODE: r=-0.42; ADNI: r=-0.47), suggesting its potential as a biomarker for AD-related brain atrophy. Moreover, our longitudinal studies suggest that SMAS may be useful for early identification and tracking of AD. The model demonstrated significant predictive accuracy in distinguishing cognitively healthy individuals from those with AD (DELCODE: AUC=0.971 at baseline, 0.833 at 36 months; ADNI: AUC=0.817 at baseline, improving to 0.903 at 24 months). Notably, over a 36-month period, SMAS index outperformed existing measures such as SPARE-AD and hippocampal volume. Relevance map analysis revealed significant morphological changes in key AD-related brain regions--including the hippocampus, posterior cingulate cortex, precuneus, and lateral parietal cortex--highlighting that SMAS is a sensitive and interpretable biomarker of brain atrophy, suitable for early AD detection and longitudinal monitoring of disease progression.

neuroscience↗

bioRxiv2022

Individualized Gaussian Process-based Prediction of Memory Performance and Biomarker Status in Ageing and Alzheimer's disease

Neuroimaging markers based on Magnetic Resonance Imaging (MRI) combined with various other measures (such as informative covariates, vascular risks, brain activity, neuropsychological test etc.,) might provide useful predictions of clinical outcomes during progression towards Alzheimers disease (AD). The Bayesian approach aims to provide a trade-off by employing relevant features combinations to build decision support systems in clinical settings where uncertainties are relevant. We tested the approach in the MRI data across 959 subjects, aged 59-89 years and 453 subjects with available neuropsychological test scores and CSF biomarker status (amyloid-beta (A{beta})42/40 & and phosphorylated tau (pTau)) from a large sample multi-centric observational cohort (DELCODE). In order to explore the beneficial combinations of information from different sources, we presented a MRI-based predictive modelling of memory performance and CSF biomarker status (positive or negative) in the healthy ageing group as well as subjects at risk of Alzheimers disease using a Gaussian process multikernel framework. Furthermore, we systematically evaluated predictive combinations of input feature sets and their model variations, i.e. (A) combinations of brain tissue classes and feature type (modulated vs. unmodulated), choices of filter size of smoothing (ranging from 0 to 15 mm full width at half maximum), and image resolution (1mm, 2mm, 4mm and 8mm); (B) incorporating demography and covariates (C) the impact of the size of the training data set (i.e., number of subjects); (D) the influence of reducing the dimensions of data and (E) choice of kernel types. Finally, the approach was tested to reveal individual cognitive scores at follow-up (up to 4 years) using the baseline features. The highest accuracy for memory performance prediction was obtained for a combination of neuroimaging markers, demographics, genetic information (ApoE4) and CSF-biomarkers explaining 57% of outcome variance in out of sample predictions. The best accuracy for A{beta}42/40 status classification was achieved for combination demographics, ApoE4 and memory score while usage of structural MRI improved the classification of individual patients pTau status.

neuroscience↗

bioRxiv2020

Regional radiomics similarity networks (R2SNs) in the human brain: reproducibility, small-world properties and a biological basis

BackgroundStructural covariance network (SCN) has been applied successfully to structural magnetic resonance imaging (MRI) study. However, most SCNs were constructed by the unitary marker, which was insensitive for the different disease phases. The aim of this study is to devise a novel regional radiomics similarity network (R2SN) that could provide more comprehensive information in morphological network analysis. MethodsRegional radiomics similarity network (R2SN) was constructed by computing the Pearson correlations between the radiomics features extracted from any pair of regions for each subject. We further assessed the small-world property of R2SN using the graph theory method, as well as the reproducibility in the different datasets and the reliability with test-retest analysis. The relationship between the R2SN and inter-regional co-expression of gene enriched was also explored, as well as the relationship with general intelligence. ResultsThe R2SN can be replicated in different datasets, also regardless of using different feature subsets. The R2SN showed high reliability with the test-retest analysis (ICC>0.7). Besides, the small-word property ({sigma}>2) and the high correlation with the gene expression (R=0.24, P<0.001) and the general intelligence was found by R2SN. ConclusionR2SN provides a novel, reliable, and biologically plausible method to understand human morphological covariance based on structural MRI. Impact StatementImaging biomarkers are the cornerstone of modern radiology, and the development of valid biomarkers is crucial for optimizing individualized prediction in neurological disorders like AD. Thus, the development of the data mining method from neuroimaging is crucial for adding the biomarkers of disease. This study confirmed that R2SN provides a novel, robust and biologically plausible model and a new perspective for understanding the human brain, therefore. Thus, the R2SN has great promise in further study.

neuroscience↗