| Title: | Exploring the relationship between body weight and cognitive functions across the lifespan using deep learning techniques |
| Lead Institution: | HUN-REN Research Centre for Natural Sciences |
| Principal investigator: | Dr Zoltan Vidnyanszky |
Application 27236
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Cognitive aging and obesity are major health concerns of the 21st century and have recently been the focus of extensive biomedical research. However, the relationship between body weight and brain/cognitive health across the adult lifespan remain largely unexplored. An emerging line of evidence suggests a complex interaction between aging and body mass index (BMI) such that high BMI is disruptive in young/middle aged adults but neuroprotective in older adults. We propose to investigate imaging, physiological, cognitive, and lifestyle characteristics to determine the interaction between body weight and aging on brain health. UK Biobank data resource provides a unique opportunity to identify individually predictive patterns of brain structure and function associated with aging and obesity. The expected results will clarify the intriguing relationship between body weight and brain health in adult development, an important step towards understanding successful cognitive aging. The proposed research therefore is in accordance with UK Biobank's stated purpose to support research projects intended to improve the prevention and diagnosis of illness and the promotion of health throughout society. We will analyse neuroimaging data together with the physiological and behavioural markers using deep neural networks to identify complex neuromarkers of brain health that are influenced by body weight and aging. To estimate the efficacy of the proposed deep learning algorithms the obtained results will be compared to those gained from traditional factor analysis and machine learning algorithms. The proposed data-driven approach involving deep neural networks to identify complex neuromarkers of brain health that are influenced by body weight and aging require data sets as large as possible. Therefore, we intend to analyse the full cohort for which brain imaging data is available to maximize the predictive power of our analysis.4 Publications
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 11476 | Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics | Pál Vakli (+10) | 2023 | Medical Image Analysis |
| 12576 | Effect of head motion-induced artefacts on the reliability of deep learning-based whole-brain segmentation | Péter Kemenczky (+6) | 2022 | Scientific Reports |
| 7637 | Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network | Pál Vakli (+3) | 2020 | Frontiers in Neuroinformatics |
| 12092 | The effect of head motion on brain age prediction using deep convolutional neural networks | Pál Vakli (+6) | 2024 | NeuroImage |
Enabling scientific discoveries that improve human health