Project Details
Description
Our unique research consortium is composed of excellent preclinical and clinical researchers, which guarantees
the chances of success of our neurotranslational research, with the aim of developing novel diagnostic and
therapeutic strategies for neurological, neurosurgical and mental disorders and better understand mechanisms of
cognition and behavior. Cognition is the central theme that unites all our preclinical and clinical expertise into a
transdisciplinary consortium. The clinical expertise (NEUR) is focused on neurological (like Alzheimer's disease,
multiple sclerosis, stroke), psychiatric (like depression) and neurosurgical disorders (like brain tumours) disorders
that affect cognition in its broadest sense. Research questions (like predicting cognitive decline) arise in daily
clinical practice and are translated to fit in the preclinical environment, where studying hypothesis-driven research
questions will lead to improved understanding of the pathophysiology of yet (largely) incurable brain disorders
(AIMS). These (pre)clinical and neuroscientific challenges create a need for multimodal non-linear modelling
(AIMS). As the scarcity of labelled cases and small datasets are a problem for the current most effective machine
learning technique, deep learning, transfer learning and data augmentation will be applied, using both
transformation algorithms and generative adversarial networks (GANs). Clinically relevant scientific results and
biomarkers (including druggable targets) will be back translated into clinical practice following the necessary
clinical (validation) studies (NEUR), which closes our neurotranslational loop
the chances of success of our neurotranslational research, with the aim of developing novel diagnostic and
therapeutic strategies for neurological, neurosurgical and mental disorders and better understand mechanisms of
cognition and behavior. Cognition is the central theme that unites all our preclinical and clinical expertise into a
transdisciplinary consortium. The clinical expertise (NEUR) is focused on neurological (like Alzheimer's disease,
multiple sclerosis, stroke), psychiatric (like depression) and neurosurgical disorders (like brain tumours) disorders
that affect cognition in its broadest sense. Research questions (like predicting cognitive decline) arise in daily
clinical practice and are translated to fit in the preclinical environment, where studying hypothesis-driven research
questions will lead to improved understanding of the pathophysiology of yet (largely) incurable brain disorders
(AIMS). These (pre)clinical and neuroscientific challenges create a need for multimodal non-linear modelling
(AIMS). As the scarcity of labelled cases and small datasets are a problem for the current most effective machine
learning technique, deep learning, transfer learning and data augmentation will be applied, using both
transformation algorithms and generative adversarial networks (GANs). Clinically relevant scientific results and
biomarkers (including druggable targets) will be back translated into clinical practice following the necessary
clinical (validation) studies (NEUR), which closes our neurotranslational loop
Acronym | IOF3021 |
---|---|
Status | Active |
Effective start/end date | 1/01/22 → 31/12/26 |
Keywords
- Artificial intelligence
- neurology
- neurosurgery
Flemish discipline codes in use since 2023
- Artificial intelligence not elsewhere classified
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.