| Title: | Developing machine learning models of brain MRI for biomarker discovery of complex diseases. |
| Lead Institution: | Stanford University |
| Principal investigator: | Professor Olivier Gevaert |
Application 51998
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
The main goal of this project is to develop mathematical models from brain images by learning from UK biobank data using novel techniques in artificial intelligence. We will focus on two main application areas of these models: (1) prediction of genetic biomarkers and molecular properties of participants, and (2) prediction of onset of complex diseases for example Alzheimer disease. In the first case, prediction of molecular properties we will predict the following: we will use images and associate them with genetic variation. These genetic characteristics are different for different diseases, and we will investigate if brain images reflect any of these genetic changes both in healthy participants and when diseases occur. Secondly, we will test if this model can be used for the prediction of the onset of diseases and prediction of future diagnoses. If successful, this work can be used to improve diagnosis by catching diseases earlier.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 16611 | DUNE: a versatile neuroimaging encoder captures brain complexity across 3 major diseases: cancer, dementia, and schizophrenia | Thomas Barba (+6) | 2025 | GigaScience |
Enabling scientific discoveries that improve human health