Neuroimaging biomarkers for major depressive disorder: current problems and future directions

Major depressive disorder, regularly known as depression, is the most common mental health disorder worldwide and is one of the leading contributors to the global burden of disease. Both the prevalence and incidence of major depressive disorder are increasing, showing the need for novel diagnosis and treatment options. In recent years the combination of neuroimaging (EEG and fMRI) and machine learning has been proposed as a solution for this problem, and while initial results show much promise no significant breaktrough has been found yet. This project will firstly investigate the underlying problems in the current approach to machine learning-based diagnosis of depression and secondly propose new methods to combat these problems. This project is a collaboration between the MEDISIP and Ghent Experimental Psychiatry (GHEP) research groups at Ghent University.

Fig 1: Analysis steps of this project. (Adapted from: fMRI preprocessing - What are the steps for preprocessing fMRI data? link: https://mriquestions.com/data-pre-processing.html; Joshi, A et al. (2017), ‘A Whole Brain Atlas with Sub-parcellation of Cortical Gyri using Resting fMRI’, SPIE Medical Imaging, 101330O-101330O-9.; Leitgeb, E. P., et al. (2020). The brain as a complex network: assessment of EEG‐based functional connectivity patterns in patients with childhood absence epilepsy. Epileptic Disorders, 22(5), 519-530.)

Contact: Gert Vanhollebeke