Projects
The big LEAP forward: teLerehabilitation and E-heAlth in Physiotherapy. University of Antwerp
Comprehensive phenotyping of neuro-organoids by deep learning. University of Antwerp
SPeech ASSessment (SPASS) KU Leuven
The Macroeconomics of corporate Debt: Causes and Consequences of the corporate debt overhang. Ghent University
Firm leverage dynamics remain a blind spot of macroeconomics despite their impact on productivity and financial stability. This proposal investigates the role of banks’ sentiment in the structural rise in firm leverage in a corporate finance model with behavioural banks. It empirically tests the role of banks’ biases by offering a new way to measure banks’ optimism with artificial intelligence.
Ecosystem response to climate change: a machine learning approach KU Leuven
The response of ecosystems to climate change is one of the largest uncertainties in future climate projections as the response of ecosystems to disturbances (e.g. wildfire), anomalies and extremes (e.g. droughts, heatwaves,…) remains poorly quantified. Although the frequency and intensity of disturbances, anomalies and extremes are projected to continue to increase with climate change, the ecological impact across ecosystems remains a major ...
Approaching personalized oncology with DNA methylation inference and computational epigenomics KU Leuven
Epigenomic profiles have unspent capacity for diagnostic and prognostic oncological applications. I hypothesize that computational methods to understand the key dimensions shaping tumor epigenomes – cellular heterogeneity, genome-epigenome interplay, cancer cell-of-origin and non-genetic evolution – will provide crucial personalized insights into tumor microenvironment, expression of somatic mutations, cancer emergence and progression. ...
Code-switching in Neo-Latin literature during the early age of printing (ca. 1470–1550): Latin between Greek and the vernaculars in the multilingual Low Countries KU Leuven
My main aim is to conduct a meticulous analysis of the literary position of Neo-Latin in the multilingual landscape of Renaissance Europe during the first century of commercialized printing, taking the Low Countries as my case study. In this area, Neo-Latin got increasing competition from other languages as vehicles of literature, thought, and supra-regional communication, especially the vernaculars and Greek. What is more, speakers and ...
Multimodal imagiNg of rEtinal ManifestatiOns of Alzheimer’s diseaSe for earlY diagNosis and clinical rEsearch. KU Leuven
Deep Learning Enhanced Parametric 4D Total Body PET Imaging Ghent University
TB-PET provides tools to image dynamic radiopharmaceutical distribution in the whole body, simultaneously capturing the uptake in different organs. We aim to investigate the potential of DL for enhancing image quality of parametric maps generated from such 4D (3D + time) TB-PET studies. The goal is to apply DL for direct parametric map estimation in clinical and preclinical settings.