Projects
Organoid painting: Unbiased cellular phenotyping of human tissue mimics using deep learning-enhanced imaging and analysis. University of Antwerp
Comprehensive phenotyping of neuro-organoids by deep learning. University of Antwerp
Deep phenotyping of cellular heterogeneity and maturation in human iPSC-derived brain organoids and cardiomyocytes. University of Antwerp
Data-driven image-based phenotyping and inferencing. KU Leuven
In the next five to twenty years, whole genome sequencing will become the standard of care in clinics. In parallel, imaging systems are improving in resolution and modalities for deep and longitudinal phenotyping. This presents new methodological challenges in image analysis, with uncharted high impact applications in personalized, preventive and precision medicine and cross-modal inferencing. My research program aims to substantially advance ...
Genetic predictors of joint shape and cartilage mechanics Ghent University
Recent genome wide association studies have revealed that several osteoarthritis (OA) risk loci involve common genetic variations related to musculoskeletal development and morphogenesis. To date, a major shortcoming, is that morphometric phenotyping is based on 2D superposition imaging, resulting in high noise levels and limited applicability. In this interdisciplinary project, DNA will be collected from patients undergoing CT scanning for ...
Data-driven search for 3D facial traits determined by major gene effects in health and disease KU Leuven
An integrated translational platform to improve the management and outcome of rare heritable connective tissue disease Ghent University
This interdisciplinary project aims to improve the outcome of heritable connective tissue disease. Using deep phenotyping techniques in combination with advanced genetic analysis, both in the clinic and in animal models, we expect to uncover molecular mechanisms which will inform better disease management strategies. In parallel, we aim to identify novel therapeutic targets using unbiased phenotypic screening in zebrafish models.
Digital pathology as a proxy for molecular profiling of prostate tumors Ghent University
Histological images (WSIs) of tumor samples are routinely available in pathology labs and reflect the physiological phenotype of tumor cells and their genomic aberrations. Deep learning techniques offer the potential to extract from these WSIs hidden morphological features that associate with molecular properties. WSIs thus contain a largely untapped source of valuable information on the molecular properties and their spatial organization. ...