methodology Facial asymmetry We developed an automated pipeline for quantifying facial asymmetry from three-dimensional craniofacial images. Geometric deep learning AI-based facial endophenotypes were derived via geometric deep learning on facial mesh, and conventional statistical analysis can be applied to these endophenotypes, in scenarios of epidemiological or genetic studies. AI-based association analysis We developed a novel AI tool to overcome the interpretability and confounding issues in deep-learning-based association analysis. application Epidemiological studies Association between prenatal alcohol exposure and children’s facial shape Genetic studies A fully data-driven approach for genome-wide-association stuides (GWAS) with image-based phenotypes Survival analysis Predicting skin cancer risk from facial images with an explainable artificial intelligence (XAI) based approach. a proof-of-concept study vacancies Available project#1 for Master thesis 10-month master thesis project Available project#2 for Master thesis 10-month master thesis project
