The last decade has seen rapid development in the use of computational techniques at bulk tissue and single‐cell level. However, our knowledge remains limited in this regard, and further progress is needed, especially in degenerative and inflammatory diseases. Controlling, modeling, or predicting cellular phenotype in this context using artificial intelligence (AI) will greatly improve the available in vitro, in situ, in vivo, and in silico methods, but also aid in the understanding of disease pathology and therapeutic efficiency. These methods not only have ramifications for our pathophysiological understanding of tissue function but are also important for advancing AI methods in cell culture, tissue explants, or in vivo to assess characteristics of single cells, cell populations, and tissues to predict function. Prof. Rolauffs aims to advance bio-image and data analysis machine learning for image-based cell phenotyping that can support and automate experimental decisions, even before performing downstream biological interpretation, and to identify disease-related phenotypes or cell signatures to determine or predict events relevant to cell or tissue function, disease onset, progression, and diagnosis.