Combining advanced 3D spheroid-based skin models with deep-learning-based image analysis enables in-depth investigation of keratinocyte differentiation and barrier function.

To date, organotypic skin models represent the gold standard for preclinical dermatological and toxicological studies. However, they are variable in quality and require long maturation times and many cells, mainly of primary origin. We propose dermal-epidermal spheroids as an alternative model that balances the physiological relevance and throughput. Alongside the corresponding full thickness skin models, three different fibroblast/keratinocyte coculture spheroids were generated. These studies used the commonly employed HaCaT cells as well as two recently immortalized keratinocyte cell lines, NHK-SV/TERT and NHK-E6/E7. To investigate their differentiation with detailed spatiotemporal resolution, a deep-learning segmentation-based pipeline capable of revealing nuclear morphology and positioning, as well as marker expression with single-cell precision, was developed and applied. Moreover, the formation of a functional barrier was assessed by live imaging of Lucifer Yellow diffusion. NHK-based coculture spheroids displayed strong evidence of functional maturation, including stratification and aspects of cornification and barrier formation, closely recapitulating the features of the corresponding full-thickness models. Furthermore, NHK-E6/E7 cells showed to be the most and HaCaT cells the least suitable alternative to primary keratinocytes in both spheroids and full thickness models. Given their scalability and compatibility with automation, micro-skin fibroblast/NHK-based 3D coculture spheroids might represent a promising new platform for pharmaceutical, cosmetic, and toxicological testing.