The primary objective of this thesis is to develop a deep-learning-based pipeline for segmenting cell nuclei in three-dimensional, fluorescence microscopy image data of organoids without the existence of reference annotations. The textual part of the thesis must include a concise and comprehensive description of the developed pipeline and its quantitative evaluation focused on detection and segmentation accuracy, execution time, and memory consumption. The implementation of the developed pipeline will be delivered in an easy-to-use form and complemented with a practical guide that documents the exemplary usage of the developed pipeline.