In teleost fish, female fecundity depends essentially on the oocyte reserve, which determines the number of eggs laid in each reproductive cycle. Unlike mammals, which have a limited and predefined stock of oocytes at birth, this reserve can be renewed throughout female's life. In adult teleost, this reserve is, on the one hand, used to generate mature oocytes ready to be laid and, on the other hand, replenished from germline stem cells present in specialized structures called germline cradles. A main issue is to understand the contribution of these germline stem cells in the renewal of the oocyte reserve in both juveniles and adults, as well as the involved regulatory mechanisms. To this end, we have implemented a 3D whole ovary imaging strategy in Medaka to provide quantitative data and study the cellular dynamics of the germinal cradle. We have refined ovary clearing protocols combined with immunolabelings (e.g., anti-vasa, anti-pH3, anti-GFP), and imaged the ovaries using light sheet microscopy. In addition, we have set up 3D image analysis pipelines that integrates pre-trained open-source neural networks suitable for precise segmentation. These deep-learning based pipelines have greatly improved our ability to manage complex 3D analysis of the germinal cradle and allow us to access quantitative data at the level of the entire ovary. We are now analyzing the number, the distribution and the composition of germinal cradles in wild-type females, as well as in two KO lines (miR-202 -/- and miR-187 -/-) showing a drastic decrease in female fecundity, to uncover the miRNA-mediated regulatory mechanisms. In the future, this approach should also provide us with the means to explore in depth the interactions between the somatic and germ cells within germinal cradles, including their spatial organisation.