The fetal cortical plate undergoes drastic morphological changes throughout\nearly in utero development that can be observed using magnetic resonance (MR)\nimaging. An accurate MR image segmentation, and more importantly a\ntopologically correct delineation of the cortical gray matter, is a key\nbaseline to perform further quantitative analysis of brain development. In this\npaper, we propose for the first time the integration of a topological\nconstraint, as an additional loss function, to enhance the morphological\nconsistency of a deep learning-based segmentation of the fetal cortical plate.\nWe quantitatively evaluate our method on 18 fetal brain atlases ranging from 21\nto 38 weeks of gestation, showing the significant benefits of our method\nthrough all gestational ages as compared to a baseline method. Furthermore,\nqualitative evaluation by three different experts on 130 randomly selected\nslices from 26 clinical MRIs evidences the out-performance of our method\nindependently of the MR reconstruction quality.\n