Motivation: There is a need for normalisation for fetal volumetry studies and lack of normative growth models for placenta, amniotic fluid and whole fetus. Goal(s): Is is feasible to combine fetal, amniotic fluid and placenta segmentation into a combined pipeline for 3D fetal MRI with normative models? Approach: We used deep learning segmentation to process 145 normal control MRI datasets and generate growth models for 16 - 40 week GA. Results: We presented the first combined fetus, placenta and amniotic fluid growth models for motion corrected 3D 3T T2w fetal MRI during the 2nd and 3rd trimesters based on deep learning segmentations from 145 controls. Impact: These models and segmentation network could be potentially used in other research studies for normalisation of fetal organ volumetry.
Uus et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: