Automatic 3D Multi-modal Ultrasound Segmentation of Human Placenta using Fusion Strategies and Deep Learning

The placenta has roles in fetal growth and development, oxygenation and nutrition, synthesising vital substances for pregnancy maintenance, including estrogen, progesterone, cytokines, and growth factors, and acting as a barrier against pathogens and drugs. Placental dysfunction is a leading cause of perinatal morbidity and mortality, including fetal growth restriction (FGR), pre-eclampsia, and stillbirth [1]. The in vivo assessment of placenta across gestation is critical to understand placental structure, function, and development and to identify strategies to optimise pregnancy outcome [2]. The primary modality for placental evaluation is two-dimensional (2D) ultrasound (US), which is non-invasive, inexpensive and more easily acceptable and accessible than other imaging modalities such as X-ray or Magnetic Resonance Imaging (MRI). It may be used to characterize location, shape, and volume of the placenta along with its interface with the endometrium and myometrium. Three-dimensional Power Doppler (PD) ultrasound permits direct visualisation of multi-directional placental vascularity, allowing assessment of both the uteroplacental and fetoplacental circulations, providing dynamic assessment of blood flow for imaging of abnormalities of the placenta. In three-dimensional (3D) ultrasound, a process called semantic segmentation could be used to separate the placenta for qualitative and quantitative analysis. Placenta segmentation is challenging because of its geometry, position, and appearance as the shape and location of placentas vary greatly across subjects [3] and fetal position can lead to shadowing artefacts. Determination of the placental boundary in relation to the uterine tissue is also challenging due to similar appearances [4], irregularity of boundary and changing size and shape with gestation, posing problems for segmentation [5]. Figure 1 shows 3D ultrasound providing placental visualisation in axial, coronal, and sagittal Springer Nature 2021 L