Automatic Segmentation of Human Placenta from 3D Multimodal Ultrasound Data

Ultrasound is the most commonly used medical imaging modality for diagnosis and screening in clinical practice. Due to its safety profile, noninvasive nature and portability, ultrasound is the primary imaging modality for fetal assessment in pregnancy. Current ultrasound processing methods are either manual or semi-automatic and are therefore laborious, time-consuming and prone to errors, and automation would go a long way in addressing these challenges. In this work, we propose auto-matic three-dimensional multi-modal ultrasound segmentation of the human placenta using deep learning combined with different fusion strategies. We collected data containing B-mode and power Doppler ultrasound scans for 400 studies. We evaluated different fusion strategies and state-of-the-art image segmentation networks for placenta segmentation based on standard overlap- and boundary-based metrics. We found that multimodal information in the form of B-mode and power Doppler scans outperform any single modality. Furthermore, we found that B-mode and power Doppler input scans fused at the data level provide the best results with a mean Dice Similarity Coefficient (DSC) of 0.849. We conclude that the proposed methodology is effective in segmenting the placenta from 3D US scans in a fully automated manner and is robust to qauality variation of the datasets.