Deep learning with ultrasound physics for fetal skull segmentation

2D ultrasound (US) is still the preferred imaging method for fetal screening. However, 2D biometrics are significantly affected by the inter/intra-observer variability and operator dependence of a traditionally manual procedure. 3DUS is an alternative emerging modality with the potential to alleviate many of these problems. This paper presents a new automatic framework for skull segmentation in fetal 3DUS. We propose a two-stage convolutional neural network (CNN) able to incorporate additional contextual and structural information into the segmentation process. In the first stage of the CNN, a partial reconstruction of the skull is obtained, segmenting only those regions visible in the original US volume. From this initial segmentation, two additional channels of information are computed inspired by the underlying physics of US image acquisition: an angle incidence map and a shadow casting map. These additional information channels are combined in the second stage of the CNN to provide a complete segmentation of the skull, able to compensate for the fading and shadowing artefacts observed in the original US image. The performance of the new segmentation architecture was evaluated on a dataset of 66 cases, obtaining an average Dice coefficient of 0.83 ± 0.06. Finally, we also evaluated the clinical potential of the new 3DUS-based analysis framework for the assessment of cranial deformation, significantly outperforming traditional 2D biometrics (100% vs. 50% specificity, respectively).