Towards segmentation and spatial alignment of the human embryonic brain using deep learning for atlas-based registration
This work addresses the challenge of automated analysis of embryonic brain development in ultrasound, but it is incremental as it builds on existing atlas-based registration techniques.
The authors tackled the problem of segmenting and spatially aligning the human embryonic brain in 3D first trimester ultrasound by proposing an unsupervised deep learning method for atlas-based registration, which showed alignment in some cases on a dataset at 9 weeks gestational age.
We propose an unsupervised deep learning method for atlas based registration to achieve segmentation and spatial alignment of the embryonic brain in a single framework. Our approach consists of two sequential networks with a specifically designed loss function to address the challenges in 3D first trimester ultrasound. The first part learns the affine transformation and the second part learns the voxelwise nonrigid deformation between the target image and the atlas. We trained this network end-to-end and validated it against a ground truth on synthetic datasets designed to resemble the challenges present in 3D first trimester ultrasound. The method was tested on a dataset of human embryonic ultrasound volumes acquired at 9 weeks gestational age, which showed alignment of the brain in some cases and gave insight in open challenges for the proposed method. We conclude that our method is a promising approach towards fully automated spatial alignment and segmentation of embryonic brains in 3D ultrasound.