Automatic hippocampal surface generation via 3D U-net and active shape modeling with hybrid particle swarm optimization
This work addresses the need for automated hippocampal surface generation in neuroimaging, offering a domain-specific solution that appears incremental by integrating existing methods like 3D U-net and active shape modeling with optimization.
The paper tackled the problem of automatically generating hippocampal surfaces from MRI scans by proposing a pipeline combining 3D U-net segmentation, active shape modeling, and hybrid particle swarm optimization, resulting in surfaces with high accuracy, correct anatomical topology, and sufficient smoothness.
In this paper, we proposed and validated a fully automatic pipeline for hippocampal surface generation via 3D U-net coupled with active shape modeling (ASM). Principally, the proposed pipeline consisted of three steps. In the beginning, for each magnetic resonance image, a 3D U-net was employed to obtain the automatic hippocampus segmentation at each hemisphere. Secondly, ASM was performed on a group of pre-obtained template surfaces to generate mean shape and shape variation parameters through principal component analysis. Ultimately, hybrid particle swarm optimization was utilized to search for the optimal shape variation parameters that best match the segmentation. The hippocampal surface was then generated from the mean shape and the shape variation parameters. The proposed pipeline was observed to provide hippocampal surfaces at both hemispheres with high accuracy, correct anatomical topology, and sufficient smoothness.