Automatic hippocampal surface generation via 3D U-net and active shape modeling with hybrid particle swarm optimization

TL;DR

This paper presents an automatic method combining 3D U-net, active shape modeling, and hybrid particle swarm optimization to generate accurate hippocampal surfaces from MRI images, ensuring high anatomical fidelity.

Contribution

The novel pipeline integrates deep learning, shape modeling, and optimization for automatic hippocampal surface reconstruction, improving accuracy and topology preservation.

Findings

High accuracy hippocampal surface generation

Correct anatomical topology achieved

Sufficient surface smoothness obtained

Abstract

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.