Analyses of AI-generated hippocampal shape deformations in relation to cognition in healthy older adults – Data and Code

Magnetic resonance imaging (MRI)-derived hippocampus measurements have been associated with different cognitive domains. Different morphological hippocampal shape analysis methods have been developed, but it is unclear how their principles relate and how consistent are the published results in relation to cognition in the normal elderly in the light of the new deep-learning-based state-of-the-art modelling methods. We compared results from analysing the hippocampal morphology using manually-generated binary masks and a Laplacian- based deformation shape analysis method, with those resulting from analysing SynthSeg-generated hippocampal binary masks using a deep-learning method based on the PointNet architecture, in relation to different cognitive domains, using data from The Lothian Birth Cohort 1936. Here we provide the MATLAB code used to analyse the deformations generated by the two shape deformation modelling methods, and validate and compare the results. We also provide the files with the deformity vectors for each hippocampal mesh point, and the average template meshes used in the analyses, as well as all the results from the statistical analyses.

磁共振成像（Magnetic resonance imaging, MRI）衍生的海马体测量值与不同认知域相关联。目前已开发出多种海马体形态学形状分析方法，但在基于深度学习的最新建模方法背景下，这些方法的原理如何关联，以及已发表的关于正常老年人认知功能的研究结果一致性如何，尚不清楚。我们利用 Lothian 1936 出生队列的数据，比较了两种方法的分析结果：一种是使用手动生成的二值掩码（binary mask）和基于拉普拉斯（Laplacian）的形变形状分析方法对海马体形态进行分析的结果；另一种是使用 SynthSeg 生成的海马体二值掩码，通过基于PointNet（PointNet）架构的深度学习方法进行分析的结果，两者均针对不同认知域展开。本文提供了用于分析两种形状形变建模方法生成的形变数据、验证并比较结果的 MATLAB 代码。此外，我们还提供了包含每个海马体网格点形变向量的文件、分析中使用的平均模板网格，以及所有统计分析结果。