van Herten Rudolf L M, Lagogiannis Ioannis, Wolterink Jelmer M, Bruns Steffen, Meulendijks Eva R, Dey Damini, de Groot Joris R, Henriques José P, Planken R Nils, Saitta Simone, Išgum Ivana
Department of Biomedical Engineering and Physics, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands; Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands; Amsterdam Cardiovascular Sciences, Amsterdam, The Netherlands.
Department of Biomedical Engineering and Physics, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands; Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands; Amsterdam Cardiovascular Sciences, Amsterdam, The Netherlands.
Med Image Anal. 2025 Jul;103:103582. doi: 10.1016/j.media.2025.103582. Epub 2025 Apr 18.
Deep learning-based medical image segmentation and surface mesh generation typically involve a sequential pipeline from image to segmentation to meshes, often requiring large training datasets while making limited use of prior geometric knowledge. This may lead to topological inconsistencies and suboptimal performance in low-data regimes. To address these challenges, we propose a data-efficient deep learning method for direct 3D anatomical object surface meshing using geometric priors. Our approach employs a multi-resolution graph neural network that operates on a prior geometric template which is deformed to fit object boundaries of interest. We show how different templates may be used for the different surface meshing targets, and introduce a novel masked autoencoder pretraining strategy for 3D spherical data. The proposed method outperforms nnUNet in a one-shot setting for segmentation of the pericardium, left ventricle (LV) cavity and the LV myocardium. Similarly, the method outperforms other lumen segmentation operating on multi-planar reformatted images. Results further indicate that mesh quality is on par with or improves upon marching cubes post-processing of voxel mask predictions, while remaining flexible in the choice of mesh triangulation prior, thus paving the way for more accurate and topologically consistent 3D medical object surface meshing.
基于深度学习的医学图像分割和表面网格生成通常涉及从图像到分割再到网格的顺序管道，通常需要大量训练数据集，同时对先验几何知识的利用有限。这可能会导致在低数据情况下出现拓扑不一致和性能次优的问题。为应对这些挑战，我们提出一种数据高效的深度学习方法，用于利用几何先验直接进行三维解剖对象表面网格划分。我们的方法采用多分辨率图神经网络，该网络在一个先验几何模板上运行，该模板会变形以拟合感兴趣的对象边界。我们展示了如何将不同的模板用于不同的表面网格划分目标，并为三维球面数据引入了一种新颖的掩码自动编码器预训练策略。在一次性设置中，对于心包、左心室（LV）腔和LV心肌的分割，所提出的方法优于nnUNet。同样，该方法在对多平面重组图像进行的其他管腔分割中也表现出色。结果进一步表明，网格质量与体素掩码预测的移动立方体后处理相当或有所提高，同时在网格三角剖分先验的选择上保持灵活性，从而为更准确和拓扑一致的三维医学对象表面网格划分铺平了道路。
