World of Forms: Deformable geometric templates for one-shot surface meshing in coronary CT angiography.
Authors
Affiliations (9)
Affiliations (9)
- 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. Electronic address: [email protected].
- 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 Applied Mathematics, Technical Medical Centre, University of Twente, Drienerlolaan 5, Enschede, 7522 NB, The Netherlands.
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands.
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands.
- Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, USA.
- Amsterdam Cardiovascular Sciences, Amsterdam, The Netherlands.
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands; Department of Radiology, Mayo Clinic, Rochester, USA.
- 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 Radiology and Nuclear Medicine, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands.
Abstract
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.