LaB-GATr: geometric algebra transformers for large biomedical surface and volume meshes

arXiv:2403.07536v1 Announce Type: cross
Abstract: Many anatomical structures can be described by surface or volume meshes. Machine learning is a promising tool to extract information from these 3D models. However, high-fidelity meshes often contain hundreds of thousands of vertices, which creates unique challenges in building deep neural network architectures. Furthermore, patient-specific meshes may not be canonically aligned which limits the generalisation of machine learning algorithms. We propose LaB-GATr, a transfomer neural network with geometric tokenisation that can effectively learn with …

3d models abstract algebra architectures arxiv biomedical building challenges cs.cv cs.lg deep neural network extract fidelity however information lab machine machine learning meshes network neural network surface tool transformers type