Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319792401> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4319792401 abstract "Convolutional neural networks (CNN) have been broadly studied on images, videos, graphs, and triangular meshes. However, it has seldom been studied on tetrahedral meshes. Given the merits of using volumetric meshes in applications like brain image analysis, we introduce a novel interpretable graph CNN framework for the tetrahedral mesh structure. Inspired by ChebyNet, our model exploits the volumetric Laplace-Beltrami Operator (LBO) to define filters over commonly used graph Laplacian which lacks the Riemannian metric information of 3D manifolds. For pooling adaptation, we introduce new objective functions for localized minimum cuts in the Graclus algorithm based on the LBO. We employ a piece-wise constant approximation scheme that uses the clustering assignment matrix to estimate the LBO on sampled meshes after each pooling. Finally, adapting the Gradient-weighted Class Activation Mapping algorithm for tetrahedral meshes, we use the obtained heatmaps to visualize discovered regions-of-interest as biomarkers. We demonstrate the effectiveness of our model on cortical tetrahedral meshes from patients with Alzheimer's disease, as there is scientific evidence showing the correlation of cortical thickness to neurodegenerative disease progression. Our results show the superiority of our LBO-based convolution layer and adapted pooling over the conventionally used unitary cortical thickness, graph Laplacian, and point cloud representation." @default.
- W4319792401 created "2023-02-11" @default.
- W4319792401 creator A5042072957 @default.
- W4319792401 creator A5056839802 @default.
- W4319792401 creator A5058590658 @default.
- W4319792401 creator A5069168079 @default.
- W4319792401 creator A5075584064 @default.
- W4319792401 date "2023-02-07" @default.
- W4319792401 modified "2023-09-26" @default.
- W4319792401 title "TetCNN: Convolutional Neural Networks on Tetrahedral Meshes" @default.
- W4319792401 doi "https://doi.org/10.48550/arxiv.2302.03830" @default.
- W4319792401 hasPublicationYear "2023" @default.
- W4319792401 type Work @default.
- W4319792401 citedByCount "0" @default.
- W4319792401 crossrefType "posted-content" @default.
- W4319792401 hasAuthorship W4319792401A5042072957 @default.
- W4319792401 hasAuthorship W4319792401A5056839802 @default.
- W4319792401 hasAuthorship W4319792401A5058590658 @default.
- W4319792401 hasAuthorship W4319792401A5069168079 @default.
- W4319792401 hasAuthorship W4319792401A5075584064 @default.
- W4319792401 hasBestOaLocation W43197924011 @default.
- W4319792401 hasConcept C105239961 @default.
- W4319792401 hasConcept C11413529 @default.
- W4319792401 hasConcept C118615104 @default.
- W4319792401 hasConcept C121684516 @default.
- W4319792401 hasConcept C132525143 @default.
- W4319792401 hasConcept C134306372 @default.
- W4319792401 hasConcept C153180895 @default.
- W4319792401 hasConcept C154945302 @default.
- W4319792401 hasConcept C165700671 @default.
- W4319792401 hasConcept C2524010 @default.
- W4319792401 hasConcept C31487907 @default.
- W4319792401 hasConcept C33923547 @default.
- W4319792401 hasConcept C41008148 @default.
- W4319792401 hasConcept C70437156 @default.
- W4319792401 hasConcept C74193536 @default.
- W4319792401 hasConcept C80444323 @default.
- W4319792401 hasConcept C81363708 @default.
- W4319792401 hasConceptScore W4319792401C105239961 @default.
- W4319792401 hasConceptScore W4319792401C11413529 @default.
- W4319792401 hasConceptScore W4319792401C118615104 @default.
- W4319792401 hasConceptScore W4319792401C121684516 @default.
- W4319792401 hasConceptScore W4319792401C132525143 @default.
- W4319792401 hasConceptScore W4319792401C134306372 @default.
- W4319792401 hasConceptScore W4319792401C153180895 @default.
- W4319792401 hasConceptScore W4319792401C154945302 @default.
- W4319792401 hasConceptScore W4319792401C165700671 @default.
- W4319792401 hasConceptScore W4319792401C2524010 @default.
- W4319792401 hasConceptScore W4319792401C31487907 @default.
- W4319792401 hasConceptScore W4319792401C33923547 @default.
- W4319792401 hasConceptScore W4319792401C41008148 @default.
- W4319792401 hasConceptScore W4319792401C70437156 @default.
- W4319792401 hasConceptScore W4319792401C74193536 @default.
- W4319792401 hasConceptScore W4319792401C80444323 @default.
- W4319792401 hasConceptScore W4319792401C81363708 @default.
- W4319792401 hasLocation W43197924011 @default.
- W4319792401 hasOpenAccess W4319792401 @default.
- W4319792401 hasPrimaryLocation W43197924011 @default.
- W4319792401 hasRelatedWork W2368694199 @default.
- W4319792401 hasRelatedWork W2424871898 @default.
- W4319792401 hasRelatedWork W2514274290 @default.
- W4319792401 hasRelatedWork W2517027266 @default.
- W4319792401 hasRelatedWork W2613736958 @default.
- W4319792401 hasRelatedWork W2758063741 @default.
- W4319792401 hasRelatedWork W2788663687 @default.
- W4319792401 hasRelatedWork W2792080776 @default.
- W4319792401 hasRelatedWork W2921836287 @default.
- W4319792401 hasRelatedWork W2969680539 @default.
- W4319792401 isParatext "false" @default.
- W4319792401 isRetracted "false" @default.
- W4319792401 workType "article" @default.