Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090886985> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3090886985 endingPage "186" @default.
- W3090886985 startingPage "176" @default.
- W3090886985 abstract "3D features are desired in nature for segmenting CT volumes. It is, however, computationally expensive to employ a 3D convolutional neural network (CNN) to learn 3D features. Existing methods hence learn 3D features by still relying on 2D CNNs while attempting to consider more 2D slices, but up until now it is difficulty for them to consider the whole volumetric data, resulting in information loss and performance degradation. In this paper, we propose a simple and effective technique that allows a 2D CNN to learn 3D features for segmenting CT volumes. Our key insight is that all boundary voxels of a 3D object form a surface that can be represented by using a 2D matrix, and therefore they can be perfectly recognized by a 2D CNN in theory. We hence learn 3D features for recognizing these boundary voxels by learning the projection distance between a set of prescribed spherical surfaces and the object’s surface, which can be readily performed by a 2D CNN. By doing so, we can consider the whole volumetric data when spherical surfaces are sampled sufficiently dense, without any information loss. We assessed the proposed method on a publicly available dataset. The experimental evidence shows that the proposed method is effective, outperforming existing methods." @default.
- W3090886985 created "2020-10-08" @default.
- W3090886985 creator A5001212991 @default.
- W3090886985 creator A5015603911 @default.
- W3090886985 creator A5031202827 @default.
- W3090886985 creator A5048680068 @default.
- W3090886985 creator A5050189914 @default.
- W3090886985 creator A5056762119 @default.
- W3090886985 creator A5091806934 @default.
- W3090886985 date "2020-01-01" @default.
- W3090886985 modified "2023-10-16" @default.
- W3090886985 title "Learning 3D Features with 2D CNNs via Surface Projection for CT Volume Segmentation" @default.
- W3090886985 cites W1901129140 @default.
- W3090886985 cites W2083927153 @default.
- W3090886985 cites W2124592697 @default.
- W3090886985 cites W2148347694 @default.
- W3090886985 cites W2413073178 @default.
- W3090886985 cites W2464708700 @default.
- W3090886985 cites W2489292218 @default.
- W3090886985 cites W2526009326 @default.
- W3090886985 cites W2791680898 @default.
- W3090886985 cites W2799142782 @default.
- W3090886985 cites W2803537647 @default.
- W3090886985 cites W2805381319 @default.
- W3090886985 cites W2891994532 @default.
- W3090886985 cites W2903814341 @default.
- W3090886985 cites W2912989244 @default.
- W3090886985 cites W2963683318 @default.
- W3090886985 cites W2964227007 @default.
- W3090886985 cites W3100612776 @default.
- W3090886985 cites W3101756320 @default.
- W3090886985 cites W855272188 @default.
- W3090886985 doi "https://doi.org/10.1007/978-3-030-59719-1_18" @default.
- W3090886985 hasPublicationYear "2020" @default.
- W3090886985 type Work @default.
- W3090886985 sameAs 3090886985 @default.
- W3090886985 citedByCount "4" @default.
- W3090886985 countsByYear W30908869852021 @default.
- W3090886985 countsByYear W30908869852022 @default.
- W3090886985 crossrefType "book-chapter" @default.
- W3090886985 hasAuthorship W3090886985A5001212991 @default.
- W3090886985 hasAuthorship W3090886985A5015603911 @default.
- W3090886985 hasAuthorship W3090886985A5031202827 @default.
- W3090886985 hasAuthorship W3090886985A5048680068 @default.
- W3090886985 hasAuthorship W3090886985A5050189914 @default.
- W3090886985 hasAuthorship W3090886985A5056762119 @default.
- W3090886985 hasAuthorship W3090886985A5091806934 @default.
- W3090886985 hasConcept C11413529 @default.
- W3090886985 hasConcept C121332964 @default.
- W3090886985 hasConcept C121684516 @default.
- W3090886985 hasConcept C153180895 @default.
- W3090886985 hasConcept C154945302 @default.
- W3090886985 hasConcept C20556612 @default.
- W3090886985 hasConcept C2524010 @default.
- W3090886985 hasConcept C2776799497 @default.
- W3090886985 hasConcept C31972630 @default.
- W3090886985 hasConcept C33923547 @default.
- W3090886985 hasConcept C41008148 @default.
- W3090886985 hasConcept C57493831 @default.
- W3090886985 hasConcept C62520636 @default.
- W3090886985 hasConcept C89600930 @default.
- W3090886985 hasConceptScore W3090886985C11413529 @default.
- W3090886985 hasConceptScore W3090886985C121332964 @default.
- W3090886985 hasConceptScore W3090886985C121684516 @default.
- W3090886985 hasConceptScore W3090886985C153180895 @default.
- W3090886985 hasConceptScore W3090886985C154945302 @default.
- W3090886985 hasConceptScore W3090886985C20556612 @default.
- W3090886985 hasConceptScore W3090886985C2524010 @default.
- W3090886985 hasConceptScore W3090886985C2776799497 @default.
- W3090886985 hasConceptScore W3090886985C31972630 @default.
- W3090886985 hasConceptScore W3090886985C33923547 @default.
- W3090886985 hasConceptScore W3090886985C41008148 @default.
- W3090886985 hasConceptScore W3090886985C57493831 @default.
- W3090886985 hasConceptScore W3090886985C62520636 @default.
- W3090886985 hasConceptScore W3090886985C89600930 @default.
- W3090886985 hasLocation W30908869851 @default.
- W3090886985 hasOpenAccess W3090886985 @default.
- W3090886985 hasPrimaryLocation W30908869851 @default.
- W3090886985 hasRelatedWork W1669643531 @default.
- W3090886985 hasRelatedWork W2005437358 @default.
- W3090886985 hasRelatedWork W2008656436 @default.
- W3090886985 hasRelatedWork W2023558673 @default.
- W3090886985 hasRelatedWork W2039154422 @default.
- W3090886985 hasRelatedWork W2122581818 @default.
- W3090886985 hasRelatedWork W2134924024 @default.
- W3090886985 hasRelatedWork W2517104666 @default.
- W3090886985 hasRelatedWork W2895616727 @default.
- W3090886985 hasRelatedWork W2182382398 @default.
- W3090886985 isParatext "false" @default.
- W3090886985 isRetracted "false" @default.
- W3090886985 magId "3090886985" @default.
- W3090886985 workType "book-chapter" @default.