Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009170070> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3009170070 abstract "Deep neural networks yield promising results in a wide range of computer vision applications, including landmark detection. A major challenge for accurate anatomical landmark detection in volumetric images such as clinical CT scans is that large-scale data often constrain the capacity of the employed neural network architecture due to GPU memory limitations, which in turn can limit the precision of the output. We propose a multi-scale, end-to-end deep learning method that achieves fast and memory-efficient landmark detection in 3D images. Our architecture consists of blocks of shift-equivariant networks, each of which performs landmark detection at a different spatial scale. These blocks are connected from coarse to fine-scale, with differentiable resampling layers, so that all levels can be trained together. We also present a noise injection strategy that increases the robustness of the model and allows us to quantify uncertainty at test time. We evaluate our method for carotid artery bifurcations detection on 263 CT volumes and achieve a better than state-of-the-art accuracy with mean Euclidean distance error of 2.81mm." @default.
- W3009170070 created "2020-03-13" @default.
- W3009170070 creator A5015505861 @default.
- W3009170070 creator A5025877936 @default.
- W3009170070 creator A5059916379 @default.
- W3009170070 date "2020-03-03" @default.
- W3009170070 modified "2023-09-25" @default.
- W3009170070 title "Volumetric landmark detection with a multi-scale shift equivariant neural network" @default.
- W3009170070 cites W1573412753 @default.
- W3009170070 cites W1901129140 @default.
- W3009170070 cites W1976948919 @default.
- W3009170070 cites W2095705004 @default.
- W3009170070 cites W2135132101 @default.
- W3009170070 cites W2325168940 @default.
- W3009170070 cites W2399244897 @default.
- W3009170070 cites W2464708700 @default.
- W3009170070 cites W2525974879 @default.
- W3009170070 cites W2754156725 @default.
- W3009170070 cites W2797997321 @default.
- W3009170070 cites W2922479016 @default.
- W3009170070 cites W2950754204 @default.
- W3009170070 cites W2951655307 @default.
- W3009170070 cites W2963377935 @default.
- W3009170070 cites W2963881378 @default.
- W3009170070 cites W2964059111 @default.
- W3009170070 cites W3101998545 @default.
- W3009170070 hasPublicationYear "2020" @default.
- W3009170070 type Work @default.
- W3009170070 sameAs 3009170070 @default.
- W3009170070 citedByCount "0" @default.
- W3009170070 crossrefType "posted-content" @default.
- W3009170070 hasAuthorship W3009170070A5015505861 @default.
- W3009170070 hasAuthorship W3009170070A5025877936 @default.
- W3009170070 hasAuthorship W3009170070A5059916379 @default.
- W3009170070 hasConcept C104317684 @default.
- W3009170070 hasConcept C108583219 @default.
- W3009170070 hasConcept C150921843 @default.
- W3009170070 hasConcept C153180895 @default.
- W3009170070 hasConcept C154945302 @default.
- W3009170070 hasConcept C185592680 @default.
- W3009170070 hasConcept C205649164 @default.
- W3009170070 hasConcept C2778755073 @default.
- W3009170070 hasConcept C2780297707 @default.
- W3009170070 hasConcept C2984842247 @default.
- W3009170070 hasConcept C31972630 @default.
- W3009170070 hasConcept C41008148 @default.
- W3009170070 hasConcept C50644808 @default.
- W3009170070 hasConcept C55493867 @default.
- W3009170070 hasConcept C58640448 @default.
- W3009170070 hasConcept C63479239 @default.
- W3009170070 hasConceptScore W3009170070C104317684 @default.
- W3009170070 hasConceptScore W3009170070C108583219 @default.
- W3009170070 hasConceptScore W3009170070C150921843 @default.
- W3009170070 hasConceptScore W3009170070C153180895 @default.
- W3009170070 hasConceptScore W3009170070C154945302 @default.
- W3009170070 hasConceptScore W3009170070C185592680 @default.
- W3009170070 hasConceptScore W3009170070C205649164 @default.
- W3009170070 hasConceptScore W3009170070C2778755073 @default.
- W3009170070 hasConceptScore W3009170070C2780297707 @default.
- W3009170070 hasConceptScore W3009170070C2984842247 @default.
- W3009170070 hasConceptScore W3009170070C31972630 @default.
- W3009170070 hasConceptScore W3009170070C41008148 @default.
- W3009170070 hasConceptScore W3009170070C50644808 @default.
- W3009170070 hasConceptScore W3009170070C55493867 @default.
- W3009170070 hasConceptScore W3009170070C58640448 @default.
- W3009170070 hasConceptScore W3009170070C63479239 @default.
- W3009170070 hasLocation W30091700701 @default.
- W3009170070 hasOpenAccess W3009170070 @default.
- W3009170070 hasPrimaryLocation W30091700701 @default.
- W3009170070 hasRelatedWork W1556839878 @default.
- W3009170070 hasRelatedWork W2130735183 @default.
- W3009170070 hasRelatedWork W2260428369 @default.
- W3009170070 hasRelatedWork W2786069628 @default.
- W3009170070 hasRelatedWork W2804654955 @default.
- W3009170070 hasRelatedWork W2999981064 @default.
- W3009170070 hasRelatedWork W3010668292 @default.
- W3009170070 hasRelatedWork W3034478221 @default.
- W3009170070 hasRelatedWork W3044643673 @default.
- W3009170070 hasRelatedWork W3048839720 @default.
- W3009170070 hasRelatedWork W3104993299 @default.
- W3009170070 hasRelatedWork W3110517830 @default.
- W3009170070 hasRelatedWork W3114174666 @default.
- W3009170070 hasRelatedWork W3126655046 @default.
- W3009170070 hasRelatedWork W3150429754 @default.
- W3009170070 hasRelatedWork W3155223001 @default.
- W3009170070 hasRelatedWork W3157615508 @default.
- W3009170070 hasRelatedWork W3161606608 @default.
- W3009170070 hasRelatedWork W3162341349 @default.
- W3009170070 hasRelatedWork W3182891170 @default.
- W3009170070 isParatext "false" @default.
- W3009170070 isRetracted "false" @default.
- W3009170070 magId "3009170070" @default.
- W3009170070 workType "article" @default.