Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379660294> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4379660294 endingPage "834" @default.
- W4379660294 startingPage "822" @default.
- W4379660294 abstract "Automated surface segmentation is an important tool for utilizing medical image data in modern precision medicine for routine clinical practice and research. Deep-learning based methods have been developed for various medical image segmentation tasks. The inherent classification nature of those methods yet limits their capability of modeling global spatial dependency, which poses great challenges in incorporating geometric priors for segmentation, such as surface shape and surface smoothness, significantly compromising the accuracy and robustness of segmentation performance. To solve this problem, we propose integrating the graph-based optimal surface segmentation model into a new form of Convolutional Neural Networks (CNNs) that unifies the strengths of both deep learning and the graph segmentation model. To this end, we propose to parameterize the graph-based surface segmentation model and formulate the optimal surface segmentation as a quadratic programming problem, which admits an efficient inference for globally optimal solutions. The resulting network fully unifies graph segmentation modeling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm. Our experiments on two medical image segmentation applications demonstrated high performance of the proposed method with respect to segmentation accuracy, demands for annotated training data, and robustness to adversarial noise." @default.
- W4379660294 created "2023-06-08" @default.
- W4379660294 creator A5028613953 @default.
- W4379660294 creator A5040980527 @default.
- W4379660294 creator A5044520965 @default.
- W4379660294 creator A5046689699 @default.
- W4379660294 creator A5070673373 @default.
- W4379660294 date "2023-01-01" @default.
- W4379660294 modified "2023-10-16" @default.
- W4379660294 title "Model-Informed Deep Learning for Surface Segmentation in Medical Imaging" @default.
- W4379660294 cites W1901129140 @default.
- W4379660294 cites W1903029394 @default.
- W4379660294 cites W2001080026 @default.
- W4379660294 cites W2076087677 @default.
- W4379660294 cites W2083181574 @default.
- W4379660294 cites W2124592697 @default.
- W4379660294 cites W2164774194 @default.
- W4379660294 cites W2357815549 @default.
- W4379660294 cites W2473131906 @default.
- W4379660294 cites W2592929672 @default.
- W4379660294 cites W2737373222 @default.
- W4379660294 cites W2753582981 @default.
- W4379660294 cites W2753924563 @default.
- W4379660294 cites W2784226479 @default.
- W4379660294 cites W2792466349 @default.
- W4379660294 cites W2888905826 @default.
- W4379660294 cites W2913655562 @default.
- W4379660294 cites W2964097310 @default.
- W4379660294 cites W3112701542 @default.
- W4379660294 cites W4229706427 @default.
- W4379660294 doi "https://doi.org/10.1007/978-3-031-34048-2_63" @default.
- W4379660294 hasPublicationYear "2023" @default.
- W4379660294 type Work @default.
- W4379660294 citedByCount "0" @default.
- W4379660294 crossrefType "book-chapter" @default.
- W4379660294 hasAuthorship W4379660294A5028613953 @default.
- W4379660294 hasAuthorship W4379660294A5040980527 @default.
- W4379660294 hasAuthorship W4379660294A5044520965 @default.
- W4379660294 hasAuthorship W4379660294A5046689699 @default.
- W4379660294 hasAuthorship W4379660294A5070673373 @default.
- W4379660294 hasConcept C104317684 @default.
- W4379660294 hasConcept C108583219 @default.
- W4379660294 hasConcept C119857082 @default.
- W4379660294 hasConcept C124504099 @default.
- W4379660294 hasConcept C153180895 @default.
- W4379660294 hasConcept C154945302 @default.
- W4379660294 hasConcept C185592680 @default.
- W4379660294 hasConcept C25694479 @default.
- W4379660294 hasConcept C2776214188 @default.
- W4379660294 hasConcept C31972630 @default.
- W4379660294 hasConcept C41008148 @default.
- W4379660294 hasConcept C55493867 @default.
- W4379660294 hasConcept C63479239 @default.
- W4379660294 hasConcept C65885262 @default.
- W4379660294 hasConcept C81363708 @default.
- W4379660294 hasConcept C89600930 @default.
- W4379660294 hasConceptScore W4379660294C104317684 @default.
- W4379660294 hasConceptScore W4379660294C108583219 @default.
- W4379660294 hasConceptScore W4379660294C119857082 @default.
- W4379660294 hasConceptScore W4379660294C124504099 @default.
- W4379660294 hasConceptScore W4379660294C153180895 @default.
- W4379660294 hasConceptScore W4379660294C154945302 @default.
- W4379660294 hasConceptScore W4379660294C185592680 @default.
- W4379660294 hasConceptScore W4379660294C25694479 @default.
- W4379660294 hasConceptScore W4379660294C2776214188 @default.
- W4379660294 hasConceptScore W4379660294C31972630 @default.
- W4379660294 hasConceptScore W4379660294C41008148 @default.
- W4379660294 hasConceptScore W4379660294C55493867 @default.
- W4379660294 hasConceptScore W4379660294C63479239 @default.
- W4379660294 hasConceptScore W4379660294C65885262 @default.
- W4379660294 hasConceptScore W4379660294C81363708 @default.
- W4379660294 hasConceptScore W4379660294C89600930 @default.
- W4379660294 hasLocation W43796602941 @default.
- W4379660294 hasOpenAccess W4379660294 @default.
- W4379660294 hasPrimaryLocation W43796602941 @default.
- W4379660294 hasRelatedWork W1507266234 @default.
- W4379660294 hasRelatedWork W1669643531 @default.
- W4379660294 hasRelatedWork W2069711651 @default.
- W4379660294 hasRelatedWork W2117664411 @default.
- W4379660294 hasRelatedWork W2117933325 @default.
- W4379660294 hasRelatedWork W2549936415 @default.
- W4379660294 hasRelatedWork W2558375057 @default.
- W4379660294 hasRelatedWork W2739874619 @default.
- W4379660294 hasRelatedWork W2897195263 @default.
- W4379660294 hasRelatedWork W1967061043 @default.
- W4379660294 isParatext "false" @default.
- W4379660294 isRetracted "false" @default.
- W4379660294 workType "book-chapter" @default.