FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892010670> ?p ?o ?g. }

• W2892010670 endingPage "27" @default.
• W2892010670 startingPage "19" @default.
• W2892010670 abstract "Deep-learning based labeling methods have gained unprecedented popularity in different computer vision and medical image segmentation tasks. However, to the best of our knowledge, these have not been used for cervical tumor segmentation. More importantly, while the majority of innovative deep-learning works using convolutional neural networks (CNNs) focus on developing more sophisticated and robust architectures (e.g., ResNet, U-Net, GANs), there is very limited work on how to aggregate different CNN architectures to improve their relational learning at multiple levels of CNN-to-CNN interactions. To address this gap, we introduce a Dynamic Multi-Scale CNN Forest (CK+1DMF), which aims to address three major issues in medical image labeling and ensemble CNN learning: (1) heterogeneous distribution of MRI training patches, (2) a bi-directional flow of information between two consecutive CNNs as opposed to cascading CNNs—where information passes in a directional way from current to the next CNN in the cascade, and (3) multiscale anatomical variability across patients. To solve the first issue, we group training samples into K clusters, then design a forest with $$ (K + 1) $$ trees: a principal tree of CNNs trained using all data samples and subordinate trees, each trained using a cluster of samples. As for the second and third issues, we design each dynamic multiscale tree (DMT) in the forest such that each node in the tree nests a CNN architecture. Two successive CNN nodes in the tree pass bidirectional contextual maps to progressively improve the learning of their relational non-linear mapping. Besides, as we traverse a path from the root node to a leaf node in the tree, the architecture of each CNN node becomes shallower to take in smaller training patches. Our CK+1DMF significantly (p < 0.05) outperformed several conventional and ensemble CNN architectures, including conventional CNN (improvement by 10.3%) and CNN-based DMT (improvement by 5%)." @default.
• W2892010670 created "2018-09-27" @default.
• W2892010670 creator A5048784346 @default.
• W2892010670 creator A5050773373 @default.
• W2892010670 creator A5080274550 @default.
• W2892010670 creator A5081289542 @default.
• W2892010670 date "2018-01-01" @default.
• W2892010670 modified "2023-10-18" @default.
• W2892010670 title "Dynamic Multi-scale CNN Forest Learning for Automatic Cervical Cancer Segmentation" @default.
• W2892010670 cites W1884191083 @default.
• W2892010670 cites W2195092867 @default.
• W2892010670 cites W2344669114 @default.
• W2892010670 cites W2345003174 @default.
• W2892010670 cites W2476575773 @default.
• W2892010670 cites W2522924304 @default.
• W2892010670 cites W2586607563 @default.
• W2892010670 cites W2604630936 @default.
• W2892010670 cites W2607306668 @default.
• W2892010670 cites W2750807812 @default.
• W2892010670 cites W2803419071 @default.
• W2892010670 cites W2808341034 @default.
• W2892010670 cites W3023609596 @default.
• W2892010670 doi "https://doi.org/10.1007/978-3-030-00919-9_3" @default.
• W2892010670 hasPublicationYear "2018" @default.
• W2892010670 type Work @default.
• W2892010670 sameAs 2892010670 @default.
• W2892010670 citedByCount "7" @default.
• W2892010670 countsByYear W28920106702019 @default.
• W2892010670 countsByYear W28920106702020 @default.
• W2892010670 countsByYear W28920106702021 @default.
• W2892010670 countsByYear W28920106702023 @default.
• W2892010670 crossrefType "book-chapter" @default.
• W2892010670 hasAuthorship W2892010670A5048784346 @default.
• W2892010670 hasAuthorship W2892010670A5050773373 @default.
• W2892010670 hasAuthorship W2892010670A5080274550 @default.
• W2892010670 hasAuthorship W2892010670A5081289542 @default.
• W2892010670 hasBestOaLocation W28920106702 @default.
• W2892010670 hasConcept C108583219 @default.
• W2892010670 hasConcept C113174947 @default.
• W2892010670 hasConcept C119857082 @default.
• W2892010670 hasConcept C134306372 @default.
• W2892010670 hasConcept C153180895 @default.
• W2892010670 hasConcept C154945302 @default.
• W2892010670 hasConcept C2944601119 @default.
• W2892010670 hasConcept C33923547 @default.
• W2892010670 hasConcept C41008148 @default.
• W2892010670 hasConcept C81363708 @default.
• W2892010670 hasConcept C89600930 @default.
• W2892010670 hasConceptScore W2892010670C108583219 @default.
• W2892010670 hasConceptScore W2892010670C113174947 @default.
• W2892010670 hasConceptScore W2892010670C119857082 @default.
• W2892010670 hasConceptScore W2892010670C134306372 @default.
• W2892010670 hasConceptScore W2892010670C153180895 @default.
• W2892010670 hasConceptScore W2892010670C154945302 @default.
• W2892010670 hasConceptScore W2892010670C2944601119 @default.
• W2892010670 hasConceptScore W2892010670C33923547 @default.
• W2892010670 hasConceptScore W2892010670C41008148 @default.
• W2892010670 hasConceptScore W2892010670C81363708 @default.
• W2892010670 hasConceptScore W2892010670C89600930 @default.
• W2892010670 hasLocation W28920106701 @default.
• W2892010670 hasLocation W28920106702 @default.
• W2892010670 hasLocation W28920106703 @default.
• W2892010670 hasOpenAccess W2892010670 @default.
• W2892010670 hasPrimaryLocation W28920106701 @default.
• W2892010670 hasRelatedWork W2731899572 @default.
• W2892010670 hasRelatedWork W2915754718 @default.
• W2892010670 hasRelatedWork W2999805992 @default.
• W2892010670 hasRelatedWork W3091976719 @default.
• W2892010670 hasRelatedWork W3116150086 @default.
• W2892010670 hasRelatedWork W3133861977 @default.
• W2892010670 hasRelatedWork W4200173597 @default.
• W2892010670 hasRelatedWork W4312417841 @default.
• W2892010670 hasRelatedWork W4321369474 @default.
• W2892010670 hasRelatedWork W4380075502 @default.
• W2892010670 isParatext "false" @default.
• W2892010670 isRetracted "false" @default.
• W2892010670 magId "2892010670" @default.
• W2892010670 workType "book-chapter" @default.