Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036371336> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3036371336 abstract "Pathological lymph node segmentation plays an important role in clinical practice. Yet it is still a challenging problem owing to low contrast to surrounding structures. In this paper, we take a deep learning based approach for pathological lymph node segmentation task. Semantic segmentation architecture, DeepLabv3+, which has the advantage to segment objects in a multi-scale way, is adopted in this paper. Meanwhile, the focal loss function, which originally applied in object detection task to deal with the imbalance class number, is integrated into DeepLabv3+ architecture for the imbalance of voxel class between pathological lymph nodes and background. Compared to the cross entropy loss function and dice function, the focal loss function can improve the segmentation performance in terms of sensitivity and dice in the DeepLabv3+ segmentation architecture. Four-fold cross validation has been done on 63 volumes containing 214 malignant lymph nodes and the mean sensitivity of 87% and average Dice score of 75% are obtained for pathological lymph node segmentation." @default.
- W3036371336 created "2020-06-25" @default.
- W3036371336 creator A5008017308 @default.
- W3036371336 creator A5017369879 @default.
- W3036371336 creator A5026804587 @default.
- W3036371336 creator A5033484584 @default.
- W3036371336 creator A5063619921 @default.
- W3036371336 creator A5080877727 @default.
- W3036371336 date "2020-04-23" @default.
- W3036371336 modified "2023-10-16" @default.
- W3036371336 title "Focal Loss Function based DeepLabv3+ for Pathological Lymph Node Segmentation on PET/CT" @default.
- W3036371336 cites W1871050032 @default.
- W3036371336 cites W1964162596 @default.
- W3036371336 cites W2008120479 @default.
- W3036371336 cites W2085370032 @default.
- W3036371336 cites W2101608218 @default.
- W3036371336 cites W2117539524 @default.
- W3036371336 cites W2228221433 @default.
- W3036371336 cites W2253429366 @default.
- W3036371336 cites W2412782625 @default.
- W3036371336 cites W2472322390 @default.
- W3036371336 cites W2734349601 @default.
- W3036371336 cites W2792305634 @default.
- W3036371336 cites W2963881378 @default.
- W3036371336 doi "https://doi.org/10.1145/3399637.3399651" @default.
- W3036371336 hasPublicationYear "2020" @default.
- W3036371336 type Work @default.
- W3036371336 sameAs 3036371336 @default.
- W3036371336 citedByCount "3" @default.
- W3036371336 countsByYear W30363713362020 @default.
- W3036371336 countsByYear W30363713362021 @default.
- W3036371336 countsByYear W30363713362022 @default.
- W3036371336 crossrefType "proceedings-article" @default.
- W3036371336 hasAuthorship W3036371336A5008017308 @default.
- W3036371336 hasAuthorship W3036371336A5017369879 @default.
- W3036371336 hasAuthorship W3036371336A5026804587 @default.
- W3036371336 hasAuthorship W3036371336A5033484584 @default.
- W3036371336 hasAuthorship W3036371336A5063619921 @default.
- W3036371336 hasAuthorship W3036371336A5080877727 @default.
- W3036371336 hasConcept C142724271 @default.
- W3036371336 hasConcept C154945302 @default.
- W3036371336 hasConcept C207886595 @default.
- W3036371336 hasConcept C22029948 @default.
- W3036371336 hasConcept C2524010 @default.
- W3036371336 hasConcept C2780849966 @default.
- W3036371336 hasConcept C31972630 @default.
- W3036371336 hasConcept C33923547 @default.
- W3036371336 hasConcept C41008148 @default.
- W3036371336 hasConcept C71924100 @default.
- W3036371336 hasConcept C89600930 @default.
- W3036371336 hasConceptScore W3036371336C142724271 @default.
- W3036371336 hasConceptScore W3036371336C154945302 @default.
- W3036371336 hasConceptScore W3036371336C207886595 @default.
- W3036371336 hasConceptScore W3036371336C22029948 @default.
- W3036371336 hasConceptScore W3036371336C2524010 @default.
- W3036371336 hasConceptScore W3036371336C2780849966 @default.
- W3036371336 hasConceptScore W3036371336C31972630 @default.
- W3036371336 hasConceptScore W3036371336C33923547 @default.
- W3036371336 hasConceptScore W3036371336C41008148 @default.
- W3036371336 hasConceptScore W3036371336C71924100 @default.
- W3036371336 hasConceptScore W3036371336C89600930 @default.
- W3036371336 hasLocation W30363713361 @default.
- W3036371336 hasOpenAccess W3036371336 @default.
- W3036371336 hasPrimaryLocation W30363713361 @default.
- W3036371336 hasRelatedWork W1669643531 @default.
- W3036371336 hasRelatedWork W2005437358 @default.
- W3036371336 hasRelatedWork W2008656436 @default.
- W3036371336 hasRelatedWork W2023558673 @default.
- W3036371336 hasRelatedWork W2039154422 @default.
- W3036371336 hasRelatedWork W2110230079 @default.
- W3036371336 hasRelatedWork W2122581818 @default.
- W3036371336 hasRelatedWork W2134924024 @default.
- W3036371336 hasRelatedWork W2517104666 @default.
- W3036371336 hasRelatedWork W2182382398 @default.
- W3036371336 isParatext "false" @default.
- W3036371336 isRetracted "false" @default.
- W3036371336 magId "3036371336" @default.
- W3036371336 workType "article" @default.