Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309079920> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4309079920 endingPage "109818" @default.
- W4309079920 startingPage "109818" @default.
- W4309079920 abstract "Medical image segmentation is one of the important steps in the computer-aided diagnosis of pancreas diseases. Although some models have been proposed to deal with the task of automatic pancreas segmentation, it is still challenging due to the small size, variable shape and unclear boundary of pancreas. In this paper, we propose a target-aware U-Net (tU-Net) using fuzzy skip connection for pancreas segmentation. Through adding a fuzzy skip connection module into the U-Net architecture, the low-level features can be transformed into the high-level semantic features, which facilitates the segmentation of small and changeable targets of pancreas. Based on the fuzzy feature mapping, we also design a target attention mechanism consists of global average pooling and depthwise convolution. It makes the decoder of the network more sensitive to target features by increasing weights of important channels. The proposed method is evaluated on the NIH dataset of 82 CT volumes, and the pancreas Medical Segmentation Decathlon (MSD) challenge dataset of 281 CT volumes. The proposed model achieves better results comparing with other state-of-the-art models. • Propose a target-aware U-Net for refined pancreas segmentation. • Design the fuzzy skip connection to obtain high-level semantics from the feature map. • Add target attention mechanism through combing global average pooling and depthwise convolution operations. • Experimental results on pancreas NIH dataset of 82 CT volumes and pancreas Medical Segmentation Decathlon (MSD) challenge dataset of 281 CT volumes validate the effectiveness of the proposed method." @default.
- W4309079920 created "2022-11-21" @default.
- W4309079920 creator A5042597849 @default.
- W4309079920 creator A5048884064 @default.
- W4309079920 creator A5058017510 @default.
- W4309079920 creator A5065952768 @default.
- W4309079920 creator A5069969191 @default.
- W4309079920 creator A5075095237 @default.
- W4309079920 date "2022-12-01" @default.
- W4309079920 modified "2023-09-30" @default.
- W4309079920 title "Target-aware U-Net with fuzzy skip connections for refined pancreas segmentation" @default.
- W4309079920 cites W2081282960 @default.
- W4309079920 cites W2163872389 @default.
- W4309079920 cites W2395611524 @default.
- W4309079920 cites W2417420127 @default.
- W4309079920 cites W2531409750 @default.
- W4309079920 cites W2560785110 @default.
- W4309079920 cites W2585890928 @default.
- W4309079920 cites W2767856675 @default.
- W4309079920 cites W2771252144 @default.
- W4309079920 cites W2789291564 @default.
- W4309079920 cites W2792834173 @default.
- W4309079920 cites W2804105936 @default.
- W4309079920 cites W2809020038 @default.
- W4309079920 cites W2888358068 @default.
- W4309079920 cites W2899570649 @default.
- W4309079920 cites W2901800437 @default.
- W4309079920 cites W2912574022 @default.
- W4309079920 cites W2923874213 @default.
- W4309079920 cites W2934195809 @default.
- W4309079920 cites W2955058313 @default.
- W4309079920 cites W2963392702 @default.
- W4309079920 cites W2963420686 @default.
- W4309079920 cites W2964307255 @default.
- W4309079920 cites W2985267475 @default.
- W4309079920 cites W2994879149 @default.
- W4309079920 cites W2999247481 @default.
- W4309079920 cites W3000100618 @default.
- W4309079920 cites W3002943723 @default.
- W4309079920 cites W3023640369 @default.
- W4309079920 cites W3043365685 @default.
- W4309079920 cites W3094669061 @default.
- W4309079920 cites W3108860939 @default.
- W4309079920 cites W3158290426 @default.
- W4309079920 cites W377632744 @default.
- W4309079920 doi "https://doi.org/10.1016/j.asoc.2022.109818" @default.
- W4309079920 hasPublicationYear "2022" @default.
- W4309079920 type Work @default.
- W4309079920 citedByCount "4" @default.
- W4309079920 countsByYear W43090799202023 @default.
- W4309079920 crossrefType "journal-article" @default.
- W4309079920 hasAuthorship W4309079920A5042597849 @default.
- W4309079920 hasAuthorship W4309079920A5048884064 @default.
- W4309079920 hasAuthorship W4309079920A5058017510 @default.
- W4309079920 hasAuthorship W4309079920A5065952768 @default.
- W4309079920 hasAuthorship W4309079920A5069969191 @default.
- W4309079920 hasAuthorship W4309079920A5075095237 @default.
- W4309079920 hasConcept C14166107 @default.
- W4309079920 hasConcept C154945302 @default.
- W4309079920 hasConcept C2524010 @default.
- W4309079920 hasConcept C33923547 @default.
- W4309079920 hasConcept C41008148 @default.
- W4309079920 hasConcept C58166 @default.
- W4309079920 hasConcept C89600930 @default.
- W4309079920 hasConceptScore W4309079920C14166107 @default.
- W4309079920 hasConceptScore W4309079920C154945302 @default.
- W4309079920 hasConceptScore W4309079920C2524010 @default.
- W4309079920 hasConceptScore W4309079920C33923547 @default.
- W4309079920 hasConceptScore W4309079920C41008148 @default.
- W4309079920 hasConceptScore W4309079920C58166 @default.
- W4309079920 hasConceptScore W4309079920C89600930 @default.
- W4309079920 hasLocation W43090799201 @default.
- W4309079920 hasOpenAccess W4309079920 @default.
- W4309079920 hasPrimaryLocation W43090799201 @default.
- W4309079920 hasRelatedWork W144883078 @default.
- W4309079920 hasRelatedWork W2005437358 @default.
- W4309079920 hasRelatedWork W2138214894 @default.
- W4309079920 hasRelatedWork W2358941527 @default.
- W4309079920 hasRelatedWork W2361006516 @default.
- W4309079920 hasRelatedWork W2394327295 @default.
- W4309079920 hasRelatedWork W2517104666 @default.
- W4309079920 hasRelatedWork W2532775738 @default.
- W4309079920 hasRelatedWork W2954384599 @default.
- W4309079920 hasRelatedWork W4385556756 @default.
- W4309079920 hasVolume "131" @default.
- W4309079920 isParatext "false" @default.
- W4309079920 isRetracted "false" @default.
- W4309079920 workType "article" @default.