Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211483> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4387211483 endingPage "512" @default.
- W4387211483 startingPage "502" @default.
- W4387211483 abstract "3D Spatially Aligned Multi-modal MRI Brain Tumor Segmentation (SAMM-BTS) is a crucial task for clinical diagnosis. While Transformer-based models have shown outstanding success in this field due to their ability to model global features using the self-attention mechanism, they still face two challenges. First, due to the high computational complexity and deficiencies in modeling local features, the traditional self-attention mechanism is ill-suited for SAMM-BTS tasks that require modeling both global and local volumetric features within an acceptable computation overhead. Second, existing models only stack spatially aligned multi-modal data on the channel dimension, without any processing for such multi-channel data in the model’s internal design. To address these challenges, we propose a Transformer-based model for the SAMM-BTS task, namely DBTrans, with dual-branch architectures for both the encoder and decoder. Specifically, the encoder implements two parallel feature extraction branches, including a local branch based on Shifted Window Self-attention and a global branch based on Shuffle Window Cross-attention to capture both local and global information with linear computational complexity. Besides, we add an extra global branch based on Shifted Window Cross-attention to the decoder, introducing the key and value matrices from the corresponding encoder block, allowing the segmented target to access a more complete context during up-sampling. Furthermore, the above dual-branch designs in the encoder and decoder are both integrated with improved channel attention mechanisms to fully explore the contribution of features at different channels. Experimental results demonstrate the superiority of our DBTrans model in both qualitative and quantitative measures. Codes will be released at https://github.com/Aru321/DBTrans ." @default.
- W4387211483 created "2023-10-01" @default.
- W4387211483 creator A5003642180 @default.
- W4387211483 creator A5006002666 @default.
- W4387211483 creator A5019644052 @default.
- W4387211483 creator A5047734972 @default.
- W4387211483 creator A5049078993 @default.
- W4387211483 creator A5055483605 @default.
- W4387211483 date "2023-01-01" @default.
- W4387211483 modified "2023-10-17" @default.
- W4387211483 title "DBTrans: A Dual-Branch Vision Transformer for Multi-Modal Brain Tumor Segmentation" @default.
- W4387211483 cites W1641498739 @default.
- W4387211483 cites W1901129140 @default.
- W4387211483 cites W2063552084 @default.
- W4387211483 cites W2108556791 @default.
- W4387211483 cites W2464708700 @default.
- W4387211483 cites W2751069891 @default.
- W4387211483 cites W2752782242 @default.
- W4387211483 cites W2903356598 @default.
- W4387211483 cites W2962937599 @default.
- W4387211483 cites W2963125010 @default.
- W4387211483 cites W2979824959 @default.
- W4387211483 cites W3011743383 @default.
- W4387211483 cites W3112139896 @default.
- W4387211483 cites W3170841864 @default.
- W4387211483 cites W3199851300 @default.
- W4387211483 cites W3200891683 @default.
- W4387211483 cites W3203841574 @default.
- W4387211483 cites W4200341256 @default.
- W4387211483 cites W4205457781 @default.
- W4387211483 cites W4212875960 @default.
- W4387211483 cites W4226502176 @default.
- W4387211483 cites W4283743992 @default.
- W4387211483 cites W4286539657 @default.
- W4387211483 cites W4295940432 @default.
- W4387211483 cites W4296123084 @default.
- W4387211483 cites W4296196833 @default.
- W4387211483 cites W4312560592 @default.
- W4387211483 cites W4321232185 @default.
- W4387211483 cites W4360981268 @default.
- W4387211483 cites W4367320036 @default.
- W4387211483 cites W4378979679 @default.
- W4387211483 doi "https://doi.org/10.1007/978-3-031-43901-8_48" @default.
- W4387211483 hasPublicationYear "2023" @default.
- W4387211483 type Work @default.
- W4387211483 citedByCount "0" @default.
- W4387211483 crossrefType "book-chapter" @default.
- W4387211483 hasAuthorship W4387211483A5003642180 @default.
- W4387211483 hasAuthorship W4387211483A5006002666 @default.
- W4387211483 hasAuthorship W4387211483A5019644052 @default.
- W4387211483 hasAuthorship W4387211483A5047734972 @default.
- W4387211483 hasAuthorship W4387211483A5049078993 @default.
- W4387211483 hasAuthorship W4387211483A5055483605 @default.
- W4387211483 hasConcept C111919701 @default.
- W4387211483 hasConcept C118505674 @default.
- W4387211483 hasConcept C121332964 @default.
- W4387211483 hasConcept C154945302 @default.
- W4387211483 hasConcept C165801399 @default.
- W4387211483 hasConcept C41008148 @default.
- W4387211483 hasConcept C62520636 @default.
- W4387211483 hasConcept C66322947 @default.
- W4387211483 hasConcept C89600930 @default.
- W4387211483 hasConceptScore W4387211483C111919701 @default.
- W4387211483 hasConceptScore W4387211483C118505674 @default.
- W4387211483 hasConceptScore W4387211483C121332964 @default.
- W4387211483 hasConceptScore W4387211483C154945302 @default.
- W4387211483 hasConceptScore W4387211483C165801399 @default.
- W4387211483 hasConceptScore W4387211483C41008148 @default.
- W4387211483 hasConceptScore W4387211483C62520636 @default.
- W4387211483 hasConceptScore W4387211483C66322947 @default.
- W4387211483 hasConceptScore W4387211483C89600930 @default.
- W4387211483 hasLocation W43872114831 @default.
- W4387211483 hasOpenAccess W4387211483 @default.
- W4387211483 hasPrimaryLocation W43872114831 @default.
- W4387211483 hasRelatedWork W2005437358 @default.
- W4387211483 hasRelatedWork W2138214894 @default.
- W4387211483 hasRelatedWork W2275988210 @default.
- W4387211483 hasRelatedWork W2358941527 @default.
- W4387211483 hasRelatedWork W2361006516 @default.
- W4387211483 hasRelatedWork W2385621972 @default.
- W4387211483 hasRelatedWork W2589098947 @default.
- W4387211483 hasRelatedWork W2954384599 @default.
- W4387211483 hasRelatedWork W4231964008 @default.
- W4387211483 hasRelatedWork W4385556756 @default.
- W4387211483 isParatext "false" @default.
- W4387211483 isRetracted "false" @default.
- W4387211483 workType "book-chapter" @default.