Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948730003> ?p ?o ?g. }
- W2948730003 abstract "Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a redundant use of information, where similar low-level features are extracted multiple times at multiple scales. Second, long-range feature dependencies are not efficiently modeled, resulting in non-optimal discriminative feature representations associated with each semantic class. In this paper we attempt to overcome these limitations with the proposed architecture, by capturing richer contextual dependencies based on the use of guided self-attention mechanisms. This approach is able to integrate local features with their corresponding global dependencies, as well as highlight interdependent channel maps in an adaptive manner. Further, the additional loss between different modules guides the attention mechanisms to neglect irrelevant information and focus on more discriminant regions of the image by emphasizing relevant feature associations. We evaluate the proposed model in the context of semantic segmentation on three different datasets: abdominal organs, cardiovascular structures and brain tumors. A series of ablation experiments support the importance of these attention modules in the proposed architecture. In addition, compared to other state-of-the-art segmentation networks our model yields better segmentation performance, increasing the accuracy of the predictions while reducing the standard deviation. This demonstrates the efficiency of our approach to generate precise and reliable automatic segmentations of medical images. Our code is made publicly available at this https URL" @default.
- W2948730003 created "2019-06-14" @default.
- W2948730003 creator A5004770604 @default.
- W2948730003 creator A5091470378 @default.
- W2948730003 date "2019-06-07" @default.
- W2948730003 modified "2023-09-27" @default.
- W2948730003 title "Multi-scale self-guided attention for medical image segmentation" @default.
- W2948730003 cites W1156767201 @default.
- W2948730003 cites W1641498739 @default.
- W2948730003 cites W1817277359 @default.
- W2948730003 cites W1901129140 @default.
- W2948730003 cites W1903029394 @default.
- W2948730003 cites W1938976761 @default.
- W2948730003 cites W1948751323 @default.
- W2948730003 cites W1987291471 @default.
- W2948730003 cites W2039466015 @default.
- W2948730003 cites W2104276184 @default.
- W2948730003 cites W2110158442 @default.
- W2948730003 cites W2266059378 @default.
- W2948730003 cites W2412782625 @default.
- W2948730003 cites W2413794162 @default.
- W2948730003 cites W2526009326 @default.
- W2948730003 cites W2550553598 @default.
- W2948730003 cites W2560023338 @default.
- W2948730003 cites W2560645892 @default.
- W2948730003 cites W2563705555 @default.
- W2948730003 cites W2567599812 @default.
- W2948730003 cites W2592929672 @default.
- W2948730003 cites W2598666589 @default.
- W2948730003 cites W2751069891 @default.
- W2948730003 cites W2759084104 @default.
- W2948730003 cites W2799142782 @default.
- W2948730003 cites W2804047627 @default.
- W2948730003 cites W2821427990 @default.
- W2948730003 cites W2884555738 @default.
- W2948730003 cites W2885218528 @default.
- W2948730003 cites W2886934227 @default.
- W2948730003 cites W2888358068 @default.
- W2948730003 cites W2891451067 @default.
- W2948730003 cites W2891511539 @default.
- W2948730003 cites W2895340641 @default.
- W2948730003 cites W2903642350 @default.
- W2948730003 cites W2913629396 @default.
- W2948730003 cites W2913736247 @default.
- W2948730003 cites W2914410118 @default.
- W2948730003 cites W2950893734 @default.
- W2948730003 cites W2955058313 @default.
- W2948730003 cites W2962677366 @default.
- W2948730003 cites W2962781062 @default.
- W2948730003 cites W2962891704 @default.
- W2948730003 cites W2963091558 @default.
- W2948730003 cites W2963403868 @default.
- W2948730003 cites W2963495494 @default.
- W2948730003 cites W2963606038 @default.
- W2948730003 cites W2963606198 @default.
- W2948730003 cites W2963730812 @default.
- W2948730003 cites W2963840672 @default.
- W2948730003 cites W2963903399 @default.
- W2948730003 cites W2963954913 @default.
- W2948730003 cites W2964105113 @default.
- W2948730003 cites W2964227007 @default.
- W2948730003 cites W2964309882 @default.
- W2948730003 cites W2979777575 @default.
- W2948730003 cites W2997225633 @default.
- W2948730003 cites W3103805449 @default.
- W2948730003 cites W3104390926 @default.
- W2948730003 hasPublicationYear "2019" @default.
- W2948730003 type Work @default.
- W2948730003 sameAs 2948730003 @default.
- W2948730003 citedByCount "1" @default.
- W2948730003 countsByYear W29487300032020 @default.
- W2948730003 crossrefType "posted-content" @default.
- W2948730003 hasAuthorship W2948730003A5004770604 @default.
- W2948730003 hasAuthorship W2948730003A5091470378 @default.
- W2948730003 hasConcept C111919701 @default.
- W2948730003 hasConcept C118505674 @default.
- W2948730003 hasConcept C119857082 @default.
- W2948730003 hasConcept C120665830 @default.
- W2948730003 hasConcept C121332964 @default.
- W2948730003 hasConcept C138885662 @default.
- W2948730003 hasConcept C151730666 @default.
- W2948730003 hasConcept C153180895 @default.
- W2948730003 hasConcept C154945302 @default.
- W2948730003 hasConcept C177264268 @default.
- W2948730003 hasConcept C192209626 @default.
- W2948730003 hasConcept C199360897 @default.
- W2948730003 hasConcept C2776401178 @default.
- W2948730003 hasConcept C2776760102 @default.
- W2948730003 hasConcept C2779343474 @default.
- W2948730003 hasConcept C41008148 @default.
- W2948730003 hasConcept C41895202 @default.
- W2948730003 hasConcept C81363708 @default.
- W2948730003 hasConcept C86803240 @default.
- W2948730003 hasConcept C89600930 @default.
- W2948730003 hasConcept C97931131 @default.
- W2948730003 hasConceptScore W2948730003C111919701 @default.
- W2948730003 hasConceptScore W2948730003C118505674 @default.
- W2948730003 hasConceptScore W2948730003C119857082 @default.
- W2948730003 hasConceptScore W2948730003C120665830 @default.
- W2948730003 hasConceptScore W2948730003C121332964 @default.