Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386352912> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4386352912 abstract "Vascular segmentation in ultrasound (US) images faces labor-intensive labeling procedures and performance degradation due to unsatisfied image quality. Herein, we propose to use the Doppler image for vascular segmentation with an incremental Transformer structure. First, local features within the image patch are extracted by a convolutional neural network (CNN) patch embedding layer and further encoded by a multi-level Transformer to enhance the global dependencies from coarse to fine. A multi-level CNN decoder is introduced to decode corresponding features. Doppler imaging is capable of blood visualization and indicating the positional and structural information used as the pseudo label. A conditional random field (CRF) module and shape similarity loss function are introduced to improve the effectiveness of the Doppler images. The segmentation accuracy of the radial artery and carotid artery datasets can achieve 78.8% and 81.9% in Dice, with 63.5% and 53.7% accuracy in noisy labels. In addition, the framework can be generalized to unseen data without related Doppler images." @default.
- W4386352912 created "2023-09-02" @default.
- W4386352912 creator A5015237423 @default.
- W4386352912 creator A5018740222 @default.
- W4386352912 creator A5031766048 @default.
- W4386352912 creator A5043060463 @default.
- W4386352912 creator A5063883351 @default.
- W4386352912 date "2023-04-18" @default.
- W4386352912 modified "2023-09-27" @default.
- W4386352912 title "Doppler Image-Based Weakly-Supervised Vascular Ultrasound Segmentation with Transformer" @default.
- W4386352912 cites W1903029394 @default.
- W4386352912 cites W2128515940 @default.
- W4386352912 cites W2306289963 @default.
- W4386352912 cites W2551562422 @default.
- W4386352912 cites W2963379688 @default.
- W4386352912 cites W3001375391 @default.
- W4386352912 cites W3033272814 @default.
- W4386352912 cites W3091852692 @default.
- W4386352912 cites W3102564565 @default.
- W4386352912 cites W3118177885 @default.
- W4386352912 cites W3168442001 @default.
- W4386352912 cites W3202524699 @default.
- W4386352912 cites W3216325881 @default.
- W4386352912 cites W4214654781 @default.
- W4386352912 cites W4214893857 @default.
- W4386352912 cites W4224991290 @default.
- W4386352912 cites W4283320059 @default.
- W4386352912 cites W4313153210 @default.
- W4386352912 doi "https://doi.org/10.1109/isbi53787.2023.10230548" @default.
- W4386352912 hasPublicationYear "2023" @default.
- W4386352912 type Work @default.
- W4386352912 citedByCount "0" @default.
- W4386352912 crossrefType "proceedings-article" @default.
- W4386352912 hasAuthorship W4386352912A5015237423 @default.
- W4386352912 hasAuthorship W4386352912A5018740222 @default.
- W4386352912 hasAuthorship W4386352912A5031766048 @default.
- W4386352912 hasAuthorship W4386352912A5043060463 @default.
- W4386352912 hasAuthorship W4386352912A5063883351 @default.
- W4386352912 hasConcept C124504099 @default.
- W4386352912 hasConcept C153180895 @default.
- W4386352912 hasConcept C154945302 @default.
- W4386352912 hasConcept C31972630 @default.
- W4386352912 hasConcept C41008148 @default.
- W4386352912 hasConcept C81363708 @default.
- W4386352912 hasConcept C89600930 @default.
- W4386352912 hasConceptScore W4386352912C124504099 @default.
- W4386352912 hasConceptScore W4386352912C153180895 @default.
- W4386352912 hasConceptScore W4386352912C154945302 @default.
- W4386352912 hasConceptScore W4386352912C31972630 @default.
- W4386352912 hasConceptScore W4386352912C41008148 @default.
- W4386352912 hasConceptScore W4386352912C81363708 @default.
- W4386352912 hasConceptScore W4386352912C89600930 @default.
- W4386352912 hasFunder F4320321001 @default.
- W4386352912 hasFunder F4320321543 @default.
- W4386352912 hasLocation W43863529121 @default.
- W4386352912 hasOpenAccess W4386352912 @default.
- W4386352912 hasPrimaryLocation W43863529121 @default.
- W4386352912 hasRelatedWork W1669643531 @default.
- W4386352912 hasRelatedWork W1982826852 @default.
- W4386352912 hasRelatedWork W2005437358 @default.
- W4386352912 hasRelatedWork W2008656436 @default.
- W4386352912 hasRelatedWork W2023558673 @default.
- W4386352912 hasRelatedWork W2110230079 @default.
- W4386352912 hasRelatedWork W2134924024 @default.
- W4386352912 hasRelatedWork W2517104666 @default.
- W4386352912 hasRelatedWork W2613186388 @default.
- W4386352912 hasRelatedWork W1967061043 @default.
- W4386352912 isParatext "false" @default.
- W4386352912 isRetracted "false" @default.
- W4386352912 workType "article" @default.