Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328106170> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4328106170 endingPage "106792" @default.
- W4328106170 startingPage "106792" @default.
- W4328106170 abstract "Segmentation of anatomical structures in ultrasound images is a challenging task due to existence of artifacts inherit to the modality such as speckle noise, attenuation, shadowing, uneven textures and blurred boundaries. This paper presents a novel attention-based predict–refine network, called ACU2E-Net, for segmentation of soft-tissue structures in ultrasound images. The network consists of two modules: a predict module, which is built upon our newly proposed attentive coordinate convolution; and a novel multi-head residual refinement module, which consists of three parallel residual refinement modules. The attentive coordinate convolution is designed to improve the segmentation accuracy by perceiving the shape and positional information of the target anatomy. The proposed multi-head residual refinement module reduces both segmentation biases and variances by integrating residual refinement and ensemble strategies. Moreover, it avoids multi-pass training and inference commonly seen in ensemble methods. To show the effectiveness of our method, we collect a comprehensive dataset of thyroid ultrasound scans from 12 different imaging centers, and evaluate our proposed network against state-of-the-art segmentation methods. Comparisons against state-of-the-art models demonstrate the competitive performance of our newly designed network on both the transverse and sagittal thyroid images. Ablation studies show that proposed modules improve the segmentation Dice score of the baseline model from 79.62% to 80.97% and 82.92% while reducing the variance from 6.12% to 4.67% and 3.21% in transverse and sagittal views, respectively." @default.
- W4328106170 created "2023-03-22" @default.
- W4328106170 creator A5006157212 @default.
- W4328106170 creator A5009754134 @default.
- W4328106170 creator A5016230593 @default.
- W4328106170 creator A5019003578 @default.
- W4328106170 creator A5032376331 @default.
- W4328106170 creator A5034378631 @default.
- W4328106170 creator A5035920057 @default.
- W4328106170 creator A5069854748 @default.
- W4328106170 creator A5082512262 @default.
- W4328106170 creator A5084709102 @default.
- W4328106170 date "2023-05-01" @default.
- W4328106170 modified "2023-09-27" @default.
- W4328106170 title "ACU<mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML altimg=si3.svg display=inline id=d1e1379><mml:msup><mml:mrow /><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>E-Net: A novel predict–refine attention network for segmentation of soft-tissue structures in ultrasound images" @default.
- W4328106170 cites W1677182931 @default.
- W4328106170 cites W1903029394 @default.
- W4328106170 cites W1994830509 @default.
- W4328106170 cites W2112796928 @default.
- W4328106170 cites W2113275954 @default.
- W4328106170 cites W2119300483 @default.
- W4328106170 cites W2544543335 @default.
- W4328106170 cites W2741754476 @default.
- W4328106170 cites W2752782242 @default.
- W4328106170 cites W2775646422 @default.
- W4328106170 cites W2780708736 @default.
- W4328106170 cites W2884585870 @default.
- W4328106170 cites W2887748972 @default.
- W4328106170 cites W2913559493 @default.
- W4328106170 cites W2941121449 @default.
- W4328106170 cites W2953129827 @default.
- W4328106170 cites W2961348656 @default.
- W4328106170 cites W3025800305 @default.
- W4328106170 cites W3211330693 @default.
- W4328106170 cites W4233537775 @default.
- W4328106170 cites W44290764 @default.
- W4328106170 doi "https://doi.org/10.1016/j.compbiomed.2023.106792" @default.
- W4328106170 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36965325" @default.
- W4328106170 hasPublicationYear "2023" @default.
- W4328106170 type Work @default.
- W4328106170 citedByCount "1" @default.
- W4328106170 countsByYear W43281061702023 @default.
- W4328106170 crossrefType "journal-article" @default.
- W4328106170 hasAuthorship W4328106170A5006157212 @default.
- W4328106170 hasAuthorship W4328106170A5009754134 @default.
- W4328106170 hasAuthorship W4328106170A5016230593 @default.
- W4328106170 hasAuthorship W4328106170A5019003578 @default.
- W4328106170 hasAuthorship W4328106170A5032376331 @default.
- W4328106170 hasAuthorship W4328106170A5034378631 @default.
- W4328106170 hasAuthorship W4328106170A5035920057 @default.
- W4328106170 hasAuthorship W4328106170A5069854748 @default.
- W4328106170 hasAuthorship W4328106170A5082512262 @default.
- W4328106170 hasAuthorship W4328106170A5084709102 @default.
- W4328106170 hasConcept C11413529 @default.
- W4328106170 hasConcept C126780896 @default.
- W4328106170 hasConcept C153180895 @default.
- W4328106170 hasConcept C154945302 @default.
- W4328106170 hasConcept C155512373 @default.
- W4328106170 hasConcept C194257627 @default.
- W4328106170 hasConcept C2776257435 @default.
- W4328106170 hasConcept C31258907 @default.
- W4328106170 hasConcept C31972630 @default.
- W4328106170 hasConcept C41008148 @default.
- W4328106170 hasConcept C89600930 @default.
- W4328106170 hasConceptScore W4328106170C11413529 @default.
- W4328106170 hasConceptScore W4328106170C126780896 @default.
- W4328106170 hasConceptScore W4328106170C153180895 @default.
- W4328106170 hasConceptScore W4328106170C154945302 @default.
- W4328106170 hasConceptScore W4328106170C155512373 @default.
- W4328106170 hasConceptScore W4328106170C194257627 @default.
- W4328106170 hasConceptScore W4328106170C2776257435 @default.
- W4328106170 hasConceptScore W4328106170C31258907 @default.
- W4328106170 hasConceptScore W4328106170C31972630 @default.
- W4328106170 hasConceptScore W4328106170C41008148 @default.
- W4328106170 hasConceptScore W4328106170C89600930 @default.
- W4328106170 hasFunder F4320322675 @default.
- W4328106170 hasLocation W43281061701 @default.
- W4328106170 hasLocation W43281061702 @default.
- W4328106170 hasOpenAccess W4328106170 @default.
- W4328106170 hasPrimaryLocation W43281061701 @default.
- W4328106170 hasRelatedWork W1669643531 @default.
- W4328106170 hasRelatedWork W2005437358 @default.
- W4328106170 hasRelatedWork W2008656436 @default.
- W4328106170 hasRelatedWork W2023558673 @default.
- W4328106170 hasRelatedWork W2039154422 @default.
- W4328106170 hasRelatedWork W2110230079 @default.
- W4328106170 hasRelatedWork W2122581818 @default.
- W4328106170 hasRelatedWork W2134924024 @default.
- W4328106170 hasRelatedWork W2517104666 @default.
- W4328106170 hasRelatedWork W2182382398 @default.
- W4328106170 hasVolume "157" @default.
- W4328106170 isParatext "false" @default.
- W4328106170 isRetracted "false" @default.
- W4328106170 workType "article" @default.
