Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214899963> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4214899963 endingPage "107777" @default.
- W4214899963 startingPage "107777" @default.
- W4214899963 abstract "Automatic ultrasound image segmentation plays an important role in early diagnosis of human diseases. This paper introduces a novel and efficient encoder–decoder network, called Lightweight Attention Encoder–Decoder Network (LAEDNet), for automatic ultrasound image segmentation. In contrast to previous encoder–decoder networks that involve complicated architecture with numerous parameters, our LAEDNet adopts lightweight version of EfficientNet as encoder. On the other hand, a Lightweight Residual Squeeze-and-Excitation (LRSE) block is employed in decoder. To achieve trade-off between segmentation accuracy and implementing efficiency, we also present a family of models, from light to heavy (denoted as LAEDNet-S, LAEDNet-M, and LAEDNet-L, respectively), with varying lightweight version of EfficientNet backbones. To evaluate LAEDNet, we have conducted extensive experiments on Brachial Plexus Dataset (BP), Breast Ultrasound Images Dataset (BUSI), and Head Circumference Ultrasound Images Dataset (HCUS), where ultrasound images are suffered from high noise, blurred borders and low contrast. The experiments show that, compared with U-Net and its variants, e.g., M-Net, U-Net++ and TransUNet, our LAEDNet achieves better results in terms of Dice Coefficient (DSC) and running speed. Particularly, LAEDNet-M only has 10.75M model parameters with 40.7 FPS, yet obtaining 73.0%, 73.8% and 91.3% DSC on BP, BUSI and HCUS datasets, respectively." @default.
- W4214899963 created "2022-03-05" @default.
- W4214899963 creator A5005039651 @default.
- W4214899963 creator A5020609129 @default.
- W4214899963 creator A5027514072 @default.
- W4214899963 creator A5028245257 @default.
- W4214899963 creator A5080376186 @default.
- W4214899963 creator A5087193137 @default.
- W4214899963 date "2022-04-01" @default.
- W4214899963 modified "2023-10-14" @default.
- W4214899963 title "LAEDNet: A Lightweight Attention Encoder–Decoder Network for ultrasound medical image segmentation" @default.
- W4214899963 cites W2010976684 @default.
- W4214899963 cites W2064675550 @default.
- W4214899963 cites W2624147939 @default.
- W4214899963 cites W2884034690 @default.
- W4214899963 cites W2884561390 @default.
- W4214899963 cites W2927980542 @default.
- W4214899963 cites W2948264761 @default.
- W4214899963 cites W2963420686 @default.
- W4214899963 cites W2979394680 @default.
- W4214899963 cites W2996290406 @default.
- W4214899963 cites W3005735100 @default.
- W4214899963 cites W3014847672 @default.
- W4214899963 cites W3034396853 @default.
- W4214899963 cites W3037414627 @default.
- W4214899963 cites W3047822139 @default.
- W4214899963 cites W3082097505 @default.
- W4214899963 cites W3082947597 @default.
- W4214899963 cites W3101507774 @default.
- W4214899963 cites W3102875249 @default.
- W4214899963 cites W3104061658 @default.
- W4214899963 cites W3126389275 @default.
- W4214899963 cites W3185556852 @default.
- W4214899963 doi "https://doi.org/10.1016/j.compeleceng.2022.107777" @default.
- W4214899963 hasPublicationYear "2022" @default.
- W4214899963 type Work @default.
- W4214899963 citedByCount "15" @default.
- W4214899963 countsByYear W42148999632022 @default.
- W4214899963 countsByYear W42148999632023 @default.
- W4214899963 crossrefType "journal-article" @default.
- W4214899963 hasAuthorship W4214899963A5005039651 @default.
- W4214899963 hasAuthorship W4214899963A5020609129 @default.
- W4214899963 hasAuthorship W4214899963A5027514072 @default.
- W4214899963 hasAuthorship W4214899963A5028245257 @default.
- W4214899963 hasAuthorship W4214899963A5080376186 @default.
- W4214899963 hasAuthorship W4214899963A5087193137 @default.
- W4214899963 hasConcept C111919701 @default.
- W4214899963 hasConcept C11413529 @default.
- W4214899963 hasConcept C118505674 @default.
- W4214899963 hasConcept C124504099 @default.
- W4214899963 hasConcept C126838900 @default.
- W4214899963 hasConcept C143753070 @default.
- W4214899963 hasConcept C153180895 @default.
- W4214899963 hasConcept C154945302 @default.
- W4214899963 hasConcept C31972630 @default.
- W4214899963 hasConcept C41008148 @default.
- W4214899963 hasConcept C57273362 @default.
- W4214899963 hasConcept C71924100 @default.
- W4214899963 hasConcept C89600930 @default.
- W4214899963 hasConceptScore W4214899963C111919701 @default.
- W4214899963 hasConceptScore W4214899963C11413529 @default.
- W4214899963 hasConceptScore W4214899963C118505674 @default.
- W4214899963 hasConceptScore W4214899963C124504099 @default.
- W4214899963 hasConceptScore W4214899963C126838900 @default.
- W4214899963 hasConceptScore W4214899963C143753070 @default.
- W4214899963 hasConceptScore W4214899963C153180895 @default.
- W4214899963 hasConceptScore W4214899963C154945302 @default.
- W4214899963 hasConceptScore W4214899963C31972630 @default.
- W4214899963 hasConceptScore W4214899963C41008148 @default.
- W4214899963 hasConceptScore W4214899963C57273362 @default.
- W4214899963 hasConceptScore W4214899963C71924100 @default.
- W4214899963 hasConceptScore W4214899963C89600930 @default.
- W4214899963 hasLocation W42148999631 @default.
- W4214899963 hasOpenAccess W4214899963 @default.
- W4214899963 hasPrimaryLocation W42148999631 @default.
- W4214899963 hasRelatedWork W1522196789 @default.
- W4214899963 hasRelatedWork W2017509870 @default.
- W4214899963 hasRelatedWork W2351061015 @default.
- W4214899963 hasRelatedWork W2351153092 @default.
- W4214899963 hasRelatedWork W2384362569 @default.
- W4214899963 hasRelatedWork W3203142394 @default.
- W4214899963 hasRelatedWork W4220731478 @default.
- W4214899963 hasRelatedWork W4302615923 @default.
- W4214899963 hasRelatedWork W4360952157 @default.
- W4214899963 hasRelatedWork W2181948922 @default.
- W4214899963 hasVolume "99" @default.
- W4214899963 isParatext "false" @default.
- W4214899963 isRetracted "false" @default.
- W4214899963 workType "article" @default.