Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366124369> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4366124369 endingPage "106952" @default.
- W4366124369 startingPage "106952" @default.
- W4366124369 abstract "For clinical treatment, the accurate segmentation of lesions from dermoscopic images is extremely valuable. Convolutional neural networks (such as U-Net and its numerous variants) have become the main methods for skin lesion segmentation in recent years. However, because these methods frequently have a large number of parameters and complicated algorithm structures, which results in high hardware requirements and long training time, it is difficult to effectively use them for fast training and segmentation tasks. For this reason, we proposed an efficient multi-attention convolutional neural network (Rema-Net) for rapid skin lesion segmentation. The down-sampling module of the network only uses a convolutional layer and a pooling layer, with spatial attention added to improve useful features. We also designed skip-connections between the down-sampling and up-sampling parts of the network, and used reverse attention operation on the skip-connections to strengthen segmentation performance of the network. We conducted extensive experiments on five publicly available datasets to validate the effectiveness of our method, including the ISIC-2016, ISIC-2017, ISIC-2018, PH2, and HAM10000 datasets. The results show that the proposed method reduced the number of parameters by nearly 40% when compared with U-Net. Furthermore, the segmentation metrics are significantly better than some previous methods, and the predictions are closer to the real lesion." @default.
- W4366124369 created "2023-04-19" @default.
- W4366124369 creator A5067842615 @default.
- W4366124369 creator A5081225542 @default.
- W4366124369 creator A5081298695 @default.
- W4366124369 creator A5089927225 @default.
- W4366124369 date "2023-06-01" @default.
- W4366124369 modified "2023-09-30" @default.
- W4366124369 title "Rema-Net: An efficient multi-attention convolutional neural network for rapid skin lesion segmentation" @default.
- W4366124369 cites W1509451745 @default.
- W4366124369 cites W1529230314 @default.
- W4366124369 cites W2022060285 @default.
- W4366124369 cites W2142259554 @default.
- W4366124369 cites W2907688358 @default.
- W4366124369 cites W2916845318 @default.
- W4366124369 cites W2923997689 @default.
- W4366124369 cites W2954119516 @default.
- W4366124369 cites W2972944446 @default.
- W4366124369 cites W3003121299 @default.
- W4366124369 cites W3090974769 @default.
- W4366124369 cites W3102785203 @default.
- W4366124369 cites W3158307528 @default.
- W4366124369 cites W3171280285 @default.
- W4366124369 cites W3206316397 @default.
- W4366124369 cites W4226351492 @default.
- W4366124369 doi "https://doi.org/10.1016/j.compbiomed.2023.106952" @default.
- W4366124369 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37084639" @default.
- W4366124369 hasPublicationYear "2023" @default.
- W4366124369 type Work @default.
- W4366124369 citedByCount "1" @default.
- W4366124369 countsByYear W43661243692023 @default.
- W4366124369 crossrefType "journal-article" @default.
- W4366124369 hasAuthorship W4366124369A5067842615 @default.
- W4366124369 hasAuthorship W4366124369A5081225542 @default.
- W4366124369 hasAuthorship W4366124369A5081298695 @default.
- W4366124369 hasAuthorship W4366124369A5089927225 @default.
- W4366124369 hasConcept C106131492 @default.
- W4366124369 hasConcept C140779682 @default.
- W4366124369 hasConcept C142724271 @default.
- W4366124369 hasConcept C153180895 @default.
- W4366124369 hasConcept C154945302 @default.
- W4366124369 hasConcept C2988168687 @default.
- W4366124369 hasConcept C31972630 @default.
- W4366124369 hasConcept C41008148 @default.
- W4366124369 hasConcept C50644808 @default.
- W4366124369 hasConcept C70437156 @default.
- W4366124369 hasConcept C71924100 @default.
- W4366124369 hasConcept C81363708 @default.
- W4366124369 hasConcept C89600930 @default.
- W4366124369 hasConceptScore W4366124369C106131492 @default.
- W4366124369 hasConceptScore W4366124369C140779682 @default.
- W4366124369 hasConceptScore W4366124369C142724271 @default.
- W4366124369 hasConceptScore W4366124369C153180895 @default.
- W4366124369 hasConceptScore W4366124369C154945302 @default.
- W4366124369 hasConceptScore W4366124369C2988168687 @default.
- W4366124369 hasConceptScore W4366124369C31972630 @default.
- W4366124369 hasConceptScore W4366124369C41008148 @default.
- W4366124369 hasConceptScore W4366124369C50644808 @default.
- W4366124369 hasConceptScore W4366124369C70437156 @default.
- W4366124369 hasConceptScore W4366124369C71924100 @default.
- W4366124369 hasConceptScore W4366124369C81363708 @default.
- W4366124369 hasConceptScore W4366124369C89600930 @default.
- W4366124369 hasLocation W43661243691 @default.
- W4366124369 hasLocation W43661243692 @default.
- W4366124369 hasOpenAccess W4366124369 @default.
- W4366124369 hasPrimaryLocation W43661243691 @default.
- W4366124369 hasRelatedWork W2424871898 @default.
- W4366124369 hasRelatedWork W2514274290 @default.
- W4366124369 hasRelatedWork W2517027266 @default.
- W4366124369 hasRelatedWork W2758063741 @default.
- W4366124369 hasRelatedWork W2940661641 @default.
- W4366124369 hasRelatedWork W2969680539 @default.
- W4366124369 hasRelatedWork W3172946746 @default.
- W4366124369 hasRelatedWork W4226401448 @default.
- W4366124369 hasRelatedWork W4308191152 @default.
- W4366124369 hasRelatedWork W4313554895 @default.
- W4366124369 hasVolume "159" @default.
- W4366124369 isParatext "false" @default.
- W4366124369 isRetracted "false" @default.
- W4366124369 workType "article" @default.