Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283746543> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4283746543 endingPage "1112" @default.
- W4283746543 startingPage "1093" @default.
- W4283746543 abstract "Histopathological image recognition of breast cancer is an onerous task. Although many deep learning models have achieved good classification results on histopathological image classification tasks, these models do not take full advantage of the staining properties of histopathological images. In this paper, we propose a novel Deconv-Transformer (DecT) network model, which incorporates the color deconvolution in the form of convolution layers . This model uses a self-attention mechanism to match the independent properties of the HED channel information obtained by the color deconvolution. It also uses a method similar to the residual connection to fuse the information of both RGB and HED color space images, which can compensate for the information loss in the process of transferring RGB images to HED images. The training process of the DecT model is divided into two stages so that the parameters of the deconvolution layer can be better adapted to different types of histopathological images. We use the color jitter in the image data augmentation process to reduce the overfitting in the model training process. The DecT model achieves an average accuracy of 93.02% and F1-score of 0.9389 on BreakHis dataset, and an average accuracy of 79.06% and 81.36% on BACH and UC datasets." @default.
- W4283746543 created "2022-07-02" @default.
- W4283746543 creator A5004145814 @default.
- W4283746543 creator A5035197607 @default.
- W4283746543 creator A5054576459 @default.
- W4283746543 creator A5064530138 @default.
- W4283746543 creator A5073568638 @default.
- W4283746543 creator A5085134695 @default.
- W4283746543 creator A5089130898 @default.
- W4283746543 date "2022-08-01" @default.
- W4283746543 modified "2023-10-16" @default.
- W4283746543 title "Deconv-transformer (DecT): A histopathological image classification model for breast cancer based on color deconvolution and transformer architecture" @default.
- W4283746543 cites W2117539524 @default.
- W4283746543 cites W2132162500 @default.
- W4283746543 cites W2148309496 @default.
- W4283746543 cites W2344480160 @default.
- W4283746543 cites W2885824038 @default.
- W4283746543 cites W2970152602 @default.
- W4283746543 cites W3025885500 @default.
- W4283746543 cites W3041133507 @default.
- W4283746543 cites W3047753861 @default.
- W4283746543 cites W3089090082 @default.
- W4283746543 cites W3094071795 @default.
- W4283746543 cites W3097065222 @default.
- W4283746543 cites W3097217077 @default.
- W4283746543 cites W3099076900 @default.
- W4283746543 cites W3100398151 @default.
- W4283746543 cites W3103245635 @default.
- W4283746543 cites W3110162748 @default.
- W4283746543 cites W3126088291 @default.
- W4283746543 cites W3141929194 @default.
- W4283746543 cites W3178621454 @default.
- W4283746543 cites W3194949249 @default.
- W4283746543 cites W3201139246 @default.
- W4283746543 cites W3213920736 @default.
- W4283746543 cites W4200597037 @default.
- W4283746543 cites W4213019189 @default.
- W4283746543 doi "https://doi.org/10.1016/j.ins.2022.06.091" @default.
- W4283746543 hasPublicationYear "2022" @default.
- W4283746543 type Work @default.
- W4283746543 citedByCount "25" @default.
- W4283746543 countsByYear W42837465432022 @default.
- W4283746543 countsByYear W42837465432023 @default.
- W4283746543 crossrefType "journal-article" @default.
- W4283746543 hasAuthorship W4283746543A5004145814 @default.
- W4283746543 hasAuthorship W4283746543A5035197607 @default.
- W4283746543 hasAuthorship W4283746543A5054576459 @default.
- W4283746543 hasAuthorship W4283746543A5064530138 @default.
- W4283746543 hasAuthorship W4283746543A5073568638 @default.
- W4283746543 hasAuthorship W4283746543A5085134695 @default.
- W4283746543 hasAuthorship W4283746543A5089130898 @default.
- W4283746543 hasConcept C119599485 @default.
- W4283746543 hasConcept C121608353 @default.
- W4283746543 hasConcept C123657996 @default.
- W4283746543 hasConcept C126322002 @default.
- W4283746543 hasConcept C127413603 @default.
- W4283746543 hasConcept C142362112 @default.
- W4283746543 hasConcept C153180895 @default.
- W4283746543 hasConcept C153349607 @default.
- W4283746543 hasConcept C154945302 @default.
- W4283746543 hasConcept C165801399 @default.
- W4283746543 hasConcept C41008148 @default.
- W4283746543 hasConcept C530470458 @default.
- W4283746543 hasConcept C66322947 @default.
- W4283746543 hasConcept C71924100 @default.
- W4283746543 hasConceptScore W4283746543C119599485 @default.
- W4283746543 hasConceptScore W4283746543C121608353 @default.
- W4283746543 hasConceptScore W4283746543C123657996 @default.
- W4283746543 hasConceptScore W4283746543C126322002 @default.
- W4283746543 hasConceptScore W4283746543C127413603 @default.
- W4283746543 hasConceptScore W4283746543C142362112 @default.
- W4283746543 hasConceptScore W4283746543C153180895 @default.
- W4283746543 hasConceptScore W4283746543C153349607 @default.
- W4283746543 hasConceptScore W4283746543C154945302 @default.
- W4283746543 hasConceptScore W4283746543C165801399 @default.
- W4283746543 hasConceptScore W4283746543C41008148 @default.
- W4283746543 hasConceptScore W4283746543C530470458 @default.
- W4283746543 hasConceptScore W4283746543C66322947 @default.
- W4283746543 hasConceptScore W4283746543C71924100 @default.
- W4283746543 hasFunder F4320321878 @default.
- W4283746543 hasFunder F4320327865 @default.
- W4283746543 hasLocation W42837465431 @default.
- W4283746543 hasOpenAccess W4283746543 @default.
- W4283746543 hasPrimaryLocation W42837465431 @default.
- W4283746543 hasRelatedWork W1819952937 @default.
- W4283746543 hasRelatedWork W1978450727 @default.
- W4283746543 hasRelatedWork W2033914206 @default.
- W4283746543 hasRelatedWork W2146076056 @default.
- W4283746543 hasRelatedWork W2163831990 @default.
- W4283746543 hasRelatedWork W2378160586 @default.
- W4283746543 hasRelatedWork W2383828164 @default.
- W4283746543 hasRelatedWork W3003836766 @default.
- W4283746543 hasRelatedWork W3107474891 @default.
- W4283746543 hasRelatedWork W396164270 @default.
- W4283746543 hasVolume "608" @default.
- W4283746543 isParatext "false" @default.
- W4283746543 isRetracted "false" @default.
- W4283746543 workType "article" @default.