Matches in SemOpenAlex for { <https://semopenalex.org/work/W3141431470> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3141431470 endingPage "67" @default.
- W3141431470 startingPage "67" @default.
- W3141431470 abstract "Skin lesion segmentation is a primary step for skin lesion analysis, which can benefit the subsequent classification task. It is a challenging task since the boundaries of pigment regions may be fuzzy and the entire lesion may share a similar color. Prevalent deep learning methods for skin lesion segmentation make predictions by ensembling different convolutional neural networks (CNN), aggregating multi-scale information, or by multi-task learning framework. The main purpose of doing so is trying to make use of as much information as possible so as to make robust predictions. A multi-task learning framework has been proved to be beneficial for the skin lesion segmentation task, which is usually incorporated with the skin lesion classification task. However, multi-task learning requires extra labeling information which may not be available for the skin lesion images. In this paper, a novel CNN architecture using auxiliary information is proposed. Edge prediction, as an auxiliary task, is performed simultaneously with the segmentation task. A cross-connection layer module is proposed, where the intermediate feature maps of each task are fed into the subblocks of the other task which can implicitly guide the neural network to focus on the boundary region of the segmentation task. In addition, a multi-scale feature aggregation module is proposed, which makes use of features of different scales and enhances the performance of the proposed method. Experimental results show that the proposed method obtains a better performance compared with the state-of-the-art methods with a Jaccard Index (JA) of 79.46, Accuracy (ACC) of 94.32, SEN of 88.76 with only one integrated model, which can be learned in an end-to-end manner." @default.
- W3141431470 created "2021-04-13" @default.
- W3141431470 creator A5003065263 @default.
- W3141431470 creator A5082240969 @default.
- W3141431470 creator A5083232093 @default.
- W3141431470 date "2021-04-02" @default.
- W3141431470 modified "2023-10-01" @default.
- W3141431470 title "Skin Lesion Segmentation Using Deep Learning with Auxiliary Task" @default.
- W3141431470 cites W1559136377 @default.
- W3141431470 cites W1594623870 @default.
- W3141431470 cites W2024476192 @default.
- W3141431470 cites W2073129260 @default.
- W3141431470 cites W2096457735 @default.
- W3141431470 cites W2151287908 @default.
- W3141431470 cites W2564782580 @default.
- W3141431470 cites W2581082771 @default.
- W3141431470 cites W2592160412 @default.
- W3141431470 cites W2802403853 @default.
- W3141431470 cites W2803575519 @default.
- W3141431470 cites W2885198879 @default.
- W3141431470 cites W2885668531 @default.
- W3141431470 cites W2952107529 @default.
- W3141431470 cites W2972517644 @default.
- W3141431470 cites W2972944446 @default.
- W3141431470 cites W2984969266 @default.
- W3141431470 cites W2996717109 @default.
- W3141431470 cites W2999417355 @default.
- W3141431470 cites W3006349040 @default.
- W3141431470 cites W3044795413 @default.
- W3141431470 cites W3120091839 @default.
- W3141431470 doi "https://doi.org/10.3390/jimaging7040067" @default.
- W3141431470 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8321325" @default.
- W3141431470 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34460517" @default.
- W3141431470 hasPublicationYear "2021" @default.
- W3141431470 type Work @default.
- W3141431470 sameAs 3141431470 @default.
- W3141431470 citedByCount "44" @default.
- W3141431470 countsByYear W31414314702021 @default.
- W3141431470 countsByYear W31414314702022 @default.
- W3141431470 countsByYear W31414314702023 @default.
- W3141431470 crossrefType "journal-article" @default.
- W3141431470 hasAuthorship W3141431470A5003065263 @default.
- W3141431470 hasAuthorship W3141431470A5082240969 @default.
- W3141431470 hasAuthorship W3141431470A5083232093 @default.
- W3141431470 hasBestOaLocation W31414314701 @default.
- W3141431470 hasConcept C108583219 @default.
- W3141431470 hasConcept C119857082 @default.
- W3141431470 hasConcept C127413603 @default.
- W3141431470 hasConcept C138885662 @default.
- W3141431470 hasConcept C153180895 @default.
- W3141431470 hasConcept C154945302 @default.
- W3141431470 hasConcept C201995342 @default.
- W3141431470 hasConcept C203519979 @default.
- W3141431470 hasConcept C2776401178 @default.
- W3141431470 hasConcept C2780451532 @default.
- W3141431470 hasConcept C28006648 @default.
- W3141431470 hasConcept C41008148 @default.
- W3141431470 hasConcept C41895202 @default.
- W3141431470 hasConcept C50644808 @default.
- W3141431470 hasConcept C81363708 @default.
- W3141431470 hasConcept C89600930 @default.
- W3141431470 hasConceptScore W3141431470C108583219 @default.
- W3141431470 hasConceptScore W3141431470C119857082 @default.
- W3141431470 hasConceptScore W3141431470C127413603 @default.
- W3141431470 hasConceptScore W3141431470C138885662 @default.
- W3141431470 hasConceptScore W3141431470C153180895 @default.
- W3141431470 hasConceptScore W3141431470C154945302 @default.
- W3141431470 hasConceptScore W3141431470C201995342 @default.
- W3141431470 hasConceptScore W3141431470C203519979 @default.
- W3141431470 hasConceptScore W3141431470C2776401178 @default.
- W3141431470 hasConceptScore W3141431470C2780451532 @default.
- W3141431470 hasConceptScore W3141431470C28006648 @default.
- W3141431470 hasConceptScore W3141431470C41008148 @default.
- W3141431470 hasConceptScore W3141431470C41895202 @default.
- W3141431470 hasConceptScore W3141431470C50644808 @default.
- W3141431470 hasConceptScore W3141431470C81363708 @default.
- W3141431470 hasConceptScore W3141431470C89600930 @default.
- W3141431470 hasIssue "4" @default.
- W3141431470 hasLocation W31414314701 @default.
- W3141431470 hasLocation W31414314702 @default.
- W3141431470 hasLocation W31414314703 @default.
- W3141431470 hasOpenAccess W3141431470 @default.
- W3141431470 hasPrimaryLocation W31414314701 @default.
- W3141431470 hasRelatedWork W2738221750 @default.
- W3141431470 hasRelatedWork W2760085659 @default.
- W3141431470 hasRelatedWork W2996106022 @default.
- W3141431470 hasRelatedWork W3102253946 @default.
- W3141431470 hasRelatedWork W3120908866 @default.
- W3141431470 hasRelatedWork W3135324209 @default.
- W3141431470 hasRelatedWork W3144574764 @default.
- W3141431470 hasRelatedWork W3156786002 @default.
- W3141431470 hasRelatedWork W4293211451 @default.
- W3141431470 hasRelatedWork W4308191152 @default.
- W3141431470 hasVolume "7" @default.
- W3141431470 isParatext "false" @default.
- W3141431470 isRetracted "false" @default.
- W3141431470 magId "3141431470" @default.
- W3141431470 workType "article" @default.