FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385695909> ?p ?o ?g. }

• W4385695909 endingPage "9" @default.
• W4385695909 startingPage "1" @default.
• W4385695909 abstract "In computer vision systems, the final measurement result can be a digital output provided by the software, i.e., a diagnostic value along with an uncertainty interval. In line with previous work on melanoma disease, we present here a platform for image analysis based on Variational Auto-Encoders (VAE), a category of deep learning generative models that learns how to reproduce an image in output by an encoder/decoder strategy. Latent variables extracted from the VAE architecture are compact representations of the appearance of image objects and are used as phenotypes of malignant skin lesions. In this work, we go ahead with the state-of-the-art approaches by proposing a way to use the propagated uncertainty through the VAE system, related to skin tone variation and gel bubble effects, as an index to select more robust descriptors of melanoma malignancy, under the assumption that the less is the expected variation of a descriptor to perturbations, the more is its capability to discriminate it. Here we consider images from the public dataset of dermoscopic images ISIC2016-2017, 500 from malignant and 500 from benign findings, to address the binary classification problem of malignancy assessment. We reported the results of the uncertainty-based feature selection strategy using seven different standard classification methods, obtaining average accuracy values of 0.82 (0.01) vs. the case of 0.74 (0.05) obtained without any feature selection approach, demonstrating the increased adequacy of the model in diagnosing melanoma. General validity has been shown by comparing the results with those obtained using a standard transfer learning strategy based on Convolution Neural Network (CNN). The proposed approach not only demonstrates an increased accuracy in identifying malignant melanomas, but also presents a completely novel approach for feature selection, framed within the theory of uncertainty propagation, specifically relevant in the case of black-box descriptors such as those extracted through deep learning." @default.
• W4385695909 created "2023-08-10" @default.
• W4385695909 creator A5001438059 @default.
• W4385695909 creator A5014451390 @default.
• W4385695909 creator A5033016897 @default.
• W4385695909 creator A5033525208 @default.
• W4385695909 creator A5062989429 @default.
• W4385695909 creator A5073056076 @default.
• W4385695909 date "2023-01-01" @default.
• W4385695909 modified "2023-10-16" @default.
• W4385695909 title "Uncertainty-based feature selection for improved adequacy of dermoscopic image classification" @default.
• W4385695909 cites W1563088657 @default.
• W4385695909 cites W1808644423 @default.
• W4385695909 cites W1966370229 @default.
• W4385695909 cites W1997435908 @default.
• W4385695909 cites W2117539524 @default.
• W4385695909 cites W2129440600 @default.
• W4385695909 cites W2131987814 @default.
• W4385695909 cites W2158714988 @default.
• W4385695909 cites W2169038408 @default.
• W4385695909 cites W2194775991 @default.
• W4385695909 cites W2574388714 @default.
• W4385695909 cites W2581082771 @default.
• W4385695909 cites W2771506813 @default.
• W4385695909 cites W2785536912 @default.
• W4385695909 cites W2905215565 @default.
• W4385695909 cites W2921785317 @default.
• W4385695909 cites W2937742783 @default.
• W4385695909 cites W2948978827 @default.
• W4385695909 cites W2965743638 @default.
• W4385695909 cites W2987821246 @default.
• W4385695909 cites W3005826475 @default.
• W4385695909 cites W3007992792 @default.
• W4385695909 cites W3012614932 @default.
• W4385695909 cites W3029120371 @default.
• W4385695909 cites W3033076407 @default.
• W4385695909 cites W3036365526 @default.
• W4385695909 cites W3093446992 @default.
• W4385695909 cites W3098269892 @default.
• W4385695909 cites W3136139906 @default.
• W4385695909 cites W3170108663 @default.
• W4385695909 cites W3190941935 @default.
• W4385695909 cites W4206576785 @default.
• W4385695909 cites W4220791756 @default.
• W4385695909 cites W4292263242 @default.
• W4385695909 cites W4293039013 @default.
• W4385695909 doi "https://doi.org/10.1109/tim.2023.3303498" @default.
• W4385695909 hasPublicationYear "2023" @default.
• W4385695909 type Work @default.
• W4385695909 citedByCount "0" @default.
• W4385695909 crossrefType "journal-article" @default.
• W4385695909 hasAuthorship W4385695909A5001438059 @default.
• W4385695909 hasAuthorship W4385695909A5014451390 @default.
• W4385695909 hasAuthorship W4385695909A5033016897 @default.
• W4385695909 hasAuthorship W4385695909A5033525208 @default.
• W4385695909 hasAuthorship W4385695909A5062989429 @default.
• W4385695909 hasAuthorship W4385695909A5073056076 @default.
• W4385695909 hasConcept C111919701 @default.
• W4385695909 hasConcept C115961682 @default.
• W4385695909 hasConcept C118505674 @default.
• W4385695909 hasConcept C12267149 @default.
• W4385695909 hasConcept C138885662 @default.
• W4385695909 hasConcept C148483581 @default.
• W4385695909 hasConcept C153180895 @default.
• W4385695909 hasConcept C154945302 @default.
• W4385695909 hasConcept C2776401178 @default.
• W4385695909 hasConcept C33923547 @default.
• W4385695909 hasConcept C41008148 @default.
• W4385695909 hasConcept C41895202 @default.
• W4385695909 hasConcept C48372109 @default.
• W4385695909 hasConcept C66905080 @default.
• W4385695909 hasConcept C75294576 @default.
• W4385695909 hasConcept C94375191 @default.
• W4385695909 hasConceptScore W4385695909C111919701 @default.
• W4385695909 hasConceptScore W4385695909C115961682 @default.
• W4385695909 hasConceptScore W4385695909C118505674 @default.
• W4385695909 hasConceptScore W4385695909C12267149 @default.
• W4385695909 hasConceptScore W4385695909C138885662 @default.
• W4385695909 hasConceptScore W4385695909C148483581 @default.
• W4385695909 hasConceptScore W4385695909C153180895 @default.
• W4385695909 hasConceptScore W4385695909C154945302 @default.
• W4385695909 hasConceptScore W4385695909C2776401178 @default.
• W4385695909 hasConceptScore W4385695909C33923547 @default.
• W4385695909 hasConceptScore W4385695909C41008148 @default.
• W4385695909 hasConceptScore W4385695909C41895202 @default.
• W4385695909 hasConceptScore W4385695909C48372109 @default.
• W4385695909 hasConceptScore W4385695909C66905080 @default.
• W4385695909 hasConceptScore W4385695909C75294576 @default.
• W4385695909 hasConceptScore W4385695909C94375191 @default.
• W4385695909 hasLocation W43856959091 @default.
• W4385695909 hasOpenAccess W4385695909 @default.
• W4385695909 hasPrimaryLocation W43856959091 @default.
• W4385695909 hasRelatedWork W2295032739 @default.
• W4385695909 hasRelatedWork W2316780152 @default.
• W4385695909 hasRelatedWork W2374344280 @default.
• W4385695909 hasRelatedWork W2382607599 @default.
• W4385695909 hasRelatedWork W2385233088 @default.
• W4385695909 hasRelatedWork W2509146328 @default.

• next