FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163452406> ?p ?o ?g. }

• W3163452406 endingPage "3954" @default.
• W3163452406 startingPage "3943" @default.
• W3163452406 abstract "When encountering a dubious diagnostic case, medical instance retrieval can help radiologists make evidence-based diagnoses by finding images containing instances similar to a query case from a large image database. The similarity between the query case and retrieved similar cases is determined by visual features extracted from pathologically abnormal regions. However, the manifestation of these regions often lacks specificity, i.e., different diseases can have the same manifestation, and different manifestations may occur at different stages of the same disease. To combat the manifestation ambiguity in medical instance retrieval, we propose a novel deep framework called Y-Net, encoding images into compact hash-codes generated from convolutional features by feature aggregation. Y-Net can learn highly discriminative convolutional features by unifying the pixel-wise segmentation loss and classification loss. The segmentation loss allows exploring subtle spatial differences for good spatial-discriminability while the classification loss utilizes class-aware semantic information for good semantic-separability. As a result, Y-Net can enhance the visual features in pathologically abnormal regions and suppress the disturbing of the background during model training, which could effectively embed discriminative features into the hash-codes in the retrieval stage. Extensive experiments on two medical image datasets demonstrate that Y-Net can alleviate the ambiguity of pathologically abnormal regions and its retrieval performance outperforms the state-of-the-art method by an average of 9.27% on the returned list of 10." @default.
• W3163452406 created "2021-05-24" @default.
• W3163452406 creator A5004658590 @default.
• W3163452406 creator A5005407838 @default.
• W3163452406 creator A5010970485 @default.
• W3163452406 creator A5015704749 @default.
• W3163452406 creator A5027255721 @default.
• W3163452406 creator A5060956246 @default.
• W3163452406 date "2021-10-01" @default.
• W3163452406 modified "2023-10-05" @default.
• W3163452406 title "Combating Ambiguity for Hash-Code Learning in Medical Instance Retrieval" @default.
• W3163452406 cites W1556531089 @default.
• W3163452406 cites W1608697715 @default.
• W3163452406 cites W1677409904 @default.
• W3163452406 cites W1960777822 @default.
• W3163452406 cites W2020498246 @default.
• W3163452406 cites W2024798729 @default.
• W3163452406 cites W2036691524 @default.
• W3163452406 cites W204268067 @default.
• W3163452406 cites W2044284589 @default.
• W3163452406 cites W2118132750 @default.
• W3163452406 cites W2125378448 @default.
• W3163452406 cites W2136725088 @default.
• W3163452406 cites W2137278143 @default.
• W3163452406 cites W2142514727 @default.
• W3163452406 cites W2151103935 @default.
• W3163452406 cites W2163605009 @default.
• W3163452406 cites W2194775991 @default.
• W3163452406 cites W2204975001 @default.
• W3163452406 cites W2295537791 @default.
• W3163452406 cites W2336803177 @default.
• W3163452406 cites W2410365153 @default.
• W3163452406 cites W2464915613 @default.
• W3163452406 cites W2472899609 @default.
• W3163452406 cites W2499468060 @default.
• W3163452406 cites W2508837377 @default.
• W3163452406 cites W2544587078 @default.
• W3163452406 cites W2565639579 @default.
• W3163452406 cites W2565993688 @default.
• W3163452406 cites W2592299985 @default.
• W3163452406 cites W2613718673 @default.
• W3163452406 cites W2656999302 @default.
• W3163452406 cites W2737939591 @default.
• W3163452406 cites W2752752840 @default.
• W3163452406 cites W2753282939 @default.
• W3163452406 cites W2760880057 @default.
• W3163452406 cites W2805173964 @default.
• W3163452406 cites W2891093866 @default.
• W3163452406 cites W2893440080 @default.
• W3163452406 cites W2949117887 @default.
• W3163452406 cites W2962740980 @default.
• W3163452406 cites W2963129433 @default.
• W3163452406 cites W2963150697 @default.
• W3163452406 cites W2963166708 @default.
• W3163452406 cites W2963398644 @default.
• W3163452406 cites W2963436667 @default.
• W3163452406 cites W2963677766 @default.
• W3163452406 cites W2963835840 @default.
• W3163452406 cites W2964076257 @default.
• W3163452406 cites W2967862025 @default.
• W3163452406 cites W2980275434 @default.
• W3163452406 cites W2990519439 @default.
• W3163452406 cites W2998702515 @default.
• W3163452406 cites W3003355614 @default.
• W3163452406 cites W3023418887 @default.
• W3163452406 cites W3034303554 @default.
• W3163452406 cites W3039706108 @default.
• W3163452406 cites W3090330860 @default.
• W3163452406 cites W3090977418 @default.
• W3163452406 cites W3103752442 @default.
• W3163452406 cites W3106250896 @default.
• W3163452406 cites W3109923227 @default.
• W3163452406 cites W3113410735 @default.
• W3163452406 cites W3122431193 @default.
• W3163452406 cites W3128345400 @default.
• W3163452406 cites W3129137136 @default.
• W3163452406 doi "https://doi.org/10.1109/jbhi.2021.3082531" @default.
• W3163452406 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34018938" @default.
• W3163452406 hasPublicationYear "2021" @default.
• W3163452406 type Work @default.
• W3163452406 sameAs 3163452406 @default.
• W3163452406 citedByCount "5" @default.
• W3163452406 countsByYear W31634524062022 @default.
• W3163452406 countsByYear W31634524062023 @default.
• W3163452406 crossrefType "journal-article" @default.
• W3163452406 hasAuthorship W3163452406A5004658590 @default.
• W3163452406 hasAuthorship W3163452406A5005407838 @default.
• W3163452406 hasAuthorship W3163452406A5010970485 @default.
• W3163452406 hasAuthorship W3163452406A5015704749 @default.
• W3163452406 hasAuthorship W3163452406A5027255721 @default.
• W3163452406 hasAuthorship W3163452406A5060956246 @default.
• W3163452406 hasBestOaLocation W31634524062 @default.
• W3163452406 hasConcept C115961682 @default.
• W3163452406 hasConcept C138885662 @default.
• W3163452406 hasConcept C142724271 @default.
• W3163452406 hasConcept C153180895 @default.
• W3163452406 hasConcept C154945302 @default.
• W3163452406 hasConcept C1667742 @default.

• next