FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2597972910> ?p ?o ?g. }

• W2597972910 endingPage "18" @default.
• W2597972910 startingPage "1" @default.
• W2597972910 abstract "Successful computer-aided diagnosis systems typically rely on training datasets containing sufficient and richly annotated images. However, detailed image annotation is often time consuming and subjective, especially for medical images, which becomes the bottleneck for the collection of large datasets and then building computer-aided diagnosis systems. In this article, we design a novel computer-aided endoscopy diagnosis system to deal with the multi-classification problem of electronic endoscopy medical records (EEMRs) containing sets of frames, while labels of EEMRs can be mined from the corresponding text records using an automatic text-matching strategy without human special labeling. With unambiguous EEMR labels and ambiguous frame labels, we propose a simple but effective pooling scheme called Multi-class Latent Concept Pooling, which learns a codebook from EEMRs with different classes step by step and encodes EEMRs based on a soft weighting strategy. In our method, a computer-aided diagnosis system can be extended to new unseen classes with ease and applied to the standard single-instance classification problem even though detailed annotated images are unavailable. In order to validate our system, we collect 1,889 EEMRs with more than 59K frames and successfully mine labels for 348 of them. The experimental results show that our proposed system significantly outperforms the state-of-the-art methods. Moreover, we apply the learned latent concept codebook to detect the abnormalities in endoscopy images and compare it with a supervised learning classifier, and the evaluation shows that our codebook learning method can effectively extract the true prototypes related to different classes from the ambiguous data." @default.
• W2597972910 created "2017-04-07" @default.
• W2597972910 creator A5001938430 @default.
• W2597972910 creator A5006477225 @default.
• W2597972910 creator A5012377120 @default.
• W2597972910 creator A5040326170 @default.
• W2597972910 creator A5053892249 @default.
• W2597972910 creator A5063305995 @default.
• W2597972910 creator A5063377357 @default.
• W2597972910 creator A5088609880 @default.
• W2597972910 creator A5091319287 @default.
• W2597972910 date "2017-03-21" @default.
• W2597972910 modified "2023-10-18" @default.
• W2597972910 title "Multi-Class Latent Concept Pooling for Computer-Aided Endoscopy Diagnosis" @default.
• W2597972910 cites W1504116408 @default.
• W2597972910 cites W1606858007 @default.
• W2597972910 cites W1766329497 @default.
• W2597972910 cites W1966385142 @default.
• W2597972910 cites W1967554913 @default.
• W2597972910 cites W1973476548 @default.
• W2597972910 cites W1981506718 @default.
• W2597972910 cites W1984309565 @default.
• W2597972910 cites W1988805924 @default.
• W2597972910 cites W2000355138 @default.
• W2597972910 cites W2002273623 @default.
• W2597972910 cites W2010430916 @default.
• W2597972910 cites W2011414622 @default.
• W2597972910 cites W2012592962 @default.
• W2597972910 cites W2012931101 @default.
• W2597972910 cites W2016292092 @default.
• W2597972910 cites W2017117888 @default.
• W2597972910 cites W2039533874 @default.
• W2597972910 cites W2065882669 @default.
• W2597972910 cites W2077474654 @default.
• W2597972910 cites W2090029815 @default.
• W2597972910 cites W2090042335 @default.
• W2597972910 cites W2095092756 @default.
• W2597972910 cites W2097018403 @default.
• W2597972910 cites W2105623448 @default.
• W2597972910 cites W2106279103 @default.
• W2597972910 cites W2110383222 @default.
• W2597972910 cites W2110941419 @default.
• W2597972910 cites W2116563953 @default.
• W2597972910 cites W2118246710 @default.
• W2597972910 cites W2120522910 @default.
• W2597972910 cites W2120725344 @default.
• W2597972910 cites W2132525626 @default.
• W2597972910 cites W2135176316 @default.
• W2597972910 cites W2155783234 @default.
• W2597972910 cites W2156290208 @default.
• W2597972910 cites W2161969291 @default.
• W2597972910 cites W2165149714 @default.
• W2597972910 cites W2167597393 @default.
• W2597972910 cites W2179713099 @default.
• W2597972910 cites W2293352836 @default.
• W2597972910 cites W2344778348 @default.
• W2597972910 cites W2353070889 @default.
• W2597972910 cites W1977533184 @default.
• W2597972910 doi "https://doi.org/10.1145/3051481" @default.
• W2597972910 hasPublicationYear "2017" @default.
• W2597972910 type Work @default.
• W2597972910 sameAs 2597972910 @default.
• W2597972910 citedByCount "1" @default.
• W2597972910 countsByYear W25979729102021 @default.
• W2597972910 crossrefType "journal-article" @default.
• W2597972910 hasAuthorship W2597972910A5001938430 @default.
• W2597972910 hasAuthorship W2597972910A5006477225 @default.
• W2597972910 hasAuthorship W2597972910A5012377120 @default.
• W2597972910 hasAuthorship W2597972910A5040326170 @default.
• W2597972910 hasAuthorship W2597972910A5053892249 @default.
• W2597972910 hasAuthorship W2597972910A5063305995 @default.
• W2597972910 hasAuthorship W2597972910A5063377357 @default.
• W2597972910 hasAuthorship W2597972910A5088609880 @default.
• W2597972910 hasAuthorship W2597972910A5091319287 @default.
• W2597972910 hasConcept C119857082 @default.
• W2597972910 hasConcept C126838900 @default.
• W2597972910 hasConcept C127759330 @default.
• W2597972910 hasConcept C149635348 @default.
• W2597972910 hasConcept C153180895 @default.
• W2597972910 hasConcept C154945302 @default.
• W2597972910 hasConcept C183115368 @default.
• W2597972910 hasConcept C199360897 @default.
• W2597972910 hasConcept C2777212361 @default.
• W2597972910 hasConcept C2780513914 @default.
• W2597972910 hasConcept C2780727963 @default.
• W2597972910 hasConcept C41008148 @default.
• W2597972910 hasConcept C70437156 @default.
• W2597972910 hasConcept C71924100 @default.
• W2597972910 hasConcept C95623464 @default.
• W2597972910 hasConceptScore W2597972910C119857082 @default.
• W2597972910 hasConceptScore W2597972910C126838900 @default.
• W2597972910 hasConceptScore W2597972910C127759330 @default.
• W2597972910 hasConceptScore W2597972910C149635348 @default.
• W2597972910 hasConceptScore W2597972910C153180895 @default.
• W2597972910 hasConceptScore W2597972910C154945302 @default.
• W2597972910 hasConceptScore W2597972910C183115368 @default.
• W2597972910 hasConceptScore W2597972910C199360897 @default.
• W2597972910 hasConceptScore W2597972910C2777212361 @default.

• next