FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009726326> ?p ?o ?g. }

• W3009726326 endingPage "4787" @default.
• W3009726326 startingPage "4772" @default.
• W3009726326 abstract "Abnormality detection in medical images is a one-class classification problem for which existing methods typically involve variants of kernel principal component analysis or one-class support vector machines. However, existing methods rely on highly-curated training sets with full supervision, often using heuristics for model fitting or ignore the variances of the data within principal subspaces. In contrast, we propose novel methods that can work with imperfectly curated datasets using robust statistical learning, by extending the multivariate generalized-Gaussian distribution to a reproducing kernel Hilbert space (RKHS) and employing it within a mixture model. We propose a novel semi-supervised extension of our learning scheme, showing that a small amount of expert feedback through high-quality labeled data of the outlier class can boost performance. We propose expectation maximization for our semi-supervised robust mixture-model learning in RKHS, using solely the Gram matrix and without the explicit lifting map. Our methods incorporate optimal component means, principal directions, and variances for abnormality detection. Results on four large public datasets on retinopathy and cancer, compared against a variety of contemporary methods, show that our method gives benefits over the state of the art in one-class classification for abnormality detection." @default.
• W3009726326 created "2020-03-13" @default.
• W3009726326 creator A5010695311 @default.
• W3009726326 creator A5017642893 @default.
• W3009726326 date "2020-01-01" @default.
• W3009726326 modified "2023-09-26" @default.
• W3009726326 title "Semi-Supervised Robust Mixture Models in RKHS for Abnormality Detection in Medical Images" @default.
• W3009726326 cites W1484228140 @default.
• W3009726326 cites W1515999713 @default.
• W3009726326 cites W1570612738 @default.
• W3009726326 cites W170832280 @default.
• W3009726326 cites W1833167738 @default.
• W3009726326 cites W1903029394 @default.
• W3009726326 cites W1909952827 @default.
• W3009726326 cites W1968953480 @default.
• W3009726326 cites W1970088130 @default.
• W3009726326 cites W1979573625 @default.
• W3009726326 cites W1989222601 @default.
• W3009726326 cites W1992511687 @default.
• W3009726326 cites W1999598817 @default.
• W3009726326 cites W2024109869 @default.
• W3009726326 cites W2027429916 @default.
• W3009726326 cites W2044465660 @default.
• W3009726326 cites W2049694710 @default.
• W3009726326 cites W2050999345 @default.
• W3009726326 cites W2065301447 @default.
• W3009726326 cites W2072072671 @default.
• W3009726326 cites W2092101233 @default.
• W3009726326 cites W2093215004 @default.
• W3009726326 cites W2098004870 @default.
• W3009726326 cites W2100860054 @default.
• W3009726326 cites W2103914106 @default.
• W3009726326 cites W2104520867 @default.
• W3009726326 cites W2112796928 @default.
• W3009726326 cites W2119823327 @default.
• W3009726326 cites W2121947440 @default.
• W3009726326 cites W2123610365 @default.
• W3009726326 cites W2124431629 @default.
• W3009726326 cites W2129004009 @default.
• W3009726326 cites W2132603077 @default.
• W3009726326 cites W2132870739 @default.
• W3009726326 cites W2134432876 @default.
• W3009726326 cites W2140095548 @default.
• W3009726326 cites W2140638323 @default.
• W3009726326 cites W2143516773 @default.
• W3009726326 cites W2147800946 @default.
• W3009726326 cites W2152548630 @default.
• W3009726326 cites W2160167256 @default.
• W3009726326 cites W2161503240 @default.
• W3009726326 cites W2204904589 @default.
• W3009726326 cites W2277747675 @default.
• W3009726326 cites W2427838904 @default.
• W3009726326 cites W2626629100 @default.
• W3009726326 cites W2743138268 @default.
• W3009726326 cites W2752011355 @default.
• W3009726326 cites W2793994880 @default.
• W3009726326 cites W2889059876 @default.
• W3009726326 cites W2890023753 @default.
• W3009726326 cites W2891038994 @default.
• W3009726326 cites W2945559256 @default.
• W3009726326 cites W2952289578 @default.
• W3009726326 cites W2963291921 @default.
• W3009726326 cites W2963934397 @default.
• W3009726326 cites W4210997624 @default.
• W3009726326 cites W4239510810 @default.
• W3009726326 cites W2078830351 @default.
• W3009726326 doi "https://doi.org/10.1109/tip.2020.2975958" @default.
• W3009726326 hasPublicationYear "2020" @default.
• W3009726326 type Work @default.
• W3009726326 sameAs 3009726326 @default.
• W3009726326 citedByCount "13" @default.
• W3009726326 countsByYear W30097263262021 @default.
• W3009726326 countsByYear W30097263262022 @default.
• W3009726326 countsByYear W30097263262023 @default.
• W3009726326 crossrefType "journal-article" @default.
• W3009726326 hasAuthorship W3009726326A5010695311 @default.
• W3009726326 hasAuthorship W3009726326A5017642893 @default.
• W3009726326 hasConcept C105795698 @default.
• W3009726326 hasConcept C114614502 @default.
• W3009726326 hasConcept C119857082 @default.
• W3009726326 hasConcept C122280245 @default.
• W3009726326 hasConcept C12267149 @default.
• W3009726326 hasConcept C134306372 @default.
• W3009726326 hasConcept C153180895 @default.
• W3009726326 hasConcept C154945302 @default.
• W3009726326 hasConcept C182081679 @default.
• W3009726326 hasConcept C182335926 @default.
• W3009726326 hasConcept C27438332 @default.
• W3009726326 hasConcept C33923547 @default.
• W3009726326 hasConcept C41008148 @default.
• W3009726326 hasConcept C49781872 @default.
• W3009726326 hasConcept C61224824 @default.
• W3009726326 hasConcept C62799726 @default.
• W3009726326 hasConcept C74193536 @default.
• W3009726326 hasConcept C79337645 @default.
• W3009726326 hasConcept C80884492 @default.
• W3009726326 hasConceptScore W3009726326C105795698 @default.
• W3009726326 hasConceptScore W3009726326C114614502 @default.

• next