Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048149209> ?p ?o ?g. }
- W3048149209 endingPage "29373" @default.
- W3048149209 startingPage "29353" @default.
- W3048149209 abstract "In this paper, we propose a quadtree based approach to capture the spatial information of medical images for explaining nonlinear SVM prediction. In medical image classification, interpretability becomes important to understand why the adopted model works. Explaining an SVM prediction is difficult due to implicit mapping done in kernel classification is uninformative about the position of data points in the feature space and the nature of the separating hyperplane in the original space. The proposed method finds ROIs which contain the discriminative regions behind the prediction. Localization of the discriminative region in small boxes can help in interpreting the prediction by SVM. Quadtree decomposition is applied recursively before applying SVMs on sub images and model identified ROIs are highlighted. Pictorial results of experiments on various medical image datasets prove the effectiveness of this approach. We validate the correctness of our method by applying occlusion methods." @default.
- W3048149209 created "2020-08-13" @default.
- W3048149209 creator A5018728658 @default.
- W3048149209 creator A5027442901 @default.
- W3048149209 creator A5053638739 @default.
- W3048149209 creator A5063234710 @default.
- W3048149209 creator A5086227422 @default.
- W3048149209 date "2020-08-11" @default.
- W3048149209 modified "2023-10-16" @default.
- W3048149209 title "Interpreting SVM for medical images using Quadtree" @default.
- W3048149209 cites W1581192802 @default.
- W3048149209 cites W1595438755 @default.
- W3048149209 cites W1865761 @default.
- W3048149209 cites W1966517947 @default.
- W3048149209 cites W1994899130 @default.
- W3048149209 cites W2008232587 @default.
- W3048149209 cites W2010049940 @default.
- W3048149209 cites W2025093810 @default.
- W3048149209 cites W2027084300 @default.
- W3048149209 cites W2035435951 @default.
- W3048149209 cites W2055957434 @default.
- W3048149209 cites W2075880488 @default.
- W3048149209 cites W2113641540 @default.
- W3048149209 cites W2114063873 @default.
- W3048149209 cites W2114980786 @default.
- W3048149209 cites W2119982438 @default.
- W3048149209 cites W2122026259 @default.
- W3048149209 cites W2131346203 @default.
- W3048149209 cites W2140392267 @default.
- W3048149209 cites W2148989106 @default.
- W3048149209 cites W2152551183 @default.
- W3048149209 cites W2154142492 @default.
- W3048149209 cites W2604091896 @default.
- W3048149209 cites W2756594072 @default.
- W3048149209 cites W2800395906 @default.
- W3048149209 cites W2803144007 @default.
- W3048149209 cites W2804951847 @default.
- W3048149209 cites W2997843867 @default.
- W3048149209 cites W3101781204 @default.
- W3048149209 doi "https://doi.org/10.1007/s11042-020-09431-2" @default.
- W3048149209 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7417748" @default.
- W3048149209 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32837249" @default.
- W3048149209 hasPublicationYear "2020" @default.
- W3048149209 type Work @default.
- W3048149209 sameAs 3048149209 @default.
- W3048149209 citedByCount "13" @default.
- W3048149209 countsByYear W30481492092021 @default.
- W3048149209 countsByYear W30481492092022 @default.
- W3048149209 countsByYear W30481492092023 @default.
- W3048149209 crossrefType "journal-article" @default.
- W3048149209 hasAuthorship W3048149209A5018728658 @default.
- W3048149209 hasAuthorship W3048149209A5027442901 @default.
- W3048149209 hasAuthorship W3048149209A5053638739 @default.
- W3048149209 hasAuthorship W3048149209A5063234710 @default.
- W3048149209 hasAuthorship W3048149209A5086227422 @default.
- W3048149209 hasBestOaLocation W30481492091 @default.
- W3048149209 hasConcept C11413529 @default.
- W3048149209 hasConcept C114614502 @default.
- W3048149209 hasConcept C115961682 @default.
- W3048149209 hasConcept C119857082 @default.
- W3048149209 hasConcept C12267149 @default.
- W3048149209 hasConcept C124101348 @default.
- W3048149209 hasConcept C138885662 @default.
- W3048149209 hasConcept C151416825 @default.
- W3048149209 hasConcept C153180895 @default.
- W3048149209 hasConcept C154945302 @default.
- W3048149209 hasConcept C2524010 @default.
- W3048149209 hasConcept C2776401178 @default.
- W3048149209 hasConcept C2781067378 @default.
- W3048149209 hasConcept C33923547 @default.
- W3048149209 hasConcept C41008148 @default.
- W3048149209 hasConcept C41895202 @default.
- W3048149209 hasConcept C55439883 @default.
- W3048149209 hasConcept C68693459 @default.
- W3048149209 hasConcept C74193536 @default.
- W3048149209 hasConcept C83665646 @default.
- W3048149209 hasConcept C97931131 @default.
- W3048149209 hasConceptScore W3048149209C11413529 @default.
- W3048149209 hasConceptScore W3048149209C114614502 @default.
- W3048149209 hasConceptScore W3048149209C115961682 @default.
- W3048149209 hasConceptScore W3048149209C119857082 @default.
- W3048149209 hasConceptScore W3048149209C12267149 @default.
- W3048149209 hasConceptScore W3048149209C124101348 @default.
- W3048149209 hasConceptScore W3048149209C138885662 @default.
- W3048149209 hasConceptScore W3048149209C151416825 @default.
- W3048149209 hasConceptScore W3048149209C153180895 @default.
- W3048149209 hasConceptScore W3048149209C154945302 @default.
- W3048149209 hasConceptScore W3048149209C2524010 @default.
- W3048149209 hasConceptScore W3048149209C2776401178 @default.
- W3048149209 hasConceptScore W3048149209C2781067378 @default.
- W3048149209 hasConceptScore W3048149209C33923547 @default.
- W3048149209 hasConceptScore W3048149209C41008148 @default.
- W3048149209 hasConceptScore W3048149209C41895202 @default.
- W3048149209 hasConceptScore W3048149209C55439883 @default.
- W3048149209 hasConceptScore W3048149209C68693459 @default.
- W3048149209 hasConceptScore W3048149209C74193536 @default.
- W3048149209 hasConceptScore W3048149209C83665646 @default.
- W3048149209 hasConceptScore W3048149209C97931131 @default.