Matches in SemOpenAlex for { <https://semopenalex.org/work/W2109765961> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2109765961 abstract "Radiologists are adept at recognizing the character and extent of lung parenchymal abnormalities in computed tomography (CT) scans. However, the inconsistent differential diagnosis due to subjective aggregation necessitates the exploration of automated classification based on supervised or unsupervised learning. The robustness of supervised learning depends on the training samples. Towards optimizing emphysema classification, we introduce a physician-in-the-loop feedback approach to minimize ambiguity in the selected training samples. An experienced thoracic radiologist selected 412 regions of interest (ROIs) across 15 datasets to represent 124, 129, 139 and 20 training samples of mild, moderate, severe emphysema and normal appearance, respectively. Using multi-view (multiple metrics to capture complementary features) inductive learning, an ensemble of seven un-optimized support vector models (SVM) each based on a specific metric was constructed in less than 6 s. The training samples were classified using seven SVM models and consensus labels were created using majority voting. In the active relearning phase, the ensemble-expert label conflicts were resolved by the expert. The efficacy and generality of active relearning feedback was assessed in the optimized parameter space of six general purpose classifiers across the seven dissimilarity metrics. The proposed just-in-time active relearning feedback with un-optimized SVMs yielded 15 % increase in classification accuracy and 25 % reduction in the number of support vectors. The average improvement in accuracy of six classifiers in their optimized parameter space was 21 %. The proposed cooperative feedback method enhances the quality of training samples used to construct automated classification of emphysematous CT scans. Such an approach could lead to substantial improvement in quantification of emphysema." @default.
- W2109765961 created "2016-06-24" @default.
- W2109765961 creator A5028145127 @default.
- W2109765961 creator A5039361974 @default.
- W2109765961 creator A5043559155 @default.
- W2109765961 creator A5078743336 @default.
- W2109765961 creator A5084606087 @default.
- W2109765961 date "2014-04-26" @default.
- W2109765961 modified "2023-09-23" @default.
- W2109765961 title "Active Relearning for Robust Supervised Training of Emphysema Patterns" @default.
- W2109765961 cites W1510678483 @default.
- W2109765961 cites W1540856690 @default.
- W2109765961 cites W1572720249 @default.
- W2109765961 cites W1596717185 @default.
- W2109765961 cites W1602966110 @default.
- W2109765961 cites W1995554623 @default.
- W2109765961 cites W2006967044 @default.
- W2109765961 cites W2008873828 @default.
- W2109765961 cites W2011810280 @default.
- W2109765961 cites W2023448987 @default.
- W2109765961 cites W2065984169 @default.
- W2109765961 cites W2077201251 @default.
- W2109765961 cites W2081617920 @default.
- W2109765961 cites W2087643311 @default.
- W2109765961 cites W2094434667 @default.
- W2109765961 cites W2099085654 @default.
- W2109765961 cites W2103430291 @default.
- W2109765961 cites W2135514714 @default.
- W2109765961 cites W2139212933 @default.
- W2109765961 cites W2140815821 @default.
- W2109765961 cites W2150045166 @default.
- W2109765961 cites W2153364064 @default.
- W2109765961 cites W2153583660 @default.
- W2109765961 cites W2160794449 @default.
- W2109765961 cites W2169010722 @default.
- W2109765961 cites W2171332245 @default.
- W2109765961 doi "https://doi.org/10.1007/s10278-014-9686-z" @default.
- W2109765961 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4090407" @default.
- W2109765961 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/24771303" @default.
- W2109765961 hasPublicationYear "2014" @default.
- W2109765961 type Work @default.
- W2109765961 sameAs 2109765961 @default.
- W2109765961 citedByCount "1" @default.
- W2109765961 countsByYear W21097659612016 @default.
- W2109765961 crossrefType "journal-article" @default.
- W2109765961 hasAuthorship W2109765961A5028145127 @default.
- W2109765961 hasAuthorship W2109765961A5039361974 @default.
- W2109765961 hasAuthorship W2109765961A5043559155 @default.
- W2109765961 hasAuthorship W2109765961A5078743336 @default.
- W2109765961 hasAuthorship W2109765961A5084606087 @default.
- W2109765961 hasBestOaLocation W21097659612 @default.
- W2109765961 hasConcept C104317684 @default.
- W2109765961 hasConcept C119857082 @default.
- W2109765961 hasConcept C12267149 @default.
- W2109765961 hasConcept C153180895 @default.
- W2109765961 hasConcept C154945302 @default.
- W2109765961 hasConcept C185592680 @default.
- W2109765961 hasConcept C41008148 @default.
- W2109765961 hasConcept C55493867 @default.
- W2109765961 hasConcept C63479239 @default.
- W2109765961 hasConceptScore W2109765961C104317684 @default.
- W2109765961 hasConceptScore W2109765961C119857082 @default.
- W2109765961 hasConceptScore W2109765961C12267149 @default.
- W2109765961 hasConceptScore W2109765961C153180895 @default.
- W2109765961 hasConceptScore W2109765961C154945302 @default.
- W2109765961 hasConceptScore W2109765961C185592680 @default.
- W2109765961 hasConceptScore W2109765961C41008148 @default.
- W2109765961 hasConceptScore W2109765961C55493867 @default.
- W2109765961 hasConceptScore W2109765961C63479239 @default.
- W2109765961 hasLocation W21097659611 @default.
- W2109765961 hasLocation W21097659612 @default.
- W2109765961 hasLocation W21097659613 @default.
- W2109765961 hasLocation W21097659614 @default.
- W2109765961 hasOpenAccess W2109765961 @default.
- W2109765961 hasPrimaryLocation W21097659611 @default.
- W2109765961 hasRelatedWork W1566557568 @default.
- W2109765961 hasRelatedWork W1976518118 @default.
- W2109765961 hasRelatedWork W2032824151 @default.
- W2109765961 hasRelatedWork W2042795343 @default.
- W2109765961 hasRelatedWork W2079569387 @default.
- W2109765961 hasRelatedWork W2580550478 @default.
- W2109765961 hasRelatedWork W2973983613 @default.
- W2109765961 hasRelatedWork W3005931683 @default.
- W2109765961 hasRelatedWork W3009118275 @default.
- W2109765961 hasRelatedWork W3010530419 @default.
- W2109765961 hasRelatedWork W3012315407 @default.
- W2109765961 hasRelatedWork W3082947597 @default.
- W2109765961 hasRelatedWork W3110555371 @default.
- W2109765961 hasRelatedWork W3139502090 @default.
- W2109765961 hasRelatedWork W3148782712 @default.
- W2109765961 hasRelatedWork W3157655146 @default.
- W2109765961 hasRelatedWork W3160467162 @default.
- W2109765961 hasRelatedWork W3169409885 @default.
- W2109765961 hasRelatedWork W1543976151 @default.
- W2109765961 isParatext "false" @default.
- W2109765961 isRetracted "false" @default.
- W2109765961 magId "2109765961" @default.
- W2109765961 workType "article" @default.