FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2017179699> ?p ?o ?g. }

• W2017179699 endingPage "1178" @default.
• W2017179699 startingPage "1171" @default.
• W2017179699 abstract "Rationale and Objectives The aim of this study was to investigate whether using a fractal dimension as an objective index (quantitative measure) to assess and control the “visual” or “texture” similarity of reference-image regions selected by a content-based image retrieval (CBIR) scheme would (or would not) affect the performance of the scheme in classification between image regions depicting suspicious breast masses. Materials and Methods An image data set depicting 1500 verified mass regions and 1500 false-positive mass regions was used. Fourteen morphologic and intensity distribution features and a fractal dimension were computed. A CBIR scheme using a k-nearest neighbor classifier was applied, and two experiments were conducted. In the first experiment, the CBIR scheme was evaluated using all 15 features. In the second experiment, the fractal dimension was used as a prescreening feature to guide the CBIR scheme to search for the most similar reference images that had similar measures in the fractal dimension. Results The CBIR scheme achieved classification performance with areas under the receiver-operating characteristic curve of 0.857 (95% confidence interval [CI], 0.844–0.870) using 14 features and 0.866 (95% CI, 0.853–0.879) after adding the fractal dimension (P = .005 for both results). After using the fractal dimension as a prescreening feature, the CBIR scheme achieved an area under the receiver-operating characteristic curve of 0.851 (95% CI, 0.837–0.864), without a significant difference from the previous result using the original 14 features (P = .120). The difference of fractal dimension values between the selected similar reference images was reduced by 56.7%, indicating improvement in image texture similarity. In addition, more than half of references were discarded early, without similarity comparisons, indicating improvement in searching efficiency. Conclusions This study demonstrated the feasibility of applying a fractal dimension as an objective (quantitative) and efficient search index to assess and maintain the texture similarity of reference mass regions selected by a CBIR scheme without reducing the scheme's performance in classifying suspicious breast masses. The aim of this study was to investigate whether using a fractal dimension as an objective index (quantitative measure) to assess and control the “visual” or “texture” similarity of reference-image regions selected by a content-based image retrieval (CBIR) scheme would (or would not) affect the performance of the scheme in classification between image regions depicting suspicious breast masses. An image data set depicting 1500 verified mass regions and 1500 false-positive mass regions was used. Fourteen morphologic and intensity distribution features and a fractal dimension were computed. A CBIR scheme using a k-nearest neighbor classifier was applied, and two experiments were conducted. In the first experiment, the CBIR scheme was evaluated using all 15 features. In the second experiment, the fractal dimension was used as a prescreening feature to guide the CBIR scheme to search for the most similar reference images that had similar measures in the fractal dimension. The CBIR scheme achieved classification performance with areas under the receiver-operating characteristic curve of 0.857 (95% confidence interval [CI], 0.844–0.870) using 14 features and 0.866 (95% CI, 0.853–0.879) after adding the fractal dimension (P = .005 for both results). After using the fractal dimension as a prescreening feature, the CBIR scheme achieved an area under the receiver-operating characteristic curve of 0.851 (95% CI, 0.837–0.864), without a significant difference from the previous result using the original 14 features (P = .120). The difference of fractal dimension values between the selected similar reference images was reduced by 56.7%, indicating improvement in image texture similarity. In addition, more than half of references were discarded early, without similarity comparisons, indicating improvement in searching efficiency. This study demonstrated the feasibility of applying a fractal dimension as an objective (quantitative) and efficient search index to assess and maintain the texture similarity of reference mass regions selected by a CBIR scheme without reducing the scheme's performance in classifying suspicious breast masses." @default.
• W2017179699 created "2016-06-24" @default.
• W2017179699 creator A5040403651 @default.
• W2017179699 creator A5045998635 @default.
• W2017179699 creator A5089558117 @default.
• W2017179699 date "2009-10-01" @default.
• W2017179699 modified "2023-10-04" @default.
• W2017179699 title "Assessment of Performance Improvement in Content-based Medical Image Retrieval Schemes Using Fractal Dimension" @default.
• W2017179699 cites W1973223234 @default.
• W2017179699 cites W1978517039 @default.
• W2017179699 cites W1982326116 @default.
• W2017179699 cites W1983093502 @default.
• W2017179699 cites W2020216156 @default.
• W2017179699 cites W2021940526 @default.
• W2017179699 cites W2022415747 @default.
• W2017179699 cites W2026506545 @default.
• W2017179699 cites W2034354125 @default.
• W2017179699 cites W2067485484 @default.
• W2017179699 cites W2070491180 @default.
• W2017179699 cites W2080846788 @default.
• W2017179699 cites W2082751466 @default.
• W2017179699 cites W2088970509 @default.
• W2017179699 cites W2090528363 @default.
• W2017179699 cites W2113180829 @default.
• W2017179699 cites W2130660124 @default.
• W2017179699 cites W2134044542 @default.
• W2017179699 cites W2137190664 @default.
• W2017179699 cites W2150242770 @default.
• W2017179699 cites W2160560129 @default.
• W2017179699 cites W4242301555 @default.
• W2017179699 cites W4256385216 @default.
• W2017179699 doi "https://doi.org/10.1016/j.acra.2009.04.009" @default.
• W2017179699 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/2779846" @default.
• W2017179699 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/19524455" @default.
• W2017179699 hasPublicationYear "2009" @default.
• W2017179699 type Work @default.
• W2017179699 sameAs 2017179699 @default.
• W2017179699 citedByCount "15" @default.
• W2017179699 countsByYear W20171796992012 @default.
• W2017179699 countsByYear W20171796992014 @default.
• W2017179699 countsByYear W20171796992015 @default.
• W2017179699 countsByYear W20171796992017 @default.
• W2017179699 countsByYear W20171796992020 @default.
• W2017179699 crossrefType "journal-article" @default.
• W2017179699 hasAuthorship W2017179699A5040403651 @default.
• W2017179699 hasAuthorship W2017179699A5045998635 @default.
• W2017179699 hasAuthorship W2017179699A5089558117 @default.
• W2017179699 hasBestOaLocation W20171796992 @default.
• W2017179699 hasConcept C105795698 @default.
• W2017179699 hasConcept C115961682 @default.
• W2017179699 hasConcept C134306372 @default.
• W2017179699 hasConcept C138885662 @default.
• W2017179699 hasConcept C153180895 @default.
• W2017179699 hasConcept C154945302 @default.
• W2017179699 hasConcept C162494671 @default.
• W2017179699 hasConcept C1667742 @default.
• W2017179699 hasConcept C202444582 @default.
• W2017179699 hasConcept C26546657 @default.
• W2017179699 hasConcept C2776401178 @default.
• W2017179699 hasConcept C2780052074 @default.
• W2017179699 hasConcept C33676613 @default.
• W2017179699 hasConcept C33923547 @default.
• W2017179699 hasConcept C40636538 @default.
• W2017179699 hasConcept C41008148 @default.
• W2017179699 hasConcept C41895202 @default.
• W2017179699 hasConcept C58471807 @default.
• W2017179699 hasConceptScore W2017179699C105795698 @default.
• W2017179699 hasConceptScore W2017179699C115961682 @default.
• W2017179699 hasConceptScore W2017179699C134306372 @default.
• W2017179699 hasConceptScore W2017179699C138885662 @default.
• W2017179699 hasConceptScore W2017179699C153180895 @default.
• W2017179699 hasConceptScore W2017179699C154945302 @default.
• W2017179699 hasConceptScore W2017179699C162494671 @default.
• W2017179699 hasConceptScore W2017179699C1667742 @default.
• W2017179699 hasConceptScore W2017179699C202444582 @default.
• W2017179699 hasConceptScore W2017179699C26546657 @default.
• W2017179699 hasConceptScore W2017179699C2776401178 @default.
• W2017179699 hasConceptScore W2017179699C2780052074 @default.
• W2017179699 hasConceptScore W2017179699C33676613 @default.
• W2017179699 hasConceptScore W2017179699C33923547 @default.
• W2017179699 hasConceptScore W2017179699C40636538 @default.
• W2017179699 hasConceptScore W2017179699C41008148 @default.
• W2017179699 hasConceptScore W2017179699C41895202 @default.
• W2017179699 hasConceptScore W2017179699C58471807 @default.
• W2017179699 hasIssue "10" @default.
• W2017179699 hasLocation W20171796991 @default.
• W2017179699 hasLocation W20171796992 @default.
• W2017179699 hasLocation W20171796993 @default.
• W2017179699 hasLocation W20171796994 @default.
• W2017179699 hasOpenAccess W2017179699 @default.
• W2017179699 hasPrimaryLocation W20171796991 @default.
• W2017179699 hasRelatedWork W1485671534 @default.
• W2017179699 hasRelatedWork W1899065381 @default.
• W2017179699 hasRelatedWork W201553385 @default.
• W2017179699 hasRelatedWork W2022698958 @default.
• W2017179699 hasRelatedWork W2053621563 @default.
• W2017179699 hasRelatedWork W2073797589 @default.
• W2017179699 hasRelatedWork W2150823093 @default.

• next