Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912784907> ?p ?o ?g. }
- W2912784907 endingPage "543" @default.
- W2912784907 startingPage "538" @default.
- W2912784907 abstract "Abstract Background Actinic keratosis (AK) is a common premalignant skin lesion that can potentially progress to squamous cell carcinoma. Appropriate long‐term management of AK requires close patient monitoring in addition to therapeutic interventions. Computer‐aided diagnostic systems based on clinical photography might evolve in the future into valuable adjuncts to AK patient management. The present study proposes a late fusion approach of color‐texture features (shallow features) and deep features extracted from pre‐trained convolutional neural networks (CNN) to boost AK detection accuracy on clinical photographs. Materials and Methods System uses a sliding rectangular window of 50 × 50 pixels and a classifier that assigns the window region to either the AK or the healthy skin class. 6010 and 13 915 cropped regions of interest (ROI) of 50 × 50 pixels of AK and healthy skin, respectively, from 22 patients were used for system implementation. Different support vector machine (SVM) classifiers employing shallow or deep features and their late fusion using the max rule at decision level were compared with the McNemar test and Yule's Q ‐statistic. Results Support vector machine classifiers based on deep and shallow features exhibited overall competitive performances with complementary improvements in detection accuracy. Late fusion yielded significant improvement (6%) in both sensitivity (87%) and specificity (86%) compared to single classifier performance. Conclusion The parallel improvement of sensitivity and specificity is encouraging, demonstrating the potential use of our system in evaluating AK burden. The latter might be of value in future clinical studies for the comparison of field‐directed treatment interventions." @default.
- W2912784907 created "2019-02-21" @default.
- W2912784907 creator A5007939716 @default.
- W2912784907 creator A5011784602 @default.
- W2912784907 creator A5021354047 @default.
- W2912784907 creator A5081961495 @default.
- W2912784907 date "2019-02-14" @default.
- W2912784907 modified "2023-09-27" @default.
- W2912784907 title "Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography" @default.
- W2912784907 cites W1480009832 @default.
- W2912784907 cites W1964143601 @default.
- W2912784907 cites W1983210231 @default.
- W2912784907 cites W2001609415 @default.
- W2912784907 cites W2006607153 @default.
- W2912784907 cites W2044658535 @default.
- W2912784907 cites W2047970921 @default.
- W2912784907 cites W2050909534 @default.
- W2912784907 cites W2051956976 @default.
- W2912784907 cites W2062118960 @default.
- W2912784907 cites W2067225558 @default.
- W2912784907 cites W2092170487 @default.
- W2912784907 cites W2097117768 @default.
- W2912784907 cites W2105478370 @default.
- W2912784907 cites W2112391921 @default.
- W2912784907 cites W2115629999 @default.
- W2912784907 cites W2131264832 @default.
- W2912784907 cites W2161588624 @default.
- W2912784907 cites W2171277124 @default.
- W2912784907 cites W2346062110 @default.
- W2912784907 cites W2426942631 @default.
- W2912784907 cites W2433088494 @default.
- W2912784907 cites W2527700229 @default.
- W2912784907 cites W2542432275 @default.
- W2912784907 cites W2581082771 @default.
- W2912784907 cites W2592451060 @default.
- W2912784907 cites W2594806444 @default.
- W2912784907 cites W2605411519 @default.
- W2912784907 cites W2621367454 @default.
- W2912784907 cites W2732064045 @default.
- W2912784907 cites W2808086448 @default.
- W2912784907 cites W394822595 @default.
- W2912784907 doi "https://doi.org/10.1111/srt.12684" @default.
- W2912784907 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30762255" @default.
- W2912784907 hasPublicationYear "2019" @default.
- W2912784907 type Work @default.
- W2912784907 sameAs 2912784907 @default.
- W2912784907 citedByCount "5" @default.
- W2912784907 countsByYear W29127849072020 @default.
- W2912784907 countsByYear W29127849072021 @default.
- W2912784907 countsByYear W29127849072022 @default.
- W2912784907 countsByYear W29127849072023 @default.
- W2912784907 crossrefType "journal-article" @default.
- W2912784907 hasAuthorship W2912784907A5007939716 @default.
- W2912784907 hasAuthorship W2912784907A5011784602 @default.
- W2912784907 hasAuthorship W2912784907A5021354047 @default.
- W2912784907 hasAuthorship W2912784907A5081961495 @default.
- W2912784907 hasConcept C108583219 @default.
- W2912784907 hasConcept C12267149 @default.
- W2912784907 hasConcept C142724271 @default.
- W2912784907 hasConcept C153180895 @default.
- W2912784907 hasConcept C154945302 @default.
- W2912784907 hasConcept C160633673 @default.
- W2912784907 hasConcept C2777873816 @default.
- W2912784907 hasConcept C3019992690 @default.
- W2912784907 hasConcept C41008148 @default.
- W2912784907 hasConcept C71924100 @default.
- W2912784907 hasConcept C81363708 @default.
- W2912784907 hasConcept C95623464 @default.
- W2912784907 hasConceptScore W2912784907C108583219 @default.
- W2912784907 hasConceptScore W2912784907C12267149 @default.
- W2912784907 hasConceptScore W2912784907C142724271 @default.
- W2912784907 hasConceptScore W2912784907C153180895 @default.
- W2912784907 hasConceptScore W2912784907C154945302 @default.
- W2912784907 hasConceptScore W2912784907C160633673 @default.
- W2912784907 hasConceptScore W2912784907C2777873816 @default.
- W2912784907 hasConceptScore W2912784907C3019992690 @default.
- W2912784907 hasConceptScore W2912784907C41008148 @default.
- W2912784907 hasConceptScore W2912784907C71924100 @default.
- W2912784907 hasConceptScore W2912784907C81363708 @default.
- W2912784907 hasConceptScore W2912784907C95623464 @default.
- W2912784907 hasIssue "4" @default.
- W2912784907 hasLocation W29127849071 @default.
- W2912784907 hasLocation W29127849072 @default.
- W2912784907 hasOpenAccess W2912784907 @default.
- W2912784907 hasPrimaryLocation W29127849071 @default.
- W2912784907 hasRelatedWork W2731899572 @default.
- W2912784907 hasRelatedWork W2996933976 @default.
- W2912784907 hasRelatedWork W2999805992 @default.
- W2912784907 hasRelatedWork W3116150086 @default.
- W2912784907 hasRelatedWork W3133861977 @default.
- W2912784907 hasRelatedWork W3208266890 @default.
- W2912784907 hasRelatedWork W4200173597 @default.
- W2912784907 hasRelatedWork W4291897433 @default.
- W2912784907 hasRelatedWork W4312417841 @default.
- W2912784907 hasRelatedWork W4321369474 @default.
- W2912784907 hasVolume "25" @default.
- W2912784907 isParatext "false" @default.
- W2912784907 isRetracted "false" @default.