{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:24:36Z","timestamp":1757701476143,"version":"3.40.5"},"reference-count":37,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T00:00:00Z","timestamp":1550102400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Skin Research and Technology"],"published-print":{"date-parts":[[2019,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Actinic keratosis (AK) is a common premalignant skin lesion that can potentially progress to squamous cell carcinoma. Appropriate long\u2010term management of AK requires close patient monitoring in addition to therapeutic interventions. Computer\u2010aided 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\u2010texture features (shallow features) and deep features extracted from pre\u2010trained convolutional neural networks (CNN) to boost AK detection accuracy on clinical photographs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>System uses a sliding rectangular window of 50\u00a0\u00d7\u00a050 pixels and a classifier that assigns the window region to either the AK or the healthy skin class. 6010 and 13\u00a0915 cropped regions of interest (ROI) of 50\u00a0\u00d7\u00a050 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 <jats:italic>Q<\/jats:italic>\u2010statistic.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>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\u2010directed treatment interventions.<\/jats:p><\/jats:sec>","DOI":"10.1111\/srt.12684","type":"journal-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T11:20:00Z","timestamp":1550143200000},"page":"538-543","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography"],"prefix":"10.1111","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5021-6577","authenticated-orcid":false,"given":"Panagiota","family":"Spyridonos","sequence":"first","affiliation":[{"name":"Department of Medical Physics Faculty of Medicine School of Health Sciences University of Ioannina  Ioannina Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Gaitanis","sequence":"additional","affiliation":[{"name":"Department of Skin and Venereal Diseases Faculty of Medicine School of Health Sciences University of Ioannina  Ioannina Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aristidis","family":"Likas","sequence":"additional","affiliation":[{"name":"Department of Computer Science &amp; Engineering University of Ioannina  Ioannina Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis D.","family":"Bassukas","sequence":"additional","affiliation":[{"name":"Department of Skin and Venereal Diseases Faculty of Medicine School of Health Sciences University of Ioannina  Ioannina Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,2,14]]},"reference":[{"key":"e_1_2_5_2_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2016.4733"},{"key":"e_1_2_5_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12325-015-0211-7"},{"key":"e_1_2_5_4_1","first-page":"184","article-title":"Cost for the treatment of actinic keratosis on the rise in Australia","volume":"3","author":"Perera E","year":"2014","journal-title":"F1000Res"},{"key":"e_1_2_5_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2012.10.001"},{"key":"e_1_2_5_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/0394632017697719"},{"key":"e_1_2_5_7_1","doi-asserted-by":"publisher","DOI":"10.2174\/1872213X11307020008"},{"key":"e_1_2_5_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.12629"},{"key":"e_1_2_5_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00403-013-1413-y"},{"key":"e_1_2_5_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0846.2008.00304.x"},{"key":"e_1_2_5_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/jdv.13720"},{"key":"e_1_2_5_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1524-4725.2008.34195.x"},{"key":"e_1_2_5_13_1","doi-asserted-by":"publisher","DOI":"10.1001\/archdermatol.2012.1060"},{"key":"e_1_2_5_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2008.2011156"},{"key":"e_1_2_5_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2011.02.007"},{"key":"e_1_2_5_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0076212"},{"key":"e_1_2_5_17_1","doi-asserted-by":"publisher","DOI":"10.4172\/2155-9538.1000170"},{"key":"e_1_2_5_18_1","first-page":"220","article-title":"Precision diagnosis of melanoma and other skin lesions from digital images","volume":"2017","author":"Bhattacharya A","year":"2017","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"e_1_2_5_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_5_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-5389-1_4"},{"key":"e_1_2_5_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2016.7493528"},{"key":"e_1_2_5_22_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0112447"},{"key":"e_1_2_5_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.07.001"},{"key":"e_1_2_5_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"e_1_2_5_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.025"},{"key":"e_1_2_5_26_1","doi-asserted-by":"publisher","DOI":"10.1001\/archderm.139.1.66"},{"key":"e_1_2_5_27_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-91"},{"key":"e_1_2_5_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022859003006"},{"key":"e_1_2_5_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"e_1_2_5_30_1","first-page":"1097","volume-title":"Proc 25th Int Conf Neural Inf Process Syst \u2013 Vol 1","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_5_31_1","first-page":"538","volume-title":"Int Conf Learn Represent","author":"Simonyan K","year":"2015"},{"key":"e_1_2_5_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_5_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13555-015-0070-9"},{"key":"e_1_2_5_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2072789"},{"issue":"3","key":"e_1_2_5_35_1","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt JC","year":"1999","journal-title":"Adv Large Margin Classif"},{"key":"e_1_2_5_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/09546634.2016.1254328"},{"key":"e_1_2_5_37_1","doi-asserted-by":"publisher","DOI":"10.2340\/00015555-2539"},{"key":"e_1_2_5_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.16826"}],"container-title":["Skin Research and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fsrt.12684","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/srt.12684","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/srt.12684","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/srt.12684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T19:31:49Z","timestamp":1694287909000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/srt.12684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,14]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["10.1111\/srt.12684"],"URL":"https:\/\/doi.org\/10.1111\/srt.12684","archive":["Portico"],"relation":{},"ISSN":["0909-752X","1600-0846"],"issn-type":[{"type":"print","value":"0909-752X"},{"type":"electronic","value":"1600-0846"}],"subject":[],"published":{"date-parts":[[2019,2,14]]},"assertion":[{"value":"2018-09-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-01-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}