{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:34:15Z","timestamp":1775583255058,"version":"3.50.1"},"reference-count":29,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T00:00:00Z","timestamp":1567900800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100008363","name":"Kr\u00e6ftens Bek\u00e6mpelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008363","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clin Physio Funct Imaging"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:title>Summary<\/jats:title><jats:sec><jats:title>Aim<\/jats:title><jats:p>To test the feasibility of a fully automated artificial intelligence\u2010based method providing <jats:styled-content style=\"fixed-case\">PET<\/jats:styled-content> measures of prostate cancer (<jats:styled-content style=\"fixed-case\">PC<\/jats:styled-content>a).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A convolutional neural network (<jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content>) was trained for automated measurements in <jats:sup>18<\/jats:sup>F\u2010choline (<jats:styled-content style=\"fixed-case\">FCH<\/jats:styled-content>) <jats:styled-content style=\"fixed-case\">PET<\/jats:styled-content>\/<jats:styled-content style=\"fixed-case\">CT<\/jats:styled-content> scans obtained prior to radical prostatectomy (<jats:styled-content style=\"fixed-case\">RP<\/jats:styled-content>) in 45 patients with newly diagnosed <jats:styled-content style=\"fixed-case\">PC<\/jats:styled-content>a. Automated values were obtained for prostate volume, maximal standardized uptake value (<jats:styled-content style=\"fixed-case\">SUV<\/jats:styled-content><jats:sub>max<\/jats:sub>), mean standardized uptake value of voxels considered abnormal (<jats:styled-content style=\"fixed-case\">SUV<\/jats:styled-content><jats:sub>mean<\/jats:sub>) and volume of abnormal voxels (Vol<jats:sub>abn<\/jats:sub>). The product <jats:styled-content style=\"fixed-case\">SUV<\/jats:styled-content><jats:sub>mean<\/jats:sub>\u00a0\u00d7\u00a0Vol<jats:sub>abn<\/jats:sub> was calculated to reflect total lesion uptake (<jats:styled-content style=\"fixed-case\">TLU<\/jats:styled-content>). Corresponding manual measurements were performed. <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content>\u2010estimated data were compared with the weighted surgically removed tissue specimens and manually derived data and related to clinical parameters assuming that 1\u00a0g\u00a0\u2248\u00a01\u00a0ml of tissue.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The mean (range) weight of the prostate specimens was 44\u00a0g (20\u2013109), while <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content>\u2010estimated volume was 62\u00a0ml (31\u2013108) with a mean difference of 13\u00b75\u00a0g or ml (95% <jats:styled-content style=\"fixed-case\">CI<\/jats:styled-content>: 9\u00b778\u201317\u00b732). The two measures were significantly correlated (<jats:italic>r\u00a0<\/jats:italic>=<jats:italic>\u00a0<\/jats:italic>0\u00b777, <jats:italic>P<\/jats:italic>&lt;0\u00b7001). Mean differences (95% <jats:styled-content style=\"fixed-case\">CI<\/jats:styled-content>) between <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content>\u2010based and manually derived <jats:styled-content style=\"fixed-case\">PET<\/jats:styled-content> measures of <jats:styled-content style=\"fixed-case\">SUV<\/jats:styled-content>max, <jats:styled-content style=\"fixed-case\">SUV<\/jats:styled-content>mean, Vol<jats:sub>abn<\/jats:sub> (ml) and <jats:styled-content style=\"fixed-case\">TLU<\/jats:styled-content> were 0\u00b737 (\u22120\u00b701 to 0\u00b775), \u22120\u00b708 (\u22120\u00b730 to 0\u00b714), 1\u00b740 (\u22122\u00b726 to 5\u00b706) and 9\u00b761 (\u22123\u00b795 to 23\u00b717), respectively. <jats:styled-content style=\"fixed-case\">PET<\/jats:styled-content> findings Vol<jats:sub>abn<\/jats:sub> and <jats:styled-content style=\"fixed-case\">TLU<\/jats:styled-content> correlated with <jats:styled-content style=\"fixed-case\">PSA<\/jats:styled-content> (<jats:italic>P<\/jats:italic>&lt;0\u00b705), but not with Gleason score or stage.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Automated <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content> segmentation provided in seconds volume and simple <jats:styled-content style=\"fixed-case\">PET<\/jats:styled-content> measures similar to manually derived ones. Further studies on automated <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content> segmentation with newer tracers such as radiolabelled prostate\u2010specific membrane antigen are warranted.<\/jats:p><\/jats:sec>","DOI":"10.1111\/cpf.12592","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T09:28:14Z","timestamp":1566466094000},"page":"399-406","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Artificial intelligence\u2010based versus manual assessment of prostate cancer in the prostate gland: a method comparison study"],"prefix":"10.1111","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7065-9623","authenticated-orcid":false,"given":"Mike A.","family":"Mortensen","sequence":"first","affiliation":[{"name":"Department of Urology Odense University Hospital Odense Denmark"},{"name":"Department of Clinical Research University of Southern Denmark Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Borrelli","sequence":"additional","affiliation":[{"name":"Department of Clinical Physiology Sahlgrenska University Hospital Gothenburg Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mads Hvid","family":"Poulsen","sequence":"additional","affiliation":[{"name":"Department of Urology Odense University Hospital Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oke","family":"Gerke","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine Odense University Hospital Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olof","family":"Enqvist","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Ul\u00e9n","sequence":"additional","affiliation":[{"name":"Eigenvision AB Malm\u00f6 Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7116-303X","authenticated-orcid":false,"given":"Elin","family":"Tr\u00e4g\u00e5rdh","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Physiology Sk\u00e5ne University Hospital Malm\u00f6 Sweden"},{"name":"Department of Translational Medicine Lund University Malm\u00f6 Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caius","family":"Constantinescu","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine Odense University Hospital Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Edenbrandt","sequence":"additional","affiliation":[{"name":"Department of Clinical Physiology Sahlgrenska University Hospital Gothenburg Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Lund","sequence":"additional","affiliation":[{"name":"Department of Urology Odense University Hospital Odense Denmark"},{"name":"Department of Clinical Research University of Southern Denmark Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Poul Flemming","family":"H\u00f8ilund\u2010Carlsen","sequence":"additional","affiliation":[{"name":"Department of Clinical Research University of Southern Denmark Odense Denmark"},{"name":"Department of Nuclear Medicine Odense University Hospital Odense Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,9,8]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.10.4923"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11307-017-1146-y"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40618-3"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2018.1093"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.09090413"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(86)90837-8"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.280.11.969"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00345-018-2524-z"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0000000000000530"},{"key":"e_1_2_8_11_1","first-page":"1642","article-title":"Detection and localization of prostate cancer: correlation of (11)C\u2010choline PET\/CT with histopathologic step\u2010section analysis","volume":"46","author":"Farsad M","year":"2005","journal-title":"J Nucl Med"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-017-3700-x"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5347(05)63946-8"},{"key":"e_1_2_8_14_1","unstructured":"JaderbergM SimonyanK ZissermanA et\u00a0al.Spatial transformer networks.eprint arXiv:1506.02025(2015): arXiv:1506.02025."},{"key":"e_1_2_8_15_1","unstructured":"KingmaDP BaJ.Adam: A Method for Stochastic Optimization.eprint arXiv:1412.6980(2014): arXiv:1412.6980."},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2010.03.002"},{"key":"e_1_2_8_17_1","first-page":"262","article-title":"Localization of primary prostate cancer with dual\u2010phase 18F\u2010fluorocholine PET","volume":"47","author":"Kwee SA","year":"2006","journal-title":"J Nucl Med"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.2310\/7290.2008.00002"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-017-0264-5"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1590\/S1677-5538.IBJU.2014.06.14"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prnil.2019.01.002"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2016.08.003"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2012.07.040"},{"key":"e_1_2_8_26_1","first-page":"1249","article-title":"Imaging prostate cancer with 11C\u2010choline PET\/CT","volume":"47","author":"Reske SN","year":"2006","journal-title":"J Nucl Med"},{"key":"e_1_2_8_27_1","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: Convolutional Networks for Biomedical Image Segmentation.eprint arXiv:1505.04597(2015): arXiv:1505.04597."},{"key":"e_1_2_8_28_1","first-page":"63","article-title":"Deep learning and its application to medical image segmentation","volume":"36","author":"Roth HR","year":"2018","journal-title":"Med Imaging Technol"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/modpathol.2010.178"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-017-0269-0"}],"updated-by":[{"DOI":"10.1111\/cpf.12617","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2020,2,3]],"date-time":"2020-02-03T00:00:00Z","timestamp":1580688000000}}],"container-title":["Clinical Physiology and Functional Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fcpf.12592","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cpf.12592","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cpf.12592","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cpf.12592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T23:31:29Z","timestamp":1694129489000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cpf.12592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,8]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["10.1111\/cpf.12592"],"URL":"https:\/\/doi.org\/10.1111\/cpf.12592","archive":["Portico"],"relation":{"erratum":[{"id-type":"doi","id":"10.1111\/cpf.12617","asserted-by":"object"}]},"ISSN":["1475-0961","1475-097X"],"issn-type":[{"value":"1475-0961","type":"print"},{"value":"1475-097X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,8]]},"assertion":[{"value":"2019-03-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}