{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T16:58:05Z","timestamp":1788022685899,"version":"build-2784847793"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T00:00:00Z","timestamp":1651017600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T00:00:00Z","timestamp":1651017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","award":["-"],"award-info":[{"award-number":["-"]}],"id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Swedish Prostate Cancer Foundation","award":["-"],"award-info":[{"award-number":["-"]}]},{"DOI":"10.13039\/501100003252","name":"Lund University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003252","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur J Nucl Med Mol Imaging"],"published-print":{"date-parts":[[2022,8]]},"abstract":"<jats:title>Abstract\n<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [<jats:sup>18<\/jats:sup>F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>[<jats:sup>18<\/jats:sup>F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement between the three readers were assessed in a separate test group of 50 patients.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The sensitivity of the AI method for detecting pelvic lymph node metastases was 82%, and the corresponding sensitivity for the human readers was 77% on average. The average number of false positives was 1.8 per patient. A total of 5\u201317 false negative lesions in the whole cohort were found, depending on which reader was used as a reference. The method is available for researchers at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.recomia.org\">www.recomia.org<\/jats:ext-link>.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>This study shows that AI can obtain a sensitivity on par with that of physicians with a reasonable number of false positives. The difficulty in achieving high inter-observer sensitivity emphasizes the need for automated methods. On the road to qualifying AI tools for clinical use, independent validation is critical and allows performance to be assessed in studies from different hospitals. Therefore, we have made our AI tool freely available to other researchers.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s00259-022-05806-9","type":"journal-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T10:04:16Z","timestamp":1651053856000},"page":"3412-3418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Freely available artificial intelligence for pelvic lymph node metastases in PSMA PET-CT that performs on par with nuclear medicine physicians"],"prefix":"10.1007","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7116-303X","authenticated-orcid":false,"given":"Elin","family":"Tr\u00e4g\u00e5rdh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olof","family":"Enqvist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Ul\u00e9n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erland","family":"Hvittfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabine","family":"Garpered","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah Lindgren","family":"Belal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders","family":"Bjartell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Edenbrandt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,4,27]]},"reference":[{"issue":"5","key":"5806_CR1","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1016\/j.juro.2015.12.025","volume":"195","author":"T Maurer","year":"2016","unstructured":"Maurer T, et al. Diagnostic efficacy of (68)gallium-PSMA positron emission tomography compared to conventional imaging for lymph node staging of 130 consecutive patients with intermediate to high risk prostate cancer. J Urol. 2016;195(5):1436\u201343. https:\/\/doi.org\/10.1016\/j.juro.2015.12.025.","journal-title":"J Urol"},{"issue":"4","key":"5806_CR2","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.eururo.2015.12.051","volume":"70","author":"A Herlemann","year":"2016","unstructured":"Herlemann A, et al. (68)Ga-PSMA positron emission tomography\/computed tomography provides accurate staging of lymph node regions prior to lymph node dissection in patients with prostate cancer. Eur Urol. 2016;70(4):553\u20137. https:\/\/doi.org\/10.1016\/j.eururo.2015.12.051.","journal-title":"Eur Urol"},{"issue":"3","key":"5806_CR3","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11307-016-0957-6","volume":"18","author":"SP Rowe","year":"2016","unstructured":"Rowe SP, et al. PSMA-based [(18)F]DCFPyL PET\/CT is superior to conventional imaging for lesion detection in patients with metastatic prostate cancer. Mol Imaging Biol. 2016;18(3):411\u20139. https:\/\/doi.org\/10.1007\/s11307-016-0957-6.","journal-title":"Mol Imaging Biol"},{"issue":"10231","key":"5806_CR4","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1016\/S0140-6736(20)30314-7","volume":"395","author":"MS Hofman","year":"2020","unstructured":"Hofman MS, et al. Prostate-specific membrane antigen PET-CT in patients with high-risk prostate cancer before curative-intent surgery or radiotherapy (proPSMA): a prospective, randomised, multicentre study. Lancet. 2020;395(10231):1208\u201316. https:\/\/doi.org\/10.1016\/S0140-6736(20)30314-7.","journal-title":"Lancet"},{"issue":"10","key":"5806_CR5","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1007\/s00259-017-3725-1","volume":"44","author":"S Fanti","year":"2017","unstructured":"Fanti S, et al. Development of standardized image interpretation for 68Ga-PSMA PET\/CT to detect prostate cancer recurrent lesions. Eur J Nucl Med Mol Imaging. 2017;44(10):1622\u201335. https:\/\/doi.org\/10.1007\/s00259-017-3725-1.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"3","key":"5806_CR6","doi-asserted-by":"publisher","first-page":"469","DOI":"10.2967\/jnumed.117.198119","volume":"59","author":"M Eiber","year":"2018","unstructured":"Eiber M, et al. Prostate cancer molecular imaging standardized evaluation (PROMISE): proposed miTNM classification for the interpretation of PSMA-ligand PET\/CT. J Nucl Med. 2018;59(3):469\u201378. https:\/\/doi.org\/10.2967\/jnumed.117.198119.","journal-title":"J Nucl Med"},{"issue":"1","key":"5806_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s13550-020-00745-8","volume":"11","author":"J Kuten","year":"2021","unstructured":"Kuten J, et al. The significance of equivocal bone findings in staging PSMA imaging in the preoperative setting: validation of the PSMA-RADS version 1.0. EJNMMI Res. 2021;11(1):3. https:\/\/doi.org\/10.1186\/s13550-020-00745-8.","journal-title":"EJNMMI Res"},{"issue":"1","key":"5806_CR8","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13550-020-0596-4","volume":"10","author":"C Derwael","year":"2020","unstructured":"Derwael C, et al. Interobserver agreement of [(68)Ga]Ga-PSMA-11 PET\/CT images interpretation in men with newly diagnosed prostate cancer. EJNMMI Res. 2020;10(1):15. https:\/\/doi.org\/10.1186\/s13550-020-0596-4.","journal-title":"EJNMMI Res"},{"issue":"4","key":"5806_CR9","doi-asserted-by":"publisher","first-page":"533","DOI":"10.2967\/jnumed.119.232504","volume":"61","author":"A Toriihara","year":"2020","unstructured":"Toriihara A, et al. Comparison of 3 interpretation criteria for (68)Ga-PSMA11 PET based on inter- and intrareader agreement. J Nucl Med. 2020;61(4):533\u20139. https:\/\/doi.org\/10.2967\/jnumed.119.232504.","journal-title":"J Nucl Med"},{"key":"5806_CR10","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1007\/s00259-021-05497-8","volume":"49","author":"K Johnsson","year":"2021","unstructured":"Johnsson K, et al. Analytical performance of aPROMISE: automated anatomic contextualization, detection, and quantification of [(18)F]DCFPyL (PSMA) imaging for standardized reporting. Eur J Nucl Med Mol Imaging. 2021;49:1041\u201351. https:\/\/doi.org\/10.1007\/s00259-021-05497-8.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"3","key":"5806_CR11","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/s00259-019-04606-y","volume":"47","author":"Y Zhao","year":"2020","unstructured":"Zhao Y, et al. Deep neural network for automatic characterization of lesions on (68)Ga-PSMA-11 PET\/CT. Eur J Nucl Med Mol Imaging. 2020;47(3):603\u201313. https:\/\/doi.org\/10.1007\/s00259-019-04606-y.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"4","key":"5806_CR12","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1007\/s00259-020-05040-1","volume":"48","author":"R Seifert","year":"2021","unstructured":"Seifert R, et al. PSMA PET total tumor volume predicts outcome of patients with advanced prostate cancer receiving [(177)Lu]Lu-PSMA-617 radioligand therapy in a bicentric analysis. Eur J Nucl Med Mol Imaging. 2021;48(4):1200\u201310. https:\/\/doi.org\/10.1007\/s00259-020-05040-1.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"9","key":"5806_CR13","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.2967\/jnumed.118.224055","volume":"60","author":"A Gafita","year":"2019","unstructured":"Gafita A, et al. qPSMA: semiautomatic software for whole-body tumor burden assessment in prostate cancer using (68)Ga-PSMA11 PET\/CT. J Nucl Med. 2019;60(9):1277\u201383. https:\/\/doi.org\/10.2967\/jnumed.118.224055.","journal-title":"J Nucl Med"},{"issue":"6","key":"5806_CR14","doi-asserted-by":"publisher","first-page":"823","DOI":"10.2967\/jnumed.120.254623","volume":"62","author":"D Kostyszyn","year":"2021","unstructured":"Kostyszyn D, et al. Intraprostatic tumor segmentation on PSMA PET images in patients with primary prostate cancer with a convolutional neural network. J Nucl Med. 2021;62(6):823\u20138. https:\/\/doi.org\/10.2967\/jnumed.120.254623.","journal-title":"J Nucl Med"},{"key":"5806_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s40658-020-00298-8","volume":"7","author":"E Tragardh","year":"2020","unstructured":"Tragardh E, et al. Optimization of [(18)F]PSMA-1007 PET-CT using regularized reconstruction in patients with prostate cancer. EJNMMI Phys. 2020;7:31. https:\/\/doi.org\/10.1186\/s40658-020-00298-8.","journal-title":"EJNMMI Phys"},{"issue":"1","key":"5806_CR16","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s40658-020-00316-9","volume":"7","author":"E Tragardh","year":"2020","unstructured":"Tragardh E, et al. RECOMIA-a cloud-based platform for artificial intelligence research in nuclear medicine and radiology. EJNMMI Phys. 2020;7(1):51. https:\/\/doi.org\/10.1186\/s40658-020-00316-9.","journal-title":"EJNMMI Phys"},{"issue":"5","key":"5806_CR17","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1007\/s00259-021-05245-y","volume":"48","author":"F Ceci","year":"2021","unstructured":"Ceci F, et al. E-PSMA: the EANM standardized reporting guidelines v1.0 for PSMA-PET. Eur J Nucl Med Mol Imaging. 2021;48(5):1626\u201338. https:\/\/doi.org\/10.1007\/s00259-021-05245-y.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"5806_CR18","doi-asserted-by":"publisher","unstructured":"Cicek \u00d6, et al.\u00a03D U-Net: learning dense volumetric segmentation from sparse annotation. Medical Image Computing and Computer-Assisted Intervension - MICCAI 2016. Lecture Notes in Computer Science. Vol 9901 https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49.","DOI":"10.1007\/978-3-319-46723-8_49"},{"issue":"1","key":"5806_CR19","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1111\/cpf.12666","volume":"41","author":"P Borrelli","year":"2020","unstructured":"Borrelli P, et al. Artificial intelligence-based detection of lymph node metastases by PET\/CT predicts prostate cancer-specific survival. Clin Physiol Funct Imaging. 2020;41(1):62\u20137. https:\/\/doi.org\/10.1111\/cpf.12666.","journal-title":"Clin Physiol Funct Imaging"},{"key":"5806_CR20","doi-asserted-by":"publisher","unstructured":"Kingma DP and J. Ba, Adam: a method for stochastic optimization. arXiv:1412.6980, 2014. https:\/\/doi.org\/10.48550\/arXiv.1412.6980.","DOI":"10.48550\/arXiv.1412.6980"},{"issue":"4","key":"5806_CR21","doi-asserted-by":"publisher","first-page":"517","DOI":"10.2967\/jnumed.118.219352","volume":"60","author":"J Violet","year":"2019","unstructured":"Violet J, et al. Dosimetry of (177)Lu-PSMA-617 in metastatic castration-resistant prostate cancer: correlations between pretherapeutic imaging and whole-body tumor dosimetry with treatment outcomes. J Nucl Med. 2019;60(4):517\u201323. https:\/\/doi.org\/10.2967\/jnumed.118.219352.","journal-title":"J Nucl Med"},{"key":"5806_CR22","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.ejrad.2018.06.020","volume":"105","author":"MI Fazal","year":"2018","unstructured":"Fazal MI, et al. The past, present and future role of artificial intelligence in imaging. Eur J Radiol. 2018;105:246\u201350. https:\/\/doi.org\/10.1016\/j.ejrad.2018.06.020.","journal-title":"Eur J Radiol"},{"key":"5806_CR23","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s12880-019-0377-6","volume":"19","author":"J Oddstig","year":"2019","unstructured":"Oddstig J, et al. Comparison of conventional and Si-photomultiplier-based PET systems for image quality and diagnostic performance. BMC Med Imaging. 2019;19:81. https:\/\/doi.org\/10.1186\/s12880-019-0377-6.","journal-title":"BMC Med Imaging"}],"container-title":["European Journal of Nuclear Medicine and Molecular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-022-05806-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00259-022-05806-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-022-05806-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,23]],"date-time":"2022-07-23T11:05:45Z","timestamp":1658574345000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00259-022-05806-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,27]]},"references-count":23,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["5806"],"URL":"https:\/\/doi.org\/10.1007\/s00259-022-05806-9","relation":{},"ISSN":["1619-7070","1619-7089"],"issn-type":[{"value":"1619-7070","type":"print"},{"value":"1619-7089","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,27]]},"assertion":[{"value":"13 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Regional Ethical Review Board (#2016\/417 and #2018\/753) and was performed in accordance with the Declaration of Helsinki. All patients provided written informed consent.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All patients provided written informed consent.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"JU and OE are board members and stockholders of Eigenvision AB, which is a company working with research and development in automated image analysis, computer vision, and machine learning. The other authors declare that they have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}