{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T14:40:17Z","timestamp":1789569617230,"version":"build-2803163510"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:00:00Z","timestamp":1736812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:00:00Z","timestamp":1736812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009400","name":"Medizinische Fakult\u00e4t, Heinrich-Heine-Universit\u00e4t D\u00fcsseldorf","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009400","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Universit\u00e4tsklinikum D\u00fcsseldorf. Anstalt \u00f6ffentlichen Rechts"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Clin Neuroradiol"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Introduction<\/jats:title>\n            <jats:p>Ventriculoperitoneal shunts (VPS) are an essential part of the treatment of hydrocephalus, with numerous valve models available with different ways of indicating pressure levels. The model types often need to be identified on X\u2011rays to assess pressure levels using a\u00a0matching template. Artificial intelligence (AI), in particular deep learning, is ideally suited to automate repetitive tasks such as identifying different VPS valve models. The aim of this work was to investigate whether AI, in particular deep learning, allows the identification of VPS models in cranial X\u2011rays.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>959 cranial X\u2011rays of patients with a\u00a0VPS were included and reviewed for image quality and complete visualization of VPS valves. The images included four VPS model types: Codman Hakim (<jats:italic>n<\/jats:italic>\u202f=\u2009774, 81%), Codman Certas Plus (<jats:italic>n<\/jats:italic>\u202f=\u2009117, 12%), Sophysa Sophy Mini SM8 (<jats:italic>n<\/jats:italic>\u202f=\u200935, 4%) and proGAV 2.0 (<jats:italic>n<\/jats:italic>\u202f=\u200933, 3%). A\u00a0Convolutional Neural Network (CNN) was trained using stratified five-fold cross-validation to classify the four VPS model types in the dataset. A\u00a0finetuned CNN pretrained on the ImageNet dataset as well as a\u00a0model trained from scratch were compared. The averaged performance and uncertainty metrics were evaluated across the cross-validation splits.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The fine-tuned model identified VPS valve models with a\u00a0mean accuracy of 0.98\u202f\u00b1\u20090.01, macro-averaged F1 score of 0.93\u202f\u00b1\u20090.04, a\u00a0recall of 0.94\u202f\u00b1\u20090.03 and a\u00a0precision of 0.95\u202f\u00b1\u20090.08 across the five cross-validation splits.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Automatic classification of VPS valve models in skull X\u2011rays, using fully automatable preprocessing steps and a\u00a0CNN, is feasible. This is an encouraging finding to further explore the possibility of automating VPS valve model identification and pressure level reading in skull X\u2011rays.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s00062-024-01490-4","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T17:37:09Z","timestamp":1736876229000},"page":"347-354","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep-Learning-based Automated Identification of Ventriculoperitoneal-Shunt Valve Models from Skull X-rays"],"prefix":"10.1007","volume":"35","author":[{"given":"Marius","family":"Vach","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivien Lorena","family":"Ivan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Boschenriedter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luisa","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Beez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn B.","family":"Hofmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Rubbert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Caspers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,14]]},"reference":[{"key":"1490_CR1","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.spen.2009.01.002","volume":"16","author":"HL Rekate","year":"2009","unstructured":"Rekate\u00a0HL. A contemporary definition and classification of hydrocephalus. Semin Pediatr Neurol. 2009;16:9\u201315. https:\/\/doi.org\/10.1016\/j.spen.2009.01.002.","journal-title":"Semin Pediatr Neurol"},{"key":"1490_CR2","doi-asserted-by":"publisher","first-page":"e0204926","DOI":"10.1371\/journal.pone.0204926","volume":"13","author":"AM Isaacs","year":"2018","unstructured":"Isaacs\u00a0AM, Riva-Cambrin\u00a0J, Yavin\u00a0D, et\u00a0al. Age-specific global epidemiology of hydrocephalus: systematic review, metanalysis and global birth surveillance. PLoS ONE. 2018;13:e204926. https:\/\/doi.org\/10.1371\/journal.pone.0204926.","journal-title":"PLoS ONE"},{"key":"1490_CR3","doi-asserted-by":"crossref","unstructured":"Maratova K, Zemkova D, Sedlak P, et\u00a0al. A comprehensive validation study of the latest version of boneXpert on a\u00a0large cohort of caucasian children and adolescents. Front Endocrinol. 2023;14.","DOI":"10.3389\/fendo.2023.1130580"},{"key":"1490_CR4","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1007\/s00247-022-05295-w","volume":"52","author":"HH Thodberg","year":"2022","unstructured":"Thodberg\u00a0HH, Thodberg\u00a0B, Ahlkvist\u00a0J, Offiah\u00a0AC. Autonomous artificial intelligence in pediatric radiology: the use and perception of boneXpert for bone age assessment. Pediatr Radiol. 2022;52:1338\u201346. https:\/\/doi.org\/10.1007\/s00247-022-05295-w.","journal-title":"Pediatr Radiol"},{"key":"1490_CR5","doi-asserted-by":"publisher","first-page":"16052","DOI":"10.1038\/s41598-018-34164-6","volume":"8","author":"L Giancardo","year":"2018","unstructured":"Giancardo\u00a0L, Arevalo\u00a0O, Tenreiro\u00a0A, et\u00a0al. MRI compatibility: automatic brain shunt valve recognition using feature engineering and deep convolutional neural networks. Sci Rep. 2018;8:16052. https:\/\/doi.org\/10.1038\/s41598-018-34164-6.","journal-title":"Sci Rep"},{"key":"1490_CR6","volume-title":"Deep residual learning for image recognition","author":"K He","year":"2015","unstructured":"He\u00a0K, Zhang\u00a0X, Ren\u00a0S, Sun\u00a0J. Deep residual learning for image recognition. 2015."},{"key":"1490_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-030-32606-7_3","volume-title":"Deep learning in healthcare: paradigms and applications","author":"W Wang","year":"2020","unstructured":"Wang\u00a0W, Liang\u00a0D, Chen\u00a0Q, et\u00a0al. Medical image classification using deep learning. In: Chen\u00a0Y\u2011W, Jain\u00a0LC, editors. Deep learning in healthcare: paradigms and applications. Cham: Springer; 2020. pp.\u00a033\u201351."},{"key":"1490_CR8","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","volume-title":"2009 IEEE conference on computer vision and pattern recognition","author":"J Deng","year":"2009","unstructured":"Deng\u00a0J, Dong\u00a0W, Socher\u00a0R, et\u00a0al. Imagenet: a\u00a0large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Miami, FL: IEEE; 2009. pp.\u00a0248\u201355."},{"key":"1490_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58","volume-title":"Cyclical learning rates for training neural networks","author":"LN Smith","year":"2017","unstructured":"Smith\u00a0LN. Cyclical learning rates for training neural networks. 2017."},{"key":"1490_CR10","doi-asserted-by":"publisher","first-page":"108","DOI":"10.3390\/info11020108","volume":"11","author":"J Howard","year":"2020","unstructured":"Howard\u00a0J, Gugger\u00a0S. fastai: a\u00a0layered API for deep learning. Information. 2020;11:108. https:\/\/doi.org\/10.3390\/info11020108.","journal-title":"Information"},{"key":"1490_CR11","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju\u00a0RR, Cogswell\u00a0M, Das\u00a0A, et\u00a0al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128:336\u201359. https:\/\/doi.org\/10.1007\/s11263-019-01228-7.","journal-title":"Int J Comput Vis"},{"key":"1490_CR12","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061773","volume-title":"Transfer learning","author":"Q Yang","year":"2020","unstructured":"Yang\u00a0Q, Zhang\u00a0Y, Dai\u00a0W, Pan\u00a0SJ. Transfer learning. 1st\u00a0ed. Cambridge University Press; 2020.","edition":"1"},{"key":"1490_CR13","doi-asserted-by":"publisher","first-page":"480","DOI":"10.3349\/ymj.2018.59.4.480","volume":"59","author":"K Kim","year":"2018","unstructured":"Kim\u00a0K, Kim\u00a0C, Kim\u00a0B\u2011K, et\u00a0al. Effects of coronary artery revascularization with a\u00a0polymer-free biolimus A9-coated biofreedom stent versus bypass surgery before noncardiac surgery. Yonsei Med\u00a0J. 2018;59:480. https:\/\/doi.org\/10.3349\/ymj.2018.59.4.480.","journal-title":"Yonsei Med J"},{"key":"1490_CR14","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","volume":"128","author":"MA Morid","year":"2021","unstructured":"Morid\u00a0MA, Borjali\u00a0A, Del Fiol\u00a0G. A scoping review of transfer learning research on medical image analysis using ImageNet. Comput Biol Med. 2021;128:104115. https:\/\/doi.org\/10.1016\/j.compbiomed.2020.104115.","journal-title":"Comput Biol Med"}],"container-title":["Clinical Neuroradiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00062-024-01490-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00062-024-01490-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00062-024-01490-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T07:19:05Z","timestamp":1750144745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00062-024-01490-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,14]]},"references-count":14,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1490"],"URL":"https:\/\/doi.org\/10.1007\/s00062-024-01490-4","relation":{},"ISSN":["1869-1439","1869-1447"],"issn-type":[{"value":"1869-1439","type":"print"},{"value":"1869-1447","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,14]]},"assertion":[{"value":"21 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.\u00a0Vach, D.\u00a0Weiss, V.L.\u00a0Ivan, C.\u00a0Boschenriedter, L.\u00a0Wolf, T.\u00a0Beez, B.B.\u00a0Hofmann, C.\u00a0Rubbert and J.\u00a0Caspers declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}