{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:12:31Z","timestamp":1792782751570,"version":"4.5.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e4tsklinik M\u00fcnchen"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Legal Med"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Radiological age assessment using reference studies is inherently limited in accuracy due to a finite number of assignable skeletal maturation stages. To overcome this limitation, we present a deep learning approach for continuous age assessment based on clavicle ossification in computed tomography (CT).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Thoracic CT scans were retrospectively collected from the picture archiving and communication system. Individuals aged 15.0 to 30.0\u00a0years examined in routine clinical practice were included. All scans were automatically cropped around the medial clavicular epiphyseal cartilages. A deep learning model was trained to predict a person\u2019s chronological age based on these scans. Performance was evaluated using mean absolute error (MAE). Model performance was compared to an optimistic human reader performance estimate for an established reference study method.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The deep learning model was trained on 4,400 scans of 1,935 patients (training set: mean age\u2009=\u200924.2\u00a0years\u2009\u00b1\u20094.0, 1132 female) and evaluated on 300 scans of 300 patients with a balanced age and sex distribution (test set: mean age\u2009=\u200922.5\u00a0years\u2009\u00b1\u20094.4, 150 female). Model MAE was 1.65\u00a0years, and the highest absolute error was 6.40\u00a0years for females and 7.32\u00a0years for males. However, performance could be attributed to norm-variants or pathologic disorders. Human reader estimate MAE was 1.84\u00a0years and the highest absolute error was 3.40\u00a0years for females and 3.78\u00a0years for males.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We present a deep learning approach for continuous age predictions using CT volumes highlighting the medial clavicular epiphyseal cartilage with performance comparable to the human reader estimate.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00414-024-03167-6","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T22:02:35Z","timestamp":1706565755000},"page":"1497-1507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Radiological age assessment based on clavicle ossification in CT: enhanced accuracy through deep learning"],"prefix":"10.1007","volume":"138","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7356-3371","authenticated-orcid":false,"given":"Philipp","family":"Wesp","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8712-3948","authenticated-orcid":false,"given":"Balthasar Maria","family":"Schachtner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8678-7152","authenticated-orcid":false,"given":"Katharina","family":"Jeblick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8623-8110","authenticated-orcid":false,"given":"Johanna","family":"Topalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marvin","family":"Weber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Randolph","family":"Penning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Ricke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0268-9078","authenticated-orcid":false,"given":"Michael","family":"Ingrisch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6027-7309","authenticated-orcid":false,"given":"Bastian Oliver","family":"Sabel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"3167_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3238\/arztebl.2016.0044","volume":"113","author":"A Schmeling","year":"2016","unstructured":"Schmeling A, Dettmeyer R, Rudolf E et al (2016) Forensic age estimation: Methods, certainty, and the law. Dtsch Arzteblatt Int 113:44\u201350. https:\/\/doi.org\/10.3238\/arztebl.2016.0044","journal-title":"Dtsch Arzteblatt Int"},{"key":"3167_CR2","doi-asserted-by":"publisher","DOI":"10.1097\/00000441-195909000-00030","volume-title":"Radiographic Atlas of Skeletal Development of the Hand and Wrist","author":"WW Greulich","year":"1959","unstructured":"Greulich WW, Pyle SI (1959) Radiographic Atlas of Skeletal Development of the Hand and Wrist. Stanford University Press, Stanford, CA, USA"},{"key":"3167_CR3","unstructured":"European Asylum Support Office (2018) EASO Practical guide on age assessment. Publications Office"},{"key":"3167_CR4","unstructured":"United Nations (1989) The Convention on the Rights of the Child. https:\/\/www.ohchr.org\/en\/instruments-mechanisms\/instruments\/convention-rights-child. Accessed 28 Feb 2023"},{"key":"3167_CR5","unstructured":"The European Parliament and The Council Of The European Union (2013) Directive 2013\/33\/EU of the European Parliament and of the Council of 26 June 2013 laying down standards for the reception of applicants for international protection (recast)"},{"key":"3167_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s00414-003-0404-5","volume":"118","author":"A Schmeling","year":"2004","unstructured":"Schmeling A, Schulz R, Reisinger W et al (2004) Studies on the time frame for ossification of the medial clavicular epiphyseal cartilage in conventional radiography. Int J Legal Med 118:5\u20138. https:\/\/doi.org\/10.1007\/s00414-003-0404-5","journal-title":"Int J Legal Med"},{"key":"3167_CR7","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s00414-009-0398-8","volume":"124","author":"M Kellinghaus","year":"2010","unstructured":"Kellinghaus M, Schulz R, Vieth V et al (2010) Forensic age estimation in living subjects based on the ossification status of the medial clavicular epiphysis as revealed by thin-slice multidetector computed tomography. Int J Legal Med 124:149\u2013154. https:\/\/doi.org\/10.1007\/s00414-009-0398-8","journal-title":"Int J Legal Med"},{"key":"3167_CR8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s00414-010-0448-2","volume":"124","author":"M Kellinghaus","year":"2010","unstructured":"Kellinghaus M, Schulz R, Vieth V et al (2010) Enhanced possibilities to make statements on the ossification status of the medial clavicular epiphysis using an amplified staging scheme in evaluating thin-slice CT scans. Int J Legal Med 124:321\u2013325. https:\/\/doi.org\/10.1007\/s00414-010-0448-2","journal-title":"Int J Legal Med"},{"key":"3167_CR9","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s12024-013-9511-x","volume":"10","author":"D Wittschieber","year":"2014","unstructured":"Wittschieber D, Schulz R, Vieth V et al (2014) The value of sub-stages and thin slices for the assessment of the medial clavicular epiphysis: a prospective multi-center CT study. Forensic Sci Med Pathol 10:163\u2013169. https:\/\/doi.org\/10.1007\/s12024-013-9511-x","journal-title":"Forensic Sci Med Pathol"},{"key":"3167_CR10","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1210\/jc.2008-2474","volume":"94","author":"HH Thodberg","year":"2009","unstructured":"Thodberg HH (2009) An Automated Method for Determination of Bone Age. J Clin Endocrinol Metab 94:2239\u20132244. https:\/\/doi.org\/10.1210\/jc.2008-2474","journal-title":"J Clin Endocrinol Metab"},{"key":"3167_CR11","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s00256-018-3033-2","volume":"48","author":"SH Tajmir","year":"2019","unstructured":"Tajmir SH, Lee H, Shailam R et al (2019) Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability. Skeletal Radiol 48:275\u2013283. https:\/\/doi.org\/10.1007\/s00256-018-3033-2","journal-title":"Skeletal Radiol"},{"key":"3167_CR12","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005","journal-title":"Med Image Anal"},{"key":"3167_CR13","doi-asserted-by":"publisher","first-page":"2374","DOI":"10.1109\/TMI.2020.2968765","volume":"39","author":"N Vila-Blanco","year":"2020","unstructured":"Vila-Blanco N, Carreira MJ, Varas-Quintana P et al (2020) Deep neural networks for chronological age estimation from OPG images. IEEE Trans Med Imaging 39:2374\u20132384. https:\/\/doi.org\/10.1109\/TMI.2020.2968765","journal-title":"IEEE Trans Med Imaging"},{"key":"3167_CR14","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s00414-020-02465-z","volume":"135","author":"auf der Mauer M, Jopp-van Well E, H","year":"2021","unstructured":"auf der Mauer M, Jopp-van Well E, Herrmann J, et al (2021) Automated age estimation of young individuals based on 3D knee MRI using deep learning. Int J Legal Med 135:649\u2013663. https:\/\/doi.org\/10.1007\/s00414-020-02465-z","journal-title":"Int J Legal Med"},{"key":"3167_CR15","doi-asserted-by":"publisher","first-page":"e0220242","DOI":"10.1371\/journal.pone.0220242","volume":"14","author":"AL Dallora","year":"2019","unstructured":"Dallora AL, Anderberg P, Kvist O et al (2019) Bone age assessment with various machine learning techniques: A systematic literature review and meta-analysis. PLoS One 14:e0220242. https:\/\/doi.org\/10.1371\/journal.pone.0220242","journal-title":"PLoS One"},{"key":"3167_CR16","doi-asserted-by":"publisher","unstructured":"Chartrand G, Cheng PM, Vorontsov E, et al (2017) Deep learning: A primer for radiologists. Radiogr Rev Publ Radiol Soc N Am Inc 37:2113\u20132131. https:\/\/doi.org\/10.1148\/rg.2017170077","DOI":"10.1148\/rg.2017170077"},{"key":"3167_CR17","doi-asserted-by":"crossref","unstructured":"Cunningham C, Scheuer L, Black S (2016) Developmental juvenile osteology. Academic press","DOI":"10.1016\/B978-0-12-382106-5.00003-7"},{"key":"3167_CR18","doi-asserted-by":"crossref","unstructured":"Levin E, Tishby N, Solla SA (1990) A statistical approach to learning and generalization in layered neural networks. In: Proceedings of the IEEE. pp 1568\u20131574","DOI":"10.1109\/5.58339"},{"key":"3167_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"3167_CR20","doi-asserted-by":"publisher","unstructured":"Wesp P, Sabel BO, Mittermeier A, et al (2023) Automated localization of the medial clavicular epiphyseal cartilages using an object detection network: a step towards deep learning-based forensic age assessment. Int J Legal Medhttps:\/\/doi.org\/10.1007\/s00414-023-02958-7","DOI":"10.1007\/s00414-023-02958-7"},{"key":"3167_CR21","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C (2017) Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In: Advances in Neural Information Processing Systems 30 (NIPS 2017). Curran Associates, Inc., Red Hook, NY, USA, Long Beach, CA, USA"},{"key":"3167_CR22","volume-title":"Allowing machine learning models to say \u201cI don\u2019t know\u201d: Improving automated clinical decision-making by balancing performance against abstention","author":"P Wesp","year":"2022","unstructured":"Wesp P, Schachtner BM, Grosu S et al (2022) Allowing machine learning models to say \u201cI don\u2019t know\u201d: Improving automated clinical decision-making by balancing performance against abstention. European Society of Radiology, Vienna, Austria, Vienna, Austria"},{"key":"3167_CR23","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1007\/s00414-019-02065-6","volume":"133","author":"E Rudolf","year":"2019","unstructured":"Rudolf E, Kramer J, Schmidt S et al (2019) Anatomic shape variants of extremitas sternalis claviculae as collected from sternoclavicular thin-slice CT-studies of 2820 male borderline-adults. Int J Legal Med 133:1517\u20131528. https:\/\/doi.org\/10.1007\/s00414-019-02065-6","journal-title":"Int J Legal Med"},{"key":"3167_CR24","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1002\/jmri.26889","volume":"51","author":"J De Tobel","year":"2020","unstructured":"De Tobel J, Hillewig E, van Wijk M et al (2020) Staging Clavicular Development on MRI: Pitfalls and Suggestions for Age Estimation. J Magn Reson Imaging 51:377\u2013388. https:\/\/doi.org\/10.1002\/jmri.26889","journal-title":"J Magn Reson Imaging"},{"key":"3167_CR25","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1148\/radiol.2018180736","volume":"290","author":"SS Halabi","year":"2019","unstructured":"Halabi SS, Prevedello LM, Kalpathy-Cramer J et al (2019) The RSNA pediatric bone age machine learning challenge. Radiology 290:498\u2013503. https:\/\/doi.org\/10.1148\/radiol.2018180736","journal-title":"Radiology"},{"key":"3167_CR26","doi-asserted-by":"publisher","first-page":"2936","DOI":"10.1007\/s00330-018-5718-2","volume":"29","author":"PS Dahlberg","year":"2019","unstructured":"Dahlberg PS, Mosd\u00f8l A, Ding Y et al (2019) A systematic review of the agreement between chronological age and skeletal age based on the Greulich and Pyle atlas. Eur Radiol 29:2936\u20132948. https:\/\/doi.org\/10.1007\/s00330-018-5718-2","journal-title":"Eur Radiol"},{"key":"3167_CR27","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s004149900102","volume":"113","author":"A Schmeling","year":"2000","unstructured":"Schmeling A, Reisinger W, Loreck D et al (2000) Effects of ethnicity on skeletal maturation: Consequences for forensic age estimations. Int J Legal Med 113:253\u2013258. https:\/\/doi.org\/10.1007\/s004149900102","journal-title":"Int J Legal Med"},{"key":"3167_CR28","unstructured":"Paszke A, Gross S, Massa F, et al (2019) PyTorch: An Imperative Style, High-Performance Deep Learning Library. In: Advances in neural information processing systems. Curran Associates, Vancouver, Canada"},{"key":"3167_CR29","unstructured":"Kingma DP, Ba JL (2015) Adam: A Method for Stochastic Optimization. In: 3rd International Conference on Learning Representations (ICLR). San Diego, CA, USA"}],"container-title":["International Journal of Legal Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00414-024-03167-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00414-024-03167-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00414-024-03167-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T23:46:44Z","timestamp":1718063204000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00414-024-03167-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["3167"],"URL":"https:\/\/doi.org\/10.1007\/s00414-024-03167-6","relation":{},"ISSN":["0937-9827","1437-1596"],"issn-type":[{"value":"0937-9827","type":"print"},{"value":"1437-1596","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]},"assertion":[{"value":"13 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The requirement for written informed consent was waived by the institutional review board (Ethics Committee, Medical Faculty, LMU Munich).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"This retrospective study was approved by the institutional review board (Approval number 20-324, Ethics Committee, Medical Faculty, LMU Munich). All methods were carried out in accordance with the Declaration of Helsinki.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}