{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:33:32Z","timestamp":1768869212525,"version":"3.49.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["1R41AR084997-01"],"award-info":[{"award-number":["1R41AR084997-01"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>Forearm fractures constitute a significant proportion of emergency department presentations in pediatric population. The treatment goal is to restore length and alignment between the distal and proximal bone fragments. While immobilization through splinting or casting is enough for non-displaced and minimally displaced fractures. However, moderately or severely displaced fractures often require reduction for realignment. However, appropriate treatment in current practices has challenges due to the lack of resources required for specialized pediatric care leading to delayed and unnecessary transfers between medical centers, which potentially create treatment complications and burdens. The purpose of this study is to build a machine learning model for analyzing forearm fractures to assist clinical centers that lack surgical expertise in pediatric orthopedics.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>X-ray scans from 1250 children were curated, preprocessed, and manually annotated at our clinical center. Several machine learning models were fine-tuned using a pretraining strategy leveraging self-supervised learning model with vision transformer backbone. We further employed strategies to identify the most important region related to fractures within the forearm X-ray. The model performance was evaluated with and without region of interest (ROI) detection to find an optimal model for forearm fracture analyses.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Our proposed strategy leverages self-supervised pretraining (without labels) followed by supervised fine-tuning (with labels). The fine-tuned model using regions cropped with ROI identification resulted in the highest classification performance with a true-positive rate (TPR) of 0.79, true-negative rate (TNR) of 0.74, AUROC of 0.81, and AUPR of 0.86 when evaluated on the testing data.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>The results showed the feasibility of using machine learning models in predicting the appropriate treatment for forearm fractures in pediatric cases. With further improvement, the algorithm could potentially be used as a tool to assist non-specialized orthopedic providers in diagnosing and providing treatment.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-025-03485-z","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T09:43:32Z","timestamp":1753350212000},"page":"1845-1850","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Analyzing pediatric forearm X-rays for fracture analysis using machine learning"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4627-6490","authenticated-orcid":false,"given":"Van","family":"Lam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijeet","family":"Parida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Dance","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sean","family":"Tabaie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Cleary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed Muhammad","family":"Anwar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"3485_CR1","doi-asserted-by":"crossref","unstructured":"Orces CH, Orces J. Trends in the U.S. Childhood emergency department visits for fall-related fractures, 2001\u20132015. Cureus. 2020 Nov 22","DOI":"10.7759\/cureus.11629"},{"issue":"4","key":"3485_CR2","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.1097\/BPO.0000000000000595","volume":"36","author":"SM Naranje","year":"2016","unstructured":"Naranje SM, Erali RA, Warner WC, Sawyer JR, Kelly DM (2016) Epidemiology of pediatric fractures presenting to emergency departments in the United States. J Pediatr Orthop 36(4):e45\u2013e48","journal-title":"J Pediatr Orthop"},{"issue":"10","key":"3485_CR3","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1016\/j.jhsa.2008.10.013","volume":"33","author":"DS Bae","year":"2008","unstructured":"Bae DS (2008) Pediatric distal radius and forearm fractures. J Hand Surg Am 33(10):1911\u20131923","journal-title":"J Hand Surg Am"},{"issue":"3","key":"3485_CR4","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1097\/01.bpo.0000153943.45396.22","volume":"25","author":"VA Smith","year":"2005","unstructured":"Smith VA, Goodman HJ, Strongwater A, Smith B (2005) Treatment of pediatric both-bone forearm fractures. J Pediatr Orthop 25(3):309\u2013313","journal-title":"J Pediatr Orthop"},{"issue":"3","key":"3485_CR5","doi-asserted-by":"publisher","first-page":"e163","DOI":"10.1542\/peds.113.3.e163","volume":"113","author":"BM Reeder","year":"2004","unstructured":"Reeder BM, Lyne ED, Patel DR, Cucos DR (2004) Referral patterns to a pediatric orthopedic clinic: implications for education and practice. Pediatrics 113(3):e163\u2013e167","journal-title":"Pediatrics"},{"issue":"7","key":"3485_CR6","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1097\/BPO.0b013e31826994a4","volume":"32","author":"EY Hsu","year":"2012","unstructured":"Hsu EY, Schwend RM, Julia L (2012) How many referrals to a pediatric orthopaedic hospital specialty clinic are primary care problems? J Pediatr Orthop 32(7):727\u2013731","journal-title":"J Pediatr Orthop"},{"issue":"2","key":"3485_CR7","first-page":"109","volume":"12","author":"TT Do","year":"2003","unstructured":"Do TT, Strub WM, Foad SL, Mehlman CT, Crawford AH (2003) Reduction versus remodeling in pediatric distal forearm fractures: a preliminary cost analysis. J Pediatr Orthop B 12(2):109\u2013115","journal-title":"J Pediatr Orthop B"},{"issue":"5","key":"3485_CR8","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1097\/PEC.0000000000000805","volume":"33","author":"RK Gattu","year":"2017","unstructured":"Gattu RK, De Fee AS, Lichenstein R, Teshome G (2017) Consideration of cost of care in pediatric emergency transfer\u2014an opportunity for improvement. Pediatr Emerg Care 33(5):334\u2013338","journal-title":"Pediatr Emerg Care"},{"issue":"1","key":"3485_CR9","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/s13244-022-01234-3","volume":"13","author":"SC Shelmerdine","year":"2022","unstructured":"Shelmerdine SC, White RD, Liu H, Arthurs OJ, Sebire NJ (2022) Artificial intelligence for radiological paediatric fracture assessment: a systematic review. Insights Imaging 13(1):94","journal-title":"Insights Imaging"},{"issue":"1","key":"3485_CR10","doi-asserted-by":"publisher","first-page":"223","DOI":"10.3390\/life13010223","volume":"13","author":"J Oppenheimer","year":"2023","unstructured":"Oppenheimer J, L\u00fcken S, Hamm B, Niehues SM (2023) A prospective approach to integration of ai fracture detection software in radiographs into clinical workflow. Life 13(1):223","journal-title":"Life"},{"issue":"1","key":"3485_CR11","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s41746-020-00352-w","volume":"3","author":"RM Jones","year":"2020","unstructured":"Jones RM, Sharma A, Hotchkiss R, Sperling JW, Hamburger J, Ledig C, O\u2019Toole R, Gardner M, Venkatesh S, Roberts M, Sauvestre R, Shatkhin M, Gupta A, Chopra S, Kumaravel M, Daluiski A, Plogger W, Nascone J, Potter H, Lindsey R (2020) Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. NPJ Digit Med 3(1):144","journal-title":"NPJ Digit Med"},{"issue":"1","key":"3485_CR12","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1038\/s41597-022-01328-z","volume":"9","author":"E Nagy","year":"2022","unstructured":"Nagy E, Janisch M, Hr\u017ei\u0107 F, Sorantin E, Tschauner S (2022) A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning. Sci Data 9(1):222","journal-title":"Sci Data"},{"key":"3485_CR13","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s11548-024-03254-4","volume":"20","author":"VK Lam","year":"2024","unstructured":"Lam VK, Fischer E, Jawad K, Tabaie S, Cleary K, Anwar SM (2024) An automated framework for pediatric hip surveillance and severity assessment using radiographs. Int J Comput Assist Radiol Surg. 20:203\u2013211","journal-title":"Int J Comput Assist Radiol Surg."},{"key":"3485_CR14","doi-asserted-by":"crossref","unstructured":"Caron M, Touvron H, Misra I, Jegou H, Mairal J, Bojanowski P, Joulin A (2021) Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) [Internet]. IEEE; 2021. p. 9630\u201340. Available from: https:\/\/ieeexplore.ieee.org\/document\/9709990\/","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3485_CR15","doi-asserted-by":"crossref","unstructured":"Anwar SM, Parida A, Atito S, Awais M, Nino G, Kittler J, Linguraru M (2024) SS-CXR: self-supervised pretraining using chest x-rays towards a domain specific foundation model. In: 2024 IEEE International Conference on Image Processing (ICIP). IEEE; 2024. p. 2975\u201381","DOI":"10.1109\/ICIP51287.2024.10647378"},{"key":"3485_CR16","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-031-16760-7_9","volume-title":"Medical Image Learning with Limited and Noisy Data","author":"S Atito","year":"2022","unstructured":"Atito S, Anwar SM, Awais M, Kittler J (2022) SB-SSL: Slice-Based Self-supervised Transformers for Knee Abnormality Classification from MRI. In: Zamzmi G, Antani S, Bagci U, Linguraru MG, Rajaraman S, Xue Z (eds) Medical Image Learning with Limited and Noisy Data. Springer Nature Switzerland, Cham, pp 86\u201395"},{"key":"3485_CR17","unstructured":"Parida A, Capellan-Martin D, Atito S, Awais M, Ledesma-Carbayo MJ, Linguraru MG, Anwar S (2024) DiCoM--diverse concept modeling towards enhancing generalizability in chest X-ray studies. arXiv preprint https:\/\/arxiv.org\/abs\/2402.15534"},{"issue":"1","key":"3485_CR18","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y, Yang Z, Zhang Y, Tao D (2023) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 45(1):87\u2013110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3485_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106126","volume":"122","author":"A Parvaiz","year":"2023","unstructured":"Parvaiz A, Khalid MA, Zafar R, Ameer H, Ali M, Fraz MM (2023) Vision Transformers in medical computer vision\u2014A contemplative retrospection. Eng Appl Artif Intell 122:106126","journal-title":"Eng Appl Artif Intell"},{"key":"3485_CR20","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"3485_CR21","unstructured":"Rajpurkar P, Irvin J, Bagul A, Ding D, Duan T, Mehta H, Yang B, Zhu K, Laird D, Ball R (2017) Mura: large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint https:\/\/arxiv.org\/abs\/1712.06957"},{"issue":"1","key":"3485_CR22","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1038\/s41597-023-02432-4","volume":"10","author":"I Abedeen","year":"2023","unstructured":"Abedeen I, Rahman MdA, Prottyasha FZ, Ahmed T, Chowdhury TM, Shatabda S (2023) FracAtlas: a dataset for fracture classification, localization and segmentation of musculoskeletal radiographs. Sci Data 10(1):521","journal-title":"Sci Data"},{"key":"3485_CR23","unstructured":"Felipe Kitamura Eduardo Farina. UNIFESP x-ray body part classifier competition, 2022. [cited 2025 Jan 9]; Available from: https:\/\/github.com\/piyumaha12\/UNIFESP-X-ray-Body-Part-Classifier-Competition\/tree\/cc654bcae4f9bab7a196b8e543a4e8a27a464b67#1"},{"key":"3485_CR24","unstructured":"Skalski P (2022) makesense.ai. GitHub"},{"key":"3485_CR25","doi-asserted-by":"crossref","unstructured":"Zhiqiang W, Jun L (2017) A review of object detection based on convolutional neural network. In: 2017 36th Chinese Control Conference (CCC). IEEE; 2017. p 11104\u20139","DOI":"10.23919\/ChiCC.2017.8029130"},{"key":"3485_CR26","first-page":"44102","volume":"37","author":"M McDermott","year":"2024","unstructured":"McDermott M, Zhang H, Hansen L, Angelotti G, Gallifant J (2024) A closer look at auroc and auprc under class imbalance. Adv Neural Inf Process Syst 37:44102\u201344163","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"3485_CR27","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1097\/RLI.0000000000000615","volume":"55","author":"J Choi","year":"2020","unstructured":"Choi J, Cho Y, Lee S, Lee J, Lee S, Choi Y, Cheon J, Ha J (2020) Using a dual-input convolutional neural network for automated detection of pediatric supracondylar fracture on conventional radiography. Invest Radiol 55(2):101\u2013110","journal-title":"Invest Radiol"},{"issue":"4","key":"3485_CR28","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1080\/17453674.2018.1453714","volume":"89","author":"S Chung","year":"2018","unstructured":"Chung S, Han S, Lee J, Oh K, Kim N, Yoon J, Kim J, Moon S, Kwon J, Lee H, Noh Y, Kim Y (2018) Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop 89(4):468\u2013473","journal-title":"Acta Orthop"},{"issue":"2","key":"3485_CR29","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s00256-018-3016-3","volume":"48","author":"T Urakawa","year":"2019","unstructured":"Urakawa T, Tanaka Y, Goto S, Matsuzawa H, Watanabe K, Endo N (2019) Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol 48(2):239\u2013244","journal-title":"Skeletal Radiol"},{"issue":"1","key":"3485_CR30","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1148\/radiol.211785","volume":"304","author":"RYL Kuo","year":"2022","unstructured":"Kuo RYL, Harrison C, Curran TA, Jones B, Freethy A, Cussons D, Stewart M, Collins G, Furniss D (2022) Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology 304(1):50\u201362","journal-title":"Radiology"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03485-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03485-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03485-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T11:22:02Z","timestamp":1758972122000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03485-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["3485"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03485-z","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"assertion":[{"value":"19 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All other authors have no conflicts of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"For this study, formal consent was not required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}]}}