{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:22:13Z","timestamp":1792783333423,"version":"4.5.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Monash Health","id":[{"id":"https:\/\/ror.org\/02t1bej08","id-type":"ROR","asserted-by":"crossref"}]}],"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>Casts in follow-up wrist X-rays reduce diagnostic image quality, complicating the assessment of fracture healing. This study developed cast suppression models using real unpaired data and synthetic paired data and investigated their impact on automated fracture detection performance in paediatric wrist X-rays.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A cast suppression model was developed using data generated with unpaired image-to-image translation methods. A published CycleGAN model was repurposed to generate a synthetic paired dataset from an institutional collection of 31,001 X-rays. This dataset was used to train Pix2Pix cast suppression models, using three architectures\u2014U-Net 256, 512, and 1024. Models were evaluated using structural similarity index measure (SSIM), mean-squared error (MSE), and peak signal-to-noise ratio (PSNR). A fracture detection model was trained on a publicly available dataset of 20,327 paediatric wrist X-rays. This model was used to evaluate CycleGAN and Pix2Pix-based cast suppression by testing performance across training sets with varying cast prevalence, defined as 100, 50, 25, and 0% of the naturally occurring cast proportion in the training dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Within Pix2Pix models, the U-Net 1024 configuration performed best across all metrics (SSIM\u2009=\u20090.957, MSE\u2009=\u200922.2, PSNR\u2009=\u200934.7\u00a0dB) and was selected for subsequent fracture detection experiments. Cast suppression improved fracture detection only in models trained without any cast exposure, where Pix2Pix preprocessing increased mAP@0.5 by 4%, from 0.823 (0.008) to 0.859 (0.004), but reduced mAP@0.5 by 1\u20132% and mAP@0.5:0.95 by 3\u20134% in models that included cast images during training. Pix2Pix consistently outperformed CycleGAN-based cast suppression across both evaluation metrics (mAP@0.5 and mAP@0.5:0.95), with comparisons assessed using bootstrap resampling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The Pix2Pix model outperformed CycleGAN-based cast suppression for fracture detection preprocessing. However, cast suppression only improved performance in models trained without cast images and reduced performance otherwise. These findings indicate that cast suppression effectiveness depends critically on the downstream model\u2019s training data composition.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03595-2","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T18:28:15Z","timestamp":1773944895000},"page":"1879-1890","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing automated fracture detection in paediatric wrist X-rays with paired and unpaired cast suppression methods"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2801-5074","authenticated-orcid":false,"given":"Stanley A.","family":"Norris","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Carrion","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franko","family":"Hr\u017ei\u0107","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John R.","family":"Zech","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4970-9710","authenticated-orcid":false,"given":"Sergio","family":"Uribe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8029-9951","authenticated-orcid":false,"given":"Mohamed K.","family":"Badawy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"3595_CR1","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1111\/1742-6723.13246","volume":"31","author":"LS Robinson","year":"2019","unstructured":"Robinson LS, O\u2019Brien L (2019) Description and cost-analysis of emergency department attendances for hand and wrist injuries. Emerg Med Australas 31:772\u2013779. https:\/\/doi.org\/10.1111\/1742-6723.13246","journal-title":"Emerg Med Australas"},{"key":"3595_CR2","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1186\/1471-2458-13-501","volume":"13","author":"H-E Rosberg","year":"2013","unstructured":"Rosberg H-E, Carlsson KS, Cederlund RI, Ramel E, Dahlin LB (2013) Costs and outcome for serious hand and arm injuries during the first year after trauma\u2014a prospective study. BMC Public Health 13:501. https:\/\/doi.org\/10.1186\/1471-2458-13-501","journal-title":"BMC Public Health"},{"key":"3595_CR3","doi-asserted-by":"publisher","first-page":"e56","DOI":"10.2106\/JBJS.K.00561","volume":"94","author":"CE De Putter","year":"2012","unstructured":"De Putter CE, Selles RW, Polinder S, Panneman MJ, Hovius SE, van Beeck EF (2012) Economic impact of hand and wrist injuries: health-care costs and productivity costs in a population-based study. J Bone Joint Surg 94:e56. https:\/\/doi.org\/10.2106\/JBJS.K.00561","journal-title":"J Bone Joint Surg"},{"key":"3595_CR4","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s13244-012-0181-0","volume":"3","author":"A Slaar","year":"2012","unstructured":"Slaar A, Bentohami A, Kessels J, Bijlsma TS, van Dijkman BA, Maas M, Wilde JC, Goslings JC, Chep NW (2012) The role of plain radiography in paediatric wrist trauma. Insights Imaging 3:513\u2013517. https:\/\/doi.org\/10.1007\/s13244-012-0181-0","journal-title":"Insights Imaging"},{"key":"3595_CR5","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1055\/s-0039-1683433","volume":"8","author":"EA van Delft","year":"2019","unstructured":"van Delft EA, van Gelder TG, de Vries R, Vermeulen J, Bloemers FW (2019) Duration of cast immobilization in distal radial fractures: a systematic review. J Wrist Surg 8:430\u2013438. https:\/\/doi.org\/10.1055\/s-0039-1683433","journal-title":"J Wrist Surg"},{"key":"3595_CR6","doi-asserted-by":"publisher","first-page":"tzad005","DOI":"10.1093\/bjro\/tzad005","volume":"6","author":"C Pauling","year":"2023","unstructured":"Pauling C, Kanber B, Arthurs OJ, Shelmerdine SC (2023) Commercially available artificial intelligence tools for fracture detection: the evidence. BJR Open 6:tzad005. https:\/\/doi.org\/10.1093\/bjro\/tzad005","journal-title":"BJR Open"},{"key":"3595_CR7","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-3-030-92087-6_15","volume-title":"Artificial intelligence in cardiothoracic imaging","author":"TW Holmes","year":"2022","unstructured":"Holmes TW, Pourmorteza A (2022) Artificial intelligence-based image enhancement and reconstruction in computed tomography imaging. Artificial intelligence in cardiothoracic imaging. Springer International Publishing, Cham, pp 149\u2013166. https:\/\/doi.org\/10.1007\/978-3-030-92087-6_15"},{"key":"3595_CR8","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s10278-022-00721-9","volume":"36","author":"Z Chen","year":"2022","unstructured":"Chen Z, Pawar K, Ekanayake M, Pain C, Zhong S, Egan GF (2022) Deep learning for image enhancement and correction in magnetic resonance imaging\u2014state-of-the-art and challenges. J Digit Imaging 36:204\u2013230. https:\/\/doi.org\/10.1007\/s10278-022-00721-9","journal-title":"J Digit Imaging"},{"key":"3595_CR9","doi-asserted-by":"publisher","first-page":"3098","DOI":"10.1007\/s00259-022-05746-4","volume":"49","author":"CD Pain","year":"2022","unstructured":"Pain CD, Egan GF, Chen Z (2022) Deep learning-based image reconstruction and post-processing methods in positron emission tomography for low-dose imaging and resolution enhancement. Eur J Nucl Med Mol Imaging 49:3098\u20133118. https:\/\/doi.org\/10.1007\/s00259-022-05746-4","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"3595_CR10","doi-asserted-by":"publisher","first-page":"720","DOI":"10.3390\/biomedicines9070720","volume":"9","author":"M Komatsu","year":"2021","unstructured":"Komatsu M, Sakai A, Dozen A, Shozu K, Yasutomi S, Machino H, Asada K, Kaneko S, Hamamoto R (2021) Towards clinical application of artificial intelligence in ultrasound imaging. Biomedicines 9:720. https:\/\/doi.org\/10.3390\/biomedicines9070720","journal-title":"Biomedicines"},{"key":"3595_CR11","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1016\/j.acra.2019.12.024","volume":"27","author":"V Sorin","year":"2020","unstructured":"Sorin V, Barash Y, Konen E, Klang E (2020) Creating artificial images for radiology applications using generative adversarial networks (GANs)\u2014a systematic review. Acad Radiol 27:1175\u20131185. https:\/\/doi.org\/10.1016\/j.acra.2019.12.024","journal-title":"Acad Radiol"},{"key":"3595_CR12","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1093\/jamia\/ocab192","volume":"28","author":"F Hr\u017ei\u0107","year":"2021","unstructured":"Hr\u017ei\u0107 F, \u017du\u017ei\u0107 I, Tschauner S, \u0160tajduhar I (2021) Cast suppression in radiographs by generative adversarial networks. J Am Med Inform Assoc 28:2687\u20132694. https:\/\/doi.org\/10.1093\/jamia\/ocab192","journal-title":"J Am Med Inform Assoc"},{"key":"3595_CR13","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.1007\/s00330-024-11232-2","volume":"35","author":"S Lee","year":"2025","unstructured":"Lee S, Chun KS, Lee S, Park H, Le TD, Jung JY (2025) Suppression of immobilisation device on wrist radiography to improve fracture visualisation. Eur Radiol 35:3418\u20133428. https:\/\/doi.org\/10.1007\/s00330-024-11232-2","journal-title":"Eur Radiol"},{"key":"3595_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-01385-3","author":"SA Norris","year":"2025","unstructured":"Norris SA, Carrion D, Ditchfield M, Gubser M, Seah J, Badawy MK (2025) Enhancing radiographic diagnosis: CycleGAN-based methods for reducing cast shadow artifacts in wrist radiographs. J Imaging Inform Med. https:\/\/doi.org\/10.1007\/s10278-024-01385-3","journal-title":"J Imaging Inform Med"},{"key":"3595_CR15","doi-asserted-by":"publisher","unstructured":"Cohen JP, Luck M, Honari S (2018) Distribution matching losses can hallucinate features in medical image translation. International conference on medical image computing and computer-assisted intervention\u2014MICCAI 2018. Springer International Publishing, Cham, pp 529\u2013536. https:\/\/doi.org\/10.1007\/978-3-030-00928-1_60","DOI":"10.1007\/978-3-030-00928-1_60"},{"key":"3595_CR16","doi-asserted-by":"publisher","unstructured":"Jia W, Zhang H, He X, Wu Q (2006) A comparison on histogram based image matching methods. IEEE International Conference on Video and Signal Based Surveillance. IEEE, Sydney, Australia, pp 97\u201397. https:\/\/doi.org\/10.1109\/AVSS.2006.5","DOI":"10.1109\/AVSS.2006.5"},{"key":"3595_CR17","unstructured":"de Lima JR, Boff FA, de Souza Jaccoud Filho D, Falate R (2012) Histogram comparison using intersection metric applied to digital images analysis. Iberoamerican J Appl Comput 2"},{"key":"3595_CR18","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.nima.2009.12.037","volume":"614","author":"ND Gagunashvili","year":"2010","unstructured":"Gagunashvili ND (2010) Chi-square tests for comparing weighted histograms. Nucl Instrum Methods Phys Res A 614:287\u2013296. https:\/\/doi.org\/10.1016\/j.nima.2009.12.037","journal-title":"Nucl Instrum Methods Phys Res A"},{"key":"3595_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1166-2","volume-title":"Asymptotics in statistics: some basic concepts","author":"LM Le Cam","year":"2000","unstructured":"Le Cam LM, Yang GL (2000) Asymptotics in statistics: some basic concepts. Springer Science and Business Media, Germany. https:\/\/doi.org\/10.1007\/978-1-4612-1166-2"},{"key":"3595_CR20","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.3348\/kjr.2023.0831","volume":"24","author":"S Jeganathan","year":"2023","unstructured":"Jeganathan S (2023) The growing problem of radiologist shortages: Australia and New Zealand\u2019s perspective. Korean J Radiol 24:1043. https:\/\/doi.org\/10.3348\/kjr.2023.0831","journal-title":"Korean J Radiol"},{"key":"3595_CR21","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1186\/s12913-020-05978-w","volume":"20","author":"J Williams","year":"2020","unstructured":"Williams J, Craig TJ, Robson D (2020) Barriers and facilitators of clinician and researcher collaborations: a qualitative study. BMC Health Serv Res 20:1126. https:\/\/doi.org\/10.1186\/s12913-020-05978-w","journal-title":"BMC Health Serv Res"},{"key":"3595_CR22","doi-asserted-by":"publisher","first-page":"100630","DOI":"10.1016\/j.jcpo.2025.100630","volume":"45","author":"A Drury","year":"2025","unstructured":"Drury A, Crockford C (2025) Barriers and enablers of research engagement among multidisciplinary cancer care professionals in Ireland: a mixed-methods study. J Cancer Policy 45:100630. https:\/\/doi.org\/10.1016\/j.jcpo.2025.100630","journal-title":"J Cancer Policy"},{"key":"3595_CR23","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. Scientific Data 9:222. https:\/\/doi.org\/10.1038\/s41597-022-01328-z","journal-title":"Scientific Data"},{"key":"3595_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/WIECON-ECE60392.2023.10456447","author":"P Isola","year":"2018","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA (2018) Image-to-image translation with conditional adversarial networks. Proc IEEE Conf Comput Vis Pattern Recognit. https:\/\/doi.org\/10.1109\/WIECON-ECE60392.2023.10456447","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"3595_CR25","doi-asserted-by":"publisher","unstructured":"Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. 3rd International conference for learning representations, San Diego. https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"3595_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600\u2013612. https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans Image Process"},{"key":"3595_CR27","doi-asserted-by":"publisher","unstructured":"Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: 2010 20th International conference on pattern recognition. IEEE, Istanbul, Turkey, pp 2366\u20132369. https:\/\/doi.org\/10.1109\/ICPR.2010.579","DOI":"10.1109\/ICPR.2010.579"},{"key":"3595_CR28","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1109\/TMI.2017.2764326","volume":"37","author":"A Chartsias","year":"2018","unstructured":"Chartsias A, Joyce T, Giuffrida MV, Tsaftaris SA (2018) Multimodal MR synthesis via modality-invariant latent representation. IEEE Trans Med Imaging 37:803\u2013814. https:\/\/doi.org\/10.1109\/TMI.2017.2764326","journal-title":"IEEE Trans Med Imaging"},{"key":"3595_CR29","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SMA, Van Gool L et al (2015) The Pascal Visual Object Classes Challenge: A retrospective. Int J Comput Vis 111:98\u2013136. https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int J Comput Vis"},{"key":"3595_CR30","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32:675\u2013701. https:\/\/doi.org\/10.1080\/01621459.1937.10503522","journal-title":"J Am Stat Assoc"},{"key":"3595_CR31","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1080\/00401706.1964.10490181","volume":"6","author":"OJ Dunn","year":"1964","unstructured":"Dunn OJ (1964) Multiple comparisons using rank sums. Technometrics 6:241\u2013252. https:\/\/doi.org\/10.1080\/00401706.1964.10490181","journal-title":"Technometrics"},{"key":"3595_CR32","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 MA, Prottyasha FZ, Ahmed T, Chowdhury TM, Shatabda S (2023) FracAtlas: a dataset for fracture classification, localization and segmentation of musculoskeletal radiographs. Sci Data 10:521. https:\/\/doi.org\/10.1038\/s41597-023-02432-4","journal-title":"Sci Data"},{"key":"3595_CR33","doi-asserted-by":"publisher","first-page":"051804","DOI":"10.1117\/1.JMI.12.5.051804","volume":"12","author":"SK Zenger","year":"2025","unstructured":"Zenger SK, Agarwal R, Auffermann WF (2025) Using a limited field of view to improve training for pulmonary nodule detection on radiographs. J Med Imaging 12:051804. https:\/\/doi.org\/10.1117\/1.JMI.12.5.051804","journal-title":"J Med Imaging"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03595-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03595-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03595-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T12:18:19Z","timestamp":1789647499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03595-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["3595"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03595-2","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"27 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}