{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:00:36Z","timestamp":1782892836633,"version":"3.54.5"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Bone age assessment (BAA) from hand radiographs is crucial for diagnosing endocrinology disorders in adolescents and supplying therapeutic investigation. In practice, due to the conventional clinical assessment being a subjective estimation, the accuracy of BAA relies highly on the pediatrician's professionalism and experience. Recently, many deep learning methods have been proposed for the automatic estimation of bone age and had good results. However, these methods do not exploit sufficient discriminative information or require additional manual annotations of critical bone regions that are important biological identifiers in skeletal maturity, which may restrict the clinical application of these approaches. In this research, we propose a novel two-stage deep learning method for BAA without any manual region annotation, which consists of a cascaded critical bone region extraction network and a gender-assisted bone age estimation network. First, the cascaded critical bone region extraction network automatically and sequentially locates two discriminative bone regions <jats:italic>via<\/jats:italic> the visual heat maps. Second, in order to obtain an accurate BAA, the extracted critical bone regions are fed into the gender-assisted bone age estimation network. The results showed that the proposed method achieved a mean absolute error (MAE) of 5.45 months on the public dataset Radiological Society of North America (RSNA) and 3.34 months on our private dataset.<\/jats:p>","DOI":"10.3389\/frai.2023.1142895","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T05:08:15Z","timestamp":1677733695000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction"],"prefix":"10.3389","volume":"6","author":[{"given":"Zhangyong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengjun","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1109\/TMI.2016.2535865","article-title":"Lung pattern classification for interstitial lung diseases using a deep convolutional neural network","volume":"35","author":"Anthimopoulos","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B2","article-title":"\u201cAssessment of skeletal maturity and prediction of adult height (TW3 method): 3rd edition\u201d","author":"Carty","year":"2002"},{"key":"B3","first-page":"1251","article-title":"\u201cXception: Deep Learning With Depthwise Separable Convolutions,\u201d","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chollet","year":"2017"},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1109\/DICTA.2018.8615764","article-title":"\u201cBone Age Assessment Based on Two-Stage Deep Neural Networks,\u201d","volume-title":"Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)","author":"Chu","year":"2018"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMI.2019.2894322","article-title":"Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach","volume":"99","author":"Duan","year":"2018","journal-title":"IEEE Trans. Med. Imaging."},{"key":"B6","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-030-32226-7_59","article-title":"\u201cHand pose estimation for pediatric bone age assessment,\u201d","author":"Escobar","year":"2019","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"B7","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1097\/00000441-195909000-00030","article-title":"Radiographic Atlas of Skeletal Development of the Hand And Wrist","volume":"238","author":"Greulich","year":"1959","journal-title":"Am J Med Sci"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1148\/radiol.2018180736","article-title":"The RSNA Pediatric Bone Age Machine Learning Challenge","volume":"290","author":"Halabi","year":"2018","journal-title":"Radiology."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"He","year":"2016","journal-title":"Deep Residual Learning for Image Recognition"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1101\/234120","article-title":"\u201cPediatric Bone Age Assessment Using Deep Convolutional Neural Networks,\u201d","author":"Iglovikov","year":"2017","journal-title":"International Workshop on Deep Learning in Medical Image Analysis International Workshop on Multimodal Learning for Clinical Decision Support"},{"key":"B11","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1148\/radiol.2017170236","article-title":"Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs","volume":"287","author":"Larson","year":"2017","journal-title":"Radiology."},{"key":"B12","doi-asserted-by":"publisher","first-page":"792","DOI":"10.3348\/kjr.2020.0941","article-title":"Automated bone age assessment using artificial intelligence: the future of bone age assessment","volume":"22","author":"Lee","year":"2021","journal-title":"Korean. J. Radiol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s40747-021-00376-z","article-title":"A deep learning-based computer-aided diagnosis method of X-ray images for bone age assessment","volume":"8","author":"Li","year":"2022","journal-title":"Complex. Intell. Systems"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2019.2937341","article-title":"\u201cBone age assessment based on rank-monotonicity enhanced ranking CNN,\u201d","volume":"99","author":"Liu","year":"2019","journal-title":"IEEE Access."},{"key":"B15","doi-asserted-by":"publisher","first-page":"2685","DOI":"10.1109\/TMI.2020.3046672","article-title":"Self-supervised attention mechanism for pediatric bone age assessment with efficient weak annotation","volume":"40","author":"Liu","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.1109\/iCoMET48670.2020.9073878","article-title":"\u201cAutomated hand X-Ray based gender classification and bone age assessment using convolutional neural network,\u201d","volume-title":"International Conference on Computing, Mathematics and Engineering Technologies (iCoMET).","author":"Marouf","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1109\/EMBC46164.2021.9629650","article-title":"Deep learning framework for automatic bone age assessment,\u201d","author":"Mehta","year":"2021","journal-title":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)"},{"key":"B18","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1002\/ajhb.10098","article-title":"Assessment of skeletal maturity and prediction of adult height (TW2 method)","volume":"14","author":"Morris","year":"1976","journal-title":"Proc. R. Soc. Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/8460493","article-title":"Fully automated bone age assessment on large-scale hand X-Ray dataset","volume":"2020","author":"Pan","year":"2020","journal-title":"Int. J. Biomed. Imaging."},{"key":"B20","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1148\/129.3.661","article-title":"Carpal length in children\u2013a useful measurement in the diagnosis of rheumatoid arthritis and some concenital malformation syndromes","volume":"129","author":"Poznanski","year":"1978","journal-title":"Radiology."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/JBHI.2018.2876916","article-title":"Regression convolutional neural network for automated pediatric bone age assessment from hand radiograph","volume":"23","author":"Ren","year":"2018","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2718622","article-title":"\u201cRobust RGB-D Hand Tracking Using Deep Learning Priors,\u201d","author":"Sanchez-Riera","year":"2018","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2903131","author":"Son","year":"2019","journal-title":"TW3.-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks"},{"key":"B24","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.media.2016.10.010","article-title":"Deep learning for automated skeletal bone age assessment in X-ray images","volume":"36","author":"Spampinato","year":"2017","journal-title":"Med. Image. Anal."},{"key":"B25","first-page":"2818","article-title":"\u201cRethinking the Inception Architecture for Computer Vision,\u201d","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Szegedy","year":"2016"},{"key":"B26","doi-asserted-by":"publisher","first-page":"101693","DOI":"10.1016\/j.media.2020.101693","article-title":"Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation","volume":"63","author":"Tajbakhsh","year":"2020","journal-title":"Med. Image. Anal."},{"key":"B27","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/TMI.2008.926067","article-title":"The BoneXpert method for automated determination of skeletal maturity","volume":"28","author":"Thodberg","year":"2009","journal-title":"IEEE Trans. Med. Imaging."},{"key":"B28","first-page":"4835","article-title":"Deep Multimodal Fusion by Channel Exchanging","volume":"33","author":"Wang","year":"2020"},{"key":"B29","first-page":"3","article-title":"\u201cCBAM: Convolutional Block Attention Module,\u201d","volume-title":"European Conference on Computer Vision","author":"Woo","year":"2018"},{"key":"B30","article-title":"\u201cResidual attention based Network for hand bone age assessment,\u201d","volume-title":"IEEE International Symposium on Biomedical Imaging.","author":"Wu","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","first-page":"012007","DOI":"10.1088\/1742-6596\/1771\/1\/012007","article-title":"End-to-end bone age assessment based on attentional region localization","volume":"1771","author":"Yang","year":"2021"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/2187247","article-title":"Versatile framework for medical image processing and analysis with application to automatic bone age assessment","volume":"2018","author":"Zhao","year":"2018","journal-title":"J. Electr. Comput. Eng."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1142895\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T05:08:23Z","timestamp":1677733703000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1142895\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,2]]},"references-count":32,"alternative-id":["10.3389\/frai.2023.1142895"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1142895","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,2]]},"article-number":"1142895"}}