Academic Journal
Automated detection of pediatric forearm fractures in X-ray images using deep learning.
| Τίτλος: | Automated detection of pediatric forearm fractures in X-ray images using deep learning. |
|---|---|
| Συγγραφείς: | Suzuki H; Graduate School of Science and Technology, Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya, 468-8502, Aichi, Japan., Teramoto A; Graduate School of Science and Technology, Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya, 468-8502, Aichi, Japan. teramoto@meijo-u.ac.jp., Honmoto T; Ibaraki Children's Hospital, 3-3-1 Futabadai, Mito, 311-4145, Ibaraki, Japan., Niki A; Ibaraki Children's Hospital, 3-3-1 Futabadai, Mito, 311-4145, Ibaraki, Japan., Kono T; Department of Radiology, Tokyo Metropolitan Children's Medical Center, 2-8-29,Musashidai, Tokyo, 183-8561, Fuchu, Japan., Fujita H; Faculty of Engineering, Gifu University, 1-1,Yanagido, Gifu, 501-1194, Japan. |
| Πηγή: | Radiological physics and technology [Radiol Phys Technol] 2026 Jun; Vol. 19 (2), pp. 830-841. Date of Electronic Publication: 2026 May 06. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Springer Japan Country of Publication: Japan NLM ID: 101467995 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1865-0341 (Electronic) Linking ISSN: 18650333 NLM ISO Abbreviation: Radiol Phys Technol Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Tokyo : Springer Japan |
| Ιατρικοί όροι (MeSH): | Fractures, Bone*/diagnostic imaging , Deep Learning* , Detection Algorithms*, Radiography/methods ; Adolescent ; Child ; Child, Preschool ; Humans ; Infant ; Convolutional Neural Networks |
| Περίληψη: | Children's bones are more elastic and have a thicker periosteum than those of adults, resulting in subtle, incomplete fractures. Diagnosis based on plain radiographs alone can be challenging. The shortage of pediatric radiologists compounds this difficulty, leading to a risk of missed fractures. Therefore, we considered that it might be possible to help prevent missed fractures by developing and validating an automated detection model for pediatric forearm fractures on plain radiographs using deep learning techniques (convolutional neural networks [CNNs] and Vision Transformers [ViTs]). To train and validate such a model, this study targeted the frontal and lateral views of plain radiographs from 517 patients aged 1-14 years with forearm fractures. We first performed preprocessing to focus on the forearm region in the images. Thirteen models (visual geometry group [VGG], ResNet, DenseNet, and ViT) were used to classify the presence or absence of fractures and were evaluated and compared using 5-fold cross-validation. Verification of these models showed that VGG16 exhibited the best performance. The overall result, which integrated the predictions from the frontal and lateral views, achieved a sensitivity of 0.872 ± 0.015, a specificity of 0.925 ± 0.016, a balanced accuracy of 0.898 ± 0.003, and an AUC of 0.962 ± 0.002. Furthermore, visualization of saliency maps (using gradient-weighted class activation mapping and an attention map) revealed that the model focused on the bone during prediction. Therefore, if the proposed method is used in hospitals, it could possibly support diagnosis and help reduce missed fractures. (© 2026. The Author(s), under exclusive licence to Japanese Society of Radiological Technology and Japan Society of Medical Physics.) |
| Competing Interests: | Declarations. Conflict of interest: The authors have no relevant financial or non-financial interests to disclose. Ethical approval: This study was performed in line with the principles of the Declaration of Helsinki. Consent for publication: Not applicable. This retrospective study was reviewed and approved by the Ethics Committee of Meijo University (Approval No. 2025-43) and the Ethics Committee of Tokyo Metropolitan Children’s Medical Center (Approval No. 2025d-6). Informed consent: Informed consent and informed assent were waived by the ethics committees due to the retrospective nature of the study and the use of fully anonymized data. At the data collection institution, the secondary use of anonymized clinical data for research purposes was publicly disclosed, and patients and their guardians were provided with the opportunity to opt out. |
| References: | Wang H, Yang YT, Lu QD, Liu CX, Bai HA, Wang JJ, et al. Research hotspots for pediatric fractures from 2017 to 2022: a bibliometric and visual analysis via Citespace. J Child Orthop. 2024;18:40–8. (PMID: 10.1177/1863252123121733338348436) Kaymaz B, Kaymaz N. Epidemiological and characteristic features of childhood fractures. Trends Pediatr. 2023;4:1–5. (PMID: 10.59213/TP.2023.54376) Marson BA, Manning JC, James M, Ikram A, Bryson DJ, Ollivere BJ. Trends in hospital admissions for childhood fractures in England. BMJ Paediatr Open. 2021;5:e001187. (PMID: 10.1136/bmjpo-2021-001187347864918587381) Davidson JS, Brown DJ, Barnes SN, Bruce CE. Simple treatment for torus fractures of the distal radius. J Bone Joint Surg Br. 2001;83:1173–5. (PMID: 10.1302/0301-620X.83B8.083117311764434) Vittas D, Larsen E, Torp-Pedersen S. Angular remodeling of midshaft forearm fractures in children. Clin Orthop Relat Res. 1991;265:261–4. (PMID: 10.1097/00003086-199104000-00030) Beaty JH, Kasser JR. Rockwood and Wilkins’ Fractures in Children. 7th ed. Philadelphia: Lippincott Williams & Wilkins; 2010. Kuhn JP, Slovis TL, Haller JO. Caffey’s Pediatric Diagnostic Imaging. 10th ed. Philadelphia: Mosby; 2004. Kis E. Pediatric radiology crossing continents. Pediatr Radiol. 2020;50:139–40. Klein WM, et al. On-call or not on-call, what difference does it make in paediatric radiology? Insights Imaging. 2025;16:73. (PMID: 10.1186/s13244-025-01948-04014011211947353) Rajpurkar P, Irvin J, Bagul A, Ding D, Duan T, Mehta H et al. MURA: large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957. 2017. Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2017. pp. 2261–9. Thian YL, Li Y, Jagmohan P, Sia D, Chan VEY, Tan RT. Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiol Artif Intell. 2019;1:e180001. (PMID: 10.1148/ryai.2019180001339377808017412) LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86:2278–324. (PMID: 10.1109/5.726791) Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T et al. An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the international conference on learning representations (ICLR); 2021. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision (ICCV); 2017. pp. 618–26. Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern. 1979;9:62–6. (PMID: 10.1109/TSMC.1979.4310076) Schneider CA, Rasband WS, Eliceiri KW. NIH Image to ImageJ: 25 years of image analysis. Nat Methods. 2012;9:671–5. (PMID: 10.1038/nmeth.2089229308345554542) Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations (ICLR); 2015. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2016. pp. 770–8. Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV); 2021. pp. 10012–22. Zhang J, Li Z, Lin H, Xue M, Wang H, Fang Y, et al. Deep learning assisted diagnosis system: improving the diagnostic accuracy of distal radius fractures. Front Med. 2023;10:1224489. (PMID: 10.3389/fmed.2023.1224489) |
| Contributed Indexing: | Keywords: Convolutional neural network; Discriminative AI models; Greenstick fracture; Pediatric forearm fracture; Torus fracture; Vision transformer |
| Entry Date(s): | Date Created: 20260506 Date Completed: 20260612 Latest Revision: 20260616 |
| Update Code: | 20260617 |
| DOI: | 10.1007/s12194-026-01061-x |
| PMID: | 42091806 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!