{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:11:40Z","timestamp":1784761900355,"version":"3.55.0"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Timely and accurate diagnosis of wrist abnormalities, especially distal radius and ulna fractures, is critical in children and adolescents, yet complicated by skeletal immaturity, overlapping anatomy, and low-contrast fracture lines. To address these challenges, we propose MFSD-YOLO, a multi-scale detection model for pediatric wrist abnormality analysis. The model integrates a Cross-Stage Partial Progressive Multi-Scale Feature Aggregation (CSP_PMSFA) module inspired by GhostNet that applies lightweight multi-scale convolutions on partial channels with partial convolution and residual connections to reduce redundancy and enhance shallow texture and subtle fracture sensitivity. The Feature Pyramid Shared Convolution (FPSConv) module replaces pooling with shared dilated convolutions to expand the receptive field and capture multi-scale context without added cost. The C2 Bi-Level Routing Attention (C2BRA) module, based on C2PSA, uses regional routing and local enhancement to refine focus on relevant areas while balancing accuracy and speed. The Recursive Gradient Dynamic Feature Pyramid Network (RepGDFPN) optimizes top-down and bottom-up multi-scale fusion, reducing semantic loss and improving robustness. Finally, the Sliding Weight Adaptive Loss (SlideLoss) addresses class imbalance, enhancing detection of rare targets. Evaluated on the GRAZPEDWRI-DX dataset, MFSD-YOLO achieves 69.7% mAP@0.5, representing a 5.3% improvement over the baseline YOLOv11, while maintaining 10.8M parameters and 3.2\u2009ms inference speed. These results validate the model\u2019s effectiveness and its potential for real-world deployment in clinical pediatric radiographic analysis.<\/jats:p>","DOI":"10.1371\/journal.pone.0340408","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:35:42Z","timestamp":1770316542000},"page":"e0340408","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["MFSD-YOLO: A multi-scale feature detection network for pediatric wrist abnormalities in radiographic images"],"prefix":"10.1371","volume":"21","author":[{"given":"Min","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinping","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiyong","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3825-983X","authenticated-orcid":true,"given":"Ruiqiang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"issue":"1","key":"pone.0340408.ref001","doi-asserted-by":"crossref","first-page":"148","DOI":"10.3109\/17453671003628780","article-title":"Epidemiology of fractures in children and adolescents: Increased incidence over the past decade: A population-based study from northern Sweden","volume":"81","author":"EM Hedstr\u00f6m","year":"2010","journal-title":"Acta Orthopaedica"},{"issue":"7","key":"pone.0340408.ref002","article-title":"Fractures in children: Epidemiology and activity-specific fracture rates","volume":"95","author":"P-H Randsborg","year":"2013","journal-title":"J Bone Joint Surg Am"},{"key":"pone.0340408.ref003","first-page":"79","article-title":"Epidemiology of children\u2019s fractures","author":"LA Landin","year":"1997"},{"issue":"1","key":"pone.0340408.ref004","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1097\/00005131-199302000-00004","article-title":"Limb fracture pattern in different pediatric age groups: A study of 3,350 children","volume":"7","author":"JC Cheng","year":"1993","journal-title":"J Orthop Trauma"},{"issue":"4","key":"pone.0340408.ref005","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1136\/emj.18.4.263","article-title":"Diagnostic errors in an accident and emergency department","volume":"18","author":"HR Guly","year":"2001","journal-title":"Emerg Med J"},{"issue":"3","key":"pone.0340408.ref006","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1177\/0009922810384725","article-title":"Most frequently missed fractures in the emergency department","volume":"50","author":"J Mounts","year":"2011","journal-title":"Clin Pediatr (Phila)"},{"issue":"1","key":"pone.0340408.ref007","doi-asserted-by":"crossref","first-page":"25","DOI":"10.5505\/tjtes.2013.08555","article-title":"Overlooked extremity fractures in the emergency department","volume":"19","author":"E Er","year":"2013","journal-title":"Ulus Travma Acil Cerrahi Derg"},{"issue":"1","key":"pone.0340408.ref008","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1177\/0846537120941671","article-title":"Artificial intelligence solutions for analysis of X-ray images","volume":"72","author":"SJ Adams","year":"2021","journal-title":"Can Assoc Radiol J"},{"key":"pone.0340408.ref009","doi-asserted-by":"crossref","first-page":"109373","DOI":"10.1016\/j.ejrad.2020.109373","article-title":"Hierarchical fracture classification of proximal femur X-Ray images using a multistage Deep Learning approach","volume":"133","author":"L Tanzi","year":"2020","journal-title":"Eur J Radiol"},{"key":"pone.0340408.ref010","volume-title":"Mask r-cnn. Proceedings of the IEEE international conference on computer vision","author":"K He","year":"2017"},{"key":"pone.0340408.ref011","volume-title":"Fast r-cnn. Proceedings of the IEEE international conference on computer vision","author":"R Girshick","year":"2015"},{"key":"pone.0340408.ref012","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"S Ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0340408.ref013","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"Ssd: Single shot multibox detector.","author":"W Liu","year":"2016","journal-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I"},{"key":"pone.0340408.ref014","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"A Wang","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0340408.ref015","author":"R Khanam","year":"2024"},{"key":"pone.0340408.ref016","author":"Y Tian","year":"2025"},{"key":"pone.0340408.ref017","author":"M Lei","year":"2025"},{"key":"pone.0340408.ref018","author":"RY Ju","year":"2023"},{"key":"pone.0340408.ref019","author":"A Ahmed","year":"2024"},{"key":"pone.0340408.ref020","author":"RY Ju","year":"2024"},{"issue":"1","key":"pone.0340408.ref021","doi-asserted-by":"crossref","DOI":"10.1007\/s13721-025-00518-0","article-title":"Enhanced diagnosis of pediatric wrist fractures using deep learning","volume":"14","author":"R Bouslimi","year":"2025","journal-title":"Netw Model Anal Health Inform Bioinforma"},{"issue":"9","key":"pone.0340408.ref022","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.3390\/math13091419","article-title":"YOLO11-driven deep learning approach for enhanced detection and visualization of wrist fractures in X-Ray images","volume":"13","author":"M Tariq","year":"2025","journal-title":"Mathematics"},{"key":"pone.0340408.ref023","author":"CT Chien","year":"2024"},{"key":"pone.0340408.ref024","author":"A Ferdi","year":"2024"},{"key":"pone.0340408.ref025","first-page":"2117","volume-title":"Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition","author":"TY Lin","year":"2017"},{"key":"pone.0340408.ref026","article-title":"Accurate and robust pulmonary nodule detection by 3D feature pyramid network with self-supervised feature learning","author":"J Liu","year":"2019","journal-title":"arXiv preprint"},{"issue":"1","key":"pone.0340408.ref027","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1186\/s12880-023-01131-1","article-title":"Brain tumor image segmentation based on improved FPN","volume":"23","author":"H Sun","year":"2023","journal-title":"BMC Med Imaging"},{"issue":"16","key":"pone.0340408.ref028","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.6237","article-title":"Pulmonary nodule detection based on 3D feature pyramid network with incorporated squeeze\u2010and\u2010excitation\u2010attention mechanism","volume":"35","author":"M Zhang","year":"2021","journal-title":"Concurrency and Computation"},{"key":"pone.0340408.ref029","doi-asserted-by":"crossref","first-page":"107149","DOI":"10.1016\/j.compbiomed.2023.107149","article-title":"EFPN: Effective medical image detection using feature pyramid fusion enhancement","volume":"163","author":"Z Xu","year":"2023","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0340408.ref030","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1038\/s41597-022-01328-z","article-title":"A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning","volume":"9","author":"E Nagy","year":"2022","journal-title":"Sci Data"},{"issue":"4","key":"pone.0340408.ref031","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1007\/s11263-022-01575-y","article-title":"GhostNets on Heterogeneous Devices via Cheap Operations","volume":"130","author":"K Han","year":"2022","journal-title":"Int J Comput Vis"},{"key":"pone.0340408.ref032","article-title":"Run, don\u2019t walk: chasing higher FLOPS for faster neural networks.","author":"J Chen","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"issue":"1","key":"pone.0340408.ref033","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TMI.2023.3310987","article-title":"OSCNet: Orientation-shared convolutional network for CT metal artifact learning","volume":"43","author":"H Wang","year":"2024","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0340408.ref034","author":"F Yu","year":"2015"},{"key":"pone.0340408.ref035","article-title":"Biformer: Learning bilateral motion estimation via bilateral transformer for 4k video frame interpolation.","author":"J Park","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0340408.ref036","article-title":"Shunted self-attention via multi-scale token aggregation.","author":"S Ren","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0340408.ref037","author":"Y Jiang","year":"2022"},{"key":"pone.0340408.ref038","volume-title":"GFPN-YOLOv8m: A Deep Learning Network for Astronomical Source Detection. 2024 International Conference on New Trends in Computational Intelligence (NTCI","author":"Y Zhang","year":"2024"},{"key":"pone.0340408.ref039","author":"X Xu","year":"2022"},{"key":"pone.0340408.ref040","volume-title":"ELAN: A professional framework for multimodality research. 5th international conference on language resources and evaluation (LREC 2006","author":"P Wittenburg","year":"2006"},{"issue":"0","key":"pone.0340408.ref041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.21608\/ijicis.2022.118834.1163","article-title":"RepConv: A novel architecture for image scene classification on Intel scenes dataset","volume":"0","author":"M Soudy","year":"2022","journal-title":"IJICIS"},{"key":"pone.0340408.ref042","volume-title":"Learning to upsample by learning to sample. Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"W Liu","year":"2023"},{"key":"pone.0340408.ref043","first-page":"1","article-title":"FFCA-YOLO for small object detection in remote sensing images","volume":"62","author":"Y Zhang","year":"2024","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0340408.ref044","author":"Y Li","year":"2024"},{"issue":"2","key":"pone.0340408.ref045","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: Fast and Flexible Image Augmentations","volume":"11","author":"A Buslaev","year":"2020","journal-title":"Information"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:35:52Z","timestamp":1770316552000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340408"}},"subtitle":[],"editor":[{"given":"Yile","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":45,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340408","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]}}}