{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T22:26:07Z","timestamp":1793831167012,"version":"4.6.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop an artificial intelligence system for the accurate detection and classification of intertrochanteric femoral fractures (types A1\u2013A3 according to the AO\/OTA classification) in X-ray images, focusing on improving precision and optimizing computational efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study adopted a retrospective design, using 976 X-ray image datasets collected from hospital archives. The images were preprocessed, annotated by orthopedic specialists, and divided into training and test sets. The model was improved by replacing the traditional convolutional downsampling modules in YOLOv8 with Average Pooling Downsampling (ADown) modules to enhance feature extraction for small fracture targets. Model training incorporated data augmentation techniques and was evaluated using metrics such as precision, recall, and mean Average Precision (mAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed YOLOv8-ADown model achieved an overall mAP50 of 81.7%, higher than the 80.5% of the original YOLOv8. The detection precision for A1, A2, and A3 type fractures increased by 7.3, 3.5, and 7.8%, respectively. Furthermore, the number of model parameters was reduced by 12.3%, and computational complexity (FLOPs) was decreased by 9.8%, demonstrating potential for deployment on edge devices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The YOLOv8-ADown model provides an efficient solution for fracture detection and is expected to assist in clinical diagnosis. Future work should address data collection challenges and conduct multi-center validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1759383","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T13:58:03Z","timestamp":1772459883000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Improved YOLOv8 with average pooling downsampling for detection and classification of intertrochanteric femoral fractures in X-ray images: a study focusing on AO\/OTA classification"],"prefix":"10.3389","volume":"13","author":[{"given":"Zheming","family":"Shen","sequence":"first","affiliation":[{"name":"Xiangcheng District Caohu People\u2019s Hospital","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiheng","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuequan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Cangzhou Integrated Traditional Chinese and Western Medicine Hospital","place":["Cangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifu","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusen","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, The First Affiliated Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e11266","DOI":"10.1016\/j.heliyon.2022.e11266","article-title":"Artificial intelligence (AI) vs. human in hip fracture detection.","volume":"8","author":"Twinprai","year":"2022","journal-title":"Heliyon"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e233391","DOI":"10.1001\/jamanetworkopen.2023.3391","article-title":"Artificial intelligence for hip fracture detection and outcome prediction: a systematic review and meta-analysis.","volume":"6","author":"Lex","year":"2023","journal-title":"JAMA Netw Open"},{"key":"B3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s00198-023-06907-3","article-title":"Global burden of hip fracture: the Global Burden of Disease Study.","volume":"35","author":"Feng","year":"2024","journal-title":"Osteoporos Int."},{"key":"B4","doi-asserted-by":"publisher","first-page":"5469","DOI":"10.1007\/s00330-019-06167-y","article-title":"Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs.","volume":"29","author":"Cheng","year":"2019","journal-title":"Eur Radiol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1302\/0301-620X.107B2.BJJ-2024-0791.R1","article-title":"Deep learning for automated hip fracture detection and classification : achieving superior accuracy.","volume":"107","author":"Zheng","year":"2025","journal-title":"Bone Joint J."},{"key":"B6","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1177\/0846537120941671","article-title":"Artificial intelligence solutions for analysis of X-ray images.","volume":"72","author":"Adams","year":"2020","journal-title":"Can Assoc Radiol J"},{"key":"B7","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s00256-018-3016-3","article-title":"Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network.","volume":"48","author":"Urakawa","year":"2018","journal-title":"Skeletal Radiol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1664219","DOI":"10.3389\/fmed.2025.1664219","article-title":"Risk prediction of osteoporotic vertebral compression fractures in postmenopausal osteoporotic women by machine learning modelling.","volume":"12","author":"Sun","year":"2025","journal-title":"Front Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"13","DOI":"10.7547\/16-112","article-title":"Comparison of biomechanical effects of different configurations of kirschner wires on the epiphyseal plate and stability in a salter-harris type 2 distal femoral fracture model.","volume":"109","author":"Inal","year":"2019","journal-title":"J Am Podiatr Med Assoc"},{"key":"B10","doi-asserted-by":"publisher","first-page":"259","DOI":"10.5194\/ms-8-259-2017","article-title":"Comparison of parallel or convergent proximal schanz screw placement of pertrochanteric fixator in intertrochanteric fracture model.","volume":"8","author":"Gok","year":"2017","journal-title":"Mech. Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"471","DOI":"10.3390\/a17110471","article-title":"Deep learning approach for arm fracture detection based on an improved YOLOv8 Algorithm.","volume":"17","author":"Meza","year":"2024","journal-title":"Algorithms."},{"key":"B12","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: a survey.","volume":"8","author":"Guo","year":"2022","journal-title":"Comput Vis Media."},{"key":"B13","doi-asserted-by":"publisher","first-page":"927926","DOI":"10.3389\/fbioe.2022.927926","article-title":"Artificial intelligence to detect the femoral intertrochanteric fracture: the arrival of the intelligent-medicine era.","volume":"10","author":"Liu","year":"2022","journal-title":"Front Bioeng Biotechnol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1111\/1754-9485.12828","article-title":"Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures.","volume":"63","author":"Adams","year":"2018","journal-title":"J Med Imaging Radiat Oncol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1007\/s10278-020-00364-8","article-title":"Advanced deep learning techniques applied to automated femoral neck fracture detection and classification.","volume":"33","author":"Mutasa","year":"2020","journal-title":"J Digit Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e190023","DOI":"10.1148\/ryai.2020190023","article-title":"Automatic hip fracture identification and functional subclassification with deep learning.","volume":"2","author":"Krogue","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"B17","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s11548-021-02552-5","article-title":"Automatic detection and classification of peri-prosthetic femur fracture.","volume":"17","author":"Alzaid","year":"2022","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"B18","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization.","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int J Comput Vis."},{"key":"B19","doi-asserted-by":"publisher","first-page":"e211276","DOI":"10.1001\/jamanetworkopen.2021.1276","article-title":"Association of clinician diagnostic performance with machine learning-based decision support systems: a systematic review.","volume":"4","author":"Vasey","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B20","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1186\/s13244-025-01958-y","article-title":"Classification and segmentation of hip fractures in x-rays: highlighting fracture regions for interpretable diagnosis.","volume":"16","author":"Gonz\u00e1lez","year":"2025","journal-title":"Insights Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"101801","DOI":"10.1016\/j.bonr.2024.101801","article-title":"Classification of AO\/OTA 31A\/B femur fractures in X-ray images using YOLOv8 and advanced data augmentation techniques.","volume":"22","author":"Marullo","year":"2024","journal-title":"Bone Rep"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e081250","DOI":"10.1136\/bmj-2024-081250","article-title":"Advances in the management of osteoporosis.","volume":"390","author":"Hoong","year":"2025","journal-title":"BMJ"},{"key":"B23","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1001\/jama.2024.21653","article-title":"Screening for osteoporosis to prevent fractures: a systematic evidence review for the US preventive services task force.","volume":"333","author":"Kahwati","year":"2025","journal-title":"JAMA."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS.","volume":"5","author":"Terven","year":"2023","journal-title":"Mach Learn Knowl Extract."},{"key":"B25","doi-asserted-by":"publisher","first-page":"166","DOI":"10.5312\/wjo.v10.i3.166","article-title":"Changing trends in the mortality rate at 1-year post hip fracture - a systematic review.","volume":"10","author":"Downey","year":"2019","journal-title":"World J Orthop"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.06504","article-title":"Detecting hip fractures with radiologist-level performance using deep neural networks.","author":"Gale","year":"2017","journal-title":"arXiv [Preprint]."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1651798","DOI":"10.3389\/fradi.2025.1651798","article-title":"YOLOv8-Seg: a deep learning approach for accurate classification of osteoporotic vertebral fractures.","volume":"5","author":"Yang","year":"2025","journal-title":"Front Radiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6468","DOI":"10.3390\/s24196468","article-title":"An improved YOLOv8-based foreign detection algorithm for transmission lines.","volume":"24","author":"Duan","year":"2024","journal-title":"Sensors"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1635016","DOI":"10.3389\/fmed.2025.1635016","article-title":"A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: scfast-yolo.","volume":"12","author":"Wang","year":"2025","journal-title":"Front Med"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-022-01707-4","article-title":"LIP: local importance-based pooling.","volume":"131","author":"Gao","year":"2022","journal-title":"Int J Comput Vis."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.2147\/IJGM.S508342","article-title":"Inter- and Intra-Observer Reliability of the New Comprehensive Classification of Intertrochanteric Fracture of the Femur.","volume":"18","author":"Xu","year":"2025","journal-title":"Int J Gen Med"},{"key":"B32","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1007\/s40430-018-1448-2","article-title":"Should we really compress the fracture line in the treatment of Salter\u2013Harris type 4 distal femoral fractures? A biomechanical study.","volume":"40","author":"Inal","year":"2018","journal-title":"J Braz. Soc. Mech. Sci. Eng."},{"key":"B33","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1097\/BRS.0000000000005303","article-title":"The role of the lumbar paravertebral muscles in the development of short-term residual pain after lumbar fusion surgery.","volume":"50","author":"Sun","year":"2025","journal-title":"Spine"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1007\/s11604-025-01754-0","article-title":"Added value of artificial intelligence for the detection of pelvic and hip fractures.","volume":"43","author":"Jaillat","year":"2025","journal-title":"Jpn J Radiol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"e351","DOI":"10.1016\/S2589-7500(22)00004-8","article-title":"Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study.","volume":"4","author":"Oakden-Rayner","year":"2022","journal-title":"Lancet Digit Health"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.1002\/jbmr.4821","article-title":"Global epidemiology of hip fractures: secular trends in incidence rate, post-fracture treatment, and all-cause mortality.","volume":"38","author":"Sing","year":"2023","journal-title":"J Bone Miner Res"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2560","DOI":"10.3390\/s24082560","article-title":"Large span sizes and irregular shapes target detection methods using variable convolution-improved YOLOv8.","volume":"24","author":"Gao","year":"2024","journal-title":"Sensors"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e70226","DOI":"10.1002\/acm2.70226","article-title":"Current progress of digital twin construction using medical imaging.","volume":"26","author":"Zhao","year":"2025","journal-title":"J Appl Clin Med Phys"},{"key":"B39","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s40430-019-1640-z","article-title":"Biomechanical performance using finite element analysis of different screw materials in the parallel screw fixation of Salter\u2013Harris Type 4 fractures.","volume":"41","author":"Gok","year":"2019","journal-title":"J Braz Soc Mech Sci Eng."},{"key":"B40","doi-asserted-by":"publisher","first-page":"1646008","DOI":"10.3389\/fradi.2025.1646008","article-title":"Intervertebral disc anomaly intelligent classification system based on deep learning, IDAICS.","volume":"5","author":"Gao","year":"2025","journal-title":"Front Radiol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"900","DOI":"10.3348\/kjr.2025.0599","article-title":"Multimodal large language models in medical imaging: current state and future directions.","volume":"26","author":"Nam","year":"2025","journal-title":"Korean J Radiol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s11554-024-01582-x","article-title":"Optimized YOLOv8 for multi-scale object detection.","volume":"22","author":"Rasheed","year":"2024","journal-title":"J Real-Time Image Process."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1759383\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T16:03:09Z","timestamp":1773331389000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1759383\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":42,"alternative-id":["10.3389\/fmed.2026.1759383"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1759383","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"article-number":"1759383"}}