{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:13:32Z","timestamp":1768940012253,"version":"3.49.0"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"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:sec>\n                    <jats:title>Rationale and objectives<\/jats:title>\n                    <jats:p>To address the challenges in detecting anterior cruciate ligament (ACL) lesions in knee MRI examinations, including difficulties in identifying tiny lesions, insufficient extraction of low-contrast features, and poor modeling of irregular lesion morphologies, and to provide a precise and efficient auxiliary diagnostic tool for clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>An enhanced framework based on YOLOv10 is constructed. The backbone network is optimized using the C2f-SimAM module to enhance multi-scale feature extraction and spatial attention; an Adaptive Spatial Fusion (ASF) module is introduced in the neck to better fuse multi-scale spatial features; and a novel hybrid loss function combining Focal-EIoU and KPT Loss is employed. To ensure rigorous statistical evaluation, we utilized a five-fold cross-validation strategy on a dataset of 917 cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Evaluation on the KneeMRI dataset demonstrates that the proposed model achieves statistically significant improvements over standard YOLOv10, Faster R-CNN, and Transformer-based detectors (RT-DETR). Specifically, mAP@0.5 is increased by 1.3% (\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.05) compared to the standard YOLOv10, and mAP@0.5:0.95 is improved by 2.5%. Qualitative analysis further confirms the model's ability to reduce false negatives in small, low-contrast tears.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This framework effectively connects general object detection models with the specific requirements of medical imaging, providing a precise and efficient solution for diagnosing ACL injuries in routine clinical workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1675834","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:54:44Z","timestamp":1768892084000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An improved YOLOv10-based framework for knee MRI lesion detection with enhanced small object recognition and low contrast feature extraction"],"prefix":"10.3389","volume":"8","author":[{"given":"Hongwei","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University","place":["Nantong, China"]},{"name":"Department of Orthopaedics, Nantong Third People's Hospital","place":["Nantong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqu","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University","place":["Nantong, China"]},{"name":"Department of Orthopaedics, Nantong Third People's Hospital","place":["Nantong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiankai","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Medicine, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanhao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Medicine, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Medicine, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhian","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Medicine, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Medicine, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University","place":["Nantong, China"]},{"name":"Department of Orthopaedics, Nantong Third People's Hospital","place":["Nantong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University","place":["Nantong, China"]},{"name":"Department of Orthopaedics, Nantong Third People's Hospital","place":["Nantong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2875","DOI":"10.18280\/ts.410608","article-title":"AI-driven dental radiography analysis: enhancing diagnosis and education through YOLOv8 and eigen-CAM","volume":"41","author":"Aldanma","year":"2024","journal-title":"Trait. Signal"},{"key":"B2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.media.2018.11.009","article-title":"Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: data from the osteoarthritis initiative","volume":"52","author":"Ambellan","year":"2018","journal-title":"Med. Image Anal"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2325967120967120","DOI":"10.1177\/2325967120967120","article-title":"Anterior cruciate ligament tears: the impact of increased time from injury to surgery on intra-articular lesions","volume":"8","author":"Chavez","year":"2025","journal-title":"Orthop. J. Sports Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-025-07103-2","article-title":"An innovative approach to classify meniscus tears by reducing vision transformers features with elasticnet approach","volume":"81","author":"Gen","year":"2025","journal-title":"J. Supercomput"},{"key":"B5","doi-asserted-by":"publisher","first-page":"141","DOI":"10.5435\/00124635-200005000-00001","article-title":"Noncontact anterior cruciate ligament injuries: risk factors and prevention strategies","volume":"8","author":"Griffin","year":"2000","journal-title":"J. Am. Acad. Orthop. Surg"},{"key":"B6","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/TMI.2020.3023463","article-title":"Cabnet: category attention block for imbalanced diabetic retinopathy grading","volume":"40","author":"He","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B7","article-title":"\u201cSqueeze-and-excitation networks,\u201d","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Hu","year":"2017"},{"key":"B8","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s40846-024-00863-x","article-title":"Role of artificial intelligence in medical image analysis: a review of current trends and future directions","volume":"44","author":"Li","year":"2024","journal-title":"J. Med. Biol. Eng"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.106","article-title":"\u201cFeature pyramid networks for object detection,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":""},{"key":"B10","first-page":"2999","article-title":"\u201cFocal loss for dense object detection,\u201d","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Lin","year":""},{"key":"B11","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1002\/mrm.26841","article-title":"Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging","volume":"79","author":"Liu","year":"2018","journal-title":"Magn. Reson. Med"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00913","article-title":"\u201cPath aggregation network for instance segmentation,\u201d","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2018"},{"key":"B14","doi-asserted-by":"crossref","first-page":"2636","DOI":"10.1109\/CVPRW56347.2022.00297","article-title":"\u201cYolo-pose: enhancing yolo for multi person pose estimation using object keypoint similarity loss,\u201d","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Maji","year":"2022"},{"key":"B15","first-page":"779","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Redmon","year":"2016"},{"key":"B16","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.compmedimag.2018.03.001","article-title":"An application of cascaded 3d fully convolutional networks for medical image segmentation","volume":"66","author":"Roth","year":"2018","journal-title":"Comput. Med. Imaging Graph"},{"key":"B17","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1109\/ICTC58733.2023.10393276","article-title":"\u201cPiddnet: Rgb-depth fusion network for real-time semantic segmentation,\u201d","volume-title":"2023 14th International Conference on Information and Communication Technology Convergence (ICTC)","author":"Shin","year":"2023"},{"key":"B18","first-page":"797","article-title":"\u201cSaunet: shape attentive U-net for interpretable medical image segmentation,\u201d","volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"Sun","year":"2021"},{"key":"B19","doi-asserted-by":"crossref","first-page":"10778","DOI":"10.1109\/CVPR42600.2020.01079","article-title":"\u201cEfficientdet: scalable and efficient object detection,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tan","year":"2020"},{"key":"B20","first-page":"72","article-title":"\u201cAmft-yolo: a adaptive multi-scale yolo algorithm withmulti-level feature fusion forobject detection inuav scenes,\u201d","volume-title":"Lecture Notes in Computer Science","author":"Wang","year":"2025"},{"key":"B21","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":"B22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","author":"Woo","year":"2018","journal-title":"CBAM: Convolutional Block Attention Module"},{"key":"B23","doi-asserted-by":"publisher","first-page":"5760107","DOI":"10.1155\/2022\/5760107","article-title":"The effect of human bone marrow mesenchymal stem cell-derived exosomes on cartilage repair in rabbits","volume":"2022","author":"Yang","year":"2022","journal-title":"Stem Cells Int"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1591400","DOI":"10.3389\/fbioe.2025.1591400","article-title":"Mesenchymal stem cells and their extracellular vesicles: new therapies for cartilage repair","volume":"13","author":"Yang","year":"2025","journal-title":"Front. Bioeng. Biotechnol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.08158","article-title":"Focal and efficient iou loss for accurate bounding box regression","author":"Zhang","year":"2021","journal-title":"arXiv"},{"key":"B26","article-title":"\u201cDeformable DETR: deformable transformers for end-to-end object detection,\u201d","author":"Zhu","year":"2021","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1675834\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:54:48Z","timestamp":1768892088000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1675834\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":26,"alternative-id":["10.3389\/frai.2025.1675834"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1675834","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]},"article-number":"1675834"}}