{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T10:11:09Z","timestamp":1790935869173,"version":"4.1.0"},"reference-count":31,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Muscle strain impairs mobility and quality of life, yet ultrasound diagnosis remains dependent on subjective expert interpretation, which can lead to variability in lesion detection. This study aimed to develop and evaluate MS-detector, a symmetry-aware, two-stage deep learning model that leverages bilateral B-mode ultrasound images to automatically detect muscle strain and provide clinicians with a consistent second-reader decision-support tool in routine practice. Methods: A YOLOv5-based detector proposes candidate regions, and a Siamese convolutional neural network (CNN) compares contralateral regions to filter false positives. The dataset comprised 559 bilateral pairs from 86 patients with consensus labels. All splits were enforced at the patient level. A fixed, independent hold-out test set of 32 pairs was never used for training, tuning, or threshold selection. Five-fold cross-validation (CV) on the remaining development set was used for model selection. The operating point was pre-specified at T1 = 0.01 and T2 = 0.20. Results: The detector achieved mAP = 0.4006 (five-fold CV mean). On the hold-out set at the pre-specified operating point, MS-detector attained recall = 0.826 and precision = 0.486, improving F1\/F2 over the YOLOv5 baseline by increasing precision with an acceptable recall trade-off. A representative figure illustrates the reduction in low-confidence false positives after filtering; this example is illustrative rather than aggregate. Conclusions: Leveraging contralateral symmetry in a hierarchical scheme improves detection precision while maintaining clinically acceptable recall, supporting MS-detector as a decision-support tool. Future work will evaluate generalizability across scanners and centers and assess calibrated probabilistic fusion and lesion grading.<\/jats:p>","DOI":"10.3390\/diagnostics15233087","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T15:14:06Z","timestamp":1764861246000},"page":"3087","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MS-Detector: A Hierarchical Deep Learning Method to Detect Muscle Strain Using Bilateral Symmetric Ultrasound Images of the Body"],"prefix":"10.3390","volume":"15","author":[{"given":"Le","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Medical Artificial Intelligence, Binzhou Medical University, Yantai 264003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifu","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Software, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huachao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[{"name":"First Clinical Medical College, Hubei University of Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Province Academy of Traditional Chinese Medicine, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Tang","sequence":"additional","affiliation":[{"name":"First Clinical Medical College, Hubei University of Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Province Academy of Traditional Chinese Medicine, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Pei","sequence":"additional","affiliation":[{"name":"Institute of Medical Artificial Intelligence, Binzhou Medical University, Yantai 264003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhou","sequence":"additional","affiliation":[{"name":"First Clinical Medical College, Hubei University of Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan 430061, China"},{"name":"Department of Tuina and Rehabilitation Medicine, Hubei Province Academy of Traditional Chinese Medicine, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-0867","authenticated-orcid":false,"given":"Zhidong","family":"Xue","sequence":"additional","affiliation":[{"name":"Institute of Medical Artificial Intelligence, Binzhou Medical University, Yantai 264003, China"},{"name":"School of Software, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3591","DOI":"10.1177\/03635465221140923","article-title":"Acute Adductor Muscle Injury: A Systematic Review on Diagnostic Imaging, Treatment, and Prevention","volume":"51","author":"Farrell","year":"2023","journal-title":"Am. J. Sports Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s40798-021-00364-0","article-title":"The Assessment, Management and Prevention of Calf Muscle Strain Injuries: A Qualitative Study of the Practices and Perspectives of 20 Expert Sports Clinicians","volume":"8","author":"Green","year":"2022","journal-title":"Sports Med.-Open"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3390\/medicina57101040","article-title":"Ultrasound Imaging in Sport-Related Muscle Injuries: Pitfalls and Opportunities","volume":"57","author":"Paoletta","year":"2021","journal-title":"Medicina"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ashir, A., Jerban, S., Barr\u00e8re, V., Wu, Y., Shah, S.B., Andre, M.P., and Chang, E.Y. (2023). Skeletal Muscle Assessment Using Quantitative Ultrasound: A Narrative Review. Sensors, 23.","DOI":"10.3390\/s23104763"},{"key":"ref_5","first-page":"16","article-title":"A review on the application of autonomous and intelligent robotic devices in medical rehabilitation","volume":"44","author":"Salgado","year":"2022","journal-title":"J. Braz. Soc. Mech. Sci. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Crawford, S.K., Kliethermes, S.A., Heiderscheit, B.C., and Bashford, G.R. (2023). Influence of ultrasound machine settings on quantitative measures derived from spatial frequency analysis of muscle tissue. BMC Musculoskelet. Disord., 24.","DOI":"10.1186\/s12891-023-06790-3"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Aslam, M.A., Naveed, A., Ahmed, N., and Ke, Z. (2025). A hybrid attention network for accurate breast tumor segmentation in ultrasound images. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-23213-6"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.ultrasmedbio.2016.08.032","article-title":"Fully Automated Muscle Ultrasound Analysis (Musa): Robust and Accurate Muscle Thickness Measurement","volume":"43","author":"Caresio","year":"2017","journal-title":"Ultrasound Med. Biol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Adkins, A.N., and Murray, W.M. (2020). Obtaining Quality Extended Field-of-View Ultrasound Images of Skeletal Muscle to Measure Muscle Fascicle Length. Jove-J. Vis. Exp.","DOI":"10.3791\/61765-v"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/s42979-022-01166-1","article-title":"Survey of Supervised Learning for Medical Image Processing","volume":"3","author":"Aljuaid","year":"2022","journal-title":"SN Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1177\/0161734620952683","article-title":"Skeletal Muscle Fatigue State Evaluation with Ultrasound Image Entropy","volume":"42","author":"Li","year":"2020","journal-title":"Ultrason. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.jmpt.2010.05.009","article-title":"Reliability of sonomyography for pectoralis major thickness measurement","volume":"33","author":"Koo","year":"2010","journal-title":"J Manip. Physiol. Ther."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1080\/10255842.2011.617003","article-title":"Computerised system for measurement of muscle thickness based on ultrasonography","volume":"16","author":"Wong","year":"2013","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1109\/JBHI.2013.2253787","article-title":"Automatic Tracking of Aponeuroses and Estimation of Muscle Thickness in Ultrasonography: A Feasibility Study","volume":"17","author":"Ling","year":"2013","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1249\/MSS.0000000000003010","article-title":"DeepACSA: Automatic Segmentation of Cross-Sectional Area in Ultrasound Images of Lower Limb Muscles Using Deep Learning","volume":"54","author":"Ritsche","year":"2022","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wyatt, L.S., van Karnenbeek, L.M., Wijkhuizen, M., Geldof, F., and Dashtbozorg, B. (2024). Explainable Artificial Intelligence (XAI) for Oncological Ultrasound Image Analysis: A Systematic Review. Appl. Sci., 14.","DOI":"10.20944\/preprints202407.0036.v1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e100954","DOI":"10.1136\/bmjhci-2023-100954","article-title":"Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: A systematic review","volume":"31","author":"Gurmessa","year":"2024","journal-title":"BMJ Health Care Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"S58","DOI":"10.1097\/RTI.0000000000000490","article-title":"Machine Learning and Deep Neural Networks Applications in Computed Tomography for Coronary Artery Disease and Myocardial Perfusion","volume":"35","author":"Monti","year":"2020","journal-title":"J. Thorac. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s41747-024-00422-8","article-title":"AI applications in musculoskeletal imaging: A narrative review","volume":"8","author":"Gitto","year":"2024","journal-title":"Eur. Radiol. Exp."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1017\/wtc.2022.10","article-title":"Toward a wearable monitor of local muscle fatigue during electrical muscle stimulation using tissue Doppler imaging","volume":"3","author":"Majdi","year":"2022","journal-title":"Wearable Technol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yagiz, G., Fredianto, M., Ulfa, M., Ariani, I., Agustin, A.D., Shida, N., Moore, E.W.G., and Kubis, H.P. (2024). A retrospective comparison of the biceps femoris long head muscle structure in athletes with and without hamstring strain injury history. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0298146"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e6","DOI":"10.1017\/wtc.2022.30","article-title":"A clustering-based method for estimating pennation angle from B-mode ultrasound images","volume":"4","author":"Bao","year":"2023","journal-title":"Wearable Technol."},{"key":"ref_24","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., NanoCode012, Kwon, Y., Michael, K., Fang, J., and Imyhxy (2022). Ultralytics\/Yolov5: v6.2-YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai Integrations, Zenodo."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/978-1-0716-0826-5_3","article-title":"Siamese Neural Networks: An Overview","volume":"2190","author":"Chicco","year":"2021","journal-title":"Methods Mol. Biol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kich, V.A., Muttaqien, M.A., Toyama, J., Miyoshi, R., Ida, Y., Ohya, A., and Date, H. (2024). Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environments. arXiv.","DOI":"10.1109\/CIS-RAM61939.2024.10673292"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, S., Duan, J., Zhang, N., Qi, M., Li, J., Wang, H., Wang, R., Ju, R., Duan, Y., and Qi, S. (2023). MSA-YOLOv5: Multi-scale attention-based YOLOv5 for automatic detection of acute ischemic stroke from multi-modality MRI images. Comput. Biol. Med., 165.","DOI":"10.1016\/j.compbiomed.2023.107471"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wang, Y., Shi, S., Wang, Q., Wang, C., and Liu, S. (2024). Improved yolov5 algorithm combined with depth camera and embedded system for blind indoor visual assistance. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-74416-2"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s43055-022-00697-0","article-title":"Qualitative and quantitative strain and shear wave elastography paradigm in differentiation of breast lesions","volume":"53","author":"Shehata","year":"2022","journal-title":"Egypt. J. Radiol. Nucl. Med."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2015, January 7\u201312). Learning to Compare Image Patches Via Convolutional Neural Networks. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity Mappings in Deep Residual Networks","volume":"Volume 9908","author":"He","year":"2016","journal-title":"Computer Vision-ECCV 2016, PT IV"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/3087\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T15:27:07Z","timestamp":1764862027000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/3087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":31,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["diagnostics15233087"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15233087","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}