{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:38:39Z","timestamp":1787027919470,"version":"build-2736575974"},"reference-count":39,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2021,5,27]],"date-time":"2021-05-27T00:00:00Z","timestamp":1622073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 109-2223-E-182-001-MY3"],"award-info":[{"award-number":["MOST 109-2223-E-182-001-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Duchenne muscular dystrophy (DMD) results in loss of ambulation and premature death. Ultrasound provides real-time, safe, and cost-effective routine examinations. Deep learning allows the automatic generation of useful features for classification. This study utilized deep learning of ultrasound imaging for classifying patients with DMD based on their ambulatory function. A total of 85 individuals (including ambulatory and nonambulatory subjects) underwent ultrasound examinations of the gastrocnemius for deep learning of image data using LeNet, AlexNet, VGG-16, VGG-16TL, VGG-19, and VGG-19TL models (the notation TL indicates fine-tuning pretrained models). Gradient-weighted class activation mapping (Grad-CAM) was used to visualize features recognized by the models. The classification performance was evaluated using the confusion matrix and receiver operating characteristic (ROC) curve analysis. The results show that each deep learning model endows muscle ultrasound imaging with the ability to enable DMD evaluations. The Grad-CAMs indicated that boundary visibility, muscular texture clarity, and posterior shadowing are relevant sonographic features recognized by the models for evaluating ambulatory function. Of the proposed models, VGG-19 provided satisfying classification performance (the area under the ROC curve: 0.98; accuracy: 94.18%) and feature recognition in terms of physical characteristics. Deep learning of muscle ultrasound is a potential strategy for DMD characterization.<\/jats:p>","DOI":"10.3390\/diagnostics11060963","type":"journal-article","created":{"date-parts":[[2021,5,27]],"date-time":"2021-05-27T04:30:46Z","timestamp":1622089846000},"page":"963","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Deep Learning of Ultrasound Imaging for Evaluating Ambulatory Function of Individuals with Duchenne Muscular Dystrophy"],"prefix":"10.3390","volume":"11","author":[{"given":"Ai-Ho","family":"Liao","sequence":"first","affiliation":[{"name":"Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan"},{"name":"Department of Biomedical Engineering, National Defense Medical Center, Taipei 114201, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jheng-Ru","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-7663","authenticated-orcid":false,"given":"Shi-Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Hao","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital Hsin-Chu Branch, Hsin-Chu 300195, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeng-Yi","family":"Shieh","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei 100225, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6923-9138","authenticated-orcid":false,"given":"Wen-Chin","family":"Weng","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, National Taiwan University Hospital, Taipei 100225, Taiwan"},{"name":"Department of Pediatric Neurology, National Taiwan University Children\u2019s Hospital, Taipei 100226, Taiwan"},{"name":"Department of Pediatrics, College of Medicine, National Taiwan University, Taipei 100233, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Hsiang","family":"Tsui","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan"},{"name":"Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital, Linkou, Taoyuan 333323, Taiwan"},{"name":"Division of Pediatric Gastroenterology, Department of Pediatrics, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/S0140-6736(02)07815-7","article-title":"The muscular dystrophies","volume":"359","author":"Emery","year":"2002","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/mus.23810","article-title":"Report of MDA muscle disease symposium on newborn screening for Duchenne muscular dystrophy","volume":"48","author":"Mendell","year":"2013","journal-title":"Muscle Nerve"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.ejpn.2004.01.009","article-title":"Developmental progress in Duchenne muscular dystrophy: Lessons for earlier detection","volume":"8","author":"Parsons","year":"2004","journal-title":"Eur. J. Paediatr. Neurol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1038\/s41582-019-0203-3","article-title":"Therapeutic developments for Duchenne muscular dystrophy","volume":"15","author":"Verhaart","year":"2019","journal-title":"Nat. Rev. Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1002\/mus.880100212","article-title":"Management of end stage respiratory failure in Duchenne muscular dystrophy","volume":"10","author":"Bach","year":"1987","journal-title":"Muscle Nerve"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.coph.2017.04.002","article-title":"Pharmacological advances for treatment in Duchenne muscular dystrophy","volume":"34","author":"Guiraud","year":"2017","journal-title":"Curr. Opin. Pharmacol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1002\/mus.21544","article-title":"The 6-minute walk test as a new outcome measure in Duchenne muscular dystrophy","volume":"41","author":"McDonald","year":"2010","journal-title":"Muscle Nerve"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1016\/j.nmd.2009.06.368","article-title":"Reliability of the North star ambulatory assessment in a multicentric setting","volume":"19","author":"Mazzone","year":"2009","journal-title":"Neuromuscul. Disord."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1097\/WCO.0000000000000589","article-title":"How useful is muscle ultrasound in the diagnostic workup of neuromuscular diseases?","volume":"31","author":"Gijsbertse","year":"2018","journal-title":"Curr. Opin. Neurol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2646","DOI":"10.1007\/s00415-018-9037-y","article-title":"Quantitative muscle MRI and ultrasound for facioscapulohumeral muscular dystrophy: Complementary imaging biomarkers","volume":"265","author":"Mul","year":"2018","journal-title":"J. Neurol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1002\/mus.24296","article-title":"Quantitative muscle ultrasound in Duchenne muscular dystrophy: A comparison of techniques","volume":"51","author":"Shklyar","year":"2015","journal-title":"Muscle Nerve"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.nmd.2011.10.020","article-title":"Quantitative muscle ultrasound is a promising longitudinal follow-up tool in Duchenne muscular dystrophy","volume":"22","author":"Jansen","year":"2012","journal-title":"Neuromuscul. Disord."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1016\/j.nmd.2010.06.019","article-title":"Quantitative ultrasound using backscatter analysis in Duchenne and Becker muscular dystrophy","volume":"20","author":"Zaidman","year":"2010","journal-title":"Neuromuscul. Disord."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.ultras.2018.09.004","article-title":"Instantaneous frequency as a new approach for evaluating the clinical severity of Duchenne muscular dystrophy through ultrasound imaging","volume":"94","author":"Weng","year":"2019","journal-title":"Ultrasonics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-04131-8","article-title":"Evaluation of muscular changes by ultrasound Nakagami imaging in Duchenne muscular dystrophy","volume":"7","author":"Weng","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yan, D., Li, Q., Lin, C.W., Shieh, J.Y., Weng, W.C., and Tsui, P.H. (2020). Clinical evaluation of duchenne muscular dystrophy severity using ultrasound small-window entropy imaging. Entropy, 22.","DOI":"10.3390\/e22070715"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1016\/B978-0-444-53486-6.00042-9","article-title":"Muscle ultrasound","volume":"136","author":"Pillen","year":"2016","journal-title":"Handb. Clin. Neurol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, J.R., Chao, Y.P., Tsai, Y.W., Chan, H.J., Wan, Y.L., Tai, D.I., and Tsui, P.H. (2020). Clinical value of information entropy compared with deep learning for ultrasound grading of hepatic steatosis. Entropy, 22.","DOI":"10.3390\/e22091006"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7556","DOI":"10.7150\/thno.38065","article-title":"Current status and future trends of clinical diagnoses via image-based deep learning","volume":"9","author":"Xu","year":"2019","journal-title":"Theranostics"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Burlina, P., Billings, S., Joshi, N., and Albayda, J. (2017). Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0184059"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"30","DOI":"10.14366\/usg.20080","article-title":"Artificial intelligence in musculoskeletal ultrasound imaging","volume":"40","author":"Shin","year":"2021","journal-title":"Ultrasonography"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Khan, S., and Yong, S.P. (2017, January 12\u201315). A Deep Learning Architecture for Classifying Medical Images of Anatomy Object. Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Kuala Lumpur, Malaysia.","DOI":"10.1109\/APSIPA.2017.8282299"},{"key":"ref_24","doi-asserted-by":"crossref","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":"ref_25","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Matthews, E., Brassington, R., Kuntzer, T., Jichi, F., and Manzur, A.Y. (2016). Corticosteroids for the treatment of Duchenne muscular dystrophy. Cochrane Database Syst. Rev., CD003725.","DOI":"10.1002\/14651858.CD003725.pub4"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/S1474-4422(18)30024-3","article-title":"Diagnosis and management of Duchenne muscular dystrophy, part 1: Diagnosis, and neuromuscular, rehabilitation, endocrine, and gastrointestinal and nutritional management","volume":"17","author":"Birnkrant","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/S1474-4422(09)70272-8","article-title":"Diagnosis and management of Duchenne muscular dystrophy, part 2: Implementation of multidisciplinary care","volume":"9","author":"Bushby","year":"2010","journal-title":"Lancet Neurol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1097\/00002060-200212000-00004","article-title":"Predictive factors of cessation of ambulation in patients with Duchenne muscular dystrophy","volume":"81","author":"Bakker","year":"2002","journal-title":"Am. J. Phys. Med. Rehabil."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1212\/WNL.0b013e318208811f","article-title":"Muscle histology vs MRI in Duchenne muscular dystrophy","volume":"76","author":"Kinali","year":"2011","journal-title":"Neurology"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Riaz, H., Park, J., Choi, H., Kim, H., and Kim, J. (2020). Deep and densely connected networks for classification of diabetic retinopathy. Diagnostics, 10.","DOI":"10.3390\/diagnostics10010024"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/538020a","article-title":"Can we open the black box of AI?","volume":"538","author":"Castelvecchi","year":"2016","journal-title":"Nat. News"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.ultrasmedbio.2008.09.016","article-title":"Skeletal muscle ultrasound: Correlation between fibrous tissue and echo intensity","volume":"35","author":"Pillen","year":"2009","journal-title":"Ultrasound Med. Biol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1016\/j.nmd.2007.03.015","article-title":"Sensitivity and specificity of qualitative muscle ultrasound in assessment of suspected neuromuscular disease in childhood","volume":"17","author":"Brockmann","year":"2007","journal-title":"Neuromuscul. Disord."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/0016-5085(85)90761-9","article-title":"Is ultrasonography useful in the assessment of diffuse parenchymal liver disease?","volume":"89","author":"Sandford","year":"1985","journal-title":"Gastroenterology"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/S0009-9260(05)80182-5","article-title":"Ultrasound in the assessment of diffuse parenchymal liver disease","volume":"44","author":"Joseph","year":"1991","journal-title":"Clin. Radiol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.eng.2018.11.020","article-title":"Deep learning in medical ultrasound analysis: A review","volume":"5","author":"Liu","year":"2019","journal-title":"Engineering"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e1255","DOI":"10.1002\/widm.1255","article-title":"From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures","volume":"9","author":"Zhong","year":"2018","journal-title":"WIREs Data Min. Knowl. Discov."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"13590","DOI":"10.1038\/s41598-020-70479-z","article-title":"Comparing different deep learning architectures for classification of chest radiographs","volume":"10","author":"Bressem","year":"2020","journal-title":"Sci. Rep."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/6\/963\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:08:41Z","timestamp":1760162921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/6\/963"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,27]]},"references-count":39,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["diagnostics11060963"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics11060963","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,27]]}}}