{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:35:46Z","timestamp":1774456546909,"version":"3.50.1"},"reference-count":42,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11974373"],"award-info":[{"award-number":["11974373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Musculoskeletal ultrasound imaging is an important basis for the early screening and accurate treatment of muscle disorders. It allows the observation of muscle status to screen for underlying neuromuscular diseases including myasthenia gravis, myotonic dystrophy, and ankylosing muscular dystrophy. Due to the complexity of skeletal muscle ultrasound image noise, it is a tedious and time-consuming process to analyze. Therefore, we proposed a multi-task learning-based approach to automatically segment and initially diagnose transverse musculoskeletal ultrasound images. The method implements muscle cross-sectional area (CSA) segmentation and abnormal muscle classification by constructing a multi-task model based on multi-scale fusion and attention mechanisms (MMA-Net). The model exploits the correlation between tasks by sharing a part of the shallow network and adding connections to exchange information in the deep network. The multi-scale feature fusion module and attention mechanism were added to MMA-Net to increase the receptive field and enhance the feature extraction ability. Experiments were conducted using a total of 1827 medial gastrocnemius ultrasound images from multiple subjects. Ten percent of the samples were randomly selected for testing, 10% as the validation set, and the remaining 80% as the training set. The results show that the proposed network structure and the added modules are effective. Compared with advanced single-task models and existing analysis methods, our method has a better performance at classification and segmentation. The mean Dice coefficients and IoU of muscle cross-sectional area segmentation were 96.74% and 94.10%, respectively. The accuracy and recall of abnormal muscle classification were 95.60% and 94.96%. The proposed method achieves convenient and accurate analysis of transverse musculoskeletal ultrasound images, which can assist physicians in the diagnosis and treatment of muscle diseases from multiple perspectives.<\/jats:p>","DOI":"10.3390\/e25040662","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T02:26:02Z","timestamp":1681698362000},"page":"662","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Automatic Analysis of Transverse Musculoskeletal Ultrasound Images Based on the Multi-Task Learning Model"],"prefix":"10.3390","volume":"25","author":[{"given":"Linxueying","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]},{"given":"Shangkun","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]},{"given":"Weimin","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Marzola, F., van Alfen, N., Salvi, M., De Santi, B., Doorduin, J., and Meiburger, K.M. (2020, January 20\u201324). Automatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks. Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada.","DOI":"10.1109\/EMBC44109.2020.9176343"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"310","DOI":"10.2340\/16501977-0959","article-title":"Musculoskeletal ultrasonography in physical and rehabilitation medicine","volume":"44","author":"Tok","year":"2012","journal-title":"J. Rehabil. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1177\/0309364612446652","article-title":"Towards the application of one-dimensional sonomyography for powered upper-limb prosthetic control using machine learning models","volume":"37","author":"Guo","year":"2013","journal-title":"Prosthetics Orthot. Int."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1164\/rccm.201604-0875LE","article-title":"Rectus femoris cross-sectional area and muscle layer thickness: Comparative markers of muscle wasting and weakness","volume":"195","author":"Puthucheary","year":"2017","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.ultrasmedbio.2007.08.013","article-title":"Quantitative muscle ultrasonography in amyotrophic lateral sclerosis","volume":"34","author":"Arts","year":"2008","journal-title":"Ultrasound Med. Biol."},{"key":"ref_6","first-page":"5528309","article-title":"Diagnosis of waist muscle injury after exercise Based on high-Frequency Ultrasound image","volume":"2021","author":"Wang","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1017\/cjn.2018.269","article-title":"Neuromuscular ultrasound: A new tool in your toolbox","volume":"45","author":"Mah","year":"2018","journal-title":"Can. J. Neurol. Sci."},{"key":"ref_8","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_9","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1002\/ana.24904","article-title":"Quantitative muscle ultrasound detects disease progression in Duchenne muscular dystrophy","volume":"81","author":"Zaidman","year":"2017","journal-title":"Ann. Neurol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1474","DOI":"10.1016\/j.ultrasmedbio.2008.02.009","article-title":"Estimation of muscle fiber orientation in ultrasound images using revoting hough transform (RVHT)","volume":"34","author":"Zhou","year":"2008","journal-title":"Ultrasound Med. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/TBME.2011.2144593","article-title":"Automatic tracking of muscle fascicles in ultrasound images using localized radon transform","volume":"58","author":"Zhao","year":"2011","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.ultras.2014.10.020","article-title":"Automatic measurement of pennation angle and fascicle length of gastrocnemius muscles using real-time ultrasound imaging","volume":"57","author":"Zhou","year":"2015","journal-title":"Ultrasonics"},{"key":"ref_13","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_14","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.ultrasmedbio.2018.11.012","article-title":"Transverse muscle ultrasound analysis (TRAMA): Robust and accurate segmentation of muscle cross-sectional area","volume":"45","author":"Salvi","year":"2019","journal-title":"Ultrasound Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"113408","DOI":"10.1016\/j.eswa.2020.113408","article-title":"An efficient convolutional neural network for coronary heart disease prediction","volume":"159","author":"Dutta","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., and Johansen, H.D. (2020, January 28\u201330). Doubleu-net: A deep convolutional neural network for medical image segmentation. Proceedings of the 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), Rochester, MN, USA.","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv.","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.gie.2020.01.054","article-title":"Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network","volume":"92","author":"Saito","year":"2020","journal-title":"Gastrointest. Endosc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cunningham, R., Harding, P., and Loram, I. (2017, January 11\u201313). Deep residual networks for quantification of muscle fiber orientation and curvature from ultrasound images. Proceedings of the Annual Conference on Medical Image Understanding and Analysis, Edinburgh, UK.","DOI":"10.1007\/978-3-319-60964-5_6"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Cunningham, R., S\u00e1nchez, M.B., May, G., and Loram, I. (2018). Estimating full regional skeletal muscle fibre orientation from B-mode ultrasound images using convolutional, residual, and deconvolutional neural networks. J. Imaging, 4.","DOI":"10.20944\/preprints201711.0053.v3"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kompella, G., Antico, M., Sasazawa, F., Jeevakala, S., Ram, K., Fontanarosa, D., Pandey, A.K., and Sivaprakasam, M. (2019, January 23\u201327). Segmentation of femoral cartilage from knee ultrasound images using mask R-CNN. Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany.","DOI":"10.1109\/EMBC.2019.8857645"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1177\/0161734621989598","article-title":"Automatic Measurement of Pennation Angle from Ultrasound Images using Resnets","volume":"43","author":"Zheng","year":"2021","journal-title":"Ultrason. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zheng, W., Zhou, L., Chai, Q., Xu, J., and Liu, S. (2022). Fully Automatic Analysis of Muscle B-Mode Ultrasound Images Based on the Deep Residual Shrinkage U-Net. Electronics, 11.","DOI":"10.3390\/electronics11071093"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104623","DOI":"10.1016\/j.compbiomed.2021.104623","article-title":"Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment","volume":"135","author":"Marzola","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_26","unstructured":"Ruder, S. (2017). An overview of multi-task learning in deep neural networks. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101593","DOI":"10.1016\/j.media.2019.101593","article-title":"Multi-indices quantification of optic nerve head in fundus image via multitask collaborative learning","volume":"60","author":"Zhao","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, E.Z., Dong, X., Li, X., Jiang, H., Rong, R., and Wu, J. (2019, January 8\u201311). Lesion attributes segmentation for melanoma detection with multi-task u-net. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759483"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Michard, H., Luvison, B., Pham, Q.C., Morales-Artacho, A.J., and Guilhem, G. (2021, January 1\u20134). AW-Net: Automatic muscle structure analysis on B-mode ultrasound images for injury prevention. Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, New York, NY, USA.","DOI":"10.1145\/3459930.3469531"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_31","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_32","first-page":"49","article-title":"The piecewise non-linear approximation of the sigmoid function and its implementation in FPGA","volume":"43","author":"SHONG","year":"2017","journal-title":"Appl. Electron. Tech."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 20\u201325). Coordinate attention for efficient mobile network design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","article-title":"A tutorial on the cross-entropy method","volume":"134","author":"Kroese","year":"2005","journal-title":"Ann. Oper. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1038\/nmeth.2019","article-title":"Fiji: An open-source platform for biological-image analysis","volume":"9","author":"Schindelin","year":"2012","journal-title":"Nat. Methods"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/0165-1684(84)90013-6","article-title":"Learning characteristics of stochastic-gradient-descent algorithms: A general study, analysis, and critique","volume":"6","author":"Gardner","year":"1984","journal-title":"Signal Process."},{"key":"ref_40","unstructured":"Zhang, Y.J. (2001, January 13\u201316). A review of recent evaluation methods for image segmentation. Proceedings of the Sixth International Symposium on Signal Processing and Its Applications (Cat. No. 01EX467), Kuala Lumpur, Malaysia."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0001-2998(78)80014-2","article-title":"Basic principles of ROC analysis","volume":"Volume 8","author":"Metz","year":"1978","journal-title":"Seminars in Nuclear Medicine"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/4\/662\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:16:15Z","timestamp":1760123775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/4\/662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,14]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["e25040662"],"URL":"https:\/\/doi.org\/10.3390\/e25040662","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,14]]}}}