[an error occurred while processing this directive]

Advanced Ultrasound in Diagnosis and Therapy ›› 2023, Vol. 7 ›› Issue (2): 122-129.doi: 10.37015/AUDT.2023.230025

• • 上一篇    下一篇

  

  • 收稿日期:2023-04-02 修回日期:2023-04-07 接受日期:2023-04-24 出版日期:2023-06-30 发布日期:2023-04-27

Advances in the Research of Ultrasound and Artificial Intelligence in Neuromuscular Disease

Tianxiang Li, BSa, Fei Ji, BSa, Ruina Zhao, MDa, Huazhen Liu, MDa, Meng Yang, MDa,*()   

  1. a Department of Ultrasound, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
  • Received:2023-04-02 Revised:2023-04-07 Accepted:2023-04-24 Online:2023-06-30 Published:2023-04-27
  • Contact: Meng Yang, MD E-mail:yangmeng_pumch@126.com

RichHTML

25

PDF (PC)

196

Abstract:

Neuromuscular disease includes a wide range of muscular disorders, but it lacks convenient and effective tools for clinical diagnosis and therapeutic monitoring. As a widely used imaging tool, ultrasound can clearly display muscle structure and create basic conditions for accurate image analysis. At present, many studies have tried to obtain information on muscle function and pathological changes by analyzing the features of muscle ultrasound images, and have shown reliable results. However, the minimal changes in muscle structure and image texture are easy to be neglected, and manual segmentation and data analysis are time-consuming tasks. Artificial intelligence (AI) can accurately identify image changes and improve the efficiency of image analysis, and the muscle ultrasonic image analysis model developed based on AI has shown advantages in a large number of research results. This review summarizes the relevant studies of muscle ultrasound imaging and AI in the field of it, including a variety of research based on traditional AI methods or deep learning methods, as well as discusses the clinical significance of ultrasound analysis assisted by AI and the future exploration directions in this field.

Key words: Ultrasonography, Artificial intelligence, Muscle imaging

"

"

"

Study Subjects Method Measurement Result
Caresio-2017 [38] 25 (31.0 ±10.9 y) MUSA Muscle thickness Average measurement Error: 2%
Caresio-2019 [40] 50 (35.3 ± 14.4 y) TRAMA CSA DSC: 0.93
Katakis-2022 [41] 74 Attention UNet Muscle thickness DSC: 0.85 (average)
IoU: 0.74 (average)
Paul-2022 [42] 153 (13-78 y) Pretrained VGG16 encoder UNet CSA IoU: 0.996-0.998
Marzola-2021 [43] 1283 (50 ± 21 y) Ensemble model CSA Precision: Normal (0.90-0.97)
Abnormal (0.78-0.92)
Katakis-2023 [39] 210 TMUNet CSA Precision: 0.95 ± 0.04
DSC: 0.96 ± 0.03
IoU: 0.92 ± 0.05
Saleh-2021 [44] 38 LCFCN + CoordConv Locations of measurement endpoints MWA: 0.312
Chanti-2021 [45] 44 IFSS-Net Volume DSC: 0.97-0.99
IoU: 0.94-0.99
Loram-2020 [46] 35 U-net Muscle boundaries DSC: 0.64 ± 0.21
Chen-2019 [47] 5 CNN CSA Precision: 0.936 ± 0.029
DSC: 0.907 ± 0.023
[1] Anziska Y, Sternberg A. Exercise in neuromuscular disease. Muscle Nerve 2013; 48:3-20.
doi: 10.1002/mus.23771 pmid: 23695822
[2] Sáez A, Acha B, Montero-Sánchez A, Rivas E, Escudero LM, Serrano C. Neuromuscular disease classification system. J Biomed Opt 2013; 18:066017.
doi: 10.1117/1.JBO.18.6.066017
[3] Fischer D, Bonati U, Wattjes MP. Recent developments in muscle imaging of neuromuscular disorders. Curr Opin Neurol 2016; 29:614-620.
doi: 10.1097/WCO.0000000000000364 pmid: 27427989
[4] Simon NG, Noto YI, Zaidman CM. Skeletal muscle imaging in neuromuscular disease. J Clin Neurosci 2016; 33:1-10.
doi: S0967-5868(16)30331-9 pmid: 27612670
[5] Pillen S, van Alfen N, Zwarts MJ. Muscle ultrasound: a grown-up technique for children with neuromuscular disorders. Muscle Nerve 2008; 38:1213-1214.
doi: 10.1002/mus.21085 pmid: 18642384
[6] Gore JC. Artificial intelligence in medical imaging. Magn Reson Imaging 2020; 68:a1-a4.
doi: 10.1016/j.mri.2019.12.006 pmid: 31857130
[7] Rozynek M, Kucybała I, Urbanik A, Wojciechowski W. Use of artificial intelligence in the imaging of sarcopenia: a narrative review of current status and perspectives. Nutrition 2021; 89:111227.
doi: 10.1016/j.nut.2021.111227
[8] Wijntjes J, van Alfen N. Muscle ultrasound: present state and future opportunities. Muscle Nerve 2021; 63:455-466.
doi: 10.1002/mus.27081 pmid: 33051891
[9] Akkus Z, Cai J, Boonrod A, Zeinoddini A, Weston AD, Philbrick KA, et al. A survey of deep-learning applications in ultrasound: artificial intelligence-powered ultrasound for improving clinical workflow. J Am Coll Radiol 2019; 16:1318-1328.
doi: S1546-1440(19)30711-2 pmid: 31492410
[10] Naruse M, Trappe S, Trappe TA. Human skeletal muscle size with ultrasound imaging: a comprehensive review. J Appl Physiol 2022; 132:1267-1279.
doi: 10.1152/japplphysiol.00041.2022
[11] Nijholt W, Scafoglieri A, Jager-Wittenaar H, Hobbelen JSM, van der Schans CP. The reliability and validity of ultrasound to quantify muscles in older adults: a systematic review. J Cachexia Sarcopenia Muscle 2017; 8:702-712.
doi: 10.1002/jcsm.12210 pmid: 28703496
[12] Fukumoto Y, Ikezoe T, Taniguchi M, Yamada Y, Sawano S, Minani S, et al. Cut-off values for lower limb muscle thickness to detect low muscle mass for sarcopenia in older adults. Clin Interv Aging 2021; 16:1215-1222.
doi: 10.2147/CIA.S304972 pmid: 34211270
[13] Goubert D, De Pauw R, Meeus M, Willems T, Cagnie B, Schouppe S, et al. Lumbar muscle structure and function in chronic versus recurrent low back pain: a cross-sectional study. Spine J 2017; 17:1285-1296.
doi: S1529-9430(17)30182-1 pmid: 28456669
[14] Seyedhoseinpoor T, Taghipour M, Dadgoo M, Sanjari MA, Takamjani IE, Kazemnejad A, et al. Alteration of lumbar muscle morphology and composition in relation to low back pain: a systematic review and meta-analysis. Spine J 2022; 22:660-676.
doi: 10.1016/j.spinee.2021.10.018
[15] Reeves ND, Maganaris CN, Narici MV. Ultrasonographic assessment of human skeletal muscle size. Eur J Appl Physiol 2004; 91:116-118.
[16] Macrae PR, Jones RD, Myall DJ, Melzer TR, Huckabee ML. Cross-sectional area of the anterior belly of the digastric muscle: comparison of MRI and ultrasound measures. Dysphagia 2013; 28:375-380.
doi: 10.1007/s00455-012-9443-8 pmid: 23334304
[17] Mendis MD, Wilson SJ, Stanton W, Hides JA. Validity of real-time ultrasound imaging to measure anterior hip muscle size: a comparison with magnetic resonance imaging. J Orthop Sports Phys Ther 2010; 40:577-581.
[18] Latey PJ, Burns J, Nightingale EJ, Clarke JL, Hiller CE. Reliability and correlates of cross-sectional area of abductor hallucis and the medial belly of the flexor hallucis brevis measured by ultrasound. J Foot Ankle Res 2018; 11:28.
doi: 10.1186/s13047-018-0259-0 pmid: 29977344
[19] Franchi MV, Longo S, Mallinson J, Quinlan JI, Taylor T, Greenhaff PL, et al. Muscle thickness correlates to muscle cross-sectional area in the assessment of strength training-induced hypertrophy. Scand J Med Sci Sports 2018; 28:846-853.
doi: 10.1111/sms.2018.28.issue-3
[20] Mohseny B, Nijhuis TH, Hundepool CA, Janssen WG, Selles RW, Coert JH. Ultrasonographic quantification of intrinsic hand muscle cross-sectional area; reliability and validity for predicting muscle strength. Arch Phys Med Rehabil 2015; 96:845-853.
doi: 10.1016/j.apmr.2014.11.014
[21] Timmins RG, Shield AJ, Williams MD, Lorenzen C, Opar DA. Architectural adaptations of muscle to training and injury: a narrative review outlining the contributions by fascicle length, pennation angle and muscle thickness. Br J Sports Med 2016; 50:1467-1472.
doi: 10.1136/bjsports-2015-094881
[22] Pillen S, Arts IM, Zwarts MJ. Muscle ultrasound in neuromuscular disorders. Muscle Nerve 2008; 37:679-693.
doi: 10.1002/mus.21015 pmid: 18506712
[23] Heckmatt JZ, Leeman S, Dubowitz V. Ultrasound imaging in the diagnosis of muscle disease. J Pediatr 1982; 101:656-660.
doi: 10.1016/S0022-3476(82)80286-2
[24] Zaidman CM, Wu JS, Kapur K, Pasternak A, Madabusi L, Yim S, et al. Quantitative muscle ultrasound detects disease progression in duchenne muscular dystrophy. Ann Neurol 2017; 81:633-640.
doi: 10.1002/ana.24904 pmid: 28241384
[25] Simon NG, Ralph JW, Lomen-Hoerth C, Poncelet AN, Vucic S, Kiernan MC, et al. Quantitative ultrasound of denervated hand muscles. Muscle Nerve 2015; 52:221-230.
doi: 10.1002/mus.24519 pmid: 25388871
[26] Pichiecchio A, Alessandrino F, Bortolotto C, Cerica A, Rosti C, Raciti MV, et al. Muscle ultrasound elastography and MRI in preschool children with duchenne muscular dystrophy. Neuromuscul Disord 2018; 28:476-483.
doi: 10.1016/j.nmd.2018.02.007
[27] Harada R, Taniguchi-Ikeda M, Nagasaka M, Nishii T, Inui A, Yamamoto T, et al. Assessment of the upper limb muscles in patients with fukuyama muscular dystrophy: noninvasive assessment using visual ultrasound muscle analysis and shear wave elastography. Neuromuscul Disord 2022; 32:754-762.
doi: 10.1016/j.nmd.2022.05.004
[28] Lacourpaille L, Hug F, Guével A, Péréon Y, Magot A, Hogrel JY, et al. Non-invasive assessment of muscle stiffness in patients with duchenne muscular dystrophy. Muscle Nerve 2015; 51:284-286.
doi: 10.1002/mus.24445 pmid: 25187068
[29] Lacourpaille L, Gross R, Hug F, Guével A, Péréon Y, Magot A, et al. Effects of duchenne muscular dystrophy on muscle stiffness and response to electrically-induced muscle contraction: a 12-month follow-up. Neuromuscul Disord 2017; 27:214-220.
doi: 10.1016/j.nmd.2017.01.001
[30] Pillen S, Scholten RR, Zwarts MJ, Verrips A. Quantitative skeletal muscle ultrasonography in children with suspected neuromuscular disease. Muscle Nerve 2003; 27:699-705.
pmid: 12766981
[31] Boon AJ, Wijntjes J, O'Brien TG, Sorenson EJ, Cazares Gonzalez ML, van Alfen N. Diagnostic accuracy of gray scale muscle ultrasound screening for pediatric neuromuscular disease. Muscle Nerve 2021; 64:50-58.
doi: 10.1002/mus.v64.1
[32] Sogawa K, Nodera H, Takamatsu N, Mori A, Yamazaki H, Shimatani Y, et al. Neurogenic and myogenic diseases: quantitative texture analysis of muscle us data for differentiation. Radiology 2017; 28:492-498.
[33] Ríos-Díaz J, Del Baño-Aledo ME, Tembl-Ferrairó JI, Chumillas MJ, Vázquez-Costa JF, Martínez-Payá JJ. Quantitative neuromuscular ultrasound analysis as biomarkers in amyotrophic lateral sclerosis. Eur Radiol 2019; 29:4266-4275.
doi: 10.1007/s00330-018-5943-8 pmid: 30666448
[34] Martínez-Payá JJ, Ríos-Díaz J, Del Baño-Aledo ME, Tembl-Ferrairó JI, Vazquez-Costa JF, Medina-Mirapeix F. Quantitative muscle ultrasonography using textural analysis in amyotrophic lateral sclerosis. Ultrason Imaging 2017; 39:357-368.
doi: 10.1177/0161734617711370 pmid: 28553752
[35] Martínez-Payá JJ, Del Baño-Aledo ME, Ríos-Díaz J, Tembl-Ferrairó JI, Vázquez-Costa JF, Medina-Mirapeix F. Muscular echovariation: a new biomarker in amyotrophic lateral sclerosis. Ultrasound Med Biol 2017; 43:1153-1162.
doi: S0301-5629(17)30058-3 pmid: 28395965
[36] John EP, Ziyin ZMD, Ji-Bin LMD, Shuo WBS. Artificial intelligence in ultrasound imaging: current research and applications. Advanced Ultrasound in Diagnosis and Therapy 2019;3.
[37] Barotsis N, Galata A, Hadjiconstanti A, Panayiotakis G. The ultrasonographic measurement of muscle thickness in sarcopenia. a prediction study. Eur J Phys Rehabil Med 2020; 56:427-437.
[38] Caresio C, Salvi M, Molinari F, Meiburger KM, Minetto MA. Fully automated muscle ultrasound analysis (MUSA): robust and accurate muscle thickness measurement. Ultrasound Med Biol 2017; 43:195-205.
doi: S0301-5629(16)30268-X pmid: 27720522
[39] Katakis S, Barotsis N, Kakotaritis A, Tsiganos P, Economou G, Panagiotopoulos E, et al. Muscle cross-sectional area segmentation in transverse ultrasound images using vision transformers. Diagnostics 2023;13.
[40] Salvi M, Caresio C, Meiburger KM, De Santi B, Molinari F, Minetto MA. Transverse muscle ultrasound analysis (TRAMA): robust and accurate segmentation of muscle cross-sectional area. Ultrasound Med Biol 2019; 45:672-683.
doi: S0301-5629(18)30523-4 pmid: 30638696
[41] Katakis S, Barotsis N, Kakotaritis A, Economou G, Panagiotopoulos E, Panayiotakis G. Automatic extraction of muscle parameters with attention UNet in ultrasonography. Sensors 2022;22.
[42] Ritsche P, Wirth P, Cronin NJ, Sarto F, Narici MV, Faude O, et al. DeepACSA: automatic segmentation of cross-sectional area in ultrasound images of lower limb muscles using deep learning. Med Sci Sports Exerc 2022; 54:2188-2195.
doi: 10.1249/MSS.0000000000003010
[43] Marzola F, van Alfen N, Doorduin J, Meiburger KM. Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment. Comput Biol Med 2021; 135:104623.
doi: 10.1016/j.compbiomed.2021.104623
[44] Saleh A, Laradji IH, Lammie C, Vazquez D, Flavell CA, Azghadi MR. A deep learning localization method for measuring abdominal muscle dimensions in ultrasound images. IEEE J Biomed Health Inform 2021; 25:3865-3873.
doi: 10.1109/JBHI.2021.3085019
[45] Chanti DA, Duque VG, Crouzier M, Nordez A, Lacourpaille L, Mateus D. IFSS-Net: interactive few-shot siamese network for faster muscle segmentation and propagation in volumetric ultrasound. IEEE Trans Med Imaging 2021; 40:2615-2628.
doi: 10.1109/TMI.2021.3058303
[46] Loram I, Siddique A, Sanchez MB, Harding P, Silverdale M, Kobylecki C, et al. Objective analysis of neck muscle boundaries for cervical dystonia using ultrasound imaging and deep learning. IEEE J Biomed Health Inform 2020; 24:1016-1027.
doi: 10.1109/JBHI.6221020
[47] Chen X, Xie C, Chen Z, Li Q. Automatic tracking of muscle cross-sectional area using convolutional neural networks with ultrasound. J Ultrasound Med 2019; 38:2901-2908.
doi: 10.1002/jum.14995 pmid: 30937932
[48] Zhou GQ, Chan P, Zheng YP. Automatic measurement of pennation angle and fascicle length of gastrocnemius muscles using real-time ultrasound imaging. Ultrasonics 2015; 57:72-83.
doi: 10.1016/j.ultras.2014.10.020
[49] Rosa LG, Zia JS, Inan OT, Sawicki GS. Machine learning to extract muscle fascicle length changes from dynamic ultrasound images in real-time. PloS one 2021; 16:e0246611.
[50] Jahanandish MH, Fey NP, Hoyt K. Lower limb motion estimation using ultrasound imaging: a framework for assistive device control. IEEE J Biomed Health Inform 2019; 23:2505-2514.
doi: 10.1109/JBHI.6221020
[51] König T, Steffen J, Rak M, Neumann G, von Rohden L, Tönnies KD. Ultrasound texture-based CAD system for detecting neuromuscular diseases. Int J Comput Assist Radiol Surg 2015; 10:1493-1503.
doi: 10.1007/s11548-014-1133-6 pmid: 25451320
[52] Srivastava T, Darras BT, Wu JS, Rutkove SB. Machine learning algorithms to classify spinal muscular atrophy subtypes. Neurology 2012; 79:358-364.
doi: 10.1212/WNL.0b013e3182604395 pmid: 22786588
[53] Burlina P, Billings S, Joshi N, Albayda J. Automated diagnosis of myositis from muscle ultrasound: exploring the use of machine learning and deep learning methods. PloS one 2017;12.
[54] Cunningham R, Harding P, Loram I. Deep residual networks for quantification of muscle fiber orientation and curvature from ultrasound images. Med Image Underst Anal Conf 2017:63-73.
[55] Cunningham R, Sánchez M, May G, Loram I. Estimating full regional skeletal muscle fibre orientation from B-mode ultrasound images using convolutional, residual, and deconvolutional neural networks. J Imaging 2018;4.
[56] Cunningham RJ, Loram ID. Estimation of absolute states of human skeletal muscle via standard B-mode ultrasound imaging and deep convolutional neural networks. J R Soc Interface 2020; 17:20190715.
[57] Li H, Bhatt M, Qu Z, Zhang S, Hartel MC, Khademhosseini A, et al. Deep learning in ultrasound elastography imaging: a review. Med Phys 2022; 49:5993-6018.
doi: 10.1002/mp.v49.9
[58] Dana J, Venkatasamy A, Saviano A, Lupberger J, Hoshida Y, Vilgrain V, et al. Conventional and artificial intelligence-based imaging for biomarker discovery in chronic liver disease. Hepatol Int 2022; 16:509-522.
doi: 10.1007/s12072-022-10303-0 pmid: 35138551
[59] Secasan CC, Onchis D, Bardan R, Cumpanas A, Novacescu D, Botoca C, et al. Artificial intelligence system for predicting prostate cancer lesions from shear wave elastography measurements. Curr Oncol 2022; 29:4212-4223.
doi: 10.3390/curroncol29060336 pmid: 35735445
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
[an error occurred while processing this directive]