Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods

PLoS ONE

Volumn 12, Issue 8, 2017, Pages

  Burlina, Philippe ^a   Billings, Seth ^a   Joshi, Neil ^a   Albayda, Jemima ^b  

^a JOHNS HOPKINS UNIVERSITY APPLIED PHYSICS LABORATORY   (United States)

^b JOHNS HOPKINS UNIVERSITY SCHOOL OF MEDICINE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CREATINE KINASE;

ADULT; AGED; ARTICLE; ARTIFICIAL NEURAL NETWORK; CLINICAL ARTICLE; COMPUTER ASSISTED DIAGNOSIS; CONTROLLED STUDY; CREATINE KINASE BLOOD LEVEL; DEEP CONVOLUTIONAL NEURAL NETWORK; DEEP LEARNING METHOD; DERMATOMYOSITIS; DIAGNOSTIC ACCURACY; DISEASE CLASSIFICATION; FEMALE; GOLD STANDARD; HUMAN; HUMAN TISSUE; INCLUSION BODY MYOSITIS; INTERMETHOD COMPARISON; MACHINE LEARNING; MALE; MYOSITIS; POLYMYOSITIS; RANDOM FOREST; ULTRASOUND; VERY ELDERLY; YOUNG ADULT; DIAGNOSTIC IMAGING; ECHOGRAPHY; MIDDLE AGED; MUSCLE; PROCEDURES;

ADULT; AGED; AGED, 80 AND OVER; DERMATOMYOSITIS; FEMALE; HUMANS; MACHINE LEARNING; MALE; MIDDLE AGED; MUSCLES; MYOSITIS; MYOSITIS, INCLUSION BODY; NEURAL NETWORKS (COMPUTER); POLYMYOSITIS; ULTRASONOGRAPHY; YOUNG ADULT;

EID: 85028647173     PISSN: None     EISSN: 19326203     Source Type: Journal    
DOI: 10.1371/journal.pone.0184059     Document Type: Article

References (56)

1. Olsen NJ, Qi J, Park JH. Imaging and skeletal muscle disease. Current Rheumatology Reports. 2005; 7(2):106–114. https://doi.org/10.1007/s11926-005-0062-3
2. Goodwin DW. Imaging of Skeletal Muscle. Rheumatic Disease Clinics of North America. 2011; 37(2): 245–251. https://doi.org/10.1016/j.rdc.2011.01.007 PMID: 21444023
3. Zaidman CM, Van Alfen N. Ultrasound in the Assessment of Myopathic Disorders. Journal of Clinical Neurophysiology. 2016; 33(2):103–11. https://doi.org/10.1097/WNP.0000000000000245 PMID: 27035250
4. Pillen S, Verrips A, van Alfen N, Arts IMP, Sie LTL, Zwarts MJ. Quantitative skeletal muscle ultrasound: Diagnostic value in childhood neuromuscular disease. Neuromuscular Disorders. 2007; 17(7):509–516. https://doi.org/10.1016/j.nmd.2007.03.008 PMID: 17537635
5. Pillen S, Boon A, Van Alfen N. Muscle ultrasound. In: Handbook of Clinical Neurology, Volume 136; 2016. p. 843–853.
6. Wu JS, Darras BT, Rutkove SB. Assessing spinal muscular atrophy with quantitative ultrasound. Neurology. 2010; 75(6):526–31. https://doi.org/10.1212/WNL.0b013e3181eccf8f
7. Pillen S, Arts IMP, Zwarts MJ. Muscle ultrasound in neuromuscular disorders. Muscle & Nerve. 2008; 37(6):679–693. https://doi.org/10.1002/mus.21015
8. Brandsma R, Verbeek RJ, Maurits NM, van der Hoeven JH, Brouwer OF, den Dunnen WFA, et al. Visual Screening of Muscle Ultrasound Images in Children. Ultrasound in Medicine & Biology. 2014; 40(10):2345–2351. https://doi.org/10.1016/j.ultrasmedbio.2014.03.027
9. Zaidman CM, Wu JS, Kapur K, Pasternak A, Madabusi L, Yim S, et al. Quantitative muscle ultrasound detects disease progression in Duchenne muscular dystrophy. Annals of Neurology. 2017; 81(5): 633–640. https://doi.org/10.1002/ana.24904 PMID: 28241384
10. Jansen M, van Alfen N, Nijhuis van der Sanden MWG, van Dijk JP, Pillen S, de Groot IJM. Quantitative muscle ultrasound is a promising longitudinal follow-up tool in Duchenne muscular dystrophy. Neuromuscular Disorders. 2012; 22(4):306–317. https://doi.org/10.1016/j.nmd.2011.10.020 PMID: 22133654
11. Pillen S, Van Alfen N. Muscle ultrasound from diagnostic tool to outcome measure-Quantification is the challenge. Muscle & Nerve. 2015; 52(3):319–320. https://doi.org/10.1002/mus.24613
12. Zaidman CM, Holland MR, Anderson CC, Pestronk A. Calibrated quantitative ultrasound imaging of skeletal muscle using backscatter analysis. Muscle & Nerve. 2008; 38(1):893–898. https://doi.org/10.1002/mus.21052
13. Schulze M, Kötter I, Ernemann U, Fenchel M, Tzaribatchev N, Claussen CD, et al. MRI Findings in Inflammatory Muscle Diseases and Their Noninflammatory Mimics. American Journal of Roentgenology. 2009; 192(6):1708–1716. https://doi.org/10.2214/AJR.08.1764
14. Reimers CD, Fleckenstein JL, Witt TN, Müller-Felber W, Pongratz DE. Muscular ultrasound in idiopathic inflammatory myopathies of adults. Journal of the Neurological Sciences. 1993; 116(1):82–92. https://doi.org/10.1016/0022-510X(93)90093-E PMID: 8509807
15. Habers GEA, Van Brussel M, Bhansing KJ, Hoppenreijs EP, Janssen AJWM, Van Royen-Kerkhof A, et al. Quantitative muscle ultrasonography in the follow-up of juvenile dermatomyositis. Muscle & Nerve. 2015; 52(4):540–546. https://doi.org/10.1002/mus.24564
16. Nodera H, Takamatsu N, Matsui N, Mori A, Terasawa Y, Shimatani Y, et al. Intramuscular dissociation of echogenicity in the triceps surae characterizes sporadic inclusion body myositis. European Journal of Neurology. 2016; 23(3):588–596. https://doi.org/10.1111/ene.12899 PMID: 26706399
17. Noto YI, Shiga K, Tsuji Y, Kondo M, Tokuda T, Mizuno T, et al. Contrasting echogenicity in flexor digitorum profundus-flexor carpi ulnaris: a diagnostic ultrasound pattern in sporadic inclusion body myositis. Muscle & nerve. 2014; 49(5):745–8. https://doi.org/10.1002/mus.24056
18. Bhansing KJ, Van Rosmalen MH, Van Engelen BG, Vonk MC, Van Riel PL, Pillen S. Increased fascial thickness of the deltoid muscle in dermatomyositis and polymyositis: An ultrasound study. Muscle & Nerve. 2015; 52(4):534–539. https://doi.org/10.1002/mus.24595
19. Malattia C, Damasio MB, Madeo A, Pistorio A, Providenti A, Pederzoli S, et al. Whole-body MRI in the assessment of disease activity in juvenile dermatomyositis. Annals of the Rheumatic Diseases. 2014; 73(6):1083–1090. https://doi.org/10.1136/annrheumdis-2012-202915 PMID: 23636654
20. Caresio C, Salvi M, Molinari F, Meiburger KM, Minetto MA. Fully automated muscle ultrasound analysis (MUSA): Robust and accurate muscle thickness measurement. Ultrasound in Medicine & Biology. 2017; 43(1):195–205. https://doi.org/10.1016/j.ultrasmedbio.2016.08.032
21. König T, Steffen J, Rak M, Neumann G, von Rohden L, Tönnies KD. Ultrasound texture-based CAD system for detecting neuromuscular diseases. International journal of computer assisted radiology and surgery. 2015; 10(9):1493–503. https://doi.org/10.1007/s11548-014-1133-6 PMID: 25451320
22. Burlina P, Freund D, Dupas B, Bressler N. Automatic screening of age-related macular degeneration and retinal abnormalities. In: Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE. IEEE; 2011. p. 3962–3966.
23. Vyas S, Banerjee A, Burlina P. Estimating physiological skin parameters from hyperspectral signatures. Journal of biomedical optics. 2013; 18(5):057008–057008. https://doi.org/10.1117/1.JBO.18.5.057008
24. Krizhevsky A, Hinton G. Using very deep autoencoders for content-based image retrieval. In: Proceedings of the European Symposium on Artificial Neural Networks (ESANN); 2011. p. 1–7.
25. Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. OverFeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv. 2013; p. 1312.6229.
26. Felzenszwalb PF, Girshick RB, Mcallester D, Ramanan D. Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2009; 32(9): 1–20.
27. Banerjee A, Burlina P, Broadwater J. A machine learning approach for finding hyperspectral endmembers. In: Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International. IEEE; 2007. p. 3817–3820.
28. Vapnik VN, Vapnik V. Statistical learning theory. vol. 1. Wiley New York; 1998.
29. Breiman L. Random forests. Machine Learning. 2001; 45(1):5–32. https://doi.org/10.1023/A:1010933404324
30. Feeny AK, Tadarati M, Freund DE, Bressler NM, Burlina P. Automated segmentation of geographic atrophy of the retinal epithelium via random forests in AREDS color fundus images. Computers in biology and medicine. 2015; 65:124–136. https://doi.org/10.1016/j.compbiomed.2015.06.018 PMID: 26318113
31. Burlina P, Pacheco KD, Joshi N, Freund DE, Bressler NM. Comparing humans and deep learning performance for grading AMD: A study in using universal deep features and transfer learning for automated AMD analysis. Computers in Biology and Medicine. 2017; 82:80–86. https://doi.org/10.1016/j.compbiomed.2017.01.018 PMID: 28167406
32. Bohan A, Peter JB. Polymyositis and dermatomyositis (second of two parts). The New England Journal of Medicine. 1975; 292(8):403–7. https://doi.org/10.1056/NEJM197502202920807 PMID: 1089199
33. Bohan A, Peter JB. Polymyositis and dermatomyositis (first of two parts). The New England Journal of Medicine. 1975; 292(7):344–7. https://doi.org/10.1056/NEJM197502132920706 PMID: 1090839
34. Hoogendijk JE, Amato AA, Lecky BR, Choy EH, Lundberg IE, Rose MR, et al. 119th ENMC international workshop: Trial design in adult idiopathic inflammatory myopathies, with the exception of inclusion body myositis, 10-12 October 2003, Naarden, The Netherlands. Neuromuscular Disorders. 2004; 14(5):337–45. https://doi.org/10.1016/j.nmd.2004.02.006 PMID: 15099594
35. Rose MR, ENMC IBM Working Group. 188th ENMC international workshop: Inclusion body myositis, 2-4 December 2011, Naarden, The Netherlands. Neuromuscular disorders: NMD. 2013; 23(12):1044–55. https://doi.org/10.1016/j.nmd.2013.08.007 PMID: 24268584
36. Rider LG, Werth VP, Huber AM, Alexanderson H, Rao AP, Ruperto N, et al. Measures of adult and juvenile dermatomyositis, polymyositis, and inclusion body myositis: Physician and Patient/Parent Global Activity, Manual Muscle Testing (MMT), Health Assessment Questionnaire (HAQ)/Childhood Health Assessment Questionnaire (C-HAQ), Childhood Myositis Assessment Scale (CMAS), Myositis Disease Activity Assessment Tool (MDAAT), Disease Activity Score (DAS), Short Form 36 (SF-36), Child Health Questionnaire (CHQ), Physician Global Damage, Myositis Damage Index (MDI), Quantitative Muscle Testing (QMT), Myositis Functional Index-2 (FI-2), Myositis Activities Profile (MAP), Inclusion Body Myositis Functional Rating Scale (IBMFRS), Cutaneous Dermatomyositis Disease Area and Severity Index (CDASI), Cutaneous Assessment Tool (CAT), Dermatomyositis Skin Severity Index (DSSI), Skin-dex, and Dermatology Life Quality Index (DLQI). Arthritis care & research. 2011; 63(S11)
37. Bengio Y. Learning deep architectures for AI. Foundations and Trends in Machine Learning. 2009; 2(1):1–127. https://doi.org/10.1561/2200000006
38. Hinton G, Deng L, Yu D, Dahl GE, Mohamed Ar, Jaitly N, et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine. 2012;(November):82–97. https://doi.org/10.1109/MSP.2012.2205597
39. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436–444. https://doi.org/10.1038/nature14539 PMID: 26017442
40. Schmidhuber J. Deep Learning in neural networks: An overview. Neural Networks. 2015; 61:85–117. https://doi.org/10.1016/j.neunet.2014.09.003 PMID: 25462637
41. Makhzani A, Shlens J, Jaitly N, Goodfellow I. Adversarial autoencoders. arXiv. 2015; p. 1–10.
42. Burlina PM, Schmidt AC, Wang IJ. Zero shot deep learning from semantic attributes. In: 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA). 1; 2015. p. 871–876.
43. Burlina P, Freund DE, Joshi N, Wolfson Y, Bressler NM. Detection of age-related macular degeneration via deep learning. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). IEEE; 2016. p. 184–188.
44. Krizhevsky A, Sutskever I, Geoffrey E H. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (NIPS2012); 2012. p. 1–9.
45. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision. 2015; 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
46. Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. NeuroImage. 2006; 31(3):1116–1128. https://doi.org/10.1016/j.neuroimage.2006.01.015 PMID: 16545965
47. Billings S, Albayda J, Burlina P. Ultrasound image analysis for myopathy detection: Relating muscle image biomarkers to severity of disease. In: 23rd International Conference on Pattern Recognition (ICPR). Cancun, Mexico; 2016.
48. Oelze ML, Mamou J. Review of quantitative ultrasound: Envelope statistics and backscatter coefficient imaging and contributions to diagnostic ultrasound. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2016; 63(2):336–351. https://doi.org/10.1109/TUFFC.2015.2513958 PMID: 26761606
49. Haralick RM, Shanmugam K, Dinstein II, Haralick, Robert M, Shanmugam K, Dinstein II, et al. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics SMC-3. 1973; 6(6):610–621. https://doi.org/10.1109/TSMC.1973.4309314
50. 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. Ultrasonic Imaging. 2017; p. 016173461771137.
51. Molinari F, Caresio C, Acharya UR, Mookiah MRK, Minetto MA. Advances in quantitative muscle ultrasonography using texture analysis of ultrasound images. Ultrasound in Medicine & Biology. 2015; 41(9):2520–2532. https://doi.org/10.1016/j.ultrasmedbio.2015.04.021
52. 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; 283(2):492–498. https://doi.org/10.1148/radiol.2016160826 PMID: 28156201
53. Scholten RR, Pillen S, Verrips A, Zwarts MJ. Quantitative ultrasonography of skeletal muscles in children: Normal values. Muscle & Nerve. 2003; 27(6):693–698. https://doi.org/10.1002/mus.10384
54. Arts IMP, Pillen S, Schelhaas HJ, Overeem S, Zwarts MJ. Normal values for quantitative muscle ultrasonography in adults. Muscle & Nerve. 2010; 41(1):32–41. https://doi.org/10.1002/mus.21458
55. Srivastava T, Darras BT, Wu JS, Rutkove SB. Machine learning algorithms to classify spinal muscular atrophy subtypes. Neurology. 2012; 79(4):358–64. https://doi.org/10.1212/WNL.0b013e3182604395 PMID: 22786588
56. Pinal-Fernandez I, Casal-Dominguez M, Carrino JA, Lahouti AH, Basharat P, Albayda J, et al. Thigh muscle MRI in immune-mediated necrotising myopathy: extensive oedema, early muscle damage and role of anti-SRP autoantibodies as a marker of severity. Annals of the Rheumatic Diseases. 2017; 76(4):681–687. https://doi.org/10.1136/annrheumdis-2016-210198 PMID: 27651398