Computer-aided diagnosis in rheumatic diseases using ultrasound: an overview

  • Josefina Gutiérrez-MartínezEmail author
  • Carlos Pineda
  • Hugo Sandoval
  • Araceli Bernal-González
Review Article
Part of the following topical collections:
  1. Artificial Intelligence and Machine Learning for Clinicians


Clinical evaluation of rheumatic and musculoskeletal diseases through images is a challenge for the beginner rheumatologist since image diagnosis is an expert task with a long learning curve. The aim of this work was to present a narrative review on the main ultrasound computer-aided diagnosis systems that may help clinicians thanks to the progress made in the application of artificial intelligence techniques. We performed a literature review searching for original articles in seven repositories, from 1970 to 2019, and identified 11 main methods currently used in ultrasound computer-aided diagnosis systems. Also, we found that rheumatoid arthritis, osteoarthritis, systemic lupus erythematosus, and idiopathic inflammatory myopathies are the four musculoskeletal and rheumatic diseases most studied that use these innovative systems, with an overall accuracy of > 75%.


Artificial intelligence Computer-assisted diagnosis Expert systems Machine learning Rheumatology 


Compliance with ethical standards




  1. 1.
    Tins BJ, Butler R (2013) Imaging in rheumatology: reconciling radiology and rheumatology. Insights Imaging 4(6):799–810. CrossRefPubMedPubMedCentralGoogle Scholar
  2. 2.
    Van Ginneken B, Schaefer-Prokop CM, Prokop M (2011) Computer-aided diagnosis: how to move from the laboratory to the clinic. Radiology 261(3):719–732. CrossRefPubMedGoogle Scholar
  3. 3.
    Hall M, Doherty S, Courtney P, Latief K, Zhang W, Doherty M (2014) Synovial pathology detected on ultrasound correlates with the severity of radiographic knee osteoarthritis more than with symptoms. Osteoarthr Cartil 22(10):1627–1633. CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Giger ML (2002) Computer-aided diagnosis in radiology. Acad Radiol 9(1):1–3CrossRefGoogle Scholar
  5. 5.
    Doi K (2007) Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31(4–5):198–211. CrossRefPubMedPubMedCentralGoogle Scholar
  6. 6.
    Montejo LD, Jia J, Kim HK, Netz UJ, Blaschke S, Muller GA, Hielscher AH (2013) Computer-aided diagnosis of rheumatoid arthritis with optical tomography, part 1: feature extraction. J Biomed Opt 18(7):076001. CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Do Prado AD, Staub HL, Bisi MC, da Silveira IG, Mendonca JA, Polido-Pereira J, Fonseca JE (2018) Ultrasound and its clinical use in rheumatoid arthritis: where do we stand? Adv Rheumatol 58(1):19–10. CrossRefPubMedGoogle Scholar
  8. 8.
    Ostendorf B, Mattes-Gyorgy K, Reichelt DC, Blondin D, Wirrwar A, Lanzman R, Muller HW, Schneider M, Modder U, Scherer A (2010) Early detection of bony alterations in rheumatoid and erosive arthritis of finger joints with high-resolution single photon emission computed tomography, and differentiation between them. Skelet Radiol 39(1):55–61. CrossRefGoogle Scholar
  9. 9.
    Giger ML, Suzuki K (2008) 16. Computer-aided diagnosis. In: Feng DD (ed) Biomedical information technology. Academic Press, Burlington, pp 359–374. CrossRefGoogle Scholar
  10. 10.
    Scire CA, Meenagh G, Filippucci E, Riente L, Delle Sedie A, Salaffi F, Iagnocco A, Bombardieri S, Grassi W, Valesini G, Montecucco C (2009) Ultrasound imaging for the rheumatologist. XXI. Role of ultrasound imaging in early arthritis. Clin Exp Rheumatol 27(3):391–394PubMedGoogle Scholar
  11. 11.
    Chen HH (2017) The third eye of the rheumatologist: applications of musculoskeletal ultrasound in rheumatic diseases. J Med Ultrasound 25(1):4–8. CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    Forien M, Ottaviani S (2017) Ultrasound and follow-up of rheumatoid arthritis. Joint Bone Spine 84(5):531–536. CrossRefPubMedGoogle Scholar
  13. 13.
    Sudol-Szopinska I, Schueller-Weidekamm C, Plagou A, Teh J (2017) Ultrasound in arthritis. Radiol Clin N Am 55(5):985–996. CrossRefPubMedGoogle Scholar
  14. 14.
    Grassi W, Salaffi F, Filippucci E (2005) Ultrasound in rheumatology. Best Pract Res Clin Rheumatol 19(3):467–485. CrossRefPubMedGoogle Scholar
  15. 15.
    Faust O, Acharya UR, Meiburger KM, Molinari F, Koh JEW, Yeong CH, Kongmebhol P, Ng KH (2018) Comparative assessment of texture features for the identification of cancer in ultrasound images: a review. Biocybernetics Biomed Eng 38(2):275–296. CrossRefGoogle Scholar
  16. 16.
    Amin MN, Rushdi MA, Marzaban RN, Yosry A, Kim K, Mahmoud AM (2019) Wavelet-based computationally-efficient computer-aided characterization of liver steatosis using conventional B-mode ultrasound images. Biom Signal Process Control 52:84–96. CrossRefGoogle Scholar
  17. 17.
    Rodriguez-Cristerna A, Gomez-Flores W, de Albuquerque Pereira WC (2018) A computer-aided diagnosis system for breast ultrasound based on weighted BI-RADS classes. Comput Methods Prog Biomed 153:33–40. CrossRefGoogle Scholar
  18. 18.
    Chang RF, Lee CC, Lo CM (2016) Computer-aided diagnosis of different rotator cuff lesions using shoulder musculoskeletal ultrasound. Ultrasound Med Biol 42(9):2315–2322. CrossRefPubMedGoogle Scholar
  19. 19.
    Pfeil A, Renz DM, Hansch A, Kainberger F, Lehmann G, Malich A, Wolf G, Bottcher J (2013) The usefulness of computer-aided joint space analysis in the assessment of rheumatoid arthritis. Joint Bone Spine 80(4):380–385. CrossRefPubMedGoogle Scholar
  20. 20.
    Zeng X, Wen L, Liu B, Qi X (2019) Deep learning for ultrasound image caption generation based on object detection. Neurocomputing:1–28.
  21. 21.
    Hemalatha RJ, Vijaybaskar V, Thamizhvani TR (2019) Automatic localization of anatomical regions in medical ultrasound images of rheumatoid arthritis using deep learning. Proc Inst Mech Eng H 233(6):657–667. CrossRefPubMedGoogle Scholar
  22. 22.
    Liu S, Wang Y, Yang X, Lei B, Liu L, Li SX, Ni D, Wang T (2019) Deep learning in medical ultrasound analysis: a review. Engineering 5(2):261–275. CrossRefGoogle Scholar
  23. 23.
    Gasparyan AY, Ayvazyan L, Blackmore H, Kitas GD (2011) Writing a narrative biomedical review: considerations for authors, peer reviewers, and editors. Rheumatol Int 31(11):1409–1417. CrossRefPubMedGoogle Scholar
  24. 24.
    Deserno T (2009) “Medical image processing”. Optipedia. SPIE Press, BellinghamGoogle Scholar
  25. 25.
    Veronese E, Stramare R, Campion A, Raffeiner B, Beltrame V, Scagliori E, Coran A, Ciprian L, Fiocco U, Grisan E (2012) Improved detection of synovial boundaries in ultrasound examination by using a cascade of active-contours. Med Eng Phys 35(2):188–194. CrossRefPubMedGoogle Scholar
  26. 26.
    Huang Q, Zhang F, Li X (2018) Machine learning in ultrasound computer-aided diagnostic systems: a survey. Biomed Res Int 2018:5137904. CrossRefPubMedPubMedCentralGoogle Scholar
  27. 27.
    Mula J, Lee JD, Liu F, Yang L, Peterson CA (2013) Automated image analysis of skeletal muscle fiber cross-sectional area. J Appl Physiol 114(1):148–155. CrossRefPubMedGoogle Scholar
  28. 28.
    Pal KK, Sudeep KS (2016) Preprocessing for image classification by convolutional neural networks. Recent Trends in Electronics, Information & Communication Technology (RTEICT). IEEE International Conference on: 1778–1781, BengaluruGoogle Scholar
  29. 29.
    Wittek P (2014) 2. Machine learning. In: Wittek P (ed) Quantum machine learning. Academic Press, Boston, pp 11–24. CrossRefGoogle Scholar
  30. 30.
    Rawat W, Wang Z (2017) Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput 29(9):2352–2449. CrossRefPubMedGoogle Scholar
  31. 31.
    Fries JF (1970) Experience counting in sequential computer diagnosis. JAMA Intern Med 126(4):647–651. CrossRefGoogle Scholar
  32. 32.
    Infantino M, Manfredi M, Soda P, Merone M, Afeltra A, Rigon A (2018) ANA testing in ‘real life’. Ann Rheum Dis.
  33. 33.
    Murakami S, Hatano K, Tan J, Kim H, Aoki T (2018) Automatic identification of bone erosions in rheumatoid arthritis from hand radiographs based on deep convolutional neural network. Multimed Tools Appl 77(9):10921–10937. CrossRefGoogle Scholar
  34. 34.
    Ashinsky BG, Bouhrara M, Coletta CE, Lehallier B, Urish KL, Lin PC, Goldberg IG, Spencer RG (2017) Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative. J Orthop Res 35(10):2243–2250. CrossRefPubMedPubMedCentralGoogle Scholar
  35. 35.
    Üreten K, Erbay H, Maras HH (2019) Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network. Clin Rheumatol:1–6.
  36. 36.
    Snekhalatha U, Rajalakshmi T, Gopikrishnan M, Gupta N (2017) Computer-based automated analysis of X-ray and thermal imaging of knee region in evaluation of rheumatoid arthritis. Proc Inst Mech Eng H J Eng Med 231(12):1178–1187. CrossRefGoogle Scholar
  37. 37.
    Horn W (1983) ESDAT - an expert system for primary medical care. In: Neumann B (ed) GWAI-83. Informatik-Fachberichte, vol 76. Springer, BerlinGoogle Scholar
  38. 38.
    Horn W, Horn W (1989) MESICAR-A medical expert system integrating causal and associative reasoning. Appl Artif Intell 3(2–3):305–336. CrossRefGoogle Scholar
  39. 39.
    Horn W (1989) Diagnostic decision support based on generic disease descriptions and detailed anatomical knowledge. In: Hunter J, Cookson J, Wyatt J (eds) AIME 89. Lecture notes in medical informatics, vol 38. Springer, BerlinGoogle Scholar
  40. 40.
    Horn W (1991) Utilizing detailed anatomical knowledge for hypothesis formation and hypothesis testing in rheumatological decision support. Artif Intell Med 3(1):21–39. CrossRefGoogle Scholar
  41. 41.
    Chokkalingam S, Komathy K (2014) Intelligent assistive methods for diagnosis of rheumatoid arthritis using histogram smoothing and feature extraction of bone images. World Acad Sci Eng Technol Int J Comput Inf Eng 8(5):905–914Google Scholar
  42. 42.
    Helwan A, Tantua D, Adeola E (2016) IKRAI: intelligent knee rheumatoid arthritis identification. Int J Intell Syst Appl 8(1):18–24. CrossRefGoogle Scholar
  43. 43.
    Subramoniam M, Barani S, Rajini V (2015) A non-invasive computer aided diagnosis of osteoarthritis from digital x-ray images. Biomed Res 26(4):721–729Google Scholar
  44. 44.
    Stachowiak G, Wolski M, Woloszynski T, Podsiadlo P (2016) Detection and prediction of osteoarthritis in knee and hand joints based on the X-ray image analysis. Biosurf Biotribol 4(2):162–172CrossRefGoogle Scholar
  45. 45.
    Shamir L, Ling SM, Scott WW Jr, Bos A, Orlov N, Macura TJ, Eckley DM, Ferrucci L, Goldberg IG (2009) Knee x-ray image analysis method for automated detection of osteoarthritis. IEEE Trans Biomed Eng 56(2):407–415. CrossRefPubMedPubMedCentralGoogle Scholar
  46. 46.
    Belmonte-Serrano M, Sierra C, de Mantaras RL (1994) RENOIR: an expert system using fuzzy logic for rheumatology diagnosis. Int J Intell Syst 9(11):985–1000. CrossRefGoogle Scholar
  47. 47.
    Hernandez C, Sancho JJ, Belmonte MA, Sierra C, Sanz F (1994) Validation of the medical expert system RENOIR. Comput Biomed Res 27(6):456–471. CrossRefPubMedGoogle Scholar
  48. 48.
    Adlassnig K-P, Leitich H, Kolarz G (1993) On the applicability of diagnostic criteria for the diagnosis of rheumatoid arthritis in an expert system. Expert Syst Appl 6(4):441–448. CrossRefGoogle Scholar
  49. 49.
    Singh S, Kumar A, Panneerselvam K, Vennila JJ (2012) Diagnosis of arthritis through fuzzy inference system. J Med Syst 36(3):1459–1468. CrossRefPubMedGoogle Scholar
  50. 50.
    Yoo J, Lim MK, Ihm C, Choi ES, Kang MS (2017) A study on prediction of rheumatoid arthritis using machine learning. Int J Appl Eng Res 12(20):9858–9862Google Scholar
  51. 51.
    Parascandolo P, Cesario L, Vosilla L, Viano G (2014) Computer aided diagnosis: state-of-the-art and application to musculoskeletal diseases. In: Magnenat-Thalmann N, Ratib O, Choi H (eds) 3D multiscale physiological human. Springer, London. CrossRefGoogle Scholar
  52. 52.
    Kingsland LC 3rd, Lindberg DA, Sharp GC (1986) Anatomy of a knowledge-based consultant system: AI/RHEUM. MD Comput 3(5):18–26PubMedGoogle Scholar
  53. 53.
    Moens HJ, van der Korst JK (1992) Development and validation of a computer program using Bayes’s theorem to support diagnosis of rheumatic disorders. Ann Rheum Dis 51(2):266–271. CrossRefPubMedPubMedCentralGoogle Scholar
  54. 54.
    Athreya BH, Cheh ML, Kingsland LC 3rd (1998) Computer-assisted diagnosis of pediatric rheumatic diseases. Pediatrics 102(4):E48. CrossRefPubMedGoogle Scholar
  55. 55.
    McCrea JD, McCredie MR, McSherry DM, Brooks PM (1989) A controlled evaluation of diagnostic criteria in the development of a rheumatology expert system. Br J Rheumatol 28(1):13–17CrossRefGoogle Scholar
  56. 56.
    Radlak K, Frackiewicz M, Palus H, Smolka B (2018) Finger joint synovitis detection in ultrasound images. Bull Pol Acad Sci Tech Sci 66(2):235–245. CrossRefGoogle Scholar
  57. 57.
    Schueller-Weidekamm C (2009) Quantification of synovial and erosive changes in rheumatoid arthritis with ultrasound- revisited. Eur J Radiol 71(2):225–231. CrossRefPubMedGoogle Scholar
  58. 58.
    Özkan AO (2017) Spectral analysis of the left and right hand radial artery Doppler signals using the Welch method to diagnose rheumatoid arthritis disease. J Multidiscip Eng Sci Technol 4(8):7842–7848Google Scholar
  59. 59.
    Burlina P, Billings S, Joshi N, Albayda J (2017) Automated diagnosis of myositis from muscle ultrasound: exploring the use of machine learning and deep learning methods. PLoS One 12(8):e0184059. CrossRefPubMedPubMedCentralGoogle Scholar
  60. 60.
    Mielnik P, Fojcik M, Segen J, Kulbacki M (2018) A novel method of synovitis stratification in ultrasound using machine learning algorithms: results from clinical validation of the MEDUSA Project. Ultrasound Med Biol 44(2):489–494. CrossRefPubMedGoogle Scholar
  61. 61.
    Ceccarelli F, Sciandrone M, Perricone C, Galvan G, Cipriano E, Galligari A, Levato T, Colasanti T, Massaro L, Natalucci F, Spinelli FR, Alessandri C, Valesini G, Conti F (2018) Biomarkers of erosive arthritis in systemic lupus erythematosus: application of machine learning models. PLoS One 13(12):e0207926. CrossRefPubMedPubMedCentralGoogle Scholar
  62. 62.
    Tang J, Jin Z, Zhou X, Chu H, Yuan J, Wu M, Cheng Q, Wang X (2018) Grading of rheumatoid arthritis on ultrasound images with deep convolutional neural network. IEEE Int Ultrason Symp 2018:1–4. CrossRefGoogle Scholar
  63. 63.
    Tang J, Jin Z, Zhou X, Zhang W, Wu M, Shen Q, Cheng Q, Wang X, Yuan J (2019) Enhancing convolutional neural network scheme for rheumatoid arthritis grading with limited clinical data. Chin Phys B 28(3):038701. CrossRefGoogle Scholar
  64. 64.
    Tiulpin A, Saarakkala S, Mathiessen A, Hammer HB, Furnes O, Fenstad AM, Nordsletten L, Englund M, Magnusson K (2019) Predicting total knee replacement from ultrasound using machine learning. Osteoarthr Cartil 27:S360–S361. CrossRefGoogle Scholar
  65. 65.
    Andersen JKH, Pedersen JS, Laursen MS, Holtz K, Grauslund J, Savarimuthu TR, Just SA (2019) Neural networks for automatic scoring of arthritis disease activity on ultrasound images. RMD Open 5(1):e000891. CrossRefPubMedPubMedCentralGoogle Scholar
  66. 66.
    Burmester GR (2018) Rheumatology 4.0: big data, wearables and diagnosis by computer. Ann Rheum Dis 77(7):963–965. CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© International League of Associations for Rheumatology (ILAR) 2019

Authors and Affiliations

  1. 1.Division of Medical Engineering ResearchInstituto Nacional de Rehabilitación Luis Guillermo Ibarra IbarraMexico CityMexico
  2. 2.Division of Musculoskeletal and Rheumatic DisordersInstituto Nacional de Rehabilitación Luis Guillermo Ibarra IbarraMexico CityMexico
  3. 3.Sociomedical Research UnitInstituto Nacional de Rehabilitación Luis Guillermo Ibarra IbarraMexico CityMexico

Personalised recommendations