Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment

  • Byoung-Dai Lee (Division of Computer Science and Engineering, Kyonggi University) ;
  • Mu Sook Lee (Department of Radiology, Keimyung University Dongsan Hospital)
  • Received : 2020.07.22
  • Accepted : 2020.10.19
  • Published : 2021.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Bone age assessments are a complicated and lengthy process, which are prone to inter- and intra-observer variabilities. Despite the great demand for fully automated systems, developing an accurate and robust bone age assessment solution has remained challenging. The rapidly evolving deep learning technology has shown promising results in automated bone age assessment. In this review article, we will provide information regarding the history of automated bone age assessments, discuss the current status, and present a literature review, as well as the future directions of artificial intelligence-based bone age assessments.

Keywords

References

  1. Sarmah SS. Concept of artificial intelligence, its impact and emerging trends. Int Res J Eng Technol 2019;6:2164-2168
  2. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun Acm 2017;60:84-90
  3. Yuksel K, Skarbek W. Convolutional and recurrent neural networks for face image analysis. Found Comput Decis Sci 2019;44:331-347
  4. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017;42:60-88
  5. Kushibar K, Valverde S, Gonzalez-Villa S, Bernal J, Cabezas M, Oliver A, et al. Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features. Med Image Anal 2018;48:177-186
  6. Alvarez JD, Matias-Guiu JA, Cabrera-Martin MN, Risco-Martin JL, Ayala JL. An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders. BMC Bioinformatics 2019;20:491
  7. Hwang EJ, Park CM. Clinical implementation of deep learning in thoracic radiology: potential applications and challenges. Korean J Radiol 2020;21:511-525
  8. Wang K, Mamidipalli A, Retson T, Bahrami N, Hasenstab K, Blansit K, et al. Automated CT and MRI liver segmentation and biometry using a generalized convolutional neural network. Radiol Artif Intell 2019;1:180022
  9. Kiani A, Uyumazturk B, Rajpurkar P, Wang A, Gao R, Jones E, et al. Impact of a deep learning assistant on the histopathologic classification of liver cancer. NPJ Digit Med 2020;3:23
  10. McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, et al. International evaluation of an AI system for breast cancer screening. Nature 2020;577:89-94
  11. Son SJ, Song Y, Kim N, Do Y, Kwak N, Lee MS, et al. TW3-based fully automated bone age assessment system using deep neural networks. IEEE Access 2019;7:33346-33358
  12. Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R. Deep learning for automated skeletal bone age assessment in X-ray images. Med Image Anal 2017;36:41-51
  13. Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas BA, Alkasab TK, et al. Fully automated deep learning system for bone age assessment. J Digit Imaging 2017;30:427-441
  14. Tajmir SH, Lee H, Shailam R, Gale HI, Nguyen JC, Westra SJ, et al. Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability. Skeletal Radiol 2019;48:275-283
  15. Kim JR, Shim WH, Yoon HM, Hong SH, Lee JS, Cho YA, et al. Computerized bone age estimation using deep learning based program: evaluation of the accuracy and efficiency. AJR Am J Roentgenol 2017;209:1374-1380
  16. Mansourvar M, Ismail MA, Herawan T, Raj RG, Kareem SA, Nasaruddin FH. Automated bone age assessment: motivation, taxonomies, and challenges. Comput Math Methods Med 2013;2013:391626
  17. Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist, 1st ed. Stanford: Stanford University Press, 1959
  18. Gilsanz V, Ratib O. A digital atlas of skeletal maturity. Berlin: Springer, 2011
  19. Tanner JM, Healy MJ, Goldstein H, Cameron N. Assessment of skeletal maturity and prediction of adult height: TW3 method. London: W.B Saunders Company, 2001
  20. Khan KM, Miller BS, Hoggard E, Somani A, Sarafoglou K. Application of ultrasound for bone age estimation in clinical practice. J Pediatr 2009;154:243-247
  21. Hojreh A, Gamper J, Schmook MT, Weber M, Prayer D, Herold CJ, et al. Hand MRI and the Greulich-Pyle atlas in skeletal age estimation in adolescents. Skeletal Radiol 2018;47:963-971
  22. Mettler FA Jr, Huda W, Yoshizumi TT, Mahesh M. Effective doses in radiology and diagnostic nuclear medicine: a catalog. Radiology 2008;248:254-263
  23. Martin DD, Wit JM, Hochberg Z, Savendahl L, van Rijn RR, Fricke O, et al. The use of bone age in clinical practice-part 1. Horm Res Paediatr 2011;76:1-9
  24. van Rijn RR, Thodberg HH. Bone age assessment: automated techniques coming of age? Acta Radiol 2013;54:1024-1029
  25. Roche AF, Rohmann CG, French NY, Davila GH. Effect of training on replicability of assessments of skeletal maturity (Greulich-Pyle). Am J Roentgenol Radium Ther Nucl Med 1970;108:511-515
  26. Michael DJ, Nelson AC. HANDX: a model-based system for automatic segmentation of bones from digital hand radiographs. IEEE Trans Med Imaging 1989;8:64-69
  27. Pietka E, McNitt-Gray MF, Kuo ML, Huang HK. Computer-assisted phalangeal analysis in skeletal age assessment. IEEE Trans Med Imaging 1991;10:616-620
  28. Tanner JM, Oshman D, Lindgren G, Grunbaum JA, Elsouki R, Labarthe D. Reliability and validity of computer-assisted estimates of Tanner-Whitehouse skeletal maturity (CASAS): comparison with the manual method. Horm Res 1994;42:288-294
  29. Yoo JW, Lee JM, Kim WY. A bone age assessment method based on normalized shape model. J Korea Multimed Soc 2009;12:383-396
  30. Oakden-Rayner L. The rebirth of CAD: how is modern AI different from the CAD we know? Radiology: Artificial Intelligence 2019;1:e180089
  31. Fujita H. AI-based computer-aided diagnosis (AI-CAD): the latest review to read first. Radiol Phys Technol 2020;13:6-19
  32. Hu TH, Wan L, Liu TA, Wang MW, Chen T, Wang YH. Advantages and application prospects of deep learning in image recognition and bone age assessment. Fa Yi Xue Za Zhi 2017;33:629-634
  33. Dallora AL, Anderberg P, Kvist O, Mendes E, Diaz Ruiz S, Sanmartin Berglund J. Bone age assessment with various machine learning techniques: a systematic literature review and meta-analysis. PLoS One 2019;14:e0220242
  34. Cunha P, Moura DC, Guevara Lopez MA, Guerra C, Pinto D, Ramos I. Impact of ensemble learning in the assessment of skeletal maturity. J Med Syst 2014;38:87
  35. O'Connor JE, Coyle J, Bogue C, Spence LD, Last J. Age prediction formulae from radiographic assessment of skeletal maturation at the knee in an Irish population. Forensic Sci Int 2014;234:188.e1-8
  36. Tang FH, Chan JLC, Chan BKL. Accurate age determination for adolescents using magnetic resonance imaging of the hand and wrist with an artificial neural network-based approach. J Digit Imaging 2019;32:283-289
  37. Kashif M, Deserno TM, Haak D, Jonas S. Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment. Comput Biol Med 2016;68:67-75
  38. Hillewig E, Degroote J, Van der Paelt T, Visscher A, Vandemaele P, Lutin B, et al. Magnetic resonance imaging of the sternal extremity of the clavicle in forensic age estimation: towards more sound age estimates. Int J Legal Med 2013;127:677-689
  39. Urschler M, Grassegger S, Stern D. What automated age estimation of hand and wrist MRI data tells us about skeletal maturation in male adolescents. Ann Hum Biol 2015;42:358-367
  40. Harmsen M, Fischer B, Schramm H, Seidl T, Deserno TM. Support vector machine classification based on correlation prototypes applied to bone age assessment. IEEE J Biomed Health Inform 2013;17:190-197
  41. Mansourvar M, Shamshirband S, Raj RG, Gunalan R, Mazinani I. An automated system for skeletal maturity assessment by extreme learning machines. PLoS One 2015;10:e0138493
  42. Thodberg HH, Kreiborg S, Juul A, Pedersen KD. The BoneXpert method for automated determination of skeletal maturity. IEEE Trans Med Imaging 2009;28:52-66
  43. Booz C, Yel I, Wichmann JL, Boettger S, Al Kamali A, Albrecht MH, et al. Artificial intelligence in bone age assessment: accuracy and efficiency of a novel fully automated algorithm compared to the Greulich-Pyle method. Eur Radiol Exp 2020;4:6
  44. Bui TD, Lee JJ, Shin J. Incorporated region detection and classification using deep convolutional networks for bone age assessment. Artif Intell Med 2019;97:1-8
  45. Ontell FK, Ivanovic M, Ablin DS, Barlow TW. Bone age in children of diverse ethnicity. AJR Am J Roentgenol 1996;167:1395-1398
  46. Thodberg HH, Savendahl L. Validation and reference values of automated bone age determination for four ethnicities. Acad Radiol 2010;17:1425-1432
  47. Margalit A, Cottrill E, Nhan D, Yu L, Tang X, Fritz J, et al. The spatial order of physeal maturation in the normal human knee using magnetic resonance imaging. J Pediatr Orthop 2019;39:e318-e322
  48. Fan F, Zhang K, Peng Z, Cui JH, Hu N, Deng ZH. Forensic age estimation of living persons from the knee: comparison of MRI with radiographs. Forensic Sci Int 2016;268:145-150
  49. Stern D, Payer C, Urschler M. Automated age estimation from MRI volumes of the hand. Med Image Anal 2019;58:101538
  50. Dallora AL, Berglund JS, Brogren M, Kvist O, Diaz Ruiz S, Dubbel A, et al. Age assessment of youth and young adults using magnetic resonance imaging of the knee: a deep learning approach. JMIR Med Inform 2019;7:e16291