DOI QR코드

DOI QR Code

Basics of Deep Learning: A Radiologist's Guide to Understanding Published Radiology Articles on Deep Learning

  • Synho Do (Department of Radiology, Massachusetts General Hospital) ;
  • Kyoung Doo Song (Department of Radiology, Massachusetts General Hospital) ;
  • Joo Won Chung (Department of Radiology, Massachusetts General Hospital)
  • Received : 2019.05.04
  • Accepted : 2019.08.22
  • Published : 2020.01.01

Abstract

Artificial intelligence has been applied to many industries, including medicine. Among the various techniques in artificial intelligence, deep learning has attained the highest popularity in medical imaging in recent years. Many articles on deep learning have been published in radiologic journals. However, radiologists may have difficulty in understanding and interpreting these studies because the study methods of deep learning differ from those of traditional radiology. This review article aims to explain the concepts and terms that are frequently used in deep learning radiology articles, facilitating general radiologists' understanding.

Keywords

References

  1. Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, et al. Deep learning: a primer for radiologists. Radiographics 2017;37:2113-2131 https://doi.org/10.1148/rg.2017170077
  2. 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 https://doi.org/10.1016/j.media.2017.07.005
  3. Dreyer KJ, Geis JR. When machines think: radiology's next frontier. Radiology 2017;285:713-718 https://doi.org/10.1148/radiol.2017171183
  4. Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, Klang E. Convolutional neural networks for radiologic images: a radiologist's guide. Radiology 2019;290:590-606 https://doi.org/10.1148/radiol.2018180547
  5. Cardoso JR, Pereira LM, Iversen MD, Ramos AL. What is gold standard and what is ground truth? Dental Press J Orthod 2014;19:27-30 https://doi.org/10.1590/2176-9451.19.5.027-030.ebo
  6. Zhong Z, Zheng L, Kang G, Li S, Yang Y. Random erasing data augmentation. eprint arXiv, 2017. Available at: https://ui.adsabs.harvard.edu/abs/2017arXiv170804896Z. Accessed April 1, 2019
  7. TIOBE index for April 2019. TIOBE Web site. https://www.tiobe.com/tiobe-index/. Accessed April 30, 2019
  8. Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, et al. Caffe: convolutional architecture for fast feature embedding. eprint arXiv, 2014. Available at: https://ui.adsabs.harvard.edu/abs/2014arXiv1408.5093J. Accessed April 1, 2019
  9. Bastien F, Lamblin P, Pascanu R, Bergstra J, Goodfellow I, Bergeron A, et al. Theano: new features and speed improvements. eprint arXiv, 2012. Available at: https://ui.adsabs.harvard.edu/abs/2012arXiv1211.5590B. Accessed April 1, 2019
  10. Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. TensorFlow: a system for large-scale machine learning. eprint arXiv, 2016. Available at: https://ui.adsabs.harvard.edu/abs/2016arXiv160508695A. Accessed April 1, 2019
  11. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol 2017;18:570-584 https://doi.org/10.3348/kjr.2017.18.4.570
  12. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 2012;25:1090-1098
  13. Lee C, Kim Y, Kim YS, Jang J. Automatic disease annotation from radiology reports using artificial intelligence implemented by a recurrent neural network. AJR Am J Roentgenol 2019;212:734-740 https://doi.org/10.2214/AJR.18.19869
  14. Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. eprint arXiv, 2013. Available at: https://ui.adsabs.harvard.edu/abs/2013arXiv1311.2524G. Accessed April 1, 2019
  15. Kazuhiro K, Werner RA, Toriumi F, Javadi MS, Pomper MG, Solnes LB, et al. Generative adversarial networks for the creation of realistic artificial brain magnetic resonance images. Tomography 2018;4:159-163 https://doi.org/10.18383/j.tom.2018.00042
  16. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. eprint arXiv, 2014. Available at: https://ui.adsabs.harvard.edu/abs/2014arXiv1406.2661G. Accessed April 1, 2019
  17. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. eprint arXiv, 2015. Available at: https://ui.adsabs.harvard.edu/ abs/2015arXiv150504597R. Accessed April 1, 2019
  18. Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. eprint arXiv, 2016. Available at: https://ui.adsabs.harvard.edu/abs/2016arXiv160806993H. Accessed April 1, 2019
  19. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. eprint arXiv, 2014. Available at: https://ui.adsabs.harvard.edu/abs/2014arXiv1409.1556S. Accessed April 1, 2019
  20. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. eprint arXiv, 2015. Available at: https://ui.adsabs.harvard.edu/abs/2015arXiv151203385H. Accessed April 1, 2019
  21. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. eprint arXiv, 2014. Available at: https://ui.adsabs.harvard.edu/abs/2014arXiv1409.4842S. Accessed April 1, 2019
  22. He K, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. eprint arXiv, 2017. Available at: https://ui.adsabs.harvard.edu/abs/2017arXiv170306870H. Accessed April 1, 2019
  23. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998;86:2278-2324
  24. Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. eprint arXiv, 2013. Available at: https://ui.adsabs.harvard.edu/abs/2013arXiv1311.2901Z. Accessed April 1, 2019
  25. Qian N. On the momentum term in gradient descent learning algorithms. Neural Netw 1999;12:145-151 https://doi.org/10.1016/S0893-6080(98)00116-6
  26. Nesterov YE. A method for solving the convex programming problem with convergence rate O(1/k2). Dokl Akad Nauk SSSR 1983;269:543-547
  27. Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 2011;12:2121-2159
  28. Zeiler MD. ADADELTA: an adaptive learning rate method. eprint arXiv, 2012. Available at: https://ui.adsabs.harvard. edu/abs/2012arXiv1212.5701Z. Accessed April 1, 2019
  29. Kingma DP, Ba J. Adam: a method for stochastic optimization. eprint arXiv, 2014. Available at: https://ui.adsabs.harvard. edu/abs/2014arXiv1412.6980K. Accessed April 1, 2019