PDF herunterladen
Semin Musculoskelet Radiol 2020; 24(01): 003-011
DOI: 10.1055/s-0039-3401041
Review Article
Thieme Medical Publishers 333 Seventh Avenue, New York, NY 10001, USA.

Artificial Intelligence Explained for Nonexperts

Narges Razavian
1   Department of Radiology and Population Health, NYU Langone Health and NYU Center for Data Science, New York, New York
,
Florian Knoll
2   Department of Radiology, NYU Langone Health, New York, New York
,
Krzysztof J. Geras
3   Department of Radiology, NYU Langone Health and NYU Center for Data Science, New York, New York
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
28. Januar 2020 (online)

Auch verfügbar auf
    Lizenzen und Reprints

Abstract

Artificial intelligence (AI) has made stunning progress in the last decade, made possible largely due to the advances in training deep neural networks with large data sets. Many of these solutions, initially developed for natural images, speech, or text, are now becoming successful in medical imaging. In this article we briefly summarize in an accessible way the current state of the field of AI. Furthermore, we highlight the most promising approaches and describe the current challenges that will need to be solved to enable broad deployment of AI in clinical practice.

Keywords

deep learning - artificial intelligence - review - medical imaging

Financial Disclosure

We acknowledge support from the National Institutes of Health under grants R01-EB024532, P41-EB017183, and R21 EB027241.


 

  • References

  • 1 Bishop CM. Pattern Recognition and Machine Learning. New York, NY: Springer; 2006
    Google Scholar
  • 2 Hastie T, Tibshirani R, Friedman J, Franklin J. The elements of statistical learning: data mining, inference and prediction. Math Intell 2005; 27 (02) 83-85
    PubMedGoogle Scholar
  • 3 Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge, MA: MIT Press; 2016
    Google Scholar
  • 4 Zhang R, Isola P, Efros AA. Colorful image colorization. Computer Vision – ECCV 2016. Available at: https://arxiv.org/abs/1603.08511 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 5 Noroozi M, Favaro P. Unsupervised learning of visual representations by solving jigsaw puzzles. Computer Vision – ECCV 2016. Available at: https://arxiv.org/abs/1603.09246 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 6 Agrawal P, Carreira J, Malik J. Learning to see by moving. Proceedings of the IEEE International Conference on Computer Vision. Available at: https://arxiv.org/abs/1505.01596 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 7 Devlin J, Chang M-W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv [csCL]. October 2018. Available at: http://arxiv.org/abs/1810.04805 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 8 Lample G, Conneau A. Cross-lingual language model pretraining. arXiv [csCL]. January 2019. Available at: http://arxiv.org/abs/1901.07291 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 9 Wang A, Singh A, Michael J, Hill F, Levy O, Bowman S. GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv [csCL]. April 2018. Available at: http://arxiv.org/abs/1804.07461 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 10 Silver D, Schrittwieser J, Simonyan K. , et al. Mastering the game of Go without human knowledge. Nature 2017; 550 (7676): 354-359
    CrossrefPubMedGoogle Scholar
  • 11 Brown N, Sandholm T. Superhuman AI for multiplayer poker. Science 2019; 365 (6456): 885-890
    CrossrefPubMedGoogle Scholar
  • 12 Mnih V, Kavukcuoglu K, Silver D. , et al. Playing Atari with deep reinforcement learning. arXiv [csLG]. December 2013. Available at: http://arxiv.org/abs/1312.5602 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 13 Arulkumaran K, Cully A, Togelius J. AlphaStar: an evolutionary computation perspective. arXiv [csNE]. February 2019. Available at: http://arxiv.org/abs/1902.01724 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 14 Zhu B, Liu J, Koonjoo N, Rosen B, Rosen MS. AUTOmated pulse SEQuence generation (AUTOSEQ) and neural network decoding for fast quantitative MR parameter measurement using continuous and simultaneous RF transmit and receive. ISMRM Annual Meeting & Exhibition. Vol 1090. 2019. Available at: http://www.enc-conference.org/portals/0/Abstracts2019/ENC20198520.4608VER.2.pdf . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 15 Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Available at: http://www.image-net.org/papers/imagenet_cvpr09.pdf . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 16 Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ. , eds. Advances in Neural Information Processing Systems 25. Red Hook, NY: Curran Associates; 2012: 1097-1105
    Google Scholar
  • 17 Raina R, Madhavan A, Ng AY. Large-scale deep unsupervised learning using graphics processors. In: Proceedings of the 26th Annual International Conference on Machine Learning. ICML '09. New York, NY: ACM; 2009: 873-880
    PubMedGoogle Scholar
  • 18 Jia Y, Shelhamer E, Donahue J. , et al. Caffe: Convolutional Architecture for Fast Feature Embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia. MM '14. New York, NY: ACM; 2014: 675-678
    PubMedGoogle Scholar
  • 19 Collobert R, Bengio S, Mariéthoz J. Torch: a modular machine learning software library. Available at: https://infoscience.epfl.ch/record/82802/files/rr02-46.pdf . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 20 Bergstra J, Breuleux O, Bastien F. , et al. Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy). Vol 4. Austin, TX; 2010. Available at: https://conference.scipy.org/scipy2010/slides/james_bergstra_theano.pdf . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 21 Abadi M, Agarwal A, Barham P. , et al. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv [csDC]. March 2016. Available at: http://arxiv.org/abs/1603.04467 . Accessed January 8, 2020
    PubMed
  • 22 Paszke A, Gross S, Chintala S. , et al. Automatic differentiation in PyTorch. October 2017. Available at: https://openreview.net/pdf?id=BJJsrmfCZ . Accessed October 14, 2019
    PubMedGoogle Scholar
  • 23 LeCun Y, Boser BE, Denker JS. , et al. Handwritten digit recognition with a back-propagation network. In: Touretzky DS. , ed. Advances in Neural Information Processing Systems 2. San Francisco, CA: Morgan-Kaufmann; 1990: 396-404
    Google Scholar
  • 24 LeCun Y, Boser B, Denker JS. , et al. Backpropagation applied to handwritten zip code recognition. Neural Comput 1989; 1 (04) 541-551
    CrossrefPubMedGoogle Scholar
  • 25 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv [csCV]. September 2014. Available at: http://arxiv.org/abs/1409.1556 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 26 Szegedy C, Liu W, Jia Y. , et al. Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015: 1-9
    PubMedGoogle Scholar
  • 27 Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. OverFeat: Integrated recognition, localization and detection using convolutional networks. arXiv [csCV]. December 2013. Available at: http://arxiv.org/abs/1312.6229 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 28 He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv [csCV]. December 2015. Available at: http://arxiv.org/abs/1512.03385 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 29 Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. arXiv [csCV]. August 2016. Available at: http://arxiv.org/abs/1608.06993 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 30 He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. Computer Vision – ECCV 2016. Available at: https://arxiv.org/abs/1603.05027 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 31 Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. arXiv [csCV]. May 2015. Available at: http://arxiv.org/abs/1505.04597 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 32 Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015: 3431-3440
    PubMedGoogle Scholar
  • 33 Hammernik K, Klatzer T, Kobler E. , et al. Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 2018; 79 (06) 3055-3071
    CrossrefPubMedGoogle Scholar
  • 34 Knoll F, Hammernik K, Kobler E, Pock T, Recht MP, Sodickson DK. Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn Reson Med 2019; 81 (01) 116-128
    CrossrefPubMedGoogle Scholar
  • 35 Kobler E, Muckley M, Chen B. , et al. Variational deep learning for low-dose computed tomography. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2018: 6687-6691
    PubMedGoogle Scholar
  • 36 Lustig M, Donoho D, Pauly JM. Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 2007; 58 (06) 1182-1195
    CrossrefPubMedGoogle Scholar
  • 37 Aggarwal HK, Mani MP, Jacob M. MoDL: Model-Based Deep Learning architecture for inverse problems. IEEE Trans Med Imaging 2019; 38 (02) 394-405
    CrossrefPubMedGoogle Scholar
  • 38 Schlemper J, Caballero J, Hajnal JV, Price AN, Rueckert D. A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging 2018; 37 (02) 491-503
    CrossrefPubMedGoogle Scholar
  • 39 Qin C, Schlemper J, Caballero J, Price AN, Hajnal JV, Rueckert D. Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging 2019; 38 (01) 280-290
    CrossrefPubMedGoogle Scholar
  • 40 Zhu B, Liu JZ, Cauley SF, Rosen BR, Rosen MS. Image reconstruction by domain-transform manifold learning. Nature 2018; 555 (7697): 487-492
    Google Scholar
  • 41 Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014; 15: 1929-1958
    PubMedGoogle Scholar
  • 42 Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10); 2010: 807-814
    PubMedGoogle Scholar
  • 43 Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016: 2818-2826
    PubMedGoogle Scholar
  • 44 Hochreiter S. The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertain Fuzziness Knowl Based Syst 1998; 06 (02) 107-116
    CrossrefPubMedGoogle Scholar
  • 45 Srivastava RK, Greff K, Schmidhuber J. Highway networks. arXiv [csLG]. May 2015. Available at: http://arxiv.org/abs/1505.00387 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 46 Yang J, Parikh D, Batra D. Joint unsupervised learning of deep representations and image clusters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016: 5147-5156
    PubMedGoogle Scholar
  • 47 Jayaraman D, Grauman K. Slow and steady feature analysis: higher order temporal coherence in video. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. Doi: 10.1109/cvpr.2016.418
    PubMedGoogle Scholar
  • 48 Doersch C, Gupta A, Efros AA. Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision; 2015: 1422-1430
    PubMedGoogle Scholar
  • 49 Wen J, Thibeau-Sutre E, Samper-Gonzalez J. , et al. Convolutional neural networks for classification of Alzheimer's disease: overview and reproducible evaluation. arXiv [csLG]. April 2019. Available at: http://arxiv.org/abs/1904.07773 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 50 Guo C, Pleiss G, Sun Y, Weinberger KQ. On calibration of modern neural networks. arXiv [csLG]. June 2017. Available at: http://arxiv.org/abs/1706.04599 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 51 Raghu M, Blumer K, Sayres R. , et al. Direct uncertainty prediction for medical second opinions. arXiv [csLG]. July 2018. Available at: http://arxiv.org/abs/1807.01771 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 52 Lipton ZC. The myth of model interpretability. Available at: https://arxiv.org/pdf/1606.03490.pdf . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 53 Adebayo J, Gilmer J, Muelly M, Goodfellow I, Hardt M, Kim B. Sanity checks for saliency maps. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R. , eds. Advances in Neural Information Processing Systems 31. Red Hook, NY: Curran Associates; 2018: 9505-9515
    Google Scholar
  • 54 Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. Computer Vision – ECCV 2014. Available at: https://arxiv.org/abs/1311.2901 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 55 Szegedy C, Zaremba W, Sutskever I. , et al. Intriguing properties of neural networks. arXiv [csCV]. December 2013. Available at: http://arxiv.org/abs/1312.6199 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 56 Olah C, Mordvintsev A, Schubert L. Feature visualization. Distill 2017; 2 (11) e7
    PubMedGoogle Scholar
  • 57 Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M. Striving for simplicity: the all convolutional net. arXiv [csLG]. December 2014. Available at: http://arxiv.org/abs/1412.6806 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 58 Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks. arXiv [csLG]. March 2017. Available at: http://arxiv.org/abs/1703.01365 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 59 Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016: 2921-2929
    PubMedGoogle Scholar
  • 60 Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv [csCL]. September 2014. Available at: http://arxiv.org/abs/1409.0473 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 61 Xu K, Ba J, Kiros R. , et al. Show, attend and tell: neural image caption generation with visual attention. arXiv [csLG]. February 2015. Available at: http://arxiv.org/abs/1502.03044 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 62 Theis L, van den Oord A, Bethge M. A note on the evaluation of generative models. arXiv [statML]. November 2015. Available at: http://arxiv.org/abs/1511.01844 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 63 Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 2018; 15 (11) e1002683
    CrossrefPubMedGoogle Scholar
  • 64 Subbaswamy A, Schulam P, Saria S. Preventing failures due to dataset shift: learning predictive models that transport. arXiv [statML]. December 2018. Available at: http://arxiv.org/abs/1812.04597 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 65 Gyftopoulos S, Lin D, Knoll F, Doshi AM, Rodrigues TC, Recht MP. Artificial intelligence in musculoskeletal imaging: current status and future directions. AJR Am J Roentgenol 2019; 213 (03) 506-513
    CrossrefPubMedGoogle Scholar
  • 66 Hirschmann A, Cyriac J, Stieltjes B, Kober T, Richiardi J, Omoumi P. Artificial intelligence in musculoskeletal imaging: review of current literature, challenges, and trends. Semin Musculoskelet Radiol 2019; 23 (03) 304-311
    Artikel in Thieme ConnectPubMedGoogle Scholar
  • 67 Burns JE, Yao J, Summers RM. Artificial intelligence in musculoskeletal imaging: a paradigm shift. J Bone Miner Res 2019 ; August 9 (Epub ahead of print)
    PubMedGoogle Scholar
  • 68 LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521 (7553): 436-444
    PubMedGoogle Scholar
  • 69 Riley P. Three pitfalls to avoid in machine learning. Nature 2019; 572 (7767): 27-29
    PubMedGoogle Scholar
  • 70 Wiens J, Saria S, Sendak M. , et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med 2019; 25 (09) 1337-1340
    CrossrefPubMedGoogle Scholar
  • 71 Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017: 2097-2106
    PubMedGoogle Scholar
  • 72 Irvin J, Rajpurkar P, Ko M. , et al. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. arXiv [preprint arXiv:1901 07031]. 2019 . Available at: https://arxiv.org/abs/1901.07031 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 73 Johnson AEW, Pollard TJ, Berkowitz SJ. , et al. MIMIC-CXR: a large publicly available database of labeled chest radiographs. arXiv [csCV]. January 2019. Available at: http://arxiv.org/abs/1901.07042 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 74 Rajpurkar P, Irvin J, Bagul A. , et al. MURA: large dataset for abnormality detection in musculoskeletal radiographs. arXiv [physics.med-ph]. December 2017. Available at: http://arxiv.org/abs/1712.06957 . Accessed January 8, 2020
    PubMedGoogle Scholar
  • 75 Zbontar J, Knoll F, Sriram A. , et al. fastMRI: an open dataset and benchmarks for accelerated MRI. arXiv [csCV]. November 2018. Available at: http://arxiv.org/abs/1811.08839 . Accessed January 8, 2020
    PubMedGoogle Scholar