Advertisement

A Deeper Understanding of Deep Learning

  • Bart M. ter Haar RomenyEmail author
Chapter

Abstract

To better understand the mechanisms of the seemingly “black box” of AI and deep learning, we take a closer look at its internal processes. We will discuss the power of contextual processing, study insights from the human visual system, and study in some detail how the different of a deep convolutional neural networks work. We do this with an engineering view, for radiologists, in an intuitive way.

Keywords

Deep convolutional neural network Visual cortex Visual learning Context Receptive fields RetinaCheck Brain efficiency Visual pathways Principal component analysis 

References

  1. 1.
    Abbasi-Sureshjani S, Dashtbozorg B, ter Haar Romeny BM, Fleuret F. Boosted exudate segmentation in retinal images using residual nets. In: Proceedings of ophthalmic medical image analysis OMIA 2017, at MICCAI 2017, Québec City. Cham: Springer; 2017. p. 210–8Google Scholar
  2. 2.
    American College of Radiology. Data Science Institute; 2018. The ACR DSI is collaborating with radiology professionals, industry leaders, government agencies, patients, and other stakeholders to facilitate the development and implementation of artificial intelligence (AI) applications that will help radiology professionals provide improved medical care. www.acrdsi.org.
  3. 3.
    Blakemore C, Cooper GF. Development of the brain depends on the visual environment. Nature. 1970;228:477–8.CrossRefGoogle Scholar
  4. 4.
    Blakemore C, Cooper GF. Development of the brain depends on the visual environment; 1970. Movie: https://www.youtube.com/watch?v=QzkMo45pcUo.
  5. 5.
    Briggman KL, Helmstaedter M, Denk W. Wiring specificity in the direction-selectivity circuit of the retina. Nature. 2011;471:183–8.CrossRefGoogle Scholar
  6. 6.
    Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, Kadoury S, Tang A. Deep learning: a primer for radiologists. RadioGraphics. 2017;37(7):2113–31.CrossRefGoogle Scholar
  7. 7.
    Doolittle B, MacLay E. The forest has eyes. Seymour: Greenwich Workshop Press; 1998.Google Scholar
  8. 8.
    Eremenko K, de Ponteves H. Deep learning A-Z: hands-on artificial neural networks in Python, Udemy Inc. https://www.udemy.com/deeplearning. Most popular course 2018.
  9. 9.
    Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. RadioGraphics. 2017;37(2):505–15.CrossRefGoogle Scholar
  10. 10.
    Ghafoorian M, Karssemeijer N, Heskes T, van Uder IWM, de Leeuw FE, Marchiori E, van Ginneken B, Platel B. Non-uniform patch sampling with deep convolutional neural networks for white matter hyperintensity segmentation. In: 13th international symposium on biomedical imaging (ISBI), April 2016. New York: IEEE; 2016. p. 1414–7.CrossRefGoogle Scholar
  11. 11.
    Google Inc. TensorFlow; 2018. An open source machine learning framework. www.tensorflow.org.
  12. 12.
    Greenspan H, van Ginneken B, Summers RM. Guest editorial: deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging. 2016;35(5):1153–9.CrossRefGoogle Scholar
  13. 13.
    Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. J Am Med Assoc. 2016;316(22):2402–10.CrossRefGoogle Scholar
  14. 14.
    ImageNet. Large scale visual recognition challenge (ILSVRC), 2010–2017. ILSVRC evaluates algorithms for object detection and image classification at large scale: 150000 photographs, 1000 classes. http://www.image-net.org/challenges/LSVRC/.
  15. 15.
    Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, Lille. Vol 37; 2015. https://arxiv.org/abs/1502.03167.
  16. 16.
    Kandel ER, Schwartz JH, Jessell TM. Principles of neural science. 5th ed. New York: McGraw-Hill; 2013.Google Scholar
  17. 17.
    Kolb H, Fernandez E, Nelson R, editors. Webvision: the organization of the retina and visual system. University of Utah Health Sciences Center, Salt Lake City (UT); 1995. https://www.ncbi.nlm.nih.gov/books/NBK11530/.
  18. 18.
    Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editors. Advances in neural information processing systems 25. Red Hook: Curran Associates, Inc.; 2012. p. 1097–105.Google Scholar
  19. 19.
    LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44.CrossRefGoogle Scholar
  20. 20.
    Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.CrossRefGoogle Scholar
  21. 21.
    Masland RH. The fundamental plan of the retina. Nat Neurosci. 2001;4:877–86.CrossRefGoogle Scholar
  22. 22.
    Nelson E. Wide-are indoor and outdoor real-time 3D SLAM; 2016. Movie: https://www.youtube.com/watch?v=08GTGfNneCI. UC Berkeley, Department of EECS/Lawrence Berkeley National Laboratory.
  23. 23.
    Nelson E, Corah M, Michael N. Environment model adaptation for mobile robot exploration. Auton Robot. 2018;42(2):257–72.CrossRefGoogle Scholar
  24. 24.
    Radboud UMC, Nijmegen, the Netherlands. Diagnostic Image Analysis Group: EuSoMII workshop hands-on with AI in radiology, April 21, 2018. http/diagnijmegen.nl/index.php/Hands-on-AI, www.linkedin.com/pulse/eusomii-hands-on-ai-workshop-nijmegen-great-success-erik-r-/.
  25. 25.
    Rodieck RW. The first steps in seeing. Sunderland: Sinauer Associates, Inc.; 1998.Google Scholar
  26. 26.
    ter Haar Romeny BM. Front-end vision and multi-scale image analysis. Computational imaging and vision series. Vol. 27. Berlin: Springer; 2003.Google Scholar
  27. 27.
    ter Haar Romeny BM, Bekkers EJ, Zhang J, Abbasi-Sureshjani S, Huang F, Duits R, Dashtbozorg B, et al. Brain-inspired algorithms for retinal image analysis. Mach Vis Appl. 2016;27(8):1117–35.CrossRefGoogle Scholar
  28. 28.
    Wagemans J, Elder JH, Kubovy M, Palmer SE, Peterson MA, Singh M, von der Heydt R. A century of gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization. Psychol Bull. 2012;138(6):1172–2012.CrossRefGoogle Scholar
  29. 29.
    Wertheimer M. Laws of organization in perceptual forms (partial translation). In: Ellis WB, editor. A sourcebook of gestalt psychology. San Diego: Harcourt, Brace; 1938. p. 71–88.Google Scholar
  30. 30.
    Zhou SK, Greenspan H, Shen D, editors. Deep learning for medical image analysis. Cambridge: Academic; 2017.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Biomedical EngineeringEindhoven University of TechnologyEindhovenThe Netherlands

Personalised recommendations