Skip to main content
SpringerLink
Log in

A Deeper Understanding of Deep Learning

  • Chapter
  • First Online:
Artificial Intelligence in Medical Imaging

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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    This explains the name of Google’s deep learning software TensorFlow [11].

  2. 2.

    The Facebook “like” button has been pressed 1.13 trillion times.

  3. 3.

    The search term “faces everywhere” in Google Images gives many common objects in which faces are perceived.

References

  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. 210–8

    Google Scholar 

  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. Blakemore C, Cooper GF. Development of the brain depends on the visual environment. Nature. 1970;228:477–8.

    Article  CAS  Google Scholar 

  4. Blakemore C, Cooper GF. Development of the brain depends on the visual environment; 1970. Movie: https://www.youtube.com/watch?v=QzkMo45pcUo.

  5. Briggman KL, Helmstaedter M, Denk W. Wiring specificity in the direction-selectivity circuit of the retina. Nature. 2011;471:183–8.

    Article  CAS  Google Scholar 

  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.

    Article  Google Scholar 

  7. Doolittle B, MacLay E. The forest has eyes. Seymour: Greenwich Workshop Press; 1998.

    Google Scholar 

  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. Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. RadioGraphics. 2017;37(2):505–15.

    Article  Google Scholar 

  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.

    Chapter  Google Scholar 

  11. Google Inc. TensorFlow; 2018. An open source machine learning framework. www.tensorflow.org.

  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.

    Article  Google Scholar 

  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.

    Article  Google Scholar 

  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. 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. Kandel ER, Schwartz JH, Jessell TM. Principles of neural science. 5th ed. New York: McGraw-Hill; 2013.

    Google Scholar 

  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. 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. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44.

    Article  CAS  Google Scholar 

  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.

    Article  Google Scholar 

  21. Masland RH. The fundamental plan of the retina. Nat Neurosci. 2001;4:877–86.

    Article  CAS  Google Scholar 

  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. Nelson E, Corah M, Michael N. Environment model adaptation for mobile robot exploration. Auton Robot. 2018;42(2):257–72.

    Article  Google Scholar 

  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. Rodieck RW. The first steps in seeing. Sunderland: Sinauer Associates, Inc.; 1998.

    Google Scholar 

  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. 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.

    Article  Google Scholar 

  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.

    Article  Google Scholar 

  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. Zhou SK, Greenspan H, Shen D, editors. Deep learning for medical image analysis. Cambridge: Academic; 2017.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

    Bart M. ter Haar Romeny

Authors
  1. Bart M. ter Haar Romeny
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bart M. ter Haar Romeny .

Editor information

Editors and Affiliations

  1. ETZ Hospital, Tilburg, The Netherlands

    Erik R. Ranschaert

  2. Radiology Research and Practical Centre, Moscow, Russia

    Sergey Morozov

  3. Department of Radiology, Northwest Hospital Group, Alkmaar, The Netherlands

    Paul R. Algra

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

ter Haar Romeny, B.M. (2019). A Deeper Understanding of Deep Learning. In: Ranschaert, E., Morozov, S., Algra, P. (eds) Artificial Intelligence in Medical Imaging. Springer, Cham. https://doi.org/10.1007/978-3-319-94878-2_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-94878-2_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-94877-5

  • Online ISBN: 978-3-319-94878-2

  • eBook Packages: MedicineMedicine (R0)

Publish with us

Policies and ethics

Search

Navigation