Advertisement

Advantages, Challenges, and Risks of Artificial Intelligence for Radiologists

  • Erik R. Ranschaert
  • André J. Duerinckx
  • Paul Algra
  • Elmar Kotter
  • Hans Kortman
  • Sergey Morozov
Chapter

Abstract

Radiology is a specialty that is closely related to technology and therefore constantly subject to change. Artificial intelligence (AI) based upon machine learning techniques is a development that will have a significant impact on the specialty. In this chapter the question is asked what radiologists can expect from this in the short and long term. Several strategies for development, adaptation, and implementation of AI in radiological practice are presented. The remaining challenges and risks of using AI-based applications are explained, and the most relevant ethical issues are addressed.

Keywords

Artificial intelligence Radiology Advantages Risks Future 

References

  1. 1.
    King BF. Artificial intelligence and radiology: what will the future hold? J Am Coll Radiol. 2018;15(3):1–3.CrossRefGoogle Scholar
  2. 2.
    Schier R. Artificial intelligence and the practice of radiology: an alternative view. J Am Coll Radiol. 2018;15(7):1004–7.CrossRefGoogle Scholar
  3. 3.
    Washington RA. Why scan-reading artificial intelligence is bad news for radiologists. The Economist [Internet]. 2017. Available from: https://www.economist.com/free-exchange/2017/11/29/why-scan-reading-artificial-intelligence-is-bad-news-for-radiologists
  4. 4.
    Jha S, Topol EJ. Adapting to artificial intelligence: radiologists and pathologists as information specialists. JAMA. 2016;316(22):2353–4.CrossRefGoogle Scholar
  5. 5.
    Obermeyer Z, Emanuel EJ. Predicting the future – big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216–9.CrossRefGoogle Scholar
  6. 6.
    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.CrossRefGoogle Scholar
  7. 7.
    Finlayson SG, Chung HW, Kohane IS, Beam AL. Adversarial attacks against medical deep learning systems. 2018. arXiv:1804.05296 [cs.CR].Google Scholar
  8. 8.
    Rajpurkar P, Irvin J, Zhu K, Yang B. arXiv HMAP, 2017. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. 2017. arXiv:1711.05225v3 [cs.CV].Google Scholar
  9. 9.
    Chen L, Carlton Jones AL, Mair G, Patel R, Gontsarova A, Ganesalingam J, et al. Rapid automated quantification of cerebral leukoaraiosis on CT images: a multicenter validation study. Radiology [Internet]. 2018. Available from: https://pubs.rsna.org/doi/abs/10.1148/radiol.2018171567
  10. 10.
    Tang A, Tam R, Cadrin-Chênevert A, Guest W, Chong J, Barfett J, et al. Canadian association of radiologists white paper on artificial intelligence in radiology. Can Assoc Radiol J. 2018;69(2):120–35.CrossRefGoogle Scholar
  11. 11.
    Davenport T, Dreyer K. AI will change radiology, but it won’t replace radiologists. Harvard Business Review [Internet]. 2018. Available from: https://hbr.org/2018/03/ai-will-change-radiology-but-it-wont-replace-radiologists
  12. 12.
    Langs G, Röhrich S, Hofmanninger J, Prayer F, Pan J, Herold C, et al. Machine learning: from radiomics to discovery and routine. Radiologe. 2018:1–6.  https://doi.org/10.1007/s00117-018-0407-3.CrossRefGoogle Scholar
  13. 13.
    Collado-Mesa F, Alvarez E, Arheart K. The role of artificial intelligence in diagnostic radiology: a survey at a single radiology residency training program. J Am Coll Radiol. 2018;  https://doi.org/10.1016/j.jacr.2017.12.021.CrossRefGoogle Scholar
  14. 14.
    Lee J-G, Jun S, Cho Y-W, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18(4):570–84.CrossRefGoogle Scholar
  15. 15.
    Erickson BJ, Korfiatis P, Kline TL, Akkus Z, Philbrick K, Weston AD. Deep learning in radiology: does one size fit all? J Am Coll Radiol. 2018;15(3):521–6.CrossRefGoogle Scholar
  16. 16.
    Choy G, Khalilzadeh O, Michalski M, Do S, Samir AE, Pianykh OS, et al. Current applications and future impact of machine learning in radiology. Radiology. 2018;288(2):318–28.CrossRefGoogle Scholar
  17. 17.
    Paiva OA, Paiva OA, Prevedello LM. The potential impact of artificial intelligence in radiology. Radiol Bras. 2017;50(5):V–VI.CrossRefGoogle Scholar
  18. 18.
    Taub LM. 2017 AI overview [Internet]. Medium.com. 2017. Available from: https://medium.com/@lolitataub/the-ai-2017-guide-de03ae82054. Accessed 15 June 2018.
  19. 19.
    Walter M. Are European radiologists skeptical about AI? A report from ECR 2018 [Internet]. Radiology Business. 2018. Available from: https://www.radiologybusiness.com/topics/artificial-intelligence/are-european-radiologists-skeptical-about-ai-report-ecr-2018. Accessed 15 June 2018.
  20. 20.
    Massat MB. Artificial intelligence in radiology: hype or hope? [Internet]. 2018. Available from: https://www.appliedradiology.com/articles/artificial-intelligence-in-radiology-hype-or-hope. Accessed 22 July 2018.
  21. 21.
    ACR, 2014. LungRADS version 1.0 assessment categories release date: April 28, 2014. Available from: https://www.emmc.org/emmc/files/c3/c337137e-f68d-403e-938a-fd3c045e35c2.pdf
  22. 22.
    Nagel S, Sinha D, Day D, Reith W, Chapot R, Papanagiotou P, et al. e-ASPECTS software is non-inferior to neuroradiologists in applying the ASPECT score to computed tomography scans of acute ischemic stroke patients. Int J Stroke. 2017;12(6):615–22.CrossRefGoogle Scholar
  23. 23.
    European Stroke Organisation Conference: Abstracts. Eur Stroke J. 2018;3(1_suppl):3–204.Google Scholar
  24. 24.
    Fornell D. What is new in FFR technology [Internet]. 2017. Available from: https://www.dicardiology.com/article/what-new-ffr-technology. Accessed 22 July 2018.
  25. 25.
    Allen B, Dreyer K. The artificial intelligence ecosystem for the radiological sciences: ideas to clinical practice. J Am Coll Radiol. 2018;  https://doi.org/10.1016/j.jacr.2018.02.032.CrossRefGoogle Scholar
  26. 26.
    Melendez J, Hogeweg L, Sánchez CI, Philipsen RHHM, Aldridge RW, Hayward AC, et al. Accuracy of an automated system for tuberculosis detection on chest radiographs in high-risk screening. Int J Tuberc Lung Dis. 2018;22(5):567–71.CrossRefGoogle Scholar
  27. 27.
    Bruynseels K, Santoni de Sio F, van den Hoven J. Digital twins in health care: ethical implications of an emerging engineering paradigm. Front Genet. 2018;9:31.CrossRefGoogle Scholar
  28. 28.
    Holzinger A. Project iML – proof of concept interactive machine learning. Brain Inform. 2016;3(2):119–31.CrossRefGoogle Scholar
  29. 29.
    Ranschaert E. MIDL 2018 panel discussion about radiology and artificial intelligence [Internet]. Medium.com. 2018. Available from: https://medium.com/@erik.ranschaert/midl-2018-panel-discussion-about-radiology-and-artificial-intelligence-2bec1d252adb. Accessed 7 July 2018.
  30. 30.
    Ruder S. An overview of multi-task learning in deep neural networks. 2017. arXiv:1706.05098v1 [cs.LG].Google Scholar
  31. 31.
    Moeskops P, Wolterink JM, van der Velden BHM, Gilhuijs KGA, Leiner T, Viergever MA, et al. Deep learning for multi-task medical image segmentation in multiple modalities. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. Cham: Springer; 2016. p. 478–86. (Lecture Notes in Computer Science; vol. 9901).CrossRefGoogle Scholar
  32. 32.
    Bassett M. The reality of deep learning/artificial intelligence in radiology: they will redefine the specialty [Internet]. rsna.org. 2018. Available from: http://www.rsna.org/RSNANewsDetailWireframe.aspx?pageid=15319& id=23533&ekfxmen_noscript=1&ekfxmensel=false falsetruetruetruefalsefalse10-18.0.0.0730truefalse. Accessed 17 June 2018.
  33. 33.
    Pearson D. Orchestrating interoperability: one size does not fit all [Internet]. Imaging Biz. 2015. Available from: https://www.imagingbiz.com/sponsored/1174/topics/technology-management/orchestrating-interoperability-one-size-does-not-fit. Accessed 17 June 2018.
  34. 34.
    Chang P. Preparing your radiology practice and IT department for big data. Maarssen, The Netherlands. 2018. Available from: https://phit.nl/nl/masterclass-meaningful-use-it-radiology-and-ai-imaging-paul-chang
  35. 35.
    Bassett M. At your service: will service oriented architecture add interoperability to imaging? [Internet]. HealthImaging.com. 2010. Available from: https://www.healthimaging.com/topics/practice-management/your-service-will-service-oriented-architecture-add-interoperability. Accessed 17 June 2018.
  36. 36.
    Patel V. A framework for secure and decentralized sharing of medical imaging data via blockchain consensus. Health Informatics J. 2018;  https://doi.org/10.1177/1460458218769699.
  37. 37.
    Schumacher A. Blockchain and healthcare. 2017. 49 p. Available from: https://www.researchgate.net/publication/317936859_Blockchain_Healthcare_-_2017_Strategy_Guide
  38. 38.
    Sagreiya H. A realist’s look at artificial intelligence in medicine [Internet]. Medium.com. 2018. Available from: https://opmed.doximity.com/artificial-intelligence-in-medicine-beyond-the-hype-3b8cc0c8b893. Accessed 1 July 2018.
  39. 39.
    ESR ESOR. The new EU general data protection regulation: what the radiologist should know. Insights Imaging. 2017;8(3):295–9.CrossRefGoogle Scholar
  40. 40.
    Haug CJ. Turning the tables—the new European general data protection regulation. N Engl J Med. 2018;379(3):207–9.  https://doi.org/10.1056/NEJMp1806637.CrossRefPubMedGoogle Scholar
  41. 41.
    Char DS, Shah NH, Magnus D. Implementing machine learning in health care—addressing ethical challenges. N Engl J Med. 2018;378(11):981–3.CrossRefGoogle Scholar
  42. 42.
    Kohli M, Geis R. Ethics, artificial intelligence, and radiology. J Am Coll Radiol. 2018;15(9):1317–9.CrossRefGoogle Scholar
  43. 43.
    Balthazar P, Harri P, Prater A, Safdar NM. Protecting your patients’ interests in the era of big data, artificial intelligence, and predictive analytics. J Am Coll Radiol. 2018;15(3 Pt B):580–6.CrossRefGoogle Scholar
  44. 44.
    Kohli MD, Summers RM, Geis JR. Medical image data and datasets in the era of machine learning—whitepaper from the 2016 C-MIMI meeting dataset session. J Digit Imaging. 2017;30(4):392–9.CrossRefGoogle Scholar
  45. 45.
    Mesko B. Could you sue diagnostic algorithms or medical robots in the future? The Medical Futurist [Internet]. 2018. Available from: https://medicalfuturist.com/could-you-sue-diagnostic-algorithms-or-medical-robots-in-the-future. Accessed 16 June 2018.
  46. 46.
    Delcker J. Europe divided over robot “personhood” [Internet]. Politico. 2018. Available from: https://www.politico.eu/article/europe-divided-over-robot-ai-artificial-intelligence-personhood/. Accessed 16 July 2018.
  47. 47.
    Dwoskin E, Romm T. Facebook makes its privacy controls simpler as company faces data reckoning [Internet]. The Washington Post. 2018. Available from: https://www.washingtonpost.com/news/the-switch/wp/2018/03/28/facebooks-makes-its-privacy-controls-simpler-as-company-faces-data-reckoning/. Accessed 23 July 2018.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Erik R. Ranschaert
    • 1
  • André J. Duerinckx
    • 2
  • Paul Algra
    • 3
  • Elmar Kotter
    • 4
  • Hans Kortman
    • 1
  • Sergey Morozov
    • 5
  1. 1.ETZ HospitalTilburgThe Netherlands
  2. 2.Howard University College of Medicine and Howard University HospitalWashington, DCUSA
  3. 3.Department of RadiologyNorthwest Hospital GroupAlkmaarThe Netherlands
  4. 4.Department of RadiologyMedical Center – University of FreiburgFreiburgGermany
  5. 5.Radiology Research and Practical CentreMoscowRussia

Personalised recommendations