A MODERN RENAISSANCE OR AN ETHICAL CONUNDRUM: REVIEWING THE IMPLICATIONS OF ARTIFICIAL INTELLIGENCE IN THE FIELD OF RADIOLOGY

Yıl 2021, Cilt: 8 Sayı: 1, 8 - 12, 28.02.2021

Muhammad Romail Manan Hamna Manan

Öz

Recent progress in the field of artificial intelligence has found its way into the diverse realms of medical imaging and radiology, raising questions regarding its po- tential, efficiency, accuracy, and reliability. This review aims to educate radiologists and medical students regarding the uncharted world of artificial intelligence through the discussion of its achievements in radiology while keeping an ethical and prognostic outlook in mind. Artificial intelligence, through the application of its subsets (i.e. machine learning and deep learning), has caused vast expansions in radiology, such as automating diagnoses. Pneumonia, pneumothorax, pulmonary tuberculosis, pulmonary nodules, etc. can now be detected through the use of various artificial intelligence algorithms. However, the acceptability of these highly accurate systems is still a matter of massive doubt. Educating the healthcare professionals in this regard would alleviate the fear of an unknown com- puting system while also answering numerous misconceptions. Moreover, with acceptability comes a huge moral and ethical responsibility. Ethical codes need to be devised that provide appropriate solutions to the moral problems connected with artificial intelligence. Thus, with all of these factors under consideration, artificial intelligence has enormous potential in the field of radiology and will broaden the horizon of healthcare professionals by creating a greater number of computing-related opportunities.

Anahtar Kelimeler

Artificial intelligence, radiology, ethics, deep learning, machine learning

Kaynakça

• 1. Kok JN, Boers EJW, Kosters WA et al. Artificial intelligence: Definition, trends, techniques and cases. Encyclopedia of Life Support Systems 2010;1096–7.
• 2. Huang TS. Computer vision: Evolution and promise. Urbana (IL): University of Illinois at Urbana-Champaign. 1997.
• 3. Chassagnon G, Vakalopoulou M, Paragios N et al. Artificial intelligence applica- tions for thoracic imaging. Eur J Radiol 2020;123:108774.
• 4. Paeglis A, Strumfs B, Mezale D et al. A review on machine learning and deep learning techniques applied to liquid biopsy. Liquid Biopsy (serial online) 2018 November (cited 2021 January 12). Available from: URL: https://www.inte- chopen.com/books/liquid-biopsy/a-review-on-machine-learning-and-deep- learning-techniques-applied-to-liquid-biopsy.
• 5. Khanna SK. Machine learning vs deep learning. 2019;455–8.
• 6. Mollura DJ, Azene EM, Starikovsky A et al. White paper report of the rad-aid conference on international radiology for developing countries: Identifying chal- lenges, opportunities, and strategies for imaging services in the developing world. J Am Coll Radiol 2010;7(7):495–500.
• 7. Raoof S, Feigin D, Sung A et al. Interpretation of plain chest roentgenogram. Chest 2012;141(2):545–58.
• 8. Rajpurkar P, Irvin J, Ball RL et al. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 2018;15(11):1–17.
• 9. Taylor AG, Mielke C, Mongan J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. PLoS Med 2018;15(11):1–15.
• 10. Kao EF, Liu GC, Lee LY et al. Computer-aided detection system for chest radiog- raphy: Reducing report turnaround times of examinations with abnormalities. Acta Radiol 2015;56(6):696–701.
• 11. Boyle P, Levin B. World Cancer report 2020. Vol. 199, Cancer Control 2008.p.512.
• 12. Zhu X, Yao J, Huang J. Deep convolutional neural network for survival analysis with pathological images. 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Shenzhen, 2016.p.544-7.
• 13. Paul R, Hawkins SH, Hall LO et al. Combining deep neural network and tra- ditional image features to improve survival prediction accuracy for lung cancer patients from diagnostic CT. IEEE International Conference on Systems, Man, and Cybernetics; 2016 Oct; 2017.p.2570–5.
• 14. Nam JG, Park S, Hwang EJ et al. Development and validation of deep learn- ing-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 2019;290(1):218–28.
• 15. Chen S, Suzuki K, MacMahon H. Development and evaluation of a computer-aid- ed diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification. Med Phys 2011;38(4):1844–58.
• 16. Firmino M, Angelo G, Morais H et al. Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy. Biomed Eng Online 2016;15(1):1–17.
• 17. Kobayashi T, Xu XW, MacMahon H et al. Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs. Radiology 1996;199(3):843–8.
• 18. Rajpurkar P, Irvin J, Zhu K et al. CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv 2017;3–9.
• 19. Islam MT, Aowal MA, Minhaz AT et al. Abnormality detection and localiza- tion in chest x-rays using deep convolutional neural networks. arXiv 2017, arX- iv:1705.09850. [Online]. Available from: URL: http://arxiv.org/abs/1705.09850.
• 20. Tuberculosis. World Health Organization Website. Available from: URL: https:// www.who.int/news-room/fact-sheets/detail/tuberculosis.
• 21. Centers for Disease Control and Prevention (CDC). Tuberculosis: data and statis- tics. Available from: URL: https://www.cdc.gov/tb/statistics/default.htm.
• 22. Hogeweg L, Sánchez CI, Maduskar P et al. Automatic detection of tuberculosis in chest radiographs using a combination of textural , focal , and shape abnormality analysis. IEEE Trans Med Imaging 2015;34(12):2429-42.
• 23. Hwang EJ, Park S, Jin K et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radio- graphs. Clin Infect Dis 2019;69:739–47.
• 24. Paras Lakhani M, Baskaran Sundaram M. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017;284(2):574–82.
• 25. George R. Washko MDM. The role and potential of imaging in COPD. Med Clin North Am 2012;96(4):729–43.
• 26. Müller NL, Staples CA, Miller RR et al. "Density Mask" an objective method to quantitate emphysema using computed tomography. Chest 1988;94(4):782-7.
• 27. Hersh CP, Washko GR, Jacobson FL et al. Interobserver variability in the determi- nation of upper lobe-predominant emphysema. Chest 2007;131(2):424-31.
• 28. Das N, Topalovic M, Janssens W. Artificial intelligence in diagnosis of obstruc- tive lung disease: current status and future potential. Curr Opin Pulm Med 2018;24(2):117–23.
• 29. Pei X. Emphysema classification using convolutional neural networks. In: Liu H., Kubota N., Zhu X., Dillmann R., Zhou D, editors. Intelligent Robotics and Ap- plications. ICIRA 2015. Lecture Notes in Computer Science, vol 9244 Springer: Cham; 2015.p.455-61.
• 30. Tajbakhsh N, Shin JY, Gurudu SR et al. Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 2016;35(5):1299–312.
• 31. Liew C. The future of radiology augmented with artificial ıntelligence: a strategy for success. Eur J Radiol 2018;102:152-6.
• 32. Beauchamp TL, Childress JF. Principles of biomedical ethics. New York; Oxford: Oxford University Press; 2013.
• 33. Floridi L, Taddeo M. What is data ethics? Philos Trans A Math Phys Eng Sci 2016;374(2083):20160360.
• 34. Mittelstadt BD, Floridi L. The ethics of big data: current and foreseeable issues in biomedical contexts. Sci Eng Ethics 2016;22(2):303–41.
• 35. Kohli M, Geis R. Ethics, artificial intelligence, and radiology. J Am Coll Radiol 2018;15(9):1317–9.
• 36. Neri E, Coppola F, Miele V et al. Artificial intelligence: who is responsible for the diagnosis? Radiol Medica 2020;125(6):517–21.
• 37. Giubilini A, Savulescu J. The artificial moral advisor. the "ideal observer" meets artificial intelligence. Philos Technol 2018;31(2):169-88.
• 38. Geis JR, Brady AP, Wu CC et al. Ethics of artificial intelligence in radiology: sum- mary of the Joint European and North American Multisociety Statement. Radiol- ogy 2019;293(2):436-40.
• 39. Cummings ML. Automation bias in intelligent time critical decision support sys- tems. Collect Tech Pap - AIAA 1st Intell Syst Tech Conf. 2004;2:557–62.
• 40. Gong B, Nugent JP, Guest W et al. Influence of artificial intelligence on Canadian medical students’ preference for radiology specialty: a national survey study. Acad Radiol 26(4):566–77.
• 41. Mayo RC, Leung J. Artificial intelligence and deep learning – radiology’s next frontier? Clin Imaging 2018;49:87–8.
• 42. Yasaka K, Abe O. Deep learning and artificial intelligence in radiology: Current applications and future directions. PLoS Med 2018;15(11):e1002707.
• 43. Forney MC, McBride AF. Artificial intelligence in radiology residency training. Semin Musculoskelet Radiol 2020;24(1):74-80.
• 44. Waymel Q, Badr S, Demondion X et al. Impact of the rise of artificial intelligence in radiology: what do radiologists think? Diagn Interv Imaging 2019;100(6):327-36.
• 45. Grace K, Salvatier J, Dafoe A et al. When will AI exceed human performance? Evidence from AI experts. J Artif Intell Res 2018;62:729–54.
• 46. Syed AB, Zoga AC. Artificial intelligence in radiology: current technology and future directions. Semin Musculoskelet Radiol 2018;22(5):540–5.
• 47. Hosny A, Parmar C, Quackenbush J et al. Artificial intelligence in radiology. Nat Rev Cancer 2018;18(8):500–10.