Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

A Nationwide Web-Based Survey of Neuroradiologists' Perceptions of Artificial Intelligence Software for Neuro-Applications in Korea

  • Hyunsu Choi (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Leonard Sunwoo (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Se Jin Cho (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Sung Hyun Baik (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Yun Jung Bae (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Byung Se Choi (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Cheolkyu Jung (Department of Radiology, Seoul National University Bundang Hospital) ;
  • Jae Hyoung Kim (Department of Radiology, Seoul National University Bundang Hospital)
  • Received : 2022.11.21
  • Accepted : 2023.03.06
  • Published : 2023.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: We aimed to investigate current expectations and clinical adoption of artificial intelligence (AI) software among neuroradiologists in Korea. Materials and Methods: In April 2022, a 30-item online survey was conducted by neuroradiologists from the Korean Society of Neuroradiology (KSNR) to assess current user experiences, perceptions, attitudes, and future expectations regarding AI for neuro-applications. Respondents with experience in AI software were further investigated in terms of the number and type of software used, period of use, clinical usefulness, and future scope. Results were compared between respondents with and without experience with AI software through multivariable logistic regression and mediation analyses. Results: The survey was completed by 73 respondents, accounting for 21.9% (73/334) of the KSNR members; 72.6% (53/73) were familiar with AI and 58.9% (43/73) had used AI software, with approximately 86% (37/43) using 1-3 AI software programs and 51.2% (22/43) having up to one year of experience with AI software. Among AI software types, brain volumetry software was the most common (62.8% [27/43]). Although 52.1% (38/73) assumed that AI is currently useful in practice, 86.3% (63/73) expected it to be useful for clinical practice within 10 years. The main expected benefits were reducing the time spent on repetitive tasks (91.8% [67/73]) and improving reading accuracy and reducing errors (72.6% [53/73]). Those who experienced AI software were more familiar with AI (adjusted odds ratio, 7.1 [95% confidence interval, 1.81-27.81]; P = 0.005). More than half of the respondents with AI software experience (55.8% [24/43]) agreed that AI should be included in training curriculums, while almost all (95.3% [41/43]) believed that radiologists should coordinate to improve its performance. Conclusion: A majority of respondents experienced AI software and showed a proactive attitude toward adopting AI in clinical practice, suggesting that AI should be incorporated into training and active participation in AI development should be encouraged.

Keywords

Acknowledgement

The authors acknowledge the participation of Korean Society of Neuroradiology (KSNR) in this survey.

References

  1. Pesapane F, Codari M, Sardanelli F. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. Eur Radiol Exp 2018;2:35
  2. Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, et al. Deep learning: a primer for radiologists. Radiographics 2017;37:2113-2131 https://doi.org/10.1148/rg.2017170077
  3. Havaei M, Guizard N, Larochelle H, Jodoin PM. Deep learning trends for focal brain pathology segmentation in MRI. In: Holzinger A, ed. Machine learning for health informatics: state-of-the-art and future challenges. Cham: Springer, 2016:125-148
  4. Anthimopoulos M, Christodoulidis S, Ebner L, Christe A, Mougiakakou S. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans Med Imaging 2016;35:1207-1216 https://doi.org/10.1109/TMI.2016.2535865
  5. Zhou LQ, Wang JY, Yu SY, Wu GG, Wei Q, Deng YB, et al. Artificial intelligence in medical imaging of the liver. World J Gastroenterol 2019;25:672-682 https://doi.org/10.3748/wjg.v25.i6.672
  6. Hwang EJ, Goo JM, Yoon SH, Beck KS, Seo JB, Choi BW, et al. Use of artificial intelligence-based software as medical devices for chest radiography: a position paper from the Korean Society of Thoracic Radiology. Korean J Radiol 2021;22:1743-1748 https://doi.org/10.3348/kjr.2021.0544
  7. Lee S, Shin HJ, Kim S, Kim EK. Successful implementation of an artificial intelligence-based computer-aided detection system for chest radiography in daily clinical practice. Korean J Radiol 2022;23:847-852 https://doi.org/10.3348/kjr.2022.0193
  8. Sakai K, Yamada K. Machine learning studies on major brain diseases: 5-year trends of 2014-2018. Jpn J Radiol 2019;37:34-72 https://doi.org/10.1007/s11604-018-0794-4
  9. Olthof AW, van Ooijen PMA, Rezazade Mehrizi MH. Promises of artificial intelligence in neuroradiology: a systematic technographic review. Neuroradiology 2020;62:1265-1278 https://doi.org/10.1007/s00234-020-02424-w
  10. van Leeuwen KG, Schalekamp S, Rutten MJCM, van Ginneken B, de Rooij M. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur Radiol 2021;31:3797-3804 https://doi.org/10.1007/s00330-021-07892-z
  11. Choi KS, Sunwoo L. Artificial intelligence in neuroimaging: clinical applications. Investig Magn Reson Imaging 2022;26:1-9 https://doi.org/10.13104/imri.2022.26.1.1
  12. Persson K, Barca ML, Cavallin L, Braekhus A, Knapskog AB, Selbaek G, et al. Comparison of automated volumetry of the hippocampus using NeuroQuant(R) and visual assessment of the medial temporal lobe in Alzheimer's disease. Acta Radiol 2018;59:997-1001 https://doi.org/10.1177/0284185117743778
  13. Sheth SA, Lopez-Rivera V, Barman A, Grotta JC, Yoo AJ, Lee S, et al. Machine learning-enabled automated determination of acute ischemic core from computed tomography angiography. Stroke 2019;50:3093-3100 https://doi.org/10.1161/STROKEAHA.119.026189
  14. Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, et al. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 2018;392:2388-2396 https://doi.org/10.1016/S0140-6736(18)31645-3
  15. Yahav-Dovrat A, Saban M, Merhav G, Lankri I, Abergel E, Eran A, et al. Evaluation of artificial intelligence-powered identification of large-vessel occlusions in a comprehensive stroke center. AJNR Am J Neuroradiol 2021;42:247-254 https://doi.org/10.3174/ajnr.A6923
  16. Radboud UMC. Products. AI for Radiology.com Web site. https://grand-challenge.org/aiforradiology/. Accessed October 25, 2022
  17. Gallix B, Chong J. Artificial intelligence in radiology: who's afraid of the big bad wolf? Eur Radiol 2019;29:1637-1639 https://doi.org/10.1007/s00330-018-5995-9
  18. Huisman M, Ranschaert E, Parker W, Mastrodicasa D, Koci M, Pinto de Santos D, et al. An international survey on AI in radiology in 1,041 radiologists and radiology residents part 1: fear of replacement, knowledge, and attitude. Eur Radiol 2021;31:7058-7066 https://doi.org/10.1007/s00330-021-07781-5
  19. Coppola F, Faggioni L, Regge D, Giovagnoni A, Golfieri R, Bibbolino C, et al. Artificial intelligence: radiologists' expectations and opinions gleaned from a nationwide online survey. Radiol Med 2021;126:63-71 https://doi.org/10.1007/s11547-020-01205-y
  20. Gong B, Nugent JP, Guest W, Parker W, Chang PJ, Khosa F, et al. Influence of artificial intelligence on Canadian medical students' preference for radiology specialty: ANational survey study. Acad Radiol 2019;26:566-577 https://doi.org/10.1016/j.acra.2018.10.007
  21. Scheetz J, Rothschild P, McGuinness M, Hadoux X, Soyer HP, Janda M, et al. A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology. Sci Rep 2021;11:5193
  22. Shin SY. Current status and future direction of digital health in Korea. Korean J Physiol Pharmacol 2019;23:311-315 https://doi.org/10.4196/kjpp.2019.23.5.311
  23. Ministry of Food and Drug Safety. The Ministry of Food and Drug Safety has become a leading country in regulating AI medical devices. Ministry of Food and Drug Safety Web site. https://www.mfds.go.kr/brd/m_99/view.do?seq=46379&srchFr=&srchTo=&srchWord=&srchTp=&itm_seq_1=0&itm_seq_2=0&multi_itm_seq=0&company_cd=&company_nm=&page=1. Published May 22, 2022. Accessed September 24, 2022
  24. Perneger TV. What's wrong with Bonferroni adjustments. BMJ 1998;316:1236-1238 https://doi.org/10.1136/bmj.316.7139.1236
  25. Pinto Dos Santos D, Giese D, Brodehl S, Chon SH, Staab W, Kleinert R, et al. Medical students' attitude towards artificial intelligence: a multicentre survey. Eur Radiol 2019;29:1640-1646 https://doi.org/10.1007/s00330-018-5601-1
  26. European Society of Radiology. Impact of artificial intelligence on radiology: a EuroAIM survey among members of the European Society of Radiology. Insights Imaging 2019;10:105