Home About us Editorial board Search Ahead of print Current issue Archives Submit article Instructions Contacts Login 
Home Print this page Email this page Users Online: 65



 
 Table of Contents  
EDITORIAL
Year : 2018  |  Volume : 6  |  Issue : 1  |  Page : 1-2

Artificial intelligence in dentomaxillofacial radiology: Hype or future?


Independent Unit of Propaedeutics of Dentomaxillofacial Radiology, Medical University of Lublin, Lublin, Poland

Date of Web Publication26-Apr-2018

Correspondence Address:
Ingrid Rozylo-Kalinowska
Independent Unit of Propaedeutics of Dentomaxillofacial Radiology, Medical University of Lublin, Lublin
Poland
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/jomr.jomr_11_18

Rights and Permissions

How to cite this article:
Rozylo-Kalinowska I. Artificial intelligence in dentomaxillofacial radiology: Hype or future?. J Oral Maxillofac Radiol 2018;6:1-2

How to cite this URL:
Rozylo-Kalinowska I. Artificial intelligence in dentomaxillofacial radiology: Hype or future?. J Oral Maxillofac Radiol [serial online] 2018 [cited 2018 Sep 21];6:1-2. Available from: http://www.joomr.org/text.asp?2018/6/1/1/231359



From the onset of radiology in the end of the 19th century, this discipline has always been considered related to visual skills and image reporting has been subjective. The famous sentence “the eye sees only what the mind is prepared to comprehend” (by some attributed to the French philosopher Henri Bergson and by others to a Canadian novelist Robertson Davies) is the best description of radiology. As adepts, we discover fewer findings in radiographs or cross-sectional imaging studies not only because our eyes are not attentive enough but also due to the fact that our knowledge is still inadequate and experience meager. We may overlook some signs and symptoms when we are not aware that they may occur and do not systematically look for them in radiographs. By and by we gain experience and our reports become more and more sophisticated. However, with time passing by routine takes over, fatigue, aging, and even professional burn out induced by an increasing workload may again negatively influence our quality of reporting. Even if our enthusiasm for work is not worn out by daily labor, increase in numbers of newly qualified radiologists does not go hand in hand with rising numbers of panoramics and cone beam computed tomography scans performed day in day out all over the world. This hiatus is even more striking in dentomaxillofacial radiology as the specialists are sparse and radiographic machines installed in dental offices prolific. One of the solutions would be to train more specialists but still there are many countries, in which dentomaxillofacial radiology is not recognized as a separate specialty and no specialists are trained at all apart from some enthusiastic hotheads dedicated to this discipline. Can the so-called “artificial intelligence” (AI)[2] – or rather to be precise – machine learning as its core component-be the solution? Some consider it a threat to humans and others treat it as a kind of enhancement of our skills. Can “intelligent” machines replace radiologists and put them out of business as AI algorithm are operational 24/7 at lower costs than humans? Maybe the machines can simply aid radiologists in their daily routines?[3],[4] For example, to relieve them from the burden of tiresome, reporting of impacted canines thus generating more time for radiologists to focus on more difficult cases and/or interventional procedures. Can deep learning machines improve our efficiency and accuracy of diagnostics resulting in a better patient outcome? Will AI change the landscape of clinical practice and scientific research? Or simply create faster turnaround times and result in a better quality of life for radiologists? When writing this editorial I could retrieve only one pilot study directly related to dentomaxillofacial radiology and dealing with an automated technique used to stage lower third molar development on panoramic radiographs for age estimation.[1] The easiest fields for the evaluation of efficiency of application of AI are diagnostics of lung nodules and breast cancer screening, so no wonder that papers and websites dealing with these issues are numerous.[5],[6] However, they are by far outnumbered by sensational debates on pros and cons of artificial intelligence.[7] So, is machine learning just a hype or the brightest future of dentomaxillofacial radiology?[8] Let's wait and see!



 
  References Top

1.
De Tobel J, Radesh P, Vandermeulen D, Thevissen PW. An automated technique to stage lower third molar development on panoramic radiographs for age estimation: A pilot study. J Forensic Odontostomatol 2017;2:42-54.  Back to cited text no. 1
    
2.
Dreyer K, Allen B. Artificial intelligence in health care: Brave new world or golden opportunity? J Am Coll Radiol 2018. pii: S1546-1440(18)30032-2.  Back to cited text no. 2
    
3.
Mayo RC, Leung J. Artificial intelligence and deep learning – Radiology's next frontier? Clin Imaging 2017;49:87-8.  Back to cited text no. 3
    
4.
Miller DD, Brown EW. Artificial intelligence in medical practice: The question to the answer? Am J Med 2018;131:129-33.  Back to cited text no. 4
    
5.
Syeda-Mahmood T. Role of big data and machine learning in diagnostic decision support in radiology. J Am Coll Radiol 2018;15:569-76.  Back to cited text no. 5
    
6.
Thrall JH, Li X, Li Q, Cruz C, Do S, Dreyer K, et al. Artificial intelligence and machine learning in radiology: Opportunities, challenges, pitfalls, and criteria for success. J Am Coll Radiol 2018;15:504-8.  Back to cited text no. 6
    
7.
Xing L, Krupinski EA, Cai J. Artificial intelligence will soon change the landscape of medical physics research and practice. Med Phys 2018.  Back to cited text no. 7
    
8.




 

Top
 
 
  Search
 
Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
Access Statistics
Email Alert *
Add to My List *
* Registration required (free)

 
  In this article
References

 Article Access Statistics
    Viewed563    
    Printed50    
    Emailed0    
    PDF Downloaded129    
    Comments [Add]    

Recommend this journal


[TAG2]
[TAG3]
[TAG4]