Hostname: page-component-586b7cd67f-t8hqh Total loading time: 0 Render date: 2024-11-22T20:17:48.507Z Has data issue: false hasContentIssue false

An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans

Published online by Cambridge University Press:  23 December 2019

J Huang
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
A-R Habib
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
D Mendis
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
J Chong
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
M Smith
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
M Duvnjak
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
C Chiu
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia
N Singh
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia Faculty of Medicine and Health Sciences, University of Sydney, Australia
E Wong*
Affiliation:
Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, Australia Faculty of Medicine and Health Sciences, University of Sydney, Australia
*
Author for correspondence: Dr Eugene H Wong, Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, University of Sydney, Sydney, Australia E-mail: [email protected]

Abstract

Objective

Deep learning using convolutional neural networks represents a form of artificial intelligence where computers recognise patterns and make predictions based upon provided datasets. This study aimed to determine if a convolutional neural network could be trained to differentiate the location of the anterior ethmoidal artery as either adhered to the skull base or within a bone ‘mesentery’ on sinus computed tomography scans.

Methods

Coronal sinus computed tomography scans were reviewed by two otolaryngology residents for anterior ethmoidal artery location and used as data for the Google Inception-V3 convolutional neural network base. The classification layer of Inception-V3 was retrained in Python (programming language software) using a transfer learning method to interpret the computed tomography images.

Results

A total of 675 images from 388 patients were used to train the convolutional neural network. A further 197 unique images were used to test the algorithm; this yielded a total accuracy of 82.7 per cent (95 per cent confidence interval = 77.7–87.8), kappa statistic of 0.62 and area under the curve of 0.86.

Conclusion

Convolutional neural networks demonstrate promise in identifying clinically important structures in functional endoscopic sinus surgery, such as anterior ethmoidal artery location on pre-operative sinus computed tomography.

Type
Main Articles
Copyright
Copyright © JLO (1984) Limited, 2019

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

Dr E H Wong takes responsibility for the integrity of the content of the paper

References

White, DV, Sincoff, EH, Abdulrauf, SI. Anterior ethmoidal artery: microsurgical anatomy and technical considerations. Neurosurgery 2005;56:406–10Google ScholarPubMed
Pernas, FG, Coughlin, AM, Hughes, SE, Riascos, R, Maeso, PA. A novel use of a landmark to avoid injury of the anterior ethmoidal artery during endoscopic sinus surgery. Am J Rhinol Allergy 2011;25:54–710.2500/ajra.2011.25.3541CrossRefGoogle ScholarPubMed
Poteet, PS, Cox, MD, Wang, RA, Fitzgerald, RT, Kannan, A. Analysis of the relationship between the location of the anterior ethmoid artery and Keros classification. Otolaryngol Head Neck Surg 2017;157:320–410.1177/0194599817696302CrossRefGoogle ScholarPubMed
Yang, Y, Lu, Q, Liao, J, Dang, R. Morphological characteristics of the anterior ethmoidal artery in ethmoid roof and endoscopic localization. Skull Base 2009;19:311–1710.1055/s-0028-1115323CrossRefGoogle ScholarPubMed
Error, M, Ashby, S, Orlandi, RR, Alt, JA. Single-blinded prospective implementation of a preoperative imaging checklist for endoscopic sinus surgery. Otolaryngol Head Neck Surg 2018;158:177–8010.1177/0194599817731740CrossRefGoogle ScholarPubMed
O'Brien, WT Sr, Hamelin, S, Weitzel, EK. The preoperative sinus CT: avoiding a “CLOSE” call with surgical complications. Radiology 2016;281:102110.1148/radiol.2016152230CrossRefGoogle ScholarPubMed
Yamashita, R, Nishio, M, Do, RK, Togashi, K. Convolutional neural networks: an overview and application in radiology. Insights Imaging 2018;9:611–1910.1007/s13244-018-0639-9CrossRefGoogle ScholarPubMed
Lakhani, P, Sundaram, B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017;284:574–8210.1148/radiol.2017162326CrossRefGoogle ScholarPubMed
Du, X, Li, W, Hu, B. Application of artificial intelligence in ophthalmology. Int J Ophthalmol 2018;11:1555–61Google ScholarPubMed
Esteva, A, Kuprel, B, Novoa, RA, Ko, J, Swetter, SM, Blau, HM et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542:115–1810.1038/nature21056CrossRefGoogle ScholarPubMed
Chowdhury, NI, Smith, TL, Chandra, RK, Turner, JH. Automated classification of osteomeatal complex inflammation on computed tomography using convolutional neural networks. Int Forum Allergy Rhinol 2019;9:465210.1002/alr.22196CrossRefGoogle ScholarPubMed
Deutschmann, MW, Yeung, J, Bosch, M, Lysack, JT, Kingstone, M, Kilty, SJ et al. Radiologic reporting for paranasal sinus computed tomography: a multi-institutional review of content and consistency. Laryngoscope 2013;123:1100–510.1002/lary.23906CrossRefGoogle ScholarPubMed
Baltrusaitis, T, Ahuja, C, Morency, LP. Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 2019;41:423–4310.1109/TPAMI.2018.2798607CrossRefGoogle ScholarPubMed