Skip to main content Accessibility help

An artificial intelligence algorithm that identifies middle turbinate pneumatisation (concha bullosa) on sinus computed tomography scans

  • P Parmar (a1), A-R Habib (a1), D Mendis (a1), A Daniel (a1), M Duvnjak (a1), J Ho (a1), M Smith (a1), D Roshan (a1), E Wong (a1) (a2) and N Singh (a1) (a2)...



Convolutional neural networks are a subclass of deep learning or artificial intelligence that are predominantly used for image analysis and classification. This proof-of-concept study attempts to train a convolutional neural network algorithm that can reliably determine if the middle turbinate is pneumatised (concha bullosa) on coronal sinus computed tomography images.


Consecutive high-resolution computed tomography scans of the paranasal sinuses were retrospectively collected between January 2016 and December 2018 at a tertiary rhinology hospital in Australia. The classification layer of Inception-V3 was retrained in Python using a transfer learning method to interpret the computed tomography images. Segmentation analysis was also performed in an attempt to increase diagnostic accuracy.


The trained convolutional neural network was found to have diagnostic accuracy of 81 per cent (95 per cent confidence interval: 73.0–89.0 per cent) with an area under the curve of 0.93.


A trained convolutional neural network algorithm appears to successfully identify pneumatisation of the middle turbinate with high accuracy. Further studies can be pursued to test its ability in other clinically important anatomical variants in otolaryngology and rhinology.


Corresponding author

Author for correspondence: Dr Eugene H Wong, Department of Otolaryngology, Head and Neck Surgery, Westmead Hospital, WestmeadNSW2145, Australia E-mail:


Hide All

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



Hide All
1Ozcan, KM, Selcuk, A, Ozkan, I, Akdogan, O, Dere, H. Anatomical variations of nasal turbinates. J Craniofac Surg 2008;19:1678–8210.1097/SCS.0b013e318188a29d
2Bolger, WE, Butzin, CA, Parsons, DS. Paranasal sinus bony anatomic variations and mucosal abnormalities: CT analysis for endoscopic sinus surgery. Laryngoscope 1991;101:566410.1288/00005537-199101000-00010
3Stallman, JS, Lobo, JN, Som, PM. The incidence of concha bullosa and its relationship to nasal septal deviation and paranasal sinus disease. AJNR Am J Neuroradiol 2004;25:1613–18
4El-Taher, M, AbdelHameed, WA, Alam-Eldeen, MH, Haridy, A. Coincidence of concha bullosa with nasal septal deviation; radiological study. Indian J Otolaryngol Head Neck Surg 2019;71:1918–2210.1007/s12070-018-1311-x
5.Smith, KD, Edwards, PC, Saini, TS, Norton, NS. The prevalence of concha bullosa and nasal septal deviation and their relationship to maxillary sinusitis by volumetric tomography. Int J Dent. 2010;2010:40498210.1155/2010/404982
6Kucybała, I, Janik, KA, Ciuk, S, Storman, D, Urbanik, A. Nasal septal deviation and concha bullosa - do they have an impact on maxillary sinus volumes and prevalence of maxillary sinusitis? Pol J Radiol 2017;82:126–33
7Clark, ST, Babin, RW, Salazar, J. The incidence of concha bullosa and its relationship to chronic sinonasal disease. Am J Rhinol Allergy 1989;3:11–12
8Ozkiris, M, Karacavus, S, Kapusuz, Z, Saydam, L. The impact of unilateral concha bullosa on mucociliary activity: an assessment by rhinoscintigraphy. Am J Rhinol Allergy 2013;27:54–710.2500/ajra.2013.27.3847
9Havas, TE, Lowinger, DS. Comparison of functional endonasal sinus surgery with and without partial middle turbinate resection. Ann Otol Rhinol Laryngol 2000;109:634–40
10Eren, SB, Kocak, I, Dogan, R, Ozturan, O, Yildirim, YS, Tugrul, S. A comparison of the long-term results of crushing and crushing with intrinsic stripping techniques in concha bullosa surgery. Int Forum Allergy Rhinol 2014;4:753–8
11Deutschmann, 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;123:1100–5
12Esteva, 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/nature21056
13Hoogendoorn, M, Szolovits, P, Moons, LM, Numans, ME. Utilizing uncoded consultation notes from electronic medical records for predictive modeling of colorectal cancer. Artif Intell Med 2016;69:536110.1016/j.artmed.2016.03.003
14Chowdhury, 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;9:4652
15Bur, AM, Shew, M, New, J. Artificial intelligence for the otolaryngologist: a state of the art review. Otolaryngol Head Neck Surg 2019;160:603–11
16Lloyd, GA. CT of the paranasal sinuses: study of a control series in relation to endoscopic sinus surgery. J Laryngol Otol 1990;104:477–81
17Calhoun, KH, Waggenspack, GA, Simpson, CB, Hokanson, JA, Bailey, BJ. CT evaluation of the paranasal sinuses in symptomatic and asymptomatic populations. Otolaryngol Head Neck Surg 1991;104:480–3
18Zinreich, SJ, Mattox, DE, Kennedy, DW, Chrisholm, HL, Diffley, DM, Rosenbaum, AE. Concha bullosa: CT evaluation. J Comput Assist Tomogr 1988;12:778–8410.1097/00004728-198809010-00012
19Yousem, DM, Kennedy, DW, Rosenberg, S. Ostiomeatal complex risk factors for sinusitis: CT evaluation. J Otolaryngol 1991;20:419–24
20Hatipoglu, HG, Cetin, MA, Yüksel, E. Concha bullosa types: their relationship with sinusitis, ostiomeatal and frontal recess disease. Diagn Interv Radiol 2005;11:145–9
21Badran, HS. Role of surgery in isolated concha bullosa. Clin Med Insights Ear Nose Throat 2011;4:131910.4137/CMENT.S6769
22Mehta, KS, Yousuf, A, Wazir, IA, Sideeq, K. Clinical benefits of surgical management of concha bullosa. Int J Otorhinolaryngol Head Neck Surg 2017;3:833–610.18203/issn.2454-5929.ijohns20173669
23.Mehta, R, Kaluskar, S. Endoscopic turbinoplasty of concha bullosa: long term results. Indian J Otolaryngol Head Neck Surg 2013;65(suppl 2):251–54


An artificial intelligence algorithm that identifies middle turbinate pneumatisation (concha bullosa) on sinus computed tomography scans

  • P Parmar (a1), A-R Habib (a1), D Mendis (a1), A Daniel (a1), M Duvnjak (a1), J Ho (a1), M Smith (a1), D Roshan (a1), E Wong (a1) (a2) and N Singh (a1) (a2)...


Altmetric attention score

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.