Hostname: page-component-586b7cd67f-dsjbd Total loading time: 0 Render date: 2024-11-26T20:46:38.280Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial intelligence to detect tympanic membrane perforations

Published online by Cambridge University Press:  02 April 2020

A-R Habib ,
E Wong ,
R Sacks  and
N Singh
A-R Habib*
Affiliation:
Department of Otolaryngology – Head and Neck Surgery, Westmead Hospital, Sydney, Australia Greenslopes Private Hospital, Ramsay Health Care, Brisbane, Australia
E Wong
Affiliation:
Department of Otolaryngology – Head and Neck Surgery, Westmead Hospital, Sydney, Australia
R Sacks
Affiliation:
Department of Otolaryngology – Head and Neck Surgery, Concord General Hospital, University of Sydney, Australia Faculty of Medicine and Health Sciences, Macquarie University, Sydney, Australia
N Singh
Affiliation:
Department of Otolaryngology – Head and Neck Surgery, Westmead Hospital, Sydney, Australia
*
Author for correspondence: Dr Al-Rahim Habib, Department of Otolaryngology – Head and Neck Surgery, Westmead Hospital, Sydney, Australia E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Objective

To explore the feasibility of constructing a proof-of-concept artificial intelligence algorithm to detect tympanic membrane perforations, for future application in under-resourced rural settings.

Methods

A retrospective review was conducted of otoscopic images analysed using transfer learning with Google's Inception-V3 convolutional neural network architecture. The ‘gold standard’ ‘ground truth’ was defined by otolaryngologists. Perforation size was categorised as less than one-third (small), one-third to two-thirds (medium), or more than two-thirds (large) of the total tympanic membrane diameter.

Results

A total of 233 tympanic membrane images were used (183 for training, 50 for testing). The algorithm correctly identified intact and perforated tympanic membranes (overall accuracy = 76.0 per cent, 95 per cent confidence interval = 62.1–86.0 per cent); the area under the curve was 0.867 (95 per cent confidence interval = 0.771–0.963).

Conclusion

A proof-of-concept image-classification artificial intelligence algorithm can be used to detect tympanic membrane perforations and, with further development, may prove to be a valuable tool for ear disease screening. Future endeavours are warranted to develop a point-of-care tool for healthcare workers in areas distant from otolaryngology.

Keywords

OtoscopyEarTympanic MembraneMachine Learning
Type
Main Articles
Information
The Journal of Laryngology & Otology , Volume 134 , Issue 4 , April 2020 , pp. 311 - 315
Copyright
Copyright © JLO (1984) Limited, 2020

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 A-R Habib takes responsibility for the integrity of the content of the paper

Presented at the Australian Society of Otolaryngology – Head and Neck Annual Scientific Meeting, 22–24 March 2019, Brisbane, Australia.

References

Jiang, F, Jiang, Y, Zhi, H, Dong, Y, Li, H, Ma, S et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017;2:230–43CrossRefGoogle ScholarPubMed
McBee, MP, Awan, OA, Colucci, AT, Ghobadi, CW, Kadom, N, Kansagra, AP et al. Deep learning in radiology. Acad Radiol 2018;25:1472–80CrossRefGoogle ScholarPubMed
Liu, X, Sinha, A, Unberath, M, Ishii, M, Hager, G, Taylor, RH et al. . Self-supervised learning for dense depth estimation in monocular endoscopy. ArXiv 2018;1–11Google Scholar
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;542:115–18CrossRefGoogle ScholarPubMed
Swaminathan, S, Qirko, K, Smith, T, Corcoran, E, Wysham, G, Bazaz, G et al. A machine learning approach to triaging patients with chronic obstructive pulmonary disease. PLoS One 2017;12:1–21CrossRefGoogle ScholarPubMed
Lakhani, P, Sundaram, B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017;284:574–82CrossRefGoogle ScholarPubMed
Wang, D, Khosla, A. Deep learning for identifying metastatic breast cancer. ArXiv 2016;1–6Google Scholar
Kapoor, R, Walters, SP, Al-Aswad, LA. The current state of artificial intelligence in ophthalmology. Surv Ophthalmol 2018;64:233–40CrossRefGoogle 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 2018;9:46–52CrossRefGoogle ScholarPubMed
Halicek, M, Little, JV, Wang, X, Griffith, CC, El-Deiry, MW, Chen, AY et al. Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging. J Biomed Opt 2017;22:60503CrossRefGoogle ScholarPubMed
Liu, GS, Zhu, MH, Kim, J, Raphael, P, Applegate, BE, Oghalai, JS. ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography. Biomed Opt Express 2017;8:4579–94CrossRefGoogle ScholarPubMed
Rosenfeld, RM, Shin, JJ, Schwartz, SR, Coggins, R, Gagnon, L, Hackell, JM et al. Clinical practice guideline: otitis media with effusion executive summary (update). Otolaryngol Neck Surg 2016;154:201–14CrossRefGoogle Scholar
Dart, J. Australia's disturbing health disparities set Aboriginals apart. Bull World Health Organ 2008;86:245–7CrossRefGoogle ScholarPubMed
Morris, PS, Leach, AJ, Silberberg, P, Mellon, G, Wilson, C, Hamilton, E et al. Otitis media in young Aboriginal children from remote communities in Northern and Central Australia: a cross-sectional survey. BMC Pediatr 2005;5:27CrossRefGoogle ScholarPubMed
Gibney, K, Morris, P, Carapetis, J, Skull, S, Leach, A. Missed opportunities for a diagnosis of acute otitis media in Aboriginal children. J Paediatr Child Health 2003;39:540–2CrossRefGoogle ScholarPubMed
Gunasekera, H, Miller, HM, Burgess, L, Chando, S, Sheriff, SL, Tsembis, JD et al. Agreement between diagnoses of otitis media by audiologists and otolaryngologists in Aboriginal Australian children. Med J Aust 2018;209:29–35CrossRefGoogle ScholarPubMed
Australian Medical Association. 2017 AMA Report Card on Indigenous Health: A National Strategic Approach to Ending Chronic Otitis Media and its Life Long Impacts in Indigenous Communities. Barton, ACT: AMA, 2017Google Scholar
Gunasekera, H, Morris, PS, Daniels, J, Couzos, S, Craig, JC. Otitis media in Aboriginal children: the discordance between burden of illness and access to services in rural/remote and urban Australia. J Paediatr Child Health 2009;45:425–30CrossRefGoogle ScholarPubMed
Morris, PS, Leach, AJ, Halpin, S, Mellon, G, Gadil, G, Wigger, C et al. An overview of acute otitis media in Australian Aboriginal children living in remote communities. Vaccine 2007;25:2389–93CrossRefGoogle ScholarPubMed
Oyewumi, M, Brandt, MG, Carrillo, B, Atkinson, A, Iglar, K, Forte, V et al. Objective evaluation of otoscopy skills among family and community medicine, pediatric, and otolaryngology residents. J Surg Educ 2016;73:129–35CrossRefGoogle ScholarPubMed
Elliott, G, Smith, AC, Bensink, ME, Brown, C, Stewart, C, Perry, C et al. The feasibility of a community-based mobile telehealth screening service for Aboriginal and Torres Strait Islander children in Australia. Telemed J E Health 2010;16:950–6CrossRefGoogle ScholarPubMed
World Medical Association. World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA 2013;310:2191–4CrossRefGoogle Scholar
GIMP: GNU Image Manipulation Program. In: https://www.gimp.org/ [9 March 2020]Google Scholar
Krizhevsky, A, Sutskever, I, Hinton, GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 2012;25:1097–105Google Scholar
Asher, E, Leibovitz, E, Press, J, Greenberg, D, Bilenko, N, Reuveni, H. Accuracy of acute otitis media diagnosis in community and hospital settings. Acta Paediatr 2005;94:423–8CrossRefGoogle ScholarPubMed
Buchanan, CM, Pothier, DD. Recognition of paediatric otopathology by general practitioners. Int J Pediatr Otorhinolaryngol 2008;72:669–73CrossRefGoogle ScholarPubMed
Myburgh, HC, van Zijl, WH, Swanepoel, DW, Hellström, S, Laurent, C. Otitis media diagnosis for developing countries using tympanic membrane image-analysis. EBioMedicine 2016;5:156–60CrossRefGoogle ScholarPubMed
Seok, J, Song, J-J, Koo, J-W, Kin, H-C, Choi, BY. The semantic segmentation approach for normal and pathologic tympanic membrane using deep learning. BioRxiv 2019;In pressCrossRefGoogle Scholar
Kasher, MS. Otitis Media Analysis: An Automated Feature Extraction and Image Classification System. Helsinki: Helsinki Metropolia University of Applied Sciences, 2018Google Scholar
Wahl, B, Cossy-Gantner, A, Germann, S, Schwalbe, NR. Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings? BMJ Glob Health 2018;3:e000798CrossRefGoogle Scholar
Kenyon, G. Social otitis media: ear infection and disparity in Australia. Lancet Infect Dis 2017;17:375–6CrossRefGoogle ScholarPubMed
Nguyen, KH, Smith, AC, Armfield, NR, Bensink, M, Scuffham, PA. Cost-effectiveness analysis of a mobile ear screening and surveillance service versus an outreach screening, surveillance and surgical service for Indigenous children in Australia. PLoS One 2015;10:e0138369CrossRefGoogle ScholarPubMed