Artificial intelligence in the diagnosis of chronic purulent otitis media: Automatic analysis of otoendoscopic images and prospects for clinical implementation

Chronic suppurative otitis media is a common ENT disorder leading to persistent hearing loss and secondary intracranial complications. Given the shortage of qualified medical personnel, especially in the periphery, the implementation of automated systems for diagnosing this condition is crucial. This study examines current methods for using artificial intelligence in the analysis of otoendoscopic images obtained during the diagnosis of chronic suppurative otitis media. Key studies demonstrating the effectiveness of machine learning are considered, including architectures of convolutional neural networks and ensemble models that achieve accuracy of up to 95–97% in differentiating middle ear pathologies. Special attention is paid to comparing the results of artificial intelligence with the diagnostics of doctors: the algorithms are superior to non-specialists and comparable to experienced otorhinolaryngologists. Attention is paid to discussing the problems of heterogeneity of data, limited samples of rare forms of chronic purulent otitis media and the dependence of the result on image quality. The potential of mobile applications based on artificial intelligence for telemedicine is assessed, and the need to create large-scale annotated databases for model training is highlighted. The integration of artificial intelligence into medicine promises to significantly improve the quality and accessibility of medical care. The use of AI solutions in clinical settings can significantly improve early disease detection procedures, which, in turn, will enable timely intervention. At the same time, the implementation of these systems can significantly reduce the workload of medical personnel, freeing them up to perform more complex and demanding tasks. Furthermore, the use of advanced AI algorithms can minimize the likelihood of unwanted complications, which is especially important for remote areas and regions where access to highly specialized medical care is often limited.

1. Гаров ЕВ, Диаб ХМ, Карнеева ОВ, Юнусов АС, Аникин ИА, Завалий МА и др. Хронический средний отит: клинические рекомендации. 2024. Режим доступа: https://cr.minzdrav.gov.ru/preview-cr/698_2.

2. Khatamov JA, Amonov Sh, Nasretdinova MT, Khaitov AA. Main Directions in Diagnostics and Treatment of Complicated Forms of Chronic Purulent Otitis Medium. Otolaryngology. Eastern Europe. 2024;(3):358–367. (In Russ.) https://doi.org/10.34883/PI.2024.14.3.018.

3. Garov EV, Garova EE. Modern principles of diagnosis and treatment of patients with chronic suppurative otitis media. RMJ. 2012;(27):1355–1359. (In Russ.) Available at: https://www.rmj.ru/articles/otorinolaringologiya/Covremennye_principy_diagnostiki_i_lecheniya_pacientov_s_hronicheskim_ gnoynym_srednim_otitom.

4. Dementieva N, Shilenkov A. Comparative assessment of the diagnostic capabilities of otoscopy, otomicroscopy, otoendoscopy in patients with chronic middle ear diseases. Kremlin Medicine. Clinical Bulletin. 2014;(1):18–22. (In Russ.) Available at: https://kremlin-medicine.ru/index.php/km/article/view/98.

5. Dement’eva NF, Shilenkov AA, Kozlov VS. Otoendoscopy for the diagnosis of chronic middle ear diseases. Vestnik Otorinolaringologii. 2010;(1):71–75. (In Russ.) Available at: https://www.mediasphera.ru/issues/vestnikotorinolaringologii/2010/1.

6. Novozhilov AA, Shilyagin PA, Shakhov AV, Gelikonov VM. Overview of modern methods for the diagnosis of exudative otitis media. Vestnik Otorinolaringologii. 2020;85(3):68–74. (In Russ.) https://doi.org/10.17116/otorino20208503168.

7. Ageenko IV. Transmeatal aerodynamical otoendoscopy for otitis media. Vestnik Otorinolaringologii. 2012;77(5):31–33. (In Russ.) Available at: https://www.mediasphera.ru/issues/vestnik-otorinolaringologii/2012/5/030042-4668201256.

8. Garov EV. Chronic suppurative otitis media: terminology, diagnostics and treatment tactics. RMJ. 2011;(6):390–393. (In Russ.) Available at: https://www.rmj.ru/articles/otorinolaringologiya/Hronicheskiy_gnoynyy_sredniy_otit_terminologiya_diagnostika_i_lechebnaya_taktika.

9. Pozdeeva TV, Kochkurova EA, Doschannikova OA, Noskova VA, Kochkurov AS. An integrated approach to the problem of staffing medical organizations in rural area in the region of Nizhny Novgorod. Profilakticheskaya Meditsina. 2020;23(5):25–32. (In Russ.) https://doi.org/10.17116/profmed20202305125.

10. Kalininskaya AA, Son IM, Shlyafer SI. The problems and perspectives of development of rural health care. Problems of Social Hygiene, Public Health and History of Medicine. 2019;(2):152–157. (In Russ.) Available at: https://journal-nriph.ru/journal/issue/viewIssue/2/pdf_1.

11. Koroleva GP, Lukyanova VV. The problem of middle-grade medical staffing in budgetary health organizations (The case of Samara region). Expert: Theory and Practice. 2020;6(9):76–79. (In Russ.) https://doi.org/10.24411/2686-7818-2020-10058.

12. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation. 1989;1(4):541–551. https://doi.org/10.1162/neco.1989.1.4.541.

13. Bredikhin AI. Training algorithms for convolutional neural networks. Yugra State University Bulletin. 2019;(1):41–54. (In Russ.) https://doi.org/10.17816/byusu20190141-54.

14. Skripachev VO, Guida MV, Guida NV, Zhukov AO. Investigation of convolutional neural networks for object detection in aerospace images. International Journal of Open Information Technologies. 2022;10(7):54–64. (In Russ.) Available at: https://www.injoit.org/index.php/j1/article/view/1308.

15. Skripachev VO, Guida MV, Guida NV, Zhukov AO. Features of convolutional neural networks. International Journal of Open Information Technologies. 2022;10(12):53–61. (In Russ.) Available at: https://www.injoit.org/index.php/j1/article/view/1395.

16. Mamedova LE, Ivanova LN, Altaev ES. Key aspects of artificial intelligence technology. News of Higher Education Institutions. Series: Economics, Finance, and Production Management. 2023;(3):78–88. (In Russ.) Available at: https://ecofin-isuct.ru/article/view/5211.

17. Utegenov NB. Artificial intelligence today. Universum: Technical Sciences: Electronic Scientific Journal. 2022;(7-1):27–30. (In Russ.) Available at: https://7universum.com/ru/tech/archive/item/14087.

18. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016;316(22):2402–2410. https://doi.org/10.1001/jama.2016.17216.

19. Dobrov ER. The use of neural networks in the diagnosis of diabetic retinopathy. Models, Systems, and Networks in economics, Engineering, Nature, and Society. 2022;(2):90–105. (In Russ.) Available at: https://mss.pnzgu.ru/mss7222.

20. Wong TY, Bressler NM. Artificial Intelligence with Deep Learning Technology Looks Into Diabetic Retinopathy Screening. JAMA. 2016;316(22):2366–2367. https://doi.org/10.1001/jama.2016.17563.

21. Mamedov TH, Dzjuba DV, Narkevich AN. Application of convolutional neural networks for recognition of diabetic retinopathy in digital images. Siberian Medical Review. 2022;(1):83–87. (In Russ.) https://doi.org/10.20333/25000136-2022-1-83-87.

22. Abdelhafiz D, Yang C, Ammar R, Nabavi S. Deep convolutional neural networks for mammography: advances, challenges and applications. BMC Bioinformatics. 2019;20(Suppl. 11):281. https://doi.org/10.1186/s12859019-2823-4.

23. Qu J, Zhao X, Chen P, Wang Z, Liu Z, Yang B, Liet H. Deep learning on digital mammography for expert-level diagnosis accuracy in breast cancer detection. Multimedia Systems. 2022;28:1263–1274. https://doi.org/10.1007/s00530-021-00823-4.

24. Yu H, Li J, Zhang L, Cao Y, Yu X, Sun J. Design of lung nodules segmentation and recognition algorithm based on deep learning. BMC Bioinformatics. 2021;22(Suppl. 5):314. https://doi.org/10.1186/s12859-021-04234-0.

25. Mehldo AA, Utkin LV, Moiseenko VM. XXI Century diagnostic algorithms. Artifitial intelligance in lung cancer detection. Practical Oncology. 2018;(3):292–298. (In Russ.) https://doi.org/10.31917/1903292.

26. Zeng X, Jiang Z, Luo W, Li H, Li H, Li G. Efficient and accurate identification of ear diseases using an ensemble deep learning model. Sci Rep. 2021;11(1):10839. https://doi.org/10.1038/s41598-021-90345-w.

27. Myburgh H, Jose S, Swanepoel DW, Laurent C. Towards low cost automated smartphoneand cloud-based otitis media diagnosis. Biomedical Signal Processing and Control. 2018;39:34–52. https://doi.org/10.1016/j.bspc.2017.07.015.

28. Sandström J, Myburgh H, Laurent C, Swanepoel DW, Lundberg T. A Machine Learning Approach to Screen for Otitis Media Using Digital Otoscope Images Labelled by an Expert Panel. Diagnostics. 2022;12(6):1318. https://doi.org/10.3390/diagnostics12061318.

29. Viscaino M, Talamilla M, Maass JC, Henríquez P, Délano PH, Auat Cheein C. Color Dependence Analysis in a CNN-Based Computer-Aided Diagnosis System for Middle and External Ear Diseases. Diagnostics. 2022;12(4):917. https://doi.org/10.3390/diagnostics12040917.

30. Viscaino M, Maass JC, Delano PH, Torrente M, Stott C, Auat Cheein F. Computeraided diagnosis of external and middle ear conditions: A machine learning approach. PLoS ONE. 2020;15(3):e0229226. https://doi.org/10.1371/journal.pone.0229226.

31. Cha D, Pae C, Seong SB, Choi JY, Park HJ. Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database. EBioMedicine. 2019;45:606–614. https://doi.org/10.1016/j.ebiom.2019.06.050.

32. Cai Y, Yu JG, Chen Y, Liu C, Xiao L, Grais EM et al. Investigating the use of a two-stage attention-aware convolutional neural network for the automated diagnosis of otitis media from tympanic membrane images: a prediction model development and validation study. BMJ Open. 2021;11(1):e041139. https://doi.org/10.1136/bmjopen-2020-041139.

33. Livingstone D, Chau J. Otoscopic diagnosis using computer vision: An automated machine learning approach. Laryngoscope. 2020;130(6):1408–1413. https://doi.org/10.1002/lary.28292.

34. Khan MA, Kwon S, Choo J, Hong SM, Kang SH, Park IH et al. Automatic detection of tympanic membrane and middle ear infection from otoendoscopic images via convolutional neural networks. Neural Netw. 2020;126:384–394. https://doi.org/10.1016/j.neunet.2020.03.02328.

35. Byun H, Yu S, Oh J, Bae J, Yoon MS, Lee SH et al. An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases. J Clin Med. 2021;10(15):3198. https://doi.org/10.3390/jcm10153198.

36. Habib AR, Kajbafzadeh M, Hasan Z, Wong E, Gunasekera H, Perry C et al. Artificial intelligence to classify ear disease from otoscopy: A systematic review and meta-analysis. Clin Otolaryngol. 2022;47(3):401–413. https://doi.org/10.1111/coa.13925.

37. Chen YC, Chu YC, Huang CY, Lee YT, Lee WY, Hsu CY. Smartphone-based artificial intelligence using a transfer learning algorithm for the detection and diagnosis of middle ear diseases: A retrospective deep learning study. EClinicalMedicine. 2022;51:101543. https://doi.org/10.1016/j.eclinm.2022.101543.

38. Zeng J, Deng W, Yu J, Xiao L, Chen S, Zhang X. A deep learning approach to the diagnosis of atelectasis and attic retraction pocket in otitis media with effusion using otoscopic images. Eur Arch Otorhinolaryngol. 2023;280(4):1621–1627. https://doi.org/10.1007/s00405-022-07632-z.

39. Alhudhaif A, Cömert Z, Polat K. Otitis media detection using tympanic membrane images with a novel multi-class machine learning algorithm. PeerJ Comput Sci. 2021;7:e405. https://doi.org/10.7717/peerj-cs.405.