Is it useful to use computerized tomography image-based artificial intelligence modelling in the differential diagnosis of chronic otitis media with and without cholesteatoma?

• Published in: American journal of otolaryngology 2022-05, Vol.43 (3), p.103395-103395, Article 103395
• Main Authors: Eroglu, Orkun Eroğlu, Eroglu, Yeşim Eroğlu, Yildirim, Muhammed Yıldırım, Karlidag Turgut Karlıdag, Cinar, Ahmet Çınar, Akyiğit, Akyigit Abdulvahap, Kaygusuz, İrfan, Yildirim Hanefi Yıldırım, Keles Erol Keleş, Yalcin Şinasi Yalçın
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial intelligence; Cholesteatoma; Chronic otitis media; Complications; Computed tomography; Datasets; Deep learning; Diagnosis; Differential diagnosis; Ear; Ear diseases; Etiology; Hearing loss; Machine learning; Magnetic resonance imaging; Medical diagnosis; Medical imaging; Modelling; Otitis media; Patients; Temporal bone; Tomography
• ISSN: 0196-0709; 1532-818X
• DOI: 10.1016/j.amjoto.2022.103395

Cholesteatoma is an aggressive form of chronic otitis media (COM). For this reason, it is important to distinguish between COM with and without cholesteatoma. In this study, the role of artificial intelligence modelling in differentiating COM with and without cholesteatoma on computed tomography images was evaluated. The files of 200 patients who underwent mastoidectomy and/or tympanoplasty for COM in our clinic between January 2016 and January 2021 were retrospectively reviewed. According to the presence of cholesteatoma, the patients were divided into two groups as chronic otitis with cholesteatoma (n = 100) and chronic otitis without cholesteatoma (n = 100). The control group (n = 100) consisted of patients who did not have any previous ear disease and did not have any active complaints about the ear. Temporal bone computed tomography (CT) images of all patients were analyzed. The distinction between cholesteatoma and COM was evaluated by using 80% of the CT images obtained for the training of artificial intelligence modelling and the remaining 20% for testing purposes. The accuracy rate obtained in the hybrid model we used in our study was 95.4%. The proposed model correctly predicted 2952 out of 3093 CT images, while it predicted 141 incorrectly. It correctly predicted 936 (93.78%) of 998 images in the COM group with cholesteatoma, 835 (92.77%) of 900 images in the COM group without cholesteatoma, and 1181 (98.82%) of 1195 images in the normal group. In our study, it has been shown that the differentiation of COM with and without cholesteatoma with artificial intelligence modelling can be made with highly accurate diagnosis rates by using CT images. With the deep learning modelling we proposed, the highest correct diagnosis rate in the literature was obtained. According to the results of our study, we think that with the use of artificial intelligence in practice, the diagnosis of cholesteatoma can be made earlier, it will help in the selection of the most appropriate treatment approach, and the complications can be reduced.