Otitis media için evrişimsel sinir ağlarına dayalı entegre bir tanı sistemi

Otitis media (OM) bir dizi iltihaplı orta kulak rahatsızlıklarını temsil eden tıbbi bir kavramdır. OM dünya genelinde, özellikle çocukluk çağında, görülen en yaygın hastalıklardan biridir. Klinik pratikte OM tanısı, otoskop cihazıyla elde edilen orta kulak görüntüsünün kulak buran boğaz uzmanları tarafından incelenmesiyle gerçekleştirilir. İncelemenin sübjektif olarak yapılması, gözlemciler arasında değişkenliklerin ortaya çıkmasına neden olmaktadır. Aynı zamanda, bu alanda bilgisayar destekli sistemlerinin kullanımının da yeteri kadar yaygın olmadığı görülmektedir. OM rahatsızlıklarının zamanında teşhis edilememesi, hastalıkların ilerlemesine ve buna bağlı olarak da işitme, konuşma ve bilişsel rahatsızlıkların ortaya çıkmasına neden olmaktadır. Tüm bu dezavantajların üstesinden gelmek üzere, bu çalışmada OM teşhisi için önceden eğitilmiş evrişimsel sinir ağlarına dayalı entegre bir tanı sistemi önerilmiştir. Deneysel çalışmalar, Özel Van Akdamar Hastanesinde gönüllü hastalardan toplanan ve toplamda beş farklı sınıfı temsil eden 898 adet otoskop imgeleri üzerinde gerçekleştirilmiştir. Sonuç olarak, önerilen model %82.16 sınıflandırma başarısı sağlanmıştır. Evrişimsel sinir ağlarına dayalı önerilen modelin sağladığı uçtan uca öğrenme ve yüksek hassasiyetle, OM teşhisinin objektif bir şekilde yapılabilmesi ve tanı sürecinde hekimlerin karar verme sürecinin desteklenmesi sağlanabilir. Önerilen yöntem bu açılardan umut verici sonuçlar üretmiştir.

Anahtar Kelimeler:

Biyomedikal işaret işleme, Tanı sistemi, Otitis media, Evrişimsel sinir ağları

An integrated diagnosis system based on pretrained deep convolutional neural networks for Otitis media

Otitis media (OM) is a medical concept representing a range of inflammatory middle ear disorders. OM is one of the most common diseases worldwide, especially in childhood. In clinical practice, the diagnosis of OM is carried out by examining the images of the middle ear obtained via the otoscope device by specialists. The subjective examination leads to arise the variabilities among observers. At the same time, the use of computer-aided systems in this area is not common enough. Failure to diagnose OM disorders in a timely manner leads to the progression of the diseases, the emergence of hearing, speech, and cognitive disorders. To overcome all these disadvantages, an integrated diagnostic system based on the pretrained deep convolutional neural networks is proposed for the diagnosis of OM in this study. Experimental studies were carried out on 898 otoscope images, representing five different classes, collected from volunteer patients admitted to Özel Van Akdamar Hospital. As a result, the proposed model achieved 82.16% classification success. With the end-to-end learning and high sensitivity provided by the proposed model based on convolutional neural networks, OM diagnosis can be realized objectively and physicians' decision-making process can be supported using this system. The proposed method has produced promising results in these respects.

Keywords:

Biomedical signal processing, Diagnosis system, Otitis media, Convolutional neural networks,

PDF

___

[1] P. Vanneste, C. Page, Otitis media with effusion in children: Pathophysiology, diagnosis, and treatment. A review, J. Otol. 14 (2019) 33–39. doi:https://doi.org/10.1016/j.joto.2019.01.005.
[2] M.E. Pichichero, Otitis Media, Pediatr. Clin. North Am. 60 (2013) 391–407. doi:https://doi.org/10.1016/j.pcl.2012.12.007.
[3] R. Anggraeni, P. Carosone-Link, B. Djelantik, E.P. Setiawan, W.W. Hartanto, A. Ghanie, D.S. Utama, E. Lukman, S. Winarto, A.M.K. Dewi, S.P. Rahardjo, R. Djamin, T. Mulyani, K. Mutyara, C.B. Kartasasmita, E.A.F. Simões, Otitis media related hearing loss in Indonesian school children, Int. J. Pediatr. Otorhinolaryngol. 125 (2019) 44–50. doi:https://doi.org/10.1016/j.ijporl.2019.06.019.
[4] F. Öz, A. Kaytaz, E. Aksoy, Otitis media, in: I.U. Cerrahpasa Tip Fak. Surekli Tip Egit. Etkinlikleri, 2008: pp. 71–84.
[5] S. Shah-Becker, M.M. Carr, Current management and referral patterns of pediatricians for acute otitis media, Int. J. Pediatr. Otorhinolaryngol. 113 (2018) 19–21. doi:https://doi.org/10.1016/j.ijporl.2018.06.036.
[6] N. Shaikh, M. Kurs-Lasky, A. Hoberman, Modification of the acute otitis media symptom severity scale, Int. J. Pediatr. Otorhinolaryngol. 122 (2019) 170–174. doi:https://doi.org/10.1016/j.ijporl.2019.04.026.
[7] E.B. Edetanlen, B.D. Saheeb, Otitis media with effusion in Nigerian children with cleft palate: incidence and risk factors, Br. J. Oral Maxillofac. Surg. 57 (2019) 36–40. doi:https://doi.org/10.1016/j.bjoms.2018.11.015.
[8] M. Sanna, A. Russo, A. Caruso, A. Taibah, G. Piras, Color Atlas of Endo-Otoscopy, Thieme, 2017.
[9] Diagnosis and management of acute otitis media., Pediatrics. 113 (2004) 1451–1465. https://pediatrics.aappublications.org/content/pediatrics/113/5/1451.full.pdf.
[10] L.S. Goggin, R.H. Eikelboom, M.D. Atlas, Clinical decision support systems and computer-aided diagnosis in otology, Otolaryngol. Neck Surg. 136 (2007) s21–s26. doi:10.1016/j.otohns.2007.01.028.
[11] A. Kuruvilla, N. Shaikh, A. Hoberman, J. Kovačević, Automated diagnosis of otitis media: vocabulary and grammar, J. Biomed. Imaging. 2013 (2013) 27.
[12] C. Vertan, D.C. Gheorghe, B. Ionescu, Eardrum color content analysis in video-otoscopy images for the diagnosis support of pediatric otitis, ISSCS 2011 - Int. Symp. Signals, Circuits Syst. Proc. (2011) 129–132. doi:10.1109/ISSCS.2011.5978676.
[13] H. Junior, E. Comunello, S.. Costa, C.C. Dornelles, Computational Techniques for Accompaniment and Measuring of Otology Pathologies, in: Twent. IEEE Int. Symp. Comput. Med. Syst., IEEE, Maribor, Slovenia, 2007.
[14] C.K. Shie, H.T. Chang, F.C. Fan, C.J. Chen, T.Y. Fang, P.C. Wang, A hybrid feature-based segmentation and classification system for the computer aided self-diagnosis of otitis media, 2014 36th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBC 2014. (2014) 4655–4658. doi:10.1109/EMBC.2014.6944662.
[15] I. Mironica, C. Vertan, D.C. Gheorghe, Automatic pediatric otitis detection by classification of global image features, in: 2011 E-Health Bioeng. Conf., 2011: pp. 1–4.
[16] H.C. Myburgh, W.H. van Zijl, D. Swanepoel, S. Hellström, C. Laurent, Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis, EBioMedicine. 5 (2016) 156–160. doi:10.1016/J.EBIOM.2016.02.017.
[17] H.C. Myburgh, S. Jose, D.W. Swanepoel, C. Laurent, Towards low cost automated smartphone- and cloud-based otitis media diagnosis, Biomed. Signal Process. Control. 39 (2018) 34–52. doi:10.1016/j.bspc.2017.07.015.
[18] Y. Altuntaş, Z. Cömert, A.F. Kocamaz, Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach, Comput. Electron. Agric. 163 (2019) 104874. doi:https://doi.org/10.1016/j.compag.2019.104874.
[19] Z. Cömert, A.F. Kocamaz, Fetal Hypoxia Detection Based on Deep Convolutional Neural Network with Transfer Learning Approach, in: R. Silhavy (Ed.), Softw. Eng. Algorithms Intell. Syst., Springer International Publishing, Cham, 2019: pp. 239–248. doi:10.1007/978-3-319-91186-1_25.
[20] Z. Zhao, Y. Zhang, Z. Comert, Y. Deng, Computer-Aided Diagnosis System of Fetal Hypoxia Incorporating Recurrence Plot With Convolutional Neural Network, Front. Physiol. 10 (2019) 255. doi:10.3389/fphys.2019.00255.
[21] M. Cıbuk, U. Budak, Y. Guo, M.C. Ince, A. Sengur, Efficient deep features selections and classification for flower species recognition, Measurement. 137 (2019) 7–13. doi:https://doi.org/10.1016/j.measurement.2019.01.041.
[22] Y. Guo, Ü. Budak, A. Şengür, A novel retinal vessel detection approach based on multiple deep convolution neural networks, Comput. Methods Programs Biomed. 167 (2018) 43–48. doi:https://doi.org/10.1016/j.cmpb.2018.10.021.
[23] E. Deniz, A. Sengür, Z. Kadiroglu, Y. Guo, V. Bajaj, Ü. Budak, Transfer learning based histopathologic image classification for breast cancer detection, Heal. Inf. Sci. Syst. 6 (2018) 18. doi:10.1007/s13755-018-0057-x.
[24] A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, in: F. Pereira, C.J.C. Burges, L. Bottou, K.Q. Weinberger (Eds.), Proc. 25th Int. Conf. Neural Inf. Process. Syst. - Vol. 1, Curran Associates, Inc., USA, 2012: pp. 1097–1105. http://dl.acm.org/citation.cfm?id=2999134.2999257.
[25] K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, ArXiv Prepr. ArXiv1409.1556. (2014).
[26] C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in: 2015 IEEE Conf. Comput. Vis. Pattern Recognit., IEEE, 2015: pp. 1–9. doi:10.1109/CVPR.2015.7298594.
[27] K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Las Vegas, NV, USA, 2016: pp. 770–778. doi:10.1109/CVPR.2016.90.
[28] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the Inception Architecture for Computer Vision, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2016. http://arxiv.org/abs/1512.00567.
[29] A. Gómez-Ríos, S. Tabik, J. Luengo, A.S.M. Shihavuddin, B. Krawczyk, F. Herrera, Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation, Expert Syst. Appl. 118 (2019) 315–328. doi:https://doi.org/10.1016/j.eswa.2018.10.010.
[30] T. Mesut, E. Burhan, Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması, Fırat Üniversitesi Mühendislik Bilim. Derg. 31 (2019) 109–121.
[31] Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE. 86 (1998) 2278–2324. doi:10.1109/5.726791.
[32] Z. Cömert, A.F. Kocamaz, Open-access software for analysis of fetal heart rate signals, Biomed. Signal Process. Control. 45 (2018) 98–108. doi:10.1016/j.bspc.2018.05.016.
[33] M. Kazandi, F. Sendag, F. Akercan, M.C. Terek, G. Gundem, Different types of variable decelerations and their effects to neonatal outcome, Singapore Med. J. 44 (2003) 243–247.
[34] A. Diker, Z. Cömert, E. Avcı, A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals, Bitlis Eren Univ. J. Sci. Technol. 7 (2017) 132–139.
[35] A. Diker, Z. Cömert, E. Avci, S. Velappan, Intelligent system based on Genetic Algorithm and support vector machine for detection of myocardial infarction from ECG signals, in: 2018 26th Signal Process. Commun. Appl. Conf., 2018: pp. 1–4. doi:10.1109/SIU.2018.8404299.