International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Classification of Tympanic Membrane Images Based on Deep Learning Model

Hamid S. MahmoodTechnical Engineering College, Northern Technical University, Mosul, IraqMarwan D. MarwanTechnical Engineering College, Northern Technical University, Mosul, IraqMena L. BasheerTechnical Engineering College, Northern Technical University, Mosul, IraqHafsah R. AmjedTechnical Engineering College, Northern Technical University, Mosul, IraqMarwa Mawfaq Mohamedsheet Al-HatabTechnical Engineering College, Northern Technical University, Mosul, Iraq

Vol 9 No 5 (2025): Volume 9, Issue 5, May 2025 | Pages: 42-50

International Research Journal of Innovations in Engineering and Technology

OPEN ACCESS | Research Article | Published Date: 12-05-2025

doi Logo doi.org/10.47001/IRJIET/2025.905005

pdf iconFull Text PDF
Abstract

This  study  investigates  the  application  of  Artificial  Intelligence  (AI)  techniques,  particularly  Convolutional  Neural  Networks  (CNNs),  for  the  diagnosis  of  tympanic  membrane  diseases.  A  dataset  comprising  956  tympanic  membrane  images  was  collected  from  various  sources,  representing  conditions  such  as  acute  otitis  media,  chronic  otitis  media,  foreign  body  presence,  tympanosclerosis,  and  other  prevalent  disorders  affecting  the  middle  ear  and  tympanic  membrane.  The images were preprocessed and utilized for training and testing using deep learning methodologies. Several deep  learning  models  were  developed  and  evaluated  on  the  dataset,  with  systematic  optimization  of  hyperparameters,  including  the  number  of  filters,  filter  sizes,  and  pooling  strategies  such  as  Max  Pooling  and  Average  Pooling,  to  enhance  classification  performance.  The proposed models were assessed  based  on  a  range  of  metrics,  and  the  optimal  CNN-based  model  achieved  an  accuracy  of  86.47%  in  classifying  the  diseases.  The  findings  of  this  study  underscore  the  potential  of  AI-driven  solutions  to  improve  medical  diagnostics  by  offering  reliable  and  efficient  tools  to  assist  healthcare  professionals  in  the  accurate  identification  of  tympanic  membrane  diseases. Future  work  is  recommended  to  explore  advanced  deep  learning  architectures  and  expand  the  dataset  to  further  enhance  accuracy  and  generalizability  across  diverse  medical  applications.

Keywords

Classification, Deep Learning, DL, Feature extraction


Citation of this Article

Hamid S. Mahmood, Marwan D. Marwan, Mena L. Basheer, Hafsah R. Amjed, & Marwa Mawfaq Mohamedsheet Al-Hatab. (2025). Classification of Tympanic Membrane Images Based on Deep Learning Model. International Research Journal of Innovations in Engineering and Technology - IRJIET, 9(5), 42-50. Article DOI https://doi.org/10.47001/IRJIET/2025.905005

Licence Copyright (c) 2026 International Research Journal of Innovations in Engineering and Technology creative common licence This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
References
  1. H. W. Gelfand, Essentials of Audiology, 4th ed. New York, NY, USA: Thieme, 2016.
  2. M. R. Clark and A. P. Smith, "Hearing loss and middle ear pathologies: A clinical overview," Otolaryngology Clinics, vol. 52, no. 1, pp. 23–38, 2020.
  3. L. K. Hunter et al., "Otitis media: Diagnosis, management, and complications," Pediatrics Review, vol. 41, no. 5, pp. 220–235, 2019.
  4. S. S. Mehta et al., "Variability in diagnosing tympanic membrane abnormalities: A systematic review," Journal of Otolaryngology Research, vol. 15, no. 2, pp. 101–115, 2021.
  5. J. C. Wang et al., "Artificial intelligence in otoscopic image analysis: A review," IEEE Transactions on Biomedical Engineering, vol. 69, no. 4, pp. 1172–1185, 2022.
  6. A.Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems (NIPS), vol. 25, pp. 1097–1105, 2012.
  7. C. Szegedy et al., "Rethinking the Inception architecture for computer vision," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 2818–2826.
  8. J. D. Livingstone et al., "Deep learning-based classification of otoscopic images for eardrum abnormalities," IEEE Access, vol. 8, pp. 182332–182341, 2020.
  9. M. Mohammad, W. R. Fathel, H. D. Ali, and M. M. Al-Hatab, "Enhanced non-invasive blood glucose monitoring system employing wearable optical technology," Fusion: Practice and Applications (FPA), vol. 19, no. 1, Jan. 2025. DOI: 10.54216/FPA.190101.
  10. K. H. J. Al-Bahar, "Integrated artificial intelligence approach for diabetic foot ulcer assessment: A comprehensive solution for precision diagnosis and patient care," Adv. Knowl.-Based Syst. Data Sci. Cybersecurity Res., vol. 1, no. 1, p. 4, 2024.
  11. M. A. Malla et al., "Adopting machine learning to automatically identify a suitable surgery type for refractive error patients," Jurnal Kejuruteraan, vol. 36, no. 4, pp. 1749–1757, 2024.
  12. M. M. M. Al-Hatab, A. S. I. Al-Obaidi, and M. A. Al-Hashim, "Exploring CIE Lab color characteristics for skin lesion images detection: A novel image analysis methodology incorporating color-based segmentation and luminosity analysis," Fusion: Practice and Applications, vol. 15, no. 1, pp. 88–97, 2024.
  13. R. R. O. Al-Nima, M. M. M. Al-Hatab, and M. A. Qasim, "An artificial intelligence approach for verifying persons by employing the deoxyribonucleic acid (DNA) nucleotides," J. Electr. Comput. Eng., vol. 2023, no. 1, Art. no. 6678837, 2023.
  14. W. R. Fathel, M. M. Al-Hatab, and M. A. Qasim, "Classification of ECG signals based on k-nearest neighbors (k-NN) algorithm," Eurasian J. Eng. Technol., vol. 16, Mar. 2023, ISSN: 2795-7640.
  15. E. Basaran, "Tympanic membrane / eardrum dataset / otitis media," Kaggle, 2024. [Online]. Available: https://www.kaggle.com/datasets/erdalbasaran/eardrum-dataset-otitis-media. [Accessed: Feb. 21, 2025].
  16. M. L. Kolhe, M. C. Trivedi, S. Tiwari and V. K. Singh, "Advances in Data and Information Sciences.," Proceedings of ICDIS, vol. 1, 2017.
  17. Z. B. Tekulu and S. Wenxuan, "Schizophrenia Disease Classification with Deep learning and Convolutional Neural Network Architectures using TensorFlow.," 2019.
  18. K. Yasaka, H. Akai, O. Abe and S. Kiryu, "Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-Enhanced CT: A Preliminary Study.," Radiology, vol. 3, no. 286, 2018.
  19. Y. Lecun,, "Generalization and Network Design Strategies.," Connectionism in perspective, vol. 19, no. 143, 1989.
  20. S. Sudha, K. B. Jayanthi, C. Rajasekaran, N. Madian and T. Sunder, "Convolutional neural network for segmentation and measurement of intima media thickness.," Journal of medical systems, vol. 8, no. 42, 2018.
  21. S. Savaş, N. Topaloğlu, Ö. Kazcı and P. N. Koşar, , "Classification of Carotid Artery Intima Media Thickness Ultrasound Images with Deep Learning.," Journal of medical systems, vol. 8, no. 43, 2019.
  22. C. Zhou, H. P. Chan, S. Patel, P. N. Cascade, B. Sahiner, L. M. Hadjiiski and E. A. Kazerooni, "Preliminary Investigation of Computer-aided Detection of Pulmonary Embolism in Three Dimensional Computed Tomography Pulmonary Angiography Iimages.," Academic radiology, vol. 6, no. 12, 2005.
  23. T. Mahmood, M. Arsalan, M. Owais, M. B.Lee and K. R. Park, "Artificial Intelligence-Based Mitosis Detection in Breast Cancer Histopathology Images Using Faster R-CNN and Deep CNNs.," Journal of Clinical Medicine, vol. 3, no. 9, 2020.
  24. S. Iqbal, M. U. Ghani, T. Saba, and A. Rehman, "Brain Tumor Segmentation in Multi‐spectral MRI Using Cconvolutional Neural Networks (CNN). ," Microscopy research and technique, vol. 4, no. 81, 2018.
  25. A.Yuan, G. Bai, L. Jiao and Y. Liu, "Offline Handwritten English Character Recognition Based on Convolutional Neural Network. In: 2012 10th IAPR International Workshop on Document Analysis Systems", IEEE, 2012.
  26. A.Krizhevsky, I. Sutskever and G. E. Hinton, "Imagenet Classification with Deep Convolutional Neural Networks", In: Advances in neural information processing systems. 2012.
  27. J. Yangqing, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick , T. Darrell, "Caffe: Convolutional Architecture for Fast Feature Embedding", In: Proceedings of the 22nd ACM international conference on Multimedia., 2014.
  28. K. Christoff, G. Glover, R. Charms, "Learned Regulation of Spatially Localized Brain Activation Using Real-time fMRI," Neuroimage, vol. 21, no. 436, 2004.
  29. P. Khaire, P. Kumar and J. Imran, "Combining CNN streams of RGB-D and Skeletal Data for Human Activity Recognition", Pattern Recognition Letters, 2018.‏
  30. R. R. O. Al-Nima, "Signal Processing and Machine Learning Techniques for Human Verification Based on Finger Textures.," Newcastle University., 2017.
  31. R. R. Omar, T. Han, S. A. Al-Sumaidaee and T. Chen, "Deep Finger Texture Learning for Verifying People.," IET Biometrics, vol. 1, no. 8, 2018.
  32. C. L. Huang and C. Y. Tsai,  "A hybrid SOFM-SVR with a Filter-based Feature Selection for Stock Market Forecasting",  Expert Systems with Applications, vol. 2, no. 36, 2009.
  33. J. Brownlee, "A Gentle Introduction to Padding and Stride for Convolutional Neural Networks". 2019.
  34. A.Khan, A. Sohail, U.  Zahoora and A. S. Qureshi, "A Survey of the Recent Architectures of Deep Convolutional Neural Networks", Artificial Intelligence Review, 2019.
  35. M. Ahmed, F. Girshick, R. Zitnick, L. Batra, D. Cogswell, "Reducing Overfitting in Deep Networks by Decorrelating Representations", arXiv preprint arXiv:1511.06068., 2015.
  36. W. Ma and J. Lu, "An Equivalence of Fully Connected Layer and Convolutional Layer", arXiv preprint arXiv:1712.01252, 2017.‏

Copyright @ 2026 IRJIET. All Right Reserved.

Licensed underCreative Commons Attribution 4.0 International License.