FEATURE SELECTION USING NEIGHBORHOOD COMPONENT ANALYSIS WITH DEEP LEARNING-BASED FOR MULTI-CLASSIFICATION OF MIDDLE AND EXTERNAL EAR CONDITIONS

Abstract

Ear diseases are common in childhood and significantly increase the probability of developing serious complications, such as speech disorders, intracranial infection, and hearing loss. Otoscopic examination is crucial for diagnosing middle and external ear diseases. Deep learning-based computer-aided systems hold great promise for the automatic evaluation of otoscopic images and the prediction of patient outcomes. In the study, an image processing-based model was developed for the multi-classification of middle and external ear diseases. We employed histogram equalization for image enhancement and then employed the bilateral filter to reduce the noise of otoscopic images. Image feature vectors were extracted using ResNet101, DenseNet201, AlexNet, and VGG19 models. The neighborhood component analysis (NCA) was employed for distinctive feature selection. Then, the performances of classification models, including bidirectional long-short-term memory (B-LSTM), convolutional neural networks (CNNs), decision tree (DT), support vector machine (SVM), and k-nearest neighbor (KNN), were compared. The B-LSTM algorithm with the NCA feature selection method reached the highest performance and promising results with 0.985 kappa statistics, 0.988 weighted-F1 score, and 98.86% accuracy. The results demonstrated that the image processing-based deep learning model can accurately and efficiently detect middle and external ear diseases from otoscopic images. Moreover, the study outperformed the known related studies.

Keywords

• Deep learning
• Ear conditions
• Image processing
• Neighborhood component analysis
• Transfer learning.

References

1. H. M. Afify, K. K. Mohammed, and A. E. Hassanien, “Insight into automatic image diagnosis of ear conditions based on optimized deep learning approach,” Ann. Biomed. Eng., vol. 52, pp. 865–876, 2024, doi: 10.1007/s10439-023-03422-8.
2. K. Graydon, C. Waterworth, H. Miller, and H. Gunasekera, “Global burden of hearing impairment and ear disease,” J. Laryngol. Otol., vol. 133, pp. 18–25, 2019, doi: 10.1017/S0022215118001275.
3. J. Won et al., “Handheld briefcase optical coherence tomography with real-time machine learning classifier for middle ear infections,” Biosensors, vol. 11, p. 143, 2021, doi: 10.3390/bios11050143.
4. R. DeAntonio, J. P. Yarzabal, J. P. Cruz, J. E. Schmidt, and J. Kleijnen, “Epidemiology of otitis media in children from developing countries: A systematic review,” Int. J. Pediatr. Otorhinolaryngol., vol. 85, pp. 65–74, 2016, doi: 10.1016/j.ijporl.2016.03.032.
5. L. Monasta et al., “Burden of disease caused by otitis media: systematic review and global estimates,” PLoS One, vol. 7, no. 4, p. e36226, 2012, doi: 10.1371/journal.pone.0036226.
6. S. Tong, C. Amand, A. Kieffer, and M. H. Kyaw, “Trends in healthcare utilization and costs associated with acute otitis media in the United States during 2008–2014,” BMC Health Serv. Res., vol. 18, p. 1, 2018, doi: 10.1186/s12913-018-3139-1.
7. H. C. Myburgh, W. H. van Zijl, D. Swanepoel, S. Hellstrom, and C. Laurent, “Otitis media diagnosis for developing countries using tympanic membrane image-analysis,” EBioMedicine, vol. 5, pp. 156–160, 2016, doi: 10.1016/j.ebiom.2016.02.017.
8. A. Granath, “Recurrent acute otitis media: What are the options for treatment and prevention?” Curr. Otorhinolaryngol. Rep., vol. 5, pp. 93–100, 2017, doi: 10.1007/s40136-017-0151-7.

9. M. G. Crowson et al., “Machine learning for accurate intraoperative pediatric middle ear effusion diagnosis,” Pediatrics, vol. 147, p. e2020034546, 2021, doi: 10.1542/peds.2020-034546.
10. X. Ding, Y. Huang, X. Tian, J. Tang, and Y. Cheng, “Diagnosis, treatment, and management of otitis media with artificial intelligence,” Diagnostics, vol. 13, p. 2309, 2023, doi: 10.3390/diagnostics13132309.
11. M. E. Pichichero and M. D. Poole, “Comparison of performance by otolaryngologists, paediatricians, and general practitioners on an otoendoscopic diagnostic video examination,” Int. J. Pediatr. Otorhinolaryngol., vol. 69, pp. 361–366, 2005, doi: 10.1016/j.ijporl.2004.10.013.
12. D. Song, T. Kim, Y. Lee, and J. Kim, “Image-based artificial intelligence technology for diagnosing middle ear diseases: a systematic review,” J. Clin. Med., vol. 12, p. 5831, 2023, doi: 10.3390/jcm12185831.
13. G. L. Monroy et al., “Automated classification platform for the identification of otitis media using optical coherence tomography,” NPJ Digit. Med., vol. 2, p. 22, 2019, doi: 10.1038/s41746-019-0094-0.
14. Z. Cömert, “Fusing fine-tuned deep features for recognizing different tympanic membranes.” Biocybernetics and Biomedical Engineering, vol. 40, pp. 40-51, 2020, doi: 10.1016/j.bbe.2019.11.001.
15. F. Demircan, M. Ekinci, Z. Cömert, and E. Gedikli, “Enhanced classification of ear disease images using metaheuristic feature selection.” Sakarya University Journal of Computer and Information Sciences, vol. 8, no. 1, pp. 58-75, 2025, doi: 10.35377/saucis...1579003.
16. T. T. Tran et al., “Development of an automatic diagnostic algorithm for pediatric otitis media,” Otol. Neurotol., vol. 39, pp. 1060–1065, 2018, doi: 10.1097/MAO.0000000000001897.
17. D. Cha et al., “Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database,” EBioMedicine, vol. 45, pp. 606–614, 2019, doi: 10.1016/j.ebiom.2019.06.050.
18. E. Başaran, Z. Cömert, and Y. Çelik, “Convolutional neural network approach for automatic tympanic membrane detection and classification,” Biomed. Signal Process. Control, vol. 56, p. 101734, 2020, doi: 10.1016/j.bspc.2019.101734.
19. J. Sandström et al., “A machine learning approach to screen for otitis media using digital otoscope images labelled by an expert panel,” Diagnostics, vol. 12, p. 1318, 2022, doi: 10.3390/diagnostics12061318.
20. A. R. Habib et al., “Evaluating the generalizability of deep learning image classification algorithms to detect middle ear disease using otoscopy,” Sci. Rep., vol. 13, p. 5368, 2023, doi: 10.1038/s41598-023-31921-0.
21. J. V. Sundgaard et al., “Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty,” Laryngoscope Investig. Otolaryngol., vol. 9, no. 1, p. e1199, 2024, doi: 10.1002/lio2.1199.
22. M. Viscaino et al., “Computer-aided diagnosis of external and middle ear conditions: A machine learning approach,” PLoS One, vol. 15, no. 3, p. e0229226, 2020, doi: 10.1371/journal.pone.0229226.
23. S. Roy, K. Bhalla, and R. Patel, “Mathematical analysis of histogram equalization techniques for medical image enhancement: a tutorial from the perspective of data loss,” Multimed. Tools Appl., vol. 83, pp. 14363–14392, 2024, doi: 10.1007/s11042-023-15799-8.
24. K. G. Dhal et al., “Histogram equalization variants as optimization problems: a review,” Arch. Comput. Methods Eng., vol. 28, pp. 1471–1496, 2021, doi: 10.1007/s11831-020-09425-1.
25. S. Singh et al., “IR and visible image fusion using DWT and bilateral filter,” Microsyst. Technol., vol. 29, pp. 457–467, 2023, doi: 10.1007/s00542-022-05315-7.
26. M. Bansal, M. Kumar, M. Sachdeva, and A. Mittal, “Transfer learning for image classification using VGG19: Caltech-101 image data set,” J. Ambient Intell. Human Comput., pp. 1–12, 2023, doi: 10.1007/s12652-021-03488-z.
27. R. Jha, V. Bhattacharjee, and A. Mustafi, “Transfer learning with feature extraction modules for improved classifier performance on medical image data”. Scientific Programming, vol. 1, p. 4983174, 2022, doi: 10.1155/2022/4983174.
28. Ö. F. Nasip and K. Zengin, “Transfer öğrenme ve komşuluk bileşen analizine dayalı balgam yayma mikroskop görüntüleri üzerinden otomatik tüberküloz teşhisi.” Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 4, no. 2, pp. 236-246, 2022, doi: 10.46387/bjesr.1160038.
29. S. G. Siddarth and S. Chokkalingam, “DenseNet 121 framework for automatic feature extraction of diabetic retinopathy images.” In 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC) (pp. 338-342). IEEE, 2024, doi: 10.1109/ESIC60604.2024.10481664.
30. K. M. He, X. Zhang, S. Ren & J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770–778.
31. Y. Yu and F. Liu, “Dense connectivity based two-stream deep feature fusion framework for aerial scene classification,” Remote Sens., vol. 10, no. 7, p. 1158, 2018, doi: 10.3390/rs10071158.
32. H. Kumar et al., “Transfer learning and supervised machine learning approach for detection of skin cancer: performance analysis and comparison,” Drugs Cell Ther. Hematol., vol. 10, no. 1, pp. 1–16, 2021.
33. Z. Jafari and E. Karami, “Breast cancer detection in mammography images: a CNN-based approach with feature selection,” Inf., vol. 14, p. 410, 2023, doi: 10.3390/info14070410.
34. A. M. Karim et al., “New optimized deep learning application for COVID-19 detection in chest X-ray images,” Symmetry, vol. 14, p. 1003, 2022, doi: 10.3390/sym14051003.
35. Y. Zheng, C. Yang, and A. Merkulov, “Breast cancer screening using convolutional neural network and follow-up digital mammography,” in Comput. Imaging III, vol. 10669, p. 1066905, SPIE, 2018, doi: 10.1117/12.2304564.
36. J. Fayaz, M. Medalla, and F. Zareian, “Sensitivity of the response of Box-Girder Seat-type bridges to the duration of ground motions arising from crustal and subduction earthquakes,” Eng. Struct., vol. 219, p. 110845, 2020, doi: 10.1016/j.engstruct.2020.110845.
37. W. Yang, K. Wang, and W. Zuo, “Neighborhood component feature selection for high-dimensional data,” J. Comput., vol. 7, no. 1, pp. 161–168, 2012, doi: 10.4304/jcp.7.1.161-168.
38. W. A. Altabey et al., “Studying acoustic behavior of BFRP laminated composite in dual-chamber muffler application using deep learning algorithm,” Materials, vol. 15, p. 8071, 2022, doi: 10.3390/ma15228071.
39. İ. Dağlı and A. Öztürk, “Comparison of Deep Learning Models in Image Classification”. Konya Journal of Engineering Sciences, vol. 9, no. 4, pp. 872-888, 2021, doi: 10.36306/konjes.722976.
40. M. M. Taye, “Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions,” Computation, vol. 11, p. 52, 2023, doi: 10.3390/computation11030052.
41. M. Çataltaş, B. Üstünel, & N. A. Baykan, “Sentiment Classification on Turkish Tweets About Covid-19 Using LSTM Network”. Konya Journal of Engineering Sciences, vol. 11, no. 2, 341-353, 2023, doi: 10.36306/konjes.1173939.
42. S. Selvarajan et al., “Cognitive intelligent decisions for big data and cloud computing in industrial applications using trifold algorithms,” Cogn. Comput., pp. 1–15, 2024, doi: 10.1007/s12559-024-10317-w.
43. H. Göker, H. I. Bülbül, and E. Irmak, “The estimation of students' academic success by data mining methods.” 12th International Conference on Machine Learning and Applications, vol. 2, pp. 535-539, 2013.
44. A. B. Cantor, “Sample-size calculations for Cohen's kappa,” Psychol. Methods, vol. 1, pp. 150–151, 1996, doi: 10.1037/1082-989X.1.2.150.
45. H. C. Myburgh, S. Jose, D. W. Swanepoel, and C. Laurent, “Towards low-cost automated smartphone-and cloud-based otitis media diagnosis,” Biomed. Signal Process. Control, vol. 39, pp. 34–52, 2018.
46. D. Livingstone and J. Chau, "Otoscopic diagnosis using computer vision: an automated machine learning approach," Laryngoscope, vol. 129, pp. 2413–2419, 2019, doi: 10.1002/lary.28292.
47. M. A. Khan et al., "Automatic detection of tympanic membrane and middle ear infection from oto-endoscopic images via convolutional neural networks," Neural Netw., vol. 126, pp. 384–394, 2020, doi: 10.1016/j.neunet.2020.03.023.
48. A. Alhudhaif, Z. Cömert and K. Polat, "Otitis media detection using tympanic membrane images with a novel multi-class machine learning algorithm," PeerJ Comput. Sci., vol. 7, p. e405, 2021, doi: 10.7717/peerj-cs.405.
49. Z. Wang et al., "Structure-aware deep learning for chronic middle ear disease," Expert Syst. Appl., vol. 194, p. 116519, 2022, doi: 10.1016/j.eswa.2022.116519.
50. A. Çalışkan, "Classification of tympanic membrane images based on VGG16 model," Kocaeli J. Sci. Eng., vol. 5, no. 1, pp. 105–111, 2022, doi: 10.34088/kojose.1081402.
51. Y. C. Chen et al., "Smartphone-based artificial intelligence using a transfer learning algorithm for the detection and diagnosis of middle ear diseases: A retrospective deep learning study," EClinicalMedicine, vol. 51, p. 101543, 2022, doi: 10.1016/j.eclinm.2022.101543.
52. T. Kim, K. Oh, J. Kim, Y. Lee and J. Choi, "Development of ResNet152 UNet++-based segmentation algorithm for the tympanic membrane and affected areas," IEEE Access, vol. 11, pp. 56225–56234, 2023, doi: 10.1109/ACCESS.2023.3281693.
53. J. H. Shim, W. Sunwoo, B. Y. Choi, K. G. Kim and Y. J. Kim, "Improving the accuracy of otitis media with effusion diagnosis in pediatric patients using deep learning," Bioengineering, vol. 10, no. 11, p. 1337, 2023, doi: 10.3390/bioengineering10111337.
54. A. K. Singh, A. S. Raghuvanshi and R. Mehta, "A soft computing approach for efficient diagnosis of otitis media infection by mucosal disease early detection and referrals," in Proc. 2024 2nd Int. Conf. Device Intell., Comput. Commun. Technol. (DICCT), 2024, pp. 687–692, doi: 10.1109/DICCT61038.2024.10532803.