A deep learning-based tool for the diagnostic decision support of peripheral vestibular disorders
DOI:
https://doi.org/10.33448/rsd-v11i4.27753Keywords:
Nystagmus; Videonystagmography; Peripheral vestibulopathy; Diagnosis; Artificial intelligence; Computer vision; Deep learning.Abstract
Nystagmus is involuntary eye movement characterized by smooth movement, called the slow phase of nystagmus, interrupted by rapid fixation in the opposite direction. It is one of the preponderant factors in the diagnosis of vestibular disorders. This study presents Smart Nystagmography, a proposal for a computer vision-based tool to support the diagnosis of peripheral vestibular disorders, which encompasses the entire process, from the eye movement collection device to the disorder classifier. The proposed solution is based on feature vectors that present eye movement patterns, which are identified using machine learning, in particular, Deep Learning (DL). The videonystagmography technique and its different tests were performed by the subjects in order to generate a representative dataset for both healthy subjects and those with vestibular dysfunction. Data pre-processing methods, as well as a hyperparameter optimization technique of the DL algorithms were employed with the purpose of improving the performance of state-of-the-art models. The performance results for identifying the presence of peripheral vestibular dysfunction reached an accuracy of 96.7% for the best model, after going through the optimization process. The results show the efficiency of Smart Nystagmography, which has a solution that involves from the video collection device to the system with data preparation techniques and the DL model deployed. Additional clinical studies are needed to validate the solution
References
Alpaydin, E. (2020). Introduction to machine learning. MIT press.
Chollet, F. (2015). Keras documentation. keras. io, 33.
Eggers, S. D. (2019). Approach to the Examination and Classification of Nystagmus. Journal of Neurologic Physical Therapy, 43, S20-S26.
Felipe, L., Staggs, A., & Hunnicutt, S. (2021). Can Type of Dizziness Influence the Vestibular Caloric Test Result?. Journal of Primary Care & Community Health, 12, 21501327211030120.
Ganança, M. M., Caovilla, H. H., & Ganança, F. F. (2010). Electronystagmography versus videonystagmography. Brazilian Journal of Otorhinolaryngology, 76(3), 399-403.
Mantokoudis, G., Otero-Millan, J., & Gold, D. R. (2022). Current concepts in acute vestibular syndrome and video-oculography. Current opinion in neurology, 35(1), 75-83.
Groezinger, M., Huppert, D., Strobl, R., & Grill, E. (2020). Development and validation of a classification algorithm to diagnose and differentiate spontaneous episodic vertigo syndromes: results from the DizzyReg patient registry. Journal of neurology, 267(1), 160-167.
Hasibi, R., Shokri, M., & Dehghan, M. (2019). Augmentation scheme for dealing with imbalanced network traffic classification using deep learning. arXiv preprint arXiv:1901.00204.
Iwana, B. K., & Uchida, S. (2021). An empirical survey of data augmentation for time series classification with neural networks. Plos one, 16(7), e0254841.
Kamogashira, T., Fujimoto, C., Kinoshita, M., Kikkawa, Y., Yamasoba, T., & Iwasaki, S. (2020). Prediction of vestibular dysfunction by applying machine learning algorithms to postural instability. Frontiers in neurology, 11, 7.
Karatas, M. (2008). Central vertigo and dizziness: epidemiology, differential diagnosis, and common causes. The neurologist, 14(6), 355-364.
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2017). Hyperband: A novel bandit-based approach to hyperparameter optimization. The Journal of Machine Learning Research, 18(1), 6765-6816.
Lim, E. C., Park, J. H., Jeon, H. J., Kim, H. J., Lee, H. J., Song, C. G., & Hong, S. K. (2019). Developing a diagnostic decision support system for benign paroxysmal positional vertigo using a deep-learning model. Journal of clinical medicine, 8(5), 633.
Mao, Y., He, Y., Liu, L., & Chen, X. (2020). Disease Classification Based on Synthesis of Multiple Long Short-Term Memory Classifiers Corresponding to Eye Movement Features. IEEE Access, 8, 151624-151633.
Mostafa, B. E., Kahky, A. O. E., Kader, H. M. A., & Rizk, M. (2014). Central vestibular dysfunction in an otorhinolaryngological vestibular unit: incidence and diagnostic strategy. International archives of otorhinolaryngology, 18, 235-238.
Neuhauser, H. K. (2016). The epidemiology of dizziness and vertigo. Handbook of clinical neurology, 137, 67-82.
Olson, M., Wyner, A., & Berk, R. (2018). Modern neural networks generalize on small data sets. Advances in Neural Information Processing Systems, 31.
Papageorgiou, E., McLean, R. J., & Gottlob, I. (2014). Nystagmus in childhood. Pediatrics & Neonatology, 55(5), 341-351.
Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2019). Deep adaptive input normalization for time series forecasting. IEEE transactions on neural networks and learning systems, 31(9), 3760-3765.
Pietkiewicz, P., Pepaś, R., Sułkowski, W. J., Zielińska-Bliźniewska, H., & Olszewski, J. (2012). Electronystagmography versus videonystagmography in diagnosis of vertigo. International journal of occupational medicine and environmental health, 25(1), 59-65.
Sahli, H., Ben Slama, A., Bouzaiane, S., Marrakchi, J., Boukriba, S., & Sayadi, M. (2020). VNG technique for a convenient vestibular neuritis rating. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 8(5), 571-580.
Savage, C. O. (2011, January). Eye position prediction in the case of nystagmus and refixations. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 7924-7927). IEEE.
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1-48.
Slama, A. B., Machraoui, A. N., & Sayadi, M. (2014, November). Pupil tracking using active contour model for videonystagmography applications. In International Image Processing, Applications and Systems Conference (pp. 1-5). IEEE.
Slama, A. B., Mouelhi, A., Sahli, H., Manoubi, S., Mbarek, C., Trabelsi, H., ... & Sayadi, M. (2017). A new preprocessing parameter estimation based on geodesic active contour model for automatic vestibular neuritis diagnosis. Artificial intelligence in medicine, 80, 48-62.
Slama, A. B., Sahli, H., Mouelhi, A., Marrakchi, J., Sayadi, M., & Trabelsi, H. (2020). DBN-DNN: discrimination and classification of VNG sequence using deep neural network framework in the EMD domain. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 8(6), 681-690.
Slama, A. B., Mouelhi, A., Sahli, H., Manoubi, S., Lahiani, R., Salah, M. B., ... & Sayadi, M. (2018). A new neural network method for peripheral vestibular disorder recognition using VNG parameter optimisation. International Journal of Biomedical Engineering and Technology, 27(4), 321-336.
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information processing & management, 45(4), 427-437.
Stanton, M., & Freeman, A. M. (2021). Vertigo. In StatPearls [Internet]. StatPearls Publishing.
Strupp, M. L., Straumann, D., & Helmchen, C. (2021). Nystagmus: Diagnosis, Topographic Anatomical Localization and Therapy. Klinische Monatsblätter für Augenheilkunde, 238(11), 1186-1195.
TensorFlow. Uma plataforma completa de código aberto para machine learning. Recuperado em 16 de março, 2022, de https://www.tensorflow.org/
Vallim, M. G. B., Gabriel, G. P., Mezzalira, R., Stoler, G., & Chone, C. T. (2021). Does the video head impulse test replace caloric testing in the assessment of patients with chronic dizziness? A systematic review and meta-analysis. Brazilian journal of otorhinolaryngology, 87, 733-741.
Visscher, R. M., Feddermann-Demont, N., Romano, F., Straumann, D., & Bertolini, G. (2019). Artificial intelligence for understanding concussion: Retrospective cluster analysis on the balance and vestibular diagnostic data of concussion patients. PloS one, 14(4), e0214525.
Wazlawick, R. S. (2014). Metodologia de Pesquisa Para Ciência Da Computação (2nd ed.). Elsevier.
West, P. D. B., Sheppard, Z. A., & King, E. V. (2012). Comparison of techniques for identification of peripheral vestibular nystagmus. The Journal of Laryngology & Otology, 126(12), 1209-1215.
Wipperman, J. (2014). Dizziness and vertigo. Primary Care: Clinics in Office Practice, 41(1), 115-131.
Wu, C. N., Luo, S. D., Chen, S. F., Huang, C. W., Chiang, P. L., Hwang, C. F., ... & Li, Y. L. (2022). Applicability of Oculomotor Tests for Predicting Central Vestibular Disorder Using Principal Component Analysis. Journal of Personalized Medicine, 12(2), 203.
Yiu, Y. H., Aboulatta, M., Raiser, T., Ophey, L., Flanagin, V. L., Zu Eulenburg, P., & Ahmadi, S. A. (2019). DeepVOG: Open-source pupil segmentation and gaze estimation in neuroscience using deep learning. Journal of neuroscience methods, 324, 108307.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Antônia de Maria Rodrigues de Sousa Castro; Ariel Soares Teles; Lucas Daniel Batista Lima; José Everton da Silva Fontenele; Victor Hugo do Vale Bastos; Silmar Silva Teixeira
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
