Machine learning based approach for vestibular disorder diagnostic in videonystagmography

Slama, Amine Ben; Sahli, Hanene; Mouelhi, Aymen; Marrakchi, J.; Trabelsi, H.; MounirSayadi,

doi:10.35841/biomedicalresearch.30-19-216

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lim et al 18 extracted the pupil trajectory and iris pattern from a video in which 10 types of tests were performed and obtained an amplitude in three directions to distinguish eight types of BPPV with a deep learning model. Slama et al 19 extracted pupil trajectories from caloric and kinetic test videos and extracted various features to diagnose vestibular neuritis using support vector machines. Reinhardt et al 20 developed an algorithm that detects the eye using a cascade classifier in a webcam image to obtain eye trajectories and determine the time when nystagmus occurs.…”

Section: Introductionmentioning

confidence: 99%

A nystagmus extraction system using artificial intelligence for video-nystagmography

Lee¹,

Lee²,

Han³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Benign paroxysmal positional vertigo (BPPV), the most common vestibular disorder, is diagnosed by an examiner changing the posture of the examinee and inducing nystagmus. Among the diagnostic methods used to observe nystagmus, video-nystagmography has been widely used recently because it is non-invasive. A specialist with professional knowledge and training in vertigo diagnosis is needed to diagnose BPPV accurately, but the ratio of vertigo patients to specialists is too high, thus necessitating the need for automated diagnosis of BPPV. In this paper, a convolutional neural network-based nystagmus extraction system, ANyEye, optimized for video-nystagmography data is proposed. A pupil was segmented to track the exact pupil trajectory from real-world data obtained during field inspection. A deep convolutional neural network model was trained with the new video-nystagmography dataset for the pupil segmentation task, and a compensation algorithm was designed to correct pupil position. In addition, a slippage detection algorithm based on moving averages was designed to eliminate the motion artifacts induced by goggle slippage. ANyEye outperformed other eye-tracking methods including learning and non-learning-based algorithms with five-pixel error detection rate of 91.26%.

show abstract

Section: Introductionmentioning

confidence: 99%

A nystagmus extraction system using artificial intelligence for video-nystagmography

Lee¹,

Lee²,

Han³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Various irrelevant features that do not contribute as an identification factor of a disease among such high-dimensional data need to be identified and excluded to reduce the feature-set dimension. Few studies have focused on feature extraction and feature transformation methods to reduce the feature-set dimension, achieving increased classification accuracy, also preventing overfitting [23,28,29]. The machine learning techniques in existing literature provide an automated procedure for disease prediction by interpreting complex clinical data, mainly resorting solely to model selection and parameter determination.…”

Section: Discussion and Potential Directionsmentioning

confidence: 99%

“…Amine, B.S. et al [29] proposed a videonystagmography (VNG)-based machine learning approach to identify vestibular neuritis. These investigators video recorded nystagmus, used a pupil tracking algorithm to measure nystagmus metrics, and then used Fischer criteria for feature selection and SVM for classification, which gave classification results higher than K-nearest neighbor and artificial neural networks with an accuracy of 94.1%.…”

Section: Machine Learning Applications To Nystagmus and Vestibulo-ocular Reflex (Vor) Testsmentioning

confidence: 99%

“…These models process the patients' data, find the correlations and associations of presenting symptoms, familiar antecedents, habits, and background medical history with a view to predicting vertigo aetiology. The machine learning models most commonly used in vertigo diagnosis include decision trees [22][23][24][25], support vector machines (SVM) [22,[25][26][27][28][29][30][31][32][33][34], k-Nearest neighbors (KNN) [20,23,[25][26][27]30,35,36], and deep learning techniques [35,37,38]. Some researchers have also used novel ML algorithms and ensemble learning to improve diagnostic accuracy [28,33,[39][40][41][42].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Techniques for Differential Diagnosis of Vertigo and Dizziness: A Review

Kabade

Hooda

Raj

et al. 2021

Sensors

View full text Add to dashboard Cite

Vertigo is a sensation of movement that results from disorders of the inner ear balance organs and their central connections, with aetiologies that are often benign and sometimes serious. An individual who develops vertigo can be effectively treated only after a correct diagnosis of the underlying vestibular disorder is reached. Recent advances in artificial intelligence promise novel strategies for the diagnosis and treatment of patients with this common symptom. Human analysts may experience difficulties manually extracting patterns from large clinical datasets. Machine learning techniques can be used to visualize, understand, and classify clinical data to create a computerized, faster, and more accurate evaluation of vertiginous disorders. Practitioners can also use them as a teaching tool to gain knowledge and valuable insights from medical data. This paper provides a review of the literatures from 1999 to 2021 using various feature extraction and machine learning techniques to diagnose vertigo disorders. This paper aims to provide a better understanding of the work done thus far and to provide future directions for research into the use of machine learning in vertigo diagnosis.

show abstract

“…In previous studies to detect nystagmus, images were binarized to track pupils to apply the Circular Huff Transform or other machine learning methods [2][3][4], but these methods have the disadvantage of distorting the pupil center when the eye blinks and the eyelids cover the pupil. In this work, the convolutional neural network was used to find the shape of the pupil, and an algorithm for pupil location compensation was applied to find the exact center.…”

Section: Introductionmentioning

confidence: 99%

An eye-tracking algorithm for nystagmus detection in videonystagmography based on convolutional neural networks

Lee

Han

et al. 2023

Ophthalmic Technologies XXXIII

View full text Add to dashboard Cite

Nystagmus is a periodic, involuntary movement of eyes examined for diagnosis of various vestibular diseases such as benign paroxysmal positional vertigo, the most frequent vestibular disorder. In recent years, videonystagmography has been widely used in the examination of nystagmus due to its non-invasive feature. However, identifying and classifying nystagmus still requires professional knowledge and training. To this end, a pupil tracking algorithm was proposed in this paper using convolutional neural networks. U-Net was selected for pupil segmentation, and we constructed the ground truth of a new dataset for the training procedure. An additional tracking algorithm was designed to prevent false outputs of the U-Net model. Results show that the proposed pupil tracking algorithm scored higher performance than conventional methods.

show abstract

Machine learning based approach for vestibular disorder diagnostic in videonystagmography

Cited by 4 publications

References 0 publications

A nystagmus extraction system using artificial intelligence for video-nystagmography

A nystagmus extraction system using artificial intelligence for video-nystagmography

Machine Learning Techniques for Differential Diagnosis of Vertigo and Dizziness: A Review

An eye-tracking algorithm for nystagmus detection in videonystagmography based on convolutional neural networks

Contact Info

Product

Resources

About