A nystagmus extraction system using artificial intelligence for video-nystagmography
Abstract 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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-39104-7 |
| _version_ | 1797559914439114752 |
|---|---|
| author | Yerin Lee Sena Lee Junghun Han Young Joon Seo Sejung Yang |
| author_facet | Yerin Lee Sena Lee Junghun Han Young Joon Seo Sejung Yang |
| author_sort | Yerin Lee |
| collection | DOAJ |
| description | Abstract 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%. |
| first_indexed | 2024-03-10T17:52:59Z |
| format | Article |
| id | doaj.art-8cc99abfb76746c6b9680cf975923447 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T17:52:59Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8cc99abfb76746c6b9680cf9759234472023-11-20T09:18:25ZengNature PortfolioScientific Reports2045-23222023-07-0113111210.1038/s41598-023-39104-7A nystagmus extraction system using artificial intelligence for video-nystagmographyYerin Lee0Sena Lee1Junghun Han2Young Joon Seo3Sejung Yang4Department of Biomedical Engineering, Yonsei UniversityDepartment of Precision Medicine, Yonsei University Wonju College of MedicineDepartment of Biomedical Engineering, Yonsei UniversityResearch Institute of Hearing Enhancement, Yonsei University Wonju College of MedicineDepartment of Precision Medicine, Yonsei University Wonju College of MedicineAbstract 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%.https://doi.org/10.1038/s41598-023-39104-7 |
| spellingShingle | Yerin Lee Sena Lee Junghun Han Young Joon Seo Sejung Yang A nystagmus extraction system using artificial intelligence for video-nystagmography Scientific Reports |
| title | A nystagmus extraction system using artificial intelligence for video-nystagmography |
| title_full | A nystagmus extraction system using artificial intelligence for video-nystagmography |
| title_fullStr | A nystagmus extraction system using artificial intelligence for video-nystagmography |
| title_full_unstemmed | A nystagmus extraction system using artificial intelligence for video-nystagmography |
| title_short | A nystagmus extraction system using artificial intelligence for video-nystagmography |
| title_sort | nystagmus extraction system using artificial intelligence for video nystagmography |
| url | https://doi.org/10.1038/s41598-023-39104-7 |
| work_keys_str_mv | AT yerinlee anystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT senalee anystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT junghunhan anystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT youngjoonseo anystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT sejungyang anystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT yerinlee nystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT senalee nystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT junghunhan nystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT youngjoonseo nystagmusextractionsystemusingartificialintelligenceforvideonystagmography AT sejungyang nystagmusextractionsystemusingartificialintelligenceforvideonystagmography |