{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T16:38:57Z","timestamp":1790959137716,"version":"4.1.0"},"reference-count":26,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T00:00:00Z","timestamp":1751068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Ministry of Health &amp; Welfare Republic of Korea","doi-asserted-by":"publisher","award":["RS-2022-KH129742"],"award-info":[{"award-number":["RS-2022-KH129742"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Motivation: Benign paroxysmal positional vertigo (BPPV) is characterized by torsional nystagmus induced by changes in head position, where accurate quantitative assessment of subtle torsional eye movements is essential for precise diagnosis. Conventional videonystagmography (VNG) techniques face challenges in accurately capturing the rotational components of pupil movements, and existing automated methods typically exhibit limited performance in identifying torsional nystagmus. Methodology: The objective of this study was to develop an automated system capable of accurately and quantitatively detecting torsional nystagmus. We introduce the Torsion Transformer model, designed to directly estimate torsion angles from iris images. This model employs a self-supervised learning framework comprising two main components: a Decoder module, which learns rotational transformations from image data, and a Finder module, which subsequently estimates the torsion angle. The resulting torsion angle data, represented as time-series, are then analyzed using a 1-dimensional convolutional neural network (1D-CNN) classifier to detect the presence of nystagmus. The performance of the proposed method was evaluated using video recordings from 127 patients diagnosed with BPPV. Findings: Our Torsion Transformer model demonstrated robust performance, achieving a sensitivity of 89.99%, specificity of 86.36%, an F1-score of 88.82%, and an area under the receiver operating characteristic curve (AUROC) of 87.93%. These results indicate that the proposed model effectively quantifies torsional nystagmus, with performance levels comparable to established methods for detecting horizontal and vertical nystagmus. Thus, the Torsion Transformer shows considerable promise as a clinical decision support tool in the diagnosis of BPPV. Key Findings: Technical performance improvement in torsional nystagmus detection; System to support clinical decision-making for healthcare professionals.<\/jats:p>","DOI":"10.3390\/s25134039","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:10:31Z","timestamp":1751285431000},"page":"4039","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Transformer-Based Detection and Clinical Evaluation System for Torsional Nystagmus"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6987-2793","authenticated-orcid":false,"given":"Ju-Hyuck","family":"Han","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Konyang University, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3443-263X","authenticated-orcid":false,"given":"Yong-Suk","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Konyang University, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0602-1529","authenticated-orcid":false,"given":"Jong Bin","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Konyang University Hospital, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hantai","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Konyang University Hospital, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1230-9307","authenticated-orcid":false,"given":"Jong-Yeup","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Konyang University Hospital, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6425-8145","authenticated-orcid":false,"given":"Yongseok","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Medical IT Engineering, Konyang University, Daejeon 32992, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3233\/VES-190658","article-title":"Classification of vestibular signs and examination techniques: Nystagmus and nystagmus-like movements","volume":"29","author":"Eggers","year":"2019","journal-title":"J. Vestib. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4360","DOI":"10.1007\/s00415-023-11771-6","article-title":"The \u201cVestibular Eye Sign\u201d-\u201dVES\u201d: A new radiological sign of vestibular neuronitis can help to determine the affected vestibule and support the diagnosis","volume":"270","author":"Farhat","year":"2023","journal-title":"J. Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"152","DOI":"10.3390\/audiolres12020018","article-title":"Atypical positional vertigo: Definition, causes, and mechanisms","volume":"12","author":"Carmona","year":"2022","journal-title":"Audiol. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1007\/s00415-020-10314-7","article-title":"Update on benign paroxysmal positional vertigo","volume":"268","author":"Kim","year":"2021","journal-title":"J. Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1007\/s00405-013-2484-2","article-title":"Benign paroxysmal positional vertigo secondary to vestibular neuritis","volume":"271","author":"Balatsouras","year":"2014","journal-title":"Eur. Arch. Oto-Rhino-Laryngol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, H., and Yang, Z. (2023). Torsional nystagmus recognition based on deep learning for vertigo diagnosis. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1160904"},{"key":"ref_7","first-page":"832","article-title":"Risk factors for recurrence of benign paroxysmal positional vertigo","volume":"37","author":"Tanimoto","year":"2008","journal-title":"J. Otolaryngol.--Head Neck Surg."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, Y., Lu, Y., Wang, S., Quan, X., Ren, Y., Rong, K., Pan, S., Lu, X., Chen, L., and Tian, C. (2023). Global research trends in benign paroxysmal positional vertigo: A bibliometric analysis. Front. Neurol., 14.","DOI":"10.3389\/fneur.2023.1204038"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lim, E.C., Park, J.H., Jeon, H.J., Kim, H.J., Lee, H.J., Song, C.G., and Hong, S.K. (2019). Developing a Diagnostic Decision Support System for Benign Paroxysmal Positional Vertigo Using a Deep-Learning Model. J. Clin. Med., 8.","DOI":"10.3390\/jcm8050633"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Barin, K., Petrak, M.R., Cassidy, A.R., and Whitney, S.L. (2025). Quantified assessment of 3D nystagmus in BPPV: Practical considerations. Front. Neurol., 16.","DOI":"10.3389\/fneur.2025.1549407"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1017\/S0022215123001111","article-title":"Bilateral simultaneous presentation of posterior canal benign paroxysmal positional vertigo","volume":"138","author":"Yetiser","year":"2024","journal-title":"J. Laryngol. Otol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1590\/S1808-86942010000300021","article-title":"Eletronistagmografia versus videonistagmografia","volume":"76","author":"Caovilla","year":"2010","journal-title":"Braz. J. Otorhinolaryngol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14253\/acn.2023.25.1.10","article-title":"Recording and interpretation of ocular movements: Spontaneous and induced nystagmus","volume":"25","author":"Kang","year":"2023","journal-title":"Ann. Clin. Neurophysiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.3109\/00016480902725247","article-title":"Three-dimensional video-oculography in patients with vestibular neuritis","volume":"129","author":"Hirvonen","year":"2009","journal-title":"Acta Oto-Laryngol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"115","DOI":"10.21790\/rvs.2024.018","article-title":"Digital therapeutics and telemedicine for benign paroxysmal positional vertigo and other vestibular disorders: A review","volume":"23","author":"Choi","year":"2024","journal-title":"Res. Vestib."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mun, S.B., Kim, Y.J., Lee, J.H., Han, G.C., Cho, S.H., Jin, S., and Kim, K.G. (2024). Deep learning-based nystagmus detection for BPPV diagnosis. Sensors, 24.","DOI":"10.3390\/s24113417"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wu, H., Liu, Y., Zheng, S., Liu, Z., Li, Y., Zhao, Y., and Zhu, Z. (2021). Deep Learning Based Torsional Nystagmus Detection for Dizziness and Vertigo Diagnosis. Biomed. Signal Process. Control, 68.","DOI":"10.1016\/j.bspc.2021.102616"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"113995","DOI":"10.1109\/ACCESS.2022.3215625","article-title":"Lad: A hybrid deep learning system for benign paroxysmal positional vertigo disorders diagnostic","volume":"10","author":"Pham","year":"2022","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.jneumeth.2010.08.004","article-title":"Measuring torsional eye movements by tracking stable iris features","volume":"192","author":"Ong","year":"2010","journal-title":"J. Neurosci. Methods"},{"key":"ref_20","unstructured":"Pham, T. (IEEE Dataport, 2022). BPPV videos dataset samples, IEEE Dataport."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"48543","DOI":"10.1109\/ACCESS.2019.2910605","article-title":"Edge detection with chroma components of video frame based on local autocorrelation","volume":"7","author":"Zhu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_22","unstructured":"(2025, May 24). UNet2DModel, Hugging Face. Available online: https:\/\/huggingface.co\/docs\/diffusers\/v0.33.1\/en\/api\/models\/unet2d#unet2dmodel."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"12395","DOI":"10.1007\/s11042-024-19488-y","article-title":"ES-Net: Unet-based model for the semantic segmentation of Iris","volume":"84","author":"Pourafkham","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1002\/lio2.1113","article-title":"Posterior canal benign paroxysmal positional vertigo with long duration: Heavy or light cupula?","volume":"8","author":"Kim","year":"2023","journal-title":"Laryngoscope Investig. Otolaryngol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jain, G., Mahara, T., Sharma, S.C., Agarwal, S., and Kim, H. (2022). TD-DNN: A Time Decay-Based Deep Neural Network for Recommendation System. Appl. Sci., 12.","DOI":"10.3390\/app12136398"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1212\/WNL.0000000000211281","article-title":"Comparing and Explaining Deep-learning Torsional Nystagmus Detection","volume":"104","author":"Mukunda","year":"2025","journal-title":"Neurology"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/13\/4039\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:00:56Z","timestamp":1760032856000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/13\/4039"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,28]]},"references-count":26,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["s25134039"],"URL":"https:\/\/doi.org\/10.3390\/s25134039","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,28]]}}}