Li Haibo, Yang Zhifan
College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China.
Front Neurosci. 2023 Jun 9;17:1160904. doi: 10.3389/fnins.2023.1160904. eCollection 2023.
Detection of torsional nystagmus can help identify the canal of origin in benign paroxysmal positional vertigo (BPPV). Most currently available pupil trackers do not detect torsional nystagmus. In view of this, a new deep learning network model was designed for the determination of torsional nystagmus.
The data set comes from the Eye, Ear, Nose and Throat (Eye&ENT) Hospital of Fudan University. In the process of data acquisition, the infrared videos were obtained from eye movement recorder. The dataset contains 24521 nystagmus videos. All torsion nystagmus videos were annotated by the ophthalmologist of the hospital. 80% of the data set was used to train the model, and 20% was used to test.
Experiments indicate that the designed method can effectively identify torsional nystagmus. Compared with other methods, it has high recognition accuracy. It can realize the automatic recognition of torsional nystagmus and provides support for the posterior and anterior canal BPPV diagnosis.
Our present work complements existing methods of 2D nystagmus analysis and could improve the diagnostic capabilities of VNG in multiple vestibular disorders. To automatically pick BPV requires detection of nystagmus in all 3 planes and identification of a paroxysm. This is the next research work to be carried out.
检测扭转性眼球震颤有助于确定良性阵发性位置性眩晕（BPPV）的起源半规管。目前大多数可用的瞳孔追踪器无法检测到扭转性眼球震颤。鉴于此，设计了一种新的深度学习网络模型来确定扭转性眼球震颤。
数据集来自复旦大学附属眼耳鼻喉科医院。在数据采集过程中，通过眼动记录仪获取红外视频。该数据集包含24521个眼球震颤视频。所有扭转性眼球震颤视频均由该医院的眼科医生进行标注。数据集的80%用于训练模型，20%用于测试。
实验表明，所设计的方法能够有效识别扭转性眼球震颤。与其他方法相比，具有较高的识别准确率。它能够实现扭转性眼球震颤的自动识别，为后半规管和前半规管BPPV的诊断提供支持。
我们目前的工作补充了现有的二维眼球震颤分析方法，并可提高视频眼震图（VNG）在多种前庭疾病中的诊断能力。要自动识别BPPV需要检测所有三个平面的眼球震颤并识别一次发作。这是接下来要开展的研究工作。
