IntroductionDetection 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.MethodsThe 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.ResultsExperiments 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.DiscussionOur 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.

Vertical nystagmus is a common neuro-ophthalmic sign in vestibular medicine. Vertical nystagmus not only reflects the functional state of vertical semicircular canal but also reflects the effect of otoliths. Medical experts can take nystagmus symptoms as the key factor to determine the cause of dizziness. Traditional observation (visual observation conducted by medical experts) may be biased subjectively. Visual examination also requires medical experts to have enough experience to make an accurate diagnosis. With the development of science and technology, the detection system for nystagmus can be realized by using artificial intelligence technology. In this paper, a vertical nystagmus recognition method is proposed based on deep learning. This method is mainly composed of a dilated convolution layer module, a depthwise separable convolution module, a convolution attention module, a Bilstm−GRU module, etc. The average recognition accuracy of the proposed method is 91%. Using the same training dataset and test set, the recognition accuracy of this method for vertical nystagmus was 2% higher than other methods.