Nystagmus Signal Feature Extraction and Tracking for Diagnosis of the Vestibular System

This paper described a new algorithm for nystagmus signal feature extraction and tracking of nystagmus images, which could contribute to diagnose the disease of the vestibular system. Firstly, image denoising and image enhancement were employed to preprocess nystagmus images by selecting structural elements. Then, the circle center search method was used to extract the pupil contour and track pupil signals with removing closed eye data and interference. Finally, the cause of the vestibular system could be determined by calculating the value of the slow-phase velocity from the track waveform. This new algorithm has high accuracy and fully meets the clinical requirements for the detection of nystagmus signals.

[1]  Amine Ben Slama,et al.  Features extraction for medical characterization of nystagmus , 2016, 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[2]  Mounir Sayadi,et al.  Pupil tracking using active contour model for videonystagmography applications , 2014, International Image Processing, Applications and Systems Conference.

[3]  Yanpeng Wu,et al.  Improved image segmentation method based on morphological reconstruction , 2017, Multimedia Tools and Applications.

[4]  Spontaneous nystagmus in benign paroxysmal positional vertigo. , 2011, American journal of otolaryngology.

[5]  Himanshu Aggarwal,et al.  A Comprehensive Review of Image Enhancement Techniques , 2010, ArXiv.

[6]  R.A. Zoroofi,et al.  Open/Closed Eye Analysis for Drowsiness Detection , 2008, 2008 First Workshops on Image Processing Theory, Tools and Applications.

[7]  Li Wen,et al.  [An improved morphological edge detection algorithm of medical image based on multi-structure element]. , 2009, Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi.

[8]  Shutao Li,et al.  Multi-morphology image super-resolution via sparse representation , 2013, Neurocomputing.

[9]  Theekapun Charoenpong,et al.  A new method to detect nystagmus for vertigo diagnosis system by eye movement velocity , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).