DBN-DNN: discrimination and classification of VNG sequence using deep neural network framework in the EMD domain

ABSTRACT

The Vestibulo-ocular response VOR is characterized by a smooth pursuit eye movements in one direction, called slow phase of ocular nystagmus, interrupted by resetting saccades fast phase of nystagmus in the other direction. Recording of ocular nystagmus during vestibular tests does not quantify the true response of the vestibulo-ocular reflex (VOR). In order to extract the real VOR, our study is focused on nystagmus analysis using videonystagmography (VNG) technique based on measuring amplitude vibration of eyeball movement. The effectiveness of this attendance is severely topic to the attention and the experience of ENT doctors. In this case, automatic methods of image analysis offer the possibility of obtaining a homogeneous, objective and above all fast diagnosis of vestibular disorder.  In this paper, a fully automatic system based on nystagmus parameter analysis using a pupil detection algorithm is proposed. After a segmentation stage, a deep neural Network based classification method is applied on 90 eye movement recordings from videonystagmography (VNG) containing two types of peripheral vestibular disorders and normal patients. Experimental results obtained after several simulation, show the efficiency of the proposed methodology when compared with other classification methods.

KEYWORDS:

• Eye movement
• (VNG) system
• vestibular disorder
• empirical mode decomposition
• deep neural network

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Amine Ben Slama

Amine Ben Slama is a PhD Doctor in Biophysics and medical imaging from the University of Tunis El Manar, ISTMT. He is a member of research group in Laboratory of Biophysics and medical technologies at the same university. His research interests include deep learning methods, pattern recognition, video and biomedical signal analysis.

Hanene Sahli

Hanene Sahli, PhD, received a doctorate degree in science and technology-electrical engineering, from the University of Tunis, ENSIT. She is a member of the research group in Signal Image and Energy Mastery laboratory (SIME) at the same university. Her research interests include deep learning methods, pattern recognition, biomedical Video and Image analysis and biomedical Signal Processing.

Aymen Mouelhi

Aymen Mouelhi was born in Tunis in 1981 (Tunisia). He received the B.Sc. degree in electrical engineering from the Higher School of Sciences and Techniques of Tunis (ESSTT), the M.Sc. degree in automatic control and the Ph.D. degree in signal and image processing from the same school, respectively in 2003, 2006 and 2014. He is currently an Associate Professor at the Higher Institute of Applied Science and Technology of Mateur and member of research group in Laboratory of Signal Image and Energy Mastery (SIME) at ENSIT - University of Tunis. His research interests include image processing, classification and intelligent data processing for cancer diagnosis.

Jihene Marrakchi

Jihene Marrakchi is a professor of otorhinolaryngology in La Rabta hospital, Tunisia. Her research interests include oral, thyroid, vocal cord surgery and vertigo exploration. 

Mounir Sayadi

Mounir Sayadi is a Professor at ENSIT- University of Tunis and head of the research laboratory Signal Image and Energy Mastery (SIME) - University of Tunis. His research interests are focused on adaptive signal processing and filtering, medical image and texture classification and segmentation.

Hedi Trabelsi

Hedi Trabelsi born in 1975 in Tunis (Tunisia), he received the B.Sc. degree in Biophysics from the faculty of Sciences of Tunis, He is currently Professor at the higher institute of medical technologies of Tunisia University of Tunis El Manar, member of the Laboratory of biophysics and medical technologies. His research interests are focused on diffuse optical Tomography and physics simulation.