Neural Network-Based Diagnosing for Optic Nerve Disease from Visual-Evoked Potential

In this paper, we purpose a diagnostic procedure to identify the optic nerve disease from visual evoked potential (VEP) signals using an Artificial Neural Network (ANN). Multilayer feed forward ANN trained with a Levenberg Marquart backpropagation algorithm was implemented. The correct classification rate was 96.87% for subjects having optic nerve disease and 96.66% for healthy subjects. The end results are classified as healthy and diseased. Testing results were found to be compliant with the expected results that are derived from the physician’s direct diagnosis, angiography, VEP and pattern electroretinography. The stated results show that the proposed method could point out the ability of design of a new intelligent assistance diagnosis system.

[1]  G. Ravindran,et al.  Automatic Discrimination of Abnormal Subjects Using the Visual Evoked Potential Spectral Components , 2004, Journal of biomedicine & biotechnology.

[2]  Sadik Kara,et al.  Utilization of artificial neural networks in the diagnosis of optic nerve diseases , 2006, Comput. Biol. Medicine.

[3]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[4]  P Tigges,et al.  Identification of input variables for feature based artificial neural networks-saccade detection in EOG recordings. , 1997, International journal of medical informatics.

[5]  Vaegan,et al.  Visual evoked potentials standard (2004) , 2004, Documenta Ophthalmologica.

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Paulo J. G. Lisboa,et al.  Artificial Neural Networks in Biomedicine , 2000, Perspectives in Neural Computing.

[8]  Davide Dazzi,et al.  Classification and prediction of the progression of thyroid-associated ophthalmopathy by an artificial neural network. , 2002, Ophthalmology.

[9]  Michael Bach,et al.  Principles and practice of clinical electrophysiology of vision , 1991 .

[10]  Paul A. Lynn,et al.  An introduction to the analysis and processing of signals , 1973 .

[11]  Sadik Kara,et al.  Utilization of artificial neural networks and autoregressive modeling in diagnosing mitral valve stenosis , 2006, Comput. Biol. Medicine.

[12]  William J. Long,et al.  Medical informatics: reasoning methods , 2001, Artif. Intell. Medicine.

[13]  L. L. Lipoth,et al.  Electroretinographical (ERG) Based Classification Of Eye Diseases , 1991, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991.

[14]  Sadık Kara,et al.  Classification of electro-oculogram signals using artificial neural network , 2006, Expert Syst. Appl..

[15]  Allal Ouhtit,et al.  A model for UV-induction of skin cancer , 2001, Journal of biomedicine & biotechnology.

[16]  J. Odom.  VISUAL EVOKED POTENTIALS STANDARD , 2004 .

[17]  W. Tasman,et al.  Duane’s Foundations of Clinical Ophthalmology: Ocular Anatomy, Embryology and Teratology. Physiology of the Eye and Visual System. Pathology of the Eye , 1991 .

[18]  Andrew C. N. Chen,et al.  Automatic recognition of alertness and drowsiness from EEG by an artificial neural network. , 2002, Medical engineering & physics.

[19]  Hung T. Nguyen,et al.  Classification of diabetic retinopathy using neural networks , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[20]  Sadik Kara,et al.  Diagnosis of the macular diseases from pattern electroretinography signals using artificial neural networks , 2006, Expert Syst. Appl..

[21]  Rashmi Malhotra.  Artificial Neural Systems in Commercial Lending , 1994 .

[22]  Sadik Kara,et al.  Training a learning vector quantization network using the pattern electroretinography signals , 2007, Comput. Biol. Medicine.

[23]  G. Ravindran,et al.  Diabetic Retinopathy Analysis. , 2005, Journal of biomedicine & biotechnology.

[24]  A. Fiorentini,et al.  Electroretinographic responses to alternating gratings before and after section of the optic nerve. , 1981, Science.

[25]  I. Wright,et al.  Artificial neural network analysis of common femoral artery Doppler shift signals: classification of proximal disease. , 1999, Ultrasound in medicine & biology.