Hybrid intelligent classification for Computer Aided Diagnosis (CAD) systems using image representation

• Autorzy: Chochra A. , Kanaoui N. , Madani K.
• Języki publikacji: EN

Abstrakty

EN

In this paper, a neural hybrid image classification for intelligent diagnosis systems from signal to image conversion (image representation) is suggested. Such hybrid approach (multiple models) mainly aims to ensure a satisfactory reliability for faults diagnosis systems, and particularly for medical diagnosis. Thus, an overview is given on how neural global and local approximators are interesting for image classification and why image classification (from signals to images conversion) is efficient than signal classification for fault diagnosis systems. Then, a neural hybrid image classification approach is suggested for intelligent medical diagnosis help, from biomedical signals, using MLP and RBF networks, under supervised learning. In this approach, each image is divided in several sub-images (local indicators) which are classified by global approxirnators (MLP) and by local approxirnators (RBF). Afterwards, a fuzzy decision-making system is suggested to give the final diagnosis with a Confidence Index (CI) parameter.

Słowa kluczowe

EN

intelligent diagnostic systems; image representation; pattern recognition; MultiLayer Perceptron (MLP) and Radial Basis Function (RBF) networks

PL

rozpoznawanie obrazów

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2005
• Tom: Vol. 10, no 2
• Strony: 7--16
• Opis fizyczny: Bibliogr. 16 poz., rys., wykr.

Twórcy

autor

Chochra A.

• Images, Signals, and Intelligent Systems Laboratory (LISSI / EA 3956), Paris-XII University, Senart Institute of Technology, Avenue Pierre Point, Lieusaint, 77127, France

autor

Kanaoui N.

• Images, Signals, and Intelligent Systems Laboratory (LISSI / EA 3956), Paris-XII University, Senart Institute of Technology, Avenue Pierre Point, Lieusaint, 77127, France

autor

Madani K.

• Images, Signals, and Intelligent Systems Laboratory (LISSI / EA 3956), Paris-XII University, Senart Institute of Technology, Avenue Pierre Point, Lieusaint, 77127, France

Bibliografia

• [1] Meneganti M., Saviello F. S., and Tagliaferri R., Fuzzy neural networks for classification and detection of anomalies, IEEE Transactions on Neural Networks, Vol. 9, No. 5, September 1998.
• [2] Balakrishnan K., and Honavar V., Intelligent diagnosis systems, Technical Report, Iowa State University, Ames, Iowa 50011-1040, U.S.A., 1997.
• [3] Haykin S., Neural Networks: A Comprehensive Foundation, International Edition, Second Edition, Prentice-Hall, 1999.
• [4] Wolf A., Hall Barbosa C., Monteiro E. C., and Vellasco M., Multiple MLP neural networks applied on the determination of segment limits in EGG signals, IWANN 2003, Proc. Part II, Mao, Menorca, Spain, June 2003, LNCS 2687, Springer-Verlag Berlin Heidelberg, pp. 607-614, 2003.
• [5] Plater J. H., Stuchlik F., von Specht H., and M tinier R., Fuzzy sets for feature identification in biomedical signals with selfassessment of reliability: an adaptable algorithm modeling human procedure in BAEP analysis, Computers and Biomedical Research, 28, pp. 335-353, Academic Press, 1995.
• [6] Vannier E., Adarn O., arid Motsch J. F., Objective detection of brainstem auditory evoked potentials with a priori information from higher presentation levels, Artificial Intelligence in Medicine, 25, pp. 283-301, 2002.
• [7] Bradley A. P., and Wilson W. J., On wavelet analysis of auditory evoked potentials, Clinical Neurophysiology, 115, pp. 1114-1128, 2004.
• [8| Zhang G. P., Neural networks for classification: a survey, IEEE Trans, on Systems, Man, and Cybernetics - Part C: Applications and Reviews, Vol. 30, no. 4, pp. 451-462, 2000.
• [9] Azouaoui O. and Chohra A., Soft computing based pattern classifiers for the obstacle avoidance behavior of Intelligent Autonomous Vehicles (IAV), Int. Journal of Applied Intelligence, Kluwer Academic Publishers, Vol. 16, No. 3, pp. 249-271, 2002.
• [10] Egmont-Petersen M., De Ridder D., and Handels II., Image processing with neural networks - a review, Pattern Recongnition, 35, pp. 2279-2301, 2002.
• [11] Motsh J. F., La dynamique temporelle du tronc cerebral: receuil, extraction, et analyse optimale des potentiels evoques auclitifs du tronc cerebral, PhD Thesis, Paris-XII University, France, 1987.
• [12] Chohra A., Kanaoui N., and Madani K., A neural network based computer aided diagnosis approach using a signal to image conversion: application to biomedical computer aided diagnosis, Computer Information Systems and Applications, Editors: K. Saeecl, R. Mosdorf, J. Pejace, O. P. Hilmola, Z. Sosnowski, I. El-Fray, Bialystok, Poland, pp. 96-107, 2004.
• [13] Gonzalez R. C. and Woods R. E., Digital Image Processing, Prentice-Hall, 2002.
• [14] Plater J. EL, Riseman E. M., arid Utgoff P. E., Interactively training pixel classifiers, Int. Journal of Pattern Recognition and Artificial Intelligence, 13 (2), 1999.
• [15] Murray-Smith R.. and Johansen T. A., Multiple Model Approaches to Modelling and Control, Taylor & Francis Publishers, 1997.
• [16] Madani K., De Trerniolles G., and Tannhof P., Image processing using RBF like neural networks: a ZISC-036 based fully parallel implementation solving real world and real complexity industrial problems, Int. Journal of Applied Intelligence, Kluwer Academic Publishers, Vol. 18, pp. 195-213, 2003.