Abstract
We present a system able to provide and to simplify the automatic analysis of the diabetic retinopathies. The system stores and classifies the retinal images of diabetic subjects, allowing image filtering and anomalies localisation by pattern recognition methodologies combined with neural networks. The performance of the system has been quite improved by using committee techniques for the detection of retinal anomalies and with new algorithms specially designed to select the best classifiers to be inserted in the committee. The system has a simple, friendly, but powerful, interface supporting the medical personnel in the diagnostic process. To automate this process is particularly important when studying the diabetic retinopathy for the large number of patients and the frequency of analysis necessary for following the evolution of the pathology.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baxes, G. A. Digital Image Processing. Wiley, New York, 1994.
Casi, E., Ceravola, A., Cionini, R., Sperduti, A., and A. Starita. Diabetic Retina Analyzer, Proceedings of the 18 th Annual International Conference of IEEE Eng. in Med. and Biol. Soc., Amsterdam, 1996, 4:282–283.
Gardner, G. G., Keating, D., Williamson, T. H., and Elliott, A. T. Detection of Diabetic Retinopathy Using Neural Network Analysis of fundus Images. In Proc. 2 nd International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, Plymouth, UK, 1996.
Haykin, S. Neural Networks: A Comprehensive Foundation. 2nd ed., Prentice Hall, 1998.
Krogh, and Sollich, P. Statistical Mechanics of Ensemble Learning. Physical Review E, 55:811–825, 1997.
Olk, R. J., and Lee, Carol M.. La Retinopatia Diabetica, Vol. I, II. Mediserve, 1993.
Turner, K., and Ghosh, J.. Error Correlation and Error Reduction in Ensemble Classifiers. Connection Science, 8, n. 3&4:385–404, 1996.
Viti, S. Metodologia Computerizzata per l’Elaborazione delle Immagini del Fundus Oculi per lo Studio della Retinopatia Diabetica. “Tesi di Specializzazione”, University of Pisa, 1997. In Italian.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag London
About this chapter
Cite this chapter
Starita, A., Sperduti, A. (2000). A Neural-Based System for the Automatic Classification and Follow-Up of Diabetic Retinopathies. In: Lisboa, P.J.G., Ifeachor, E.C., Szczepaniak, P.S. (eds) Artificial Neural Networks in Biomedicine. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0487-2_18
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0487-2_18
Publisher Name: Springer, London
Print ISBN: 978-1-85233-005-7
Online ISBN: 978-1-4471-0487-2
eBook Packages: Springer Book Archive