Cytological image analysis with a genetic fuzzy finite state machine

Authors:
J. Estévez;S. Alayón;L. Moreno;J. Sigut;R. Aguilar
Affiliations:
-;-;-;-;-
Venue:
Computer Methods and Programs in Biomedicine
Year:
2005

Citing 3
Cited 4

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Learning feed-forward and recurrent fuzzy systems: a genetic approach

Journal of Systems Architecture: the EUROMICRO Journal - Special issue on evolutionary computing
Proceedings of the First European Workshop on Genetic Programming

EuroGP '98 Proceedings of the First European Workshop on Genetic Programming

Segmentation of kidney from ultrasound B-mode images with texture-based classification

Computer Methods and Programs in Biomedicine
An evolutionary Michigan recurrent fuzzy system for nuclei classification in cytological images using nuclear chromatin distribution

Journal of Biomedical Informatics
A fuzzy system for helping medical diagnosis of malformations of cortical development

Journal of Biomedical Informatics
Texture measures combination for improved meningioma classification of histopathological images

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of this research is to design a pattern recognition system based on a Fuzzy Finite State Machine (FFSM). We try to find an optimal FFSM with Genetic Algorithms (GA). In order to validate this system, the classifier has been applied to a real problem: distinction between normal and abnormal cells in cytological breast fine needle aspirate images and cytological peritoneal fluid images. The characteristic used in the discrimination between normal and abnormal cells is a texture measurement of the chromatin distribution in cellular nuclei. Furthermore, the effectiveness of this method as a pattern classifier is compared with other existing supervised and unsupervised methods and evaluated with Receiver Operating Curves (ROC) methodology.