Cytological Breast Fine Needle Aspirate Images Analysis with a Genetic Fuzzy Finite State Machine

Authors:
J. Estévez;S. Alayón;L. Moreno;R. Aguilar;J. Sigut
Affiliations:
-;-;-;-;-
Venue:
CBMS '02 Proceedings of the 15th IEEE Symposium on Computer-Based Medical Systems (CBMS'02)
Year:
2002

Citing 0
Cited 3

Virtual reality for medical training: a prototype to simulate breast aspiration exam

VRCAI '04 Proceedings of the 2004 ACM SIGGRAPH international conference on Virtual Reality continuum and its applications in industry
An evolutionary Michigan recurrent fuzzy system for nuclei classification in cytological images using nuclear chromatin distribution

Journal of Biomedical Informatics
Global optimization of case-based reasoning for breast cytology diagnosis

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

A system based on fuzzy finite State Machine (SM) has been developed for evaluatingcytological features derived directly from a digital scan of breast fine needle aspirate (NA)slides.The system uses computer vision techniques to analyse cell nuclei in order to extractdeterminate features and try to find by Genetic Algorithms (GA) the ideal SM able toclassify them.This application to breast cancer diagnosis uses characteristics of individualcells to discriminate benign from malignant breast lumps.In our system we try to find a texturemeasurement that can be included in the feature set to improve the classifier performance: acomplexity measurement of the structural pattern is used to discriminate between benign andmalign cells. With this measure and the technique described below we have observed that not only the absolute complexity of the image is relevant, but also the way in which the complexity is distributed at different scales .