Reducing bias and inefficiency in the selection algorithm
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
An introduction to fuzzy control (2nd ed.)
An introduction to fuzzy control (2nd ed.)
Fuzzy Algorithms: With Applications to Image Processing and Pattern Recognition
Fuzzy Algorithms: With Applications to Image Processing and Pattern Recognition
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Segmentation of ultrasound breast images: optimization of algorithm parameters
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
Hi-index | 0.00 |
Clinical practice in echotomography often requires effective and time-efficient procedures for segmenting anatomical structures to take medical decisions for therapy and diagnosis. In this work we present a methodology for image segmentation in echography with the aim to assist the clinician in these delicate tasks. A generic segmentation algorithm, based on region evaluation by means of a fuzzy rules based inference system (FRBS), is refined in a fully unseeded segmentation algorithm. Rules composing knowledge base are learned with a genetic algorithm, by comparing computed segmentation with human expert segmentation. Generalization capabilities of the approach are assessed with a larger test set and over different applications: breast lesions, ovarian follicles and anesthetic detection during brachial anesthesia.