A prior pertinence evaluation using fuzzy set and Bayes theory for esophagus wall segmentation

In this work, our interest is related to the esophagus inner and outer wall segmentation from ultrasound images sequences. We aim to elaborate a general methodology of data mining that coherently links works on data selection and fusion architectures, in order to extract useful information from raw data. In the presented method, based on fuzzy logic, some fuzzy propositions are defined using physicians a priori knowledge. The use of probability distributions, estimated thanks to a learning base, allows the veracity of these propositions to be qualified. This promising idea enables information to be managed through the consideration of both information imprecision and uncertainty. By considering that, the fuzzyfication process is optimized relatively to a given criteria using a genetic algorithm. We conclude this paper with some preliminary results and outline some further works.