Medical Image Retrieval in Private Network Based on Dynamic Fuzzy Data Model and Wavelet Entropy

By analyzing the characters of CT medical image, this paper proposes a new model for CT medical image retrieval, which is using dynamic fuzzy logic and wavelet information entropy. Firstly, the image was decomposed by 2-D discrete wavelet transform to obtain the different level information. Then the entropy from low-frequency subband of CT medical image was calculated, and a membership function based on dynamic fuzzy logic was constructed to adjust the weight for image attribute. At last a model was constructed to obtain the similarity parameter by order for CT image retrieval. The efficiency of our model indicate it is very adaptive to the medical image retrieval in nosocomial private network.