APPLICATION CHAN-VESE METHODS IN MEDICAL IMAGE SEGMENTATION

The article presents the problem of determining the edges of objects enclosed in a medical CT images, which will be subject to further analysis, for the purpose of medical diagnosis. The use of a transformation which introduces two-point thresholding, eliminates presenting pixels of objects for tissues that are not a subject to further analysis. This approach allowed us to sharpen the edges of objects presenting soft tissue. A way to detect the edge of the soft tissue was compared for the original image and processed one using the transformation using the method of Chan-Vese. Sharpening of edges of the image have improved the accuracy of detection of objects presenting the soft tissue.