Research of Liver Segmentation Algorithm Based on High-Speed Complete Euclidean Distance Transformation and Statistical Analysis

Liver segmentation is a prerequisite for liver cancer CAD, and the result of it affects the accuracy rate of feature extraction and recognition of liver cancer directly. Euclidean distance transformation is one of the main methods in medical image segmentation. However, simply using Euclidean distance transformation will lead to some problems, such as over-segmentation and excessively high cost of calculation. Therefore, this paper puts forward a new method of liver segmentation, which combines high-speed complete Euclidean distance transformation with statistical analysis. The effectiveness of this method has been verified after we apply it to the liver segmentation of abdominal liver CT images.