Gallstone segmentation and extraction from ultrasound images using level set model

Gallstone is a high incidence of gallbladder disease, especially in the northwest of China. Segmentation and extraction of gallstone from an ultrasound image is prerequisite for taking decision regarding treatment. Because of the presence of speckle noise, low contrast and luminous in-homogeneity in ultrasound images, the available segmentation algorithms are general techniques and fail to detect gallstones in ultrasound images. A validation is required for proper identification of gallstone. As a result, there exists no general segmentation algorithm in hand that is suitable for segmentation. A new method for the segmentation of ultrasonic images of gallstones using level set as presented. The experimental results show that this method outperforms PCNN and is robust to extract gallstone from ultrasound images which is a subset of database with typical characteristics from the hospital of Ultrasound Diagnosis Department in Lanzhou. This is a publicly available and real dataset. Furthermore, the proposed method is helpful for clinicians as a decision support tool.