The Direction of Gradient Vector Flow Based on the Dynamic Model of Brain Tumor Segmentation
Yan Zhu · Xiandai shengwu yixue jinzhan · 2012
Objective: Convergence of GVF Snake model for the algorithm is easy to fall into local minimum and the initial out-line of a position-sensitive and other shortcomings,propose a dynamic model of the direction of gradient vector flow(DDGVF),make it more suitable for medical image segmentation.Method: Extraction using active contour model and track the target within a specific re-gion contour method,can be applied to medical imaging such as CT,MRI and ultrasound image processing,access to specific organs and tissues of the contour.Result: This method can extract the images of brain tumors.Conclusion: It provides a reliable basis for further study on their characteristics such as texture and shape description and analysis.