The feasibility of hybrid automatic segmentation of axillary lymph nodes from a 3-D sonogram.

摘要: The use of manual segmentation lymph nodes, within an ultrasound image, is challenging due to operator dependency and speckle. A group 23 healthy female volunteers consented a short imaging session capture maximum three axillary nodes. feasibility study was completed using both automatic techniques analyze sample 45, three-dimensional (3-D) nodal volume sets. Level-set based on geodesic active contours shape-space learning level-set approach used global node shapes. Most the image feature methods failed; however, more precise algorithm obtained superimposed shape model. Shape model significantly improved compared with standard level best results were achieved when experienced sonographer assisted setting seed surfaces. initialization surfaces lymphatic vessels.