A New 3D Model-based Minimal Path Segmentation method for Kidney MR Images
We present a robust, automated, model-based segmentation method for kidney MR Images. We used dynamic programming and a minimal path approach to detect the optimal path within a weighted graph between two end points. We used an energy function to combine distance and gradient information to guide the marching curve and thus evaluate the best path and span a broken edge. We developed an algorithm to automate the placement of initial end points. Dynamic programming was used to automatically optimize and update end points in the procedure for searching curves. A deformable 3D model was generated using principle component analysis (PCA) and it was used as the prior knowledge for the selection of initial end points and for the evaluation of the best path. We used our minimal path method with surface models to segment mouse kidneys slice-by-slice. The method has been tested for kidney MR images of 44 mice. To quantitatively assess the automatic segmentation method, we compared the automatic segmentation results with manual segmentation. The average and standard deviation of the overlap ratios is 0.93 ± 0.05. The distance error between the automatic and manual segmentation is 0.85 ± 0.41 pixel. The 3D automatic minimal path segmentation method is fast, accurate, and robust. It provides a useful tool for quantification and characterization of kidney MR images.
3D Segmentation minimal path deformable model Dynamic Programming polycystic kidney disease MRI
Ke Li Baowei Fei
Departments of Radiology Case Western Reserve University, Cleveland, OH, 44106 Departments of Radiology Case Western Reserve University, Cleveland, OH, 44106 Biomedical Engineerin
国际会议
上海
英文
2364-2366
2008-05-16（万方平台首次上网日期，不代表论文的发表时间）