Automatic Liver Segmentation from CT Images Using Adaptive Fast Marching Method

Liver segmentation is the fundamental step in computer-aided liver disease diagnosis and surgery planning. In this study, we developed a fully automatic liver extraction scheme based on an adaptive fast marching method (FMM). Firstly, a thresholding operation was applied to remove the ribs, spines and kidneys. Followed by a smooth filter for noise reduction. Secondly, a nonlinear gray scale converter was used to enhance the contrast of the liver parenchyma. The enhanced image is then eroded with 3-voxel radius so that small regions are deleted. The seed points located in the liver were selected automatically. Finally, using the processed image as a speed function, FMM was employed to generate the liver contour. Clinical validation has performed on 30 abdominal computed tomography (CT) datasets. The proposed algorithm achieved an overall true positive rate (TPR) of 0.98. It takes about 0.30 s for a 512×512-pixel slice. The method has been applied successfully for fast and accurate liver segmentation.