Liver segmentation in CT image based on priori sparse dictionary and hole filling

For complicated liver images, this paper presents a three-dimensional automatic liver segmentation method based on sparse dictionary and hole filling technologies. The Gabor feature of an abdominal CT image was extracted. The image blocks with the same size on the border of liver gold standard in Gabor images and CT images were selected as two groups of train sets. Then, the training sets were used to get the dictionaries and sparse coding. The golden standard image was registered with the image to be segmented, and registered liver boundary was taken as the initial liver boundary of the image to be segmented. Furthermore, two sets of images with the same size were selected as the training sets in ten neighborhoods on the initial boundary. The sparse coding and image reconstruction error were computed by using the testing sets and the block-sparse dictionary, and the final liver boundary with the smallest image reconstruction error was obtained. Finally, a hole filling method was designed for liver boundary completion and smoothing to obtain the final segmentation results. The proposed method for the liver segmentation was evaluated by using the data sets of MICCAI 2007. The results show that this method has better segmentation applicability and robustness for the liver. It shows a higher segmentation accuracy, the volume overlap error rate is reduced to 5.21±0.0045, the relative volume error is 0.72±0.0012, and the average symmetric surface distance error is reduced to (0.93±0.14) mm.