AUTOMATIC SEGMENTATION OF LIVER STRUCTURE IN CT IMAGES USING A NEURAL-NETWORK

This paper describes a segmentation method of liver structure from abd ominal CT images using a three-layered neural network (NN). Before the NN segmentation, preprocessing is employed to locally enhance the con trast of the region of interest. Postprocessing is also automatically applied after the NN segmentation in order to remove the unwanted spot s and smooth the detected boundary. To evaluate the performance of the proposed method, the NN-determined boundaries are compared with those traced by two highly trained surgeons. Our preliminary results show t hat the proposed method has potential utility in automatic segmentatio n of liver structure and other organs in the human body.