Liver segmentation in CT images based on region-scalable fitting model

Liver segmentation in CT images is still a challenge in both radiology, medical image processing and machine learning. Due to the limitations from imaging procedure and other factors, most of liver CT images suffer from noise, edge blur and so on. In order to overcome the difficulties in liver CT image segmentation, a segmentation method based on region-scalable fitting model(RSF) is proposed. RSF model defines a data fitting energy and two fitting functions that locally approximate the image intensities on the two sides of the contour. After segmenting by RSF model, histogram statistics is employed for post-processing. Experimental results for liver CT images demonstrated desirable performances of the proposed method.