Automatic segmentation method for solitary pulmonary nodules based on PET/CT

A solitary pulmonary nodule segmentation method was developed based on PET/CT (positron emission tomography/computed tomography) to assist doctors in clinical diagnosis. The image registration algorithm was used to complete the appropriate process with the processed images segmented and extracted using PET and CT. The metabolic imaging area of the modules was located in PET, with the high metabolic center of the region then regarded as the seed points to be mapped to the corresponding positions on the CT using the registration algorithm. The nodule images were extracted using the regional growth algorithm. The developed method was used to analyze the PET/CT data to show that complete functional and structural images of pulmonary nodules can be obtained, thus demonstrating the accuracy of the method even in the absence of supervision.