The invention relates to the technical field of medical image processing, and discloses a method and system for automatically generating a left and right lung three-dimensional model based on a CT image in order to solve the technical problem that existing equipment is low in automation degree, and the method comprises the steps that S1, an original image is acquired and recombined into three-dimensional data; s2, the three-dimensional data are automatically selected for preprocessing, and a secondary image is obtained; s3, segmenting and marking the secondary image to generate a binary image; step S4, generating a Label mark graph of the same peripheral contour ROI, and clearing all pixel values; pixel points are screened, and Label image feature analysis is carried out; s5, extracting a third image from the second image, establishing a corresponding relation, automatically realizing separation of the left lung, the right lung and the bronchial tube, and marking the left lung and the right lung; s6, extracting left and right lung segmentation data; and S7, reconstructing a left and right lung 3D model. The process does not need human interaction intervention, the automation level is improved, and the problem of low automation degree is solved.