| Lung cancer has become the most deadly cancer,in recent years,the rapid development of pulmonary segmental bed resection compared to conventional lobectomy can retain more healthy lung tissue,is conducive to the protection of patients with postoperative pulmonary function,improves postoperative quality of life,reduces postoperative complications.Because the pulmonary segment has separate pulmonary artery and pulmonary vein,the segmentation of pulmonary artery and pulmonary vein is critical for surgical path planning for segmental resection of the lung.Based on the above background,the chest CT images are used as data sources,combined with the anatomical structure characteristics of pulmonary vessels,the segmentation method of pulmonary artery and pulmonary vein is studied in the thesis.Firstly,the knowledge of medical image segmentation and center line extraction is introduced,and the method of lung parenchyma segmentation based on 3D region growth method is realized in the thesis.Secondly,Morphology is used to fill the holes in the segmented pulmonary parenchyma,and operation is made between the filled images and the original image to obtain the filled lungs with pulmonary vessels,the fractional differential operator is designed to enhance the gray level of the small blood vessels,and the complete pulmonary blood vessel is segmented by local optimal threshold.Thirdly,the algorithm of extracting the centerline of lung blood vessels based on two distance field is researched and the arteriovenous conglutination part of the pulmonary centerline is detected and removed automatically to obtain the vascular subtree.Finally,Using the knowledge of topological anatomy of pulmonary artery and vein,the vascular tree classification algorithm based on the subtree leaf node matching is studied and the pulmonary blood vessels are grown by region growth method through the center line,according to the anatomical knowledge that the volume of the pulmonary artery is smaller than that of the pulmonary vein,pulmonary artery and vein are extracted from chest CT image.The experimental results show that this proposed pulmonary artery and vein segmentation method has high accuracy and short operation time,and has good clinical application value. |