Magnetic Resonance Imaging Segmentation on the Basis of Boundary Tracking Algorithm in Lung Cancer Surgery.

This work was to study the guiding value of magnetic resonance imaging (MRI) based on the target region boundary tracking algorithm in lung cancer surgery. In this study, the traditional boundary tracking algorithm was optimized, and the target neighborhood point boundary tracking method was proposed. The iterative method was used to binarize the lung MRI image, which was applied to the MRI images of 50 lung cancer patients in hospital. The patients were divided into two groups as the progression-free survival (PFS) and overall survival (OS) of surgical treatment group (experimental group,  = 25) and nonsurgical treatment group (control group,  = 25). The experimental group received surgical resection, while the control group received systemic chemotherapy. The results showed that the traditional boundary tracking algorithm needed to manually rejudge whether the concave and convex parts of the image were missing. The target boundary tracking algorithm can effectively avoid the leakage of concave and convex parts and accurately locate the target image contour, fast operation, without manual intervention. The PFS time of the experimental group (325 days) was significantly higher than that of the control group (186 days) ( < 0.05). The OS time of the experimental group (697 days) was significantly higher than that of the control group (428 days) ( < 0.05). Fisher exact probability method was used to test the total survival time of patients in the two groups, and the tumor classification and treatment group had significant influence on the OS time ( < 0.05). The target boundary tracking algorithm in this study can effectively locate the contour of the target image, and the operation speed was fast. Surgical resection of lung cancer can improve the PFS and OS of patients.