Pulmonary nodule interactive segmentation method based on medical image

Abstract

The invention discloses a pulmonary nodule interactive segmentation method based on a medical image. The method comprises the following steps: extracting a focus area according to a real nodule and aground glass nodule, wherein the segmentation algorithm is a semi-automatic segmentation algorithm, the lung real nodule segmentation method needs artificial participation to delineate a nodule region, and the lung frosted glass nodule segmentation method is automatic segmentation; if modification is needed after segmentation is completed, selecting two-dimensional modification or three-dimensional modification according to requirements to obtain an accurate segmentation result. Therefore, the rapid segmentation of pulmonary nodules is realized for further diagnosis and analysis.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, in particular to an interactive segmentation method of pulmonary nodules based on medical images. Background technique [0002] The situation of lung nodule screening for early prevention and control of lung cancer is still grim. There are many people suffering from lung cancer in my country, the incidence rate is high, and the medical expenses are large. According to the order of incidence, lung cancer accounts for 20.3% of all cancers, ranking first in the incidence of malignant tumors. According to the "National Cancer Report 2019" issued by the National Cancer Quality Control Center, the death rate of malignant tumors is as high as 23.91% of all residents' deaths, and the incidence and death of malignant tumors have continued to rise in the past ten years. More than 220 billion. In the process of clinical diagnosis, doctors need to screen nodules one by one in hundreds of ...

Images