Image Segmentation Method, Pulmonary Nodule Detection Method and Computer Aided Detection System

Abstract

The invention relates to an image segmentation method, a pulmonary nodule detection method and a computer-aided detection system. The image segmentation method comprises the following steps: a lung CT image is acquired; initial positioning is carried out on the CT image to obtain one or more positioning areas; a filter is adopted to enhance the positioning areas to acquire a target area; the target area processed based on a clustering model is judged, if a first judgment is met, a real region for the nodule is acquired; the target area processed based on a morphological model is judged, if a second judgment is met, a surrounding region for the nodule is acquired; and the real region and the surrounding region are fused to acquire an image segmentation result. According to the method and the system provided by the invention, different types of nodules can be accurately segmented, and follow-up diagnostic analysis can be effectively improved.

Description

【Technical field】 [0001] The invention relates to the field of medical image processing, in particular to an image segmentation method, a pulmonary nodule detection method and a computer-aided detection system thereof. 【Background technique】 [0002] Lung cancer is the cancer with the highest mortality rate worldwide. Although the level of medical diagnosis and treatment continues to improve, the five-year survival rate of lung cancer is only about 15%. Early detection and early treatment are the main ways to improve the cure rate of lung cancer. Pulmonary nodules are an early manifestation of lung cancer. CT scanning is currently the most effective imaging method for lung cancer screening. With the application of Computed Tomography (LDCT), the detection rate of small pulmonary nodules and early lung cancer has been continuously improved. The key technology to realize the automatic analysis and recognition of pulmonary nodules is: the research and application of a series...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the level set algorithm or the multi-scale threshold method are used for nodule segmentation, but because pulmonary nodules have various forms such as solid nodules, mixed ground-glass nodules, and ground-glass nodules, it is impossible to simply pass the morphological Method to accurately identify pulmonary nodules, especially mixed ground-glass nodules, ground-glass nodules and other irregular and fuzzy pulmonary nodules, which cannot be identified by edge-based algorithms such as Level Set

In addition, the gray value of pulmonary nodules in the CT image does not obey the Gaussian distribution, and the multi-threshold method is easy to cause leakage and result in inaccurate segmentation results.

Images