A pulmonary nodule segmentation method based on a CT image

Abstract

The invention provides a pulmonary nodule segmentation method based on a CT image. The pulmonary nodule segmentation method comprises pulmonary parenchyma region extraction, pulmonary cavity region extraction, pulmonary lobe region extraction and region of interest extraction. According to the method and the device, through the first binarization processing and the second binarization processing,the influence of the binarization processing on the extraction of the focus region, namely the first appearing region and the second appearing region, is weakened, so that the focus separation precision is improved. After the first appearing area is highlighted, the threshold value of the first appearing area is further increased, whether the coordinates marked by a doctor are accurate or not is detected, such as whether the coordinates are on the blood vessel or not, so that the accurate separation of the nodules and the blood vessel is achieved, and meanwhile the workload of manual judgmentand the workload of manual repair during later verification of the doctor are reduced. On the premise that the threshold change range of the first appearing area is reasonably expanded, the second appearing area is determined and extracted, and the focus separation precision is further improved.

Description

technical field [0001] The invention belongs to the field of medical image processing, in particular to a method for segmenting pulmonary nodules based on CT images. Background technique [0002] Lung cancer has become the malignant tumor with the highest morbidity and mortality in the world, seriously threatening human life and health. Early detection is an effective way to improve the treatment effect of lung cancer patients. The detection and identification of nodules is increasingly important in the treatment of lung cancer. Accurate segmentation of pulmonary nodules is the key content of pulmonary nodule detection and recognition research, which directly affects the reliability of pulmonary nodule-assisted diagnostic techniques. [0003] Segmenting pulmonary nodules from lung CT images is an important application of image processing technology in medical images, and is of great significance in computer-aided diagnosis. Most methods start with noise reduction and then ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a lung nodule segmentation method based on CT images to solve the problems of low segmentation accuracy and poor robustness in the prior art, and can accurately separate nodules and blood vessels at the same time

Images