Pulmonary nodule detection method based on CT image

Abstract

The invention discloses a pulmonary nodule detection method based on a CT image. The method particularly comprises steps: (1) a CT sequence image is acquired; (2) lung parenchyma segmentation is carried out; (3) trachea / main bronchus is removed; (4) marginal nodules are detected; (5) suspected nodules are detected; (6) features are extracted and classified; and (7) pulmonary nodules are calibrated. Detection on tiny nodules can be realized, the three-dimensional information of the CT sequence image is made full use of, partial volume effects are reduced, three-dimensional visualization of the pulmonary nodules can improve the detail display capability of the pulmonary nodules, a doctor can be better assisted to improve the diagnostic accuracy, pulmonary nodule feature extraction and classification do not need a large amount of priori knowledge, the detection real-time performance is good, the pulmonary nodule detection sensitivity is high, tiny nodules formed during an early lung cancer stage can be detected particularly, and requirements on the lung cancer CAD system accuracy, the handleability and the real-time performance by the doctor can be met.

Description

technical field [0001] The invention relates to the technical field of CT, in particular to a method for detecting pulmonary nodules based on CT images. Background technique [0002] With the rapid development of the economic level, human beings pay more and more attention to their own health. Early detection, early diagnosis and early treatment of cancer have increasingly become the common concern of the whole society. If lung cancer can be diagnosed and treated at an early stage, the 5-year survival rate of patients will increase from 14% to 49%. Because CT images can provide high-definition images and provide high contrast for each tissue in the image, it is usually used in Diagnosis of lung disease. With the development of multi-slice spiral CT, doctors can obtain higher-resolution images (HRCT), and obtain more patient image information through one detection, further expanding the application of CT images. But at the same time, it also increases the daily burden of re...

AI Technical Summary

Problems solved by technology

This is mainly due to the fact that the diameter of the pulmonary nodule is smaller than the thickness of the CT layer, which causes the local volume effect inside the volume data, and the detection results cannot meet the sensitivity requirements of the lung cancer CAD system in clinical applications; The computer-interactive method is used to detect pulmonary nodules. This type of method is generally more complicated to operate, requires high computer operation and medical diagnosis expertise, and requires high user ability; the method of pattern classification needs to be based on a large number of sample data. training, and needs to extract multiple features, the algorithm processing time is long, and it cannot meet the real-time requirements of CAD systems in clinical applications

Images