An automatic detection system for pulmonary nodules based on 3D convolutional neural network

Abstract

The invention discloses an automatic detection system for pulmonary nodules based on a 3D convolutional neural network. The invention innovatively divides the detection into two stages: (1) candidate pulmonary nodule detection stage and (2) false positive Pulmonary nodule screening stage. At the same time, each stage will construct and train a unique 3D CNN to be suitable for the detection and screening of pulmonary nodules; the 3D CNN in the first stage can initially detect suspected lung nodules. The location of the candidate lung nodules of the nodules, and then use the second stage of 3D CNN to filter out the false positive lung nodules among the candidate nodules, and finally find out the locations of all existing nodules in the entire lung CT image. The present invention can automatically detect the presence of nodules in a pair of lung CT images. Compared with the traditional manual nodule detection method, it has high detection accuracy, strong robustness, high efficiency, and short time consumption. Features, making the detection of pulmonary nodules more convenient and effective.

Description

technical field [0001] The invention belongs to the technical field of lung CT image detection and screening, and more specifically relates to a lung nodule automatic detection system based on a 3D convolutional neural network (CNN for short). Background technique [0002] At present, due to long-term smoking, air pollution and other reasons, the number of lung cancer cases is increasing rapidly all over the world. Lung cancer is a type of cancer with high morbidity and mortality in the world. According to data, the average 5-year survival rate of lung cancer in the world is only 16%, while the 5-year survival rate of early stage (I stage) lung cancer can reach 65%, but unfortunately only 10% of patients can survive lung cancer. Disease is detected at an early stage and treated accordingly. Evidence shows that annual lung computed tomography (CT) screening of lung health among high-risk groups can reduce lung cancer mortality by 20%. [0003] Lung nodules are often associ...

AI Technical Summary

Problems solved by technology

Such traditional methods often have problems such as heavy workload, time-consuming, error-prone and omissions, etc., and the screening results also mostly depend on the professional technical level of individual medical personnel

Images