Pulmonary nodule false positive screening method and system based on convolutional neural network

Abstract

The invention discloses a pulmonary nodule false positive screening method and system based on a convolutional neural network. The method comprises the steps of acquiring the coordinate position and the maximum radius value of a candidate pulmonary nodule from pulmonary CT image data; extracting original 3D image data of the candidate pulmonary nodule from the pulmonary CT image data according tothe coordinate position and the maximum radius value, and performing interpolation processing on the original 3D image data; obtaining sample data of three planes corresponding to the candidate pulmonary nodule 3D image data obtained through interpolation, and performing scaling processing on the sample data of the three planes to form a training set; and training a convolutional neural network based on the training set, and performing false positive screening on the candidate pulmonary nodules through a convolutional neural network model obtained through training. According to the embodimentof the invention, the problem of high false positive rate of the existing end-to-end network in the pulmonary nodule recognition process can be solved, and the accuracy of computer-assisted pulmonarynodule automatic detection is improved.

Description

technical field [0001] The invention relates to the field of medical technology, in particular to a method and system for screening out false positives of pulmonary nodules based on a convolutional neural network. Background technique [0002] Lung cancer is the most common malignant tumor in the world. In recent years, the newly discovered cases and deaths of lung cancer in my country far exceed those in other countries. The 5-year survival rate of lung cancer patients in my country is only 16.1%, which is far lower than that of western developed countries. One of the main reasons is that it is discovered too late. Early detection and early treatment are the only effective way to improve the survival rate. Low-dose CT (Computed Tomography, namely Computed tomography) is currently the only available means of early lung cancer screening. The main manifestation of early lung cancer is asymptomatic pulmonary nodules. Due to its complex shape, it is difficult for even experience...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for screening out false positives of pulmonary nodules based on a convolutional neural network, which can solve the problem of the existing end-to-end network in the process of identifying pulmonary nodules. There is a problem of high false positive rate, to improve the accuracy of computer-aided automatic detection of pulmonary nodules

Images