System and method of detecting pulmonary nodule

Abstract

The invention discloses a system and a method of detecting a pulmonary nodule. The system comprises an image preprocessing module, a three-dimensional RPN network model and a three-dimensional capsulenetwork model, wherein the image preprocessing module is used for preprocessing an original three-dimensional CT image to acquire a standard CT image; the three-dimensional RPN network model is usedfor detecting a first candidate pulmonary nodule from the standard CT image outputted from the image preprocessing module; and the three-dimensional capsule network model is used for carrying out false positive pulmonary nodule screening on the first candidate pulmonary nodule outputted by the three-dimensional RPN network model to acquire a pulmonary nodule detection result. According to the technical scheme provided in the invention, while the false positive pulmonary nodule detection rate is ensured to be lower, a high recall ratio is ensured to be realized for the pulmonary nodule, and thedetection method is simple and the detection speed is quick.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a system and method for detecting pulmonary nodules. Background technique [0002] Lung cancer is a malignant tumor with the highest morbidity and mortality in the world. With the widespread use of computed tomography (CT) technology in hospitals, the mortality rate of lung cancer has been reduced by about 20%. All lung cancers evolve from pulmonary nodules, and the early imaging studies of lung cancer and pulmonary tuberculosis both show pulmonary nodules. At present, CT detection is a key step in the early screening of lung cancer. However, CT screening for early lung cancer is also challenging. To make a definite diagnosis of small pulmonary nodules, fine examination, three-dimensional mapping, and comprehensive analysis are necessary, which consume a lot of resources and time, and the diagnosis of pulmonary nodules is highly subjective. According to the "2017 Chi...

AI Technical Summary

Problems solved by technology

This method is complex to operate, and some errors will occur when the results of different slices are fused, resulting in the generation of wrong candidate pulmonary nodules

Images