Pulmonary nodule recognition and segmentation method and system based on deep learning

Abstract

The invention discloses a pulmonary nodule recognition and segmentation method based on deep learning, and the method comprises the steps: preprocessing a DICOM file so as to generate a chest CT image, segmenting a lung mask from the chest CT image, and repairing the lung mask; generating a three-channel lung image according to the chest CT image and the repaired lung mask, and inputting the three-channel lung image into a two-dimensional YOLO v3 neural network to detect a suspicious area of pulmonary nodules; standardizing the chest CT image according to the suspicious area to generate a standardized matrix, inputting the standardized matrix into a 3D Dense Net neural network and a C3D neural network for prediction, and generating a target prediction box according to a prediction result;and normalizing the chest CT image according to the target prediction box to generate a normalization matrix, inputting the normalization matrix into the 3D UNet neural network for segmentation, and optimizing a segmentation result. The invention further discloses a pulmonary nodule recognition and segmentation system based on deep learning. According to the invention, the accuracy and speed of identification and segmentation can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a method for identifying and segmenting pulmonary nodules based on deep learning and a system for identifying and segmenting pulmonary nodules based on deep learning. Background technique [0002] In the process of identifying pulmonary nodules in images, the commonly used identification methods mainly include the following: [0003] 1. Traditional morphological method: Based on three-dimensional shape pairs, different three-dimensional shapes (such as spherical, cylindrical, and curved surfaces) are used to simulate nodules, blood vessels, and pleura, respectively. However, this method tends to rely on the similarity between the nodule and the spherical shape, and it is easy to cause missed detection due to dissimilarity with the simulated shape. [0004] 2. Radiomics method: On the 3D image, traditional segmentation methods such as OTSU (maximum betwee...

AI Technical Summary

Problems solved by technology

However, the accuracy and speed of the small 3D CNN recognition network depend on the step size of the sliding window, and the two are mutually restrained; while the training of the large 3D CNN detection network is not easy to converge due to the large number of training parameters, and the prediction speed is relatively slow

Images