Lung lobe segmentation method and system based on three-dimensional convolutional neural network

Abstract

The invention discloses a lung lobe segmentation method and system based on a three-dimensional convolutional neural network. The method comprises the following steps: constructing a training image data set of lung lobe segmentation; constructing a lung lobe segmentation network based on a three-dimensional convolutional neural network, performing network training, preprocessing the training imagedata set, and outputting a category probability graph to which each pixel belongs after the training is completed; calculating the loss of the category probability graph to which each pixel belongs by adopting a Dice Loss loss function, and weighting the loss of a plurality of category probability graphs to obtain total loss; setting weight attenuation and learning rate attenuation, and trainingthe network until the network converges; preprocessing a to-be-detected image, inputting the preprocessed to-be-detected image into a trained lung lobe segmentation network, and outputting a prediction result; and restoring the prediction result subjected to post-processing to the original input size of the to-be-detected image to obtain a final segmentation result. The lung lobe segmentation result can be obtained through preprocessing and network reasoning, end-to-end design is achieved, and the lung lobe segmentation efficiency and precision are improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a lung lobe segmentation method and system based on a three-dimensional convolutional neural network. Background technique [0002] At present, lung lobe segmentation methods are roughly divided into four strategies: methods based on image registration, methods based on watershed segmentation, methods based on supervised learning, and methods based on deep learning. The existing methods based on image registration rely more on structure Atlas and large amount of calculation; the accuracy of the existing methods based on watershed segmentation depends on the constructed feature map, which is prone to mis-segmentation problems due to unclear watershed boundaries; the accuracy of existing methods based on supervised learning depends on artificial The extracted features require a large number of labeled samples; the existing deep learning-based methods first segment ...

AI Technical Summary

Problems solved by technology

[0002] At present, lung lobe segmentation methods are roughly divided into four strategies: methods based on image registration, methods based on watershed segmentation, methods based on supervised learning, and methods based on deep learning. The existing methods based on image registration rely more on structure Atlas and large amount of calculation; the accuracy of the existing methods based on watershed segmentation depends on the constructed feature map, which is prone to mis-segmentation problems due to unclear watershed boundaries; the accuracy of existing methods based on supervised learning depends on artificial The extracted features require a large number of labeled samples; the existing deep learning-based methods first segment the 3D bounding box of the lung area by cascading, and then perform lung lobe segmentation on the 3D bounding box, although the lung lobe segmentation accuracy is improved. , but the end-to-end workflow is not implemented, and the workflow is more complicated

Images