A CT image pulmonary parenchyma three-dimensional semantic segmentation method based on a deep neural network

Abstract

The invention discloses a CT image pulmonary parenchyma three-dimensional semantic segmentation method based on a deep neural network. The segmentation method comprises an offline part and an online part. The offline part comprises four steps: preprocessing a data set; Constructing a full convolutional neural network framework; Constructing a GRU cyclic convolutional neural network framework; Network training. The online part comprises the following five steps: preprocessing an image; Extracting and fusing pixel features; Extracting and fusing voxel characteristics; Performing segmented output; Segmentation result evaluation. The feature fusion comprises feature fusion between an encoding layer and a decoding layer and feature fusion between anatomical structure layers. A deep neural network model with a gating circulation unit is designed, and spatial features are extracted by using anatomical structure prior information of a lung to effectively represent an apparent evolution relationship between fault sequences, so that accurate three-dimensional semantic segmentation is carried out on lung parenchyma in a CT image.

Description

technical field [0001] The invention belongs to the image segmentation technology in the field of medical image processing, in particular to a three-dimensional semantic segmentation method of lung parenchyma in CT images based on deep neural networks. Background technique [0002] Lung disease has always been a serious threat to human health. Lung cancer has the highest mortality rate of all malignant tumors, and the overall 5-year survival rate does not exceed 15%. With the rapid development of my country's economic level, people's attention to their own health is also increasing. Early diagnosis and early treatment of diseases have increasingly become the common concern of the whole society. In order to reduce the workload of doctors and detect lung diseases more quickly and accurately, the application of medical image processing technology in the auxiliary diagnosis of lung diseases is of great significance to the auxiliary diagnosis of clinical lung diseases. The segme...

AI Technical Summary

Problems solved by technology

The shortcomings of the region growing method are: (1) how to define the regional consistency criterion; (2) the segmentation result has a great relationship with the selection of the seed point; (3) this method is also very sensitive to noise and may Formation of porous or even discontinuous regions at all

[0008] Although these 2D CNN-based methods greatly improve the segmentation accuracy of traditional handcrafted feature-based methods, for volumetric medical image analysis, the effect may not be optimal because they cannot fully utilize the special information in the volumetric data.

Later, researchers proposed a 2.5D method to add richer spatial information, but it is still limited by the 2D kernel

Images