Liver CT automatic segmentation method based on deep shape learning

Abstract

The invention discloses a liver CT automatic segmentation method based on deep shape learning, and the method comprises the steps: firstly building a liver segmentation data set, carrying out the preprocessing, and carrying out the coarse segmentation of a liver CT through the liver segmentation; secondly, establishing a liver shape set, learning a liver shape by using a variational auto-encoder, constructing a geometrical shape regularization module, and then adding the geometrical shape regularization module into liver segmentation to obtain a liver segmentation model constrained by geometrical shape consistency for automatic segmentation of liver CT. According to the method, the expressed shape features are creatively added into the existing deep segmentation network through the regularization module, and shape prior information is introduced in the training process of the convolutional neural network, so that the regularity and generalization ability of the segmentation model can be improved, and the segmentation result is enabled to better conform to the medical anatomy characteristics of the standard liver. The method has the advantages of being automatic, high in precision and capable of being migrated and expanded, and automatic and accurate segmentation of the abdominal large organs, such as the liver, can be achieved.

Description

Technical field [0001] The present invention relates to the depth of the liver CT shape learning automatic segmentation CT segmentation method, and in particular relates based. Background technique [0002] Liver cancer is one of the most common malignant tumors, a serious threat to human life and health. Our country is a high incidence of liver cancer, liver cancer ranks third in cancer cause of death in our country. Liver cancer not only high degree of malignancy, rapid disease progression, and patients with early HCC lack of specific clinical manifestations, often at a late stage of the disease when the patient symptoms, difficult to treat and the prognosis is poor. Computer tomography (CT) diagnosis of liver cancer is one of the clinical imaging modality, provide quantitative information on volume, size, shape and the like based on accurate segmentation of liver CT image, and a subsequent lesion detection, image analysis, and the necessary steps basis, it is important applica...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the prior art, and propose a liver CT automatic segmentation method based on deep shape learning. The technical problem addressed by the present invention is that the existing deep learning liver segmentation method lacks geometric shape regularity, and cannot be well represented and Fusion Geometry Priors

Images