Liver CT tumor segmentation and classification method based on deep learning

Abstract

The invention discloses a liver CT tumor segmentation and classification method based on deep learning. The method comprises the following steps of preprocessing a liver CT image, performing interpolation according to resolution ratios in X and Y directions, performing resampling, searching data, constructing training data, performing liver and tumor segmentation through 2D Dense U-Net, extracting corresponding three-dimensional features through 3D Dense U-Net, and forming a generative adversarial network. The invention belongs to the technical field of liver CT tumor segmentation and classification methods, and particularly relates to a method which can assist doctors in early screening and diagnosis of liver cancer by using a deep learning technology, can greatly reduce the workload of the doctors, improves the accuracy of liver cancer diagnosis, and improves the accuracy of liver cancer diagnosis. The liver CT tumor segmentation and classification method based on deep learning has a great application prospect.

Description

technical field [0001] The invention belongs to the technical field of liver CT tumor segmentation and classification methods, and specifically refers to a method for liver CT tumor segmentation and classification based on deep learning. Background technique [0002] Worldwide, the incidence of liver cancer ranks sixth, and the mortality rate ranks fourth. The early symptoms of liver cancer are not easy to detect. Whenever a patient has clinical symptoms, he has often reached the middle and late stages of liver cancer, which greatly reduces the chance of cure. Therefore, early detection, early diagnosis, and early treatment of liver tumors are one of the important topics in the research of diagnosis and treatment of liver tumors. Abdominal computed tomography (CT) is a common medical imaging method for detecting liver diseases. In the clinical work of reagents, liver tumors are mainly segmented manually by professional doctors, and then classified and judged based on clinic...

AI Technical Summary

Problems solved by technology

[0003] 1. The accuracy of liver region and tumor segmentation algorithm is not high;

[0004] 2. At present, most of the research is focused on the segmentation of liver and tumors, and there is no classification of the segmented tumors.

[0005] Patent CN202110049310.2, designed a method for segmenting liver tumors based on deep learning, compared with traditional image segmentation algorithms and machine learning-based segmentation algorithms, using a network structure similar to u-net for training, and solving The timeliness, versatility, and accuracy of traditional segmentation methods have been improved, but the current mainstream segmentation methods have used deep learning methods, so their methods lack theoretical innovation.

Patent CN202110493749.4, the present invention provides a liver image segmentation method based on deep learning, by using coarse segmentation neural network and fine segmentation neural network to process abdominal CT images, the effect of liver segmentation is improved, but it needs to obtain the final segmentation result After two different network models, the results obtained in the middle need to be cropped into image blocks and then input into the next-level network, and the final result cannot be obtained end-to-end

Images