An automatic segmentation method of endangered organs based on convolution neural network

Abstract

The invention discloses an automatic segmentation method of a dangerous organ based on a convolution neural network, belonging to the technical field of image processing. The method comprises the following steps: S1, acquiring patient CT image data and corresponding labeling data; S2, preprocessing the CT graphic data and the corresponding labeling data; 3, establish a 3D convolution neural network model, inputting data block, and obtaining a prediction result image output by that model; S4: optimizing the prediction result image output by the 3D convolution neural network model. The present invention is only based on CT image data, has small difficulty in obtaining original data and wide application range, and can realize automatic segmentation of dangerous organs in CT image, and the segmentation process does not require manual interference, effectively improves segmentation efficiency and segmentation result precision, increases post-processing operation, and further optimizes the segmentation result.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an automatic segmentation method for organs at risk based on a convolutional neural network. Background technique [0002] Malignant tumor, which is often called cancer, is currently a global disease that is difficult to treat. It is equivalent to a killer in medicine and is the number one cause of death in the world. Among them, lung cancer is one of the thoracic malignant tumors with the fastest increasing morbidity and mortality rate and the greatest threat to the health and life of the population. The etiology of lung cancer is still not completely clear, but a lot of data show that long-term heavy smoking, urban air pollution and carcinogens contained in smoke may all lead to the occurrence of lung cancer. In addition, esophageal cancer is also a common thoracic tumor. According to statistics, about 300,000 people die of esophageal cancer every year in the world, a...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of the prior art, an embodiment of the present invention provides an automatic segmentation method of organs at risk based on a convolutional neural network to overcome the inability of the prior art to achieve fully automatic segmentation of organs at risk, low segmentation efficiency, and low accuracy of segmentation results. Problems such as poor image quality after segmentation

Images