Automatic delineation method and delineation system for lung tumor, calculation device and storage medium

Abstract

The invention discloses an automatic delineation method and delineation system for a lung tumor, a calculation device and a storage medium. The method comprises the following steps: collecting planned CT images, binary images of the lung tumor and binary images of a lung region of a preset number of lung tumor patients before radiotherapy; performing three-dimensional cutting on the divided planned CT image and the corresponding binary image, and extracting a tumor region; taking the planned CT image in the tumor area as input, taking the binary image of the lung area as output, and training to obtain a lung area segmentation model A; taking the segmentation result of the lung region and the preprocessed planned CT image in the tumor region as input, taking the binary image of the lung tumor as output, and training an obtained lung tumor segmentation optimization model B; and processing a planned CT image of a to-be-tested lung tumor patient, and sequentially inputting the processed planned CT image into the trained lung region segmentation model A and the lung tumor segmentation optimization model B to obtain a lung tumor segmentation result.

Description

technical field [0001] The present invention relates to the fields of medical image processing technology and deep learning technology, in particular to an automatic delineation method for lung tumors, a delineation system, a computing device and a storage medium. Background technique [0002] Most lung tumors originate from the bronchial mucosal epithelium, so it is also called bronchial lung cancer. In the past 50 years, the incidence of lung cancer has increased significantly all over the world. According to statistics, in some countries in Europe and the United States and in large cities in my country, the incidence of lung cancer has ranked first among all male tumors. If diagnosed early, the 5-year survival rate of lung cancer patients can increase to 70%, improving the prognosis of patients. [0003] In the process of radiotherapy for patients with lung tumors in hospitals, the delineation of the target area is often involved; at present, doctors mainly use manual de...

AI Technical Summary

Problems solved by technology

[0003] In the process of radiotherapy for patients with lung tumors in hospitals, the delineation of the target area is often involved; at present, doctors mainly use manual delineation, which requires high expert knowledge and experience, and there are inevitably human errors , affecting the patient's treatment; at the same time, manual drawing is time-consuming and laborious, affecting the doctor's work efficiency

Images