System and method for lymph node recognition in gastric CT images based on low-rank decomposition

Abstract

The invention discloses a stomach CT image lymph gland recognition system and method based on low-rank decomposition. Firstly, suspected lymph glands in a single image are extracted according to the spatial positions and shape characteristics of the lymph glands, and then local self-adaptive windows in one-to-one correspondence to the suspected lymph glands are built considering the fact that lymph glands and blood vessels are difficult to distinguish; if the size of a window is larger than 11*11, a lymph gland tracking and recognition method based on a decolor low-rank model is put forward, the initial frame and terminal frame of the corresponding suspected lymph gland are acquired, and whether the suspected lymph gland is a lymph gland or not is judged according to local-region area changes of the initial frame, the terminal frame and the frame with the largest area; if the size of a window is smaller than 11*11, a lymph gland tracking and recognition method based on region overlapping is put forward, a tracking sequence of the suspected lymph glands is acquired, if the length of the sequence is larger than 10, blood vessel judgment is carried out according to relevant features, and if the length of the sequence is smaller than 10, lymph gland judgment is carried out according to related features. By means of the system and method, lymph glands in a stomach CT image can be automatically and effectively recognized.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a medical detection system, which can be used for lymph node identification and auxiliary diagnosis of medical images, and in particular to a system and method for lymph node identification of gastric CT images based on low-rank decomposition. Background technique [0002] Gastric cancer is one of the most common malignant tumors in my country. According to the 2010 Health Statistics Yearbook, the incidence and mortality of gastric cancer in my country are second only to lung cancer, ranking second. There are as many as 400,000 new cases of gastric cancer in my country every year. The number of deaths due to gastric cancer is 300,000 every year, accounting for 23% of all malignant tumor deaths, and the mortality rate is extremely high. In clinical practice, CT imaging is a major tool for the diagnosis of gastric cancer. Traditionally, doctors analyze the pati...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a system and method for lymph node recognition of gastric CT images based on low-rank decomposition, which can accurately Complete target tracking and distinguish lymph nodes from blood vessels

Images