Lymph node detection system in gastric CT images based on low-rank decomposition and centroid tracking

Abstract

The invention discloses a stomach CT (computed tomography) image lymph gland detecting system based on low-rank decomposition and centroid tracking and mainly solves the problem that suspected lymph gland is inaccurate or mistaken in tracking in an existing stomach CT image. The stomach CT image lymph gland detecting method includes steps of 1, acquiring a suspected lymph gland sequence diagram; 2, decreasingly sequencing all suspected lymph glands in the acquired suspected lymph gland sequence diagram according to area and size; 3, determining initial head-end frames by low-rank decomposition of the suspected lymph gland largest in size after sequencing; 4, performing centroid tracking of the suspected lymph gland largest in area and with a self-adaptive window larger than 11*11 within the self-adaptive window after sequencing; 5, performing centroid tracking of the suspected lymph gland largest in area and with the self-adaptive window larger than 11*11 after sequencing without limits of the self-adaptive window; 6, deleting the tracked suspected lymph gland. Compared with other lymph gland detecting methods, the stomach CT image lymph gland detecting method improves accuracy of lymph gland tracking.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to medical image processing, which can be used for lymph node detection and auxiliary diagnosis of medical images. Background technique [0002] Due to the good visual properties of CT images, CT images have been widely used in the medical field. In the medical diagnosis of CT images, doctors find pathogens by observing a series of two-dimensional slice images, that is, the current analysis of CT image information mainly relies on doctors' own experience. However, with the rapid development of medical imaging technology, the number of CT images taken for each person is increasing day by day. Relying solely on doctors to process these images will lead to an increase in the workload of doctors. With the rapid development of computer technology and image processing technology, the information in CT images can be processed by computer, so that doctors do not need to spend a lo...

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to address the deficiencies of the above-mentioned prior art and provide a gastric CT image lymph node detection system based on low-rank decomposition and centroid tracking to solve the problems of tracking errors and inaccurate determination of the first frame in the process of suspected lymph node tracking

Images