System and method for detecting lymph nodes in gastric CT images based on shape and ellipse fitting

Abstract

The invention discloses a lymph gland detection system and a method based on a stomach computed tomography (CT) image with a shape fitting with an oval. The system and the method mainly solve the problem that in an existing stomach CT image, missing inspection exists in automatic aquisition of a suspected lymph gland or left irrelevant information is excessively much. The system comprises a pre-processing module, an interested boundary point detection module, a boundary oval fitting module, an area combination module and a lymph gland tracking and extraction module. The pre-processing module carries out pre-processing on a to-be-detected image. The interested boundary point detection module carries out further processing on the processed image to obtain interested boundary points. The boundary oval fitting module carries out oval fitting on a curve formed by the interested boundary points to obtain an oval-like closed area. The area combination module eliminates ambiguous areas formed in oval intersection. The lymph gland tracking and extraction module carries out window characteristic match and tracking on the suspected lymph gland to complete extraction of the lymph gland. The system and the method can automatically and effectively extract a suspected lymph gland area which a doctor is interested in and ultimately detect the lymph gland, and can be used for medical image processing.

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] In recent years, medical imaging technology has developed rapidly, enabling clinicians to observe the internal lesions of the human body more directly and clearly, and the diagnosis rate is also higher. Computer-aided diagnosis CAD technology is called the doctor's "second pair of eyes". application prospects. As the key to computer-aided diagnosis, medical image processing technology continues to develop, and the crossover of various disciplines is an inevitable trend, but there are still many problems to be solved urgently, especially with the vigorous development of telemedicine, the proposed methods for medical image processing and analysis The requirements are getting higher and higher, so further research on medical image p...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the information contained in stomach CT images is complicated, and propose a system and method for detecting lymph nodes in stomach CT images based on shape and ellipse fitting, and detect lymph nodes in stomach CT images through computer function modules To avoid missed detection caused by human factors, accurately detect lymph nodes in gastric CT images

Images