Capsule endoscope image preprocessing system and method

Abstract

The invention relates to a capsule endoscope image preprocessing system, comprising a body-out image removing module, an invalid image removing module, an alimentary canal image classifying module, a focus and anatomy structure recognizing module, and a focus and anatomy structure redundant image removing module, wherein the data output end of the body-out image removing module is connected with the data input end of the invalid image removing module; the output end of the invalid image removing module is connected with the data input end of the alimentary canal image classifying module; the data output end of the alimentary canal image classifying module is connected with the data input end of the focus and anatomy structure recognizing module; and the output end of the focus and anatomy structure recognizing module is connected with the data input end of the focus and anatomy structure redundant image removing module. According to the system and the method of the invention, it is possible for the doctors to reduce the time to check the body-out images, the redundant images and the invalid images, therefore, increasing the working efficiency.

Description

technical field [0001] The invention relates to the technical field of computer aided detection, in particular to a capsule endoscope image preprocessing system and method. Background technique [0002] The existing wireless capsule endoscope operation process requires that the subject’s appearance, brief information (such as name, gender, mobile phone number, etc.), capsule information (serial number, battery power, etc.) The proficiency of the instrument and capsule endoscope is different, and the subjects' adaptability to the capsule is different, which will make the capsule take a lot of pictures outside the body. [0003] These pictures can prevent the problem that the inspection data does not match the person being inspected, and are beneficial to data management. But these in vitro image data are of no use to the doctors who view the images. The main purpose of the doctor is to check whether there is any abnormality in the digestive tract of the tested person, and a...

AI Technical Summary

Problems solved by technology

But these in vitro image data are of no use to the doctors who view the images

The main purpose of the doctor is to check whether there is any abnormality in the digestive tract of the tested person, and a large amount of in vitro image data will affect the efficiency of the doctor's image review

[0004] For lesion locations (such as bleeding, polyps, ulcers, tumors, etc.) and specific anatomical structures (such as cardia, pylorus, etc.), when the wireless capsule endoscope shoots in the digestive tract, it will take multiple images continuously, resulting in redundant images. In addition, it will also affect the efficiency of doctors looking up images

[0005] During the shooting process, the distance between the stomach cavity and the stomach wall will cause the image to be too bright or too dark, resulting in more invalid images, which will affect the efficiency of doctors' image review

Images