Method and system for marking irregular lesion area of endoscopic image of digestive tract

Abstract

The invention belongs to the technical field of image processing, and particularly relates to a method a system for marking an irregular lesion area of an endoscopic image of a digestive tract. The method of the invention comprises: selecting a target folder, and obtaining a file name of an image under the folder; automatically generating an output path; initializing an image mask; cropping the image and the mask and recording a cropping position; marking the lesion area, and updating the mask; and generating a border; saving the cropped image, the cropping position, the mask, and the border of the lesion area. The system mainly includes two functions of cropping and marking. A doctor can cut off the part of the endoscopic image that has a negative influence on the training of a deep neural network, and outline the irregular lesion area in the endoscopic image by a curve. The system automatically saves the cropped Image, the position, the mask, and the border of the lesion area, and the marking efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method and a system for labeling irregular lesion areas in endoscopic images of the digestive tract. Background technique [0002] Endoscopy and postoperative CT examination are important methods in the diagnosis and treatment of early gastrointestinal cancer, and endoscopy is a more important way of diagnosis and treatment. Japan, South Korea, and China are countries with a high incidence of gastrointestinal cancers. Japan has used gastrointestinal angiography to screen gastric cancer since 1960, and South Korea has launched a national upper gastrointestinal endoscopy screening project since 2002, and it is believed that endoscopic screening is in the Most cost-effective in the country [1] . Affected by the population base and medical level in our country, a gastrointestinal endoscopy screening project for the whole population has not yet been carried ou...

AI Technical Summary

Problems solved by technology

A simpler labeling method is to enclose the lesion area with a rectangular frame. However, due to the lack of ready-made tools, it takes a lot of time to label a picture. After the labeling is completed, special processing is usually required, such as detecting the rectangular frame marked by the doctor, and The shape of the lesion area is often irregular, and the method of marking the lesion area with a rectangular frame is not accurate enough

Images