Unlock instant, AI-driven research and patent intelligence for your innovation.

Colorectal polyp segmentation method based on endoscopic image

An endoscope and colorectal technology, applied in the field of medical image processing, can solve the problems such as difficult to distinguish the edge area, difficult to determine the specific area of ​​colorectal polyps, and variable shape of colorectal polyps

Inactive Publication Date: 2020-01-10
UNIV OF SHANGHAI FOR SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When determining the specific location of colorectal polyps in the colorectum, it is usually judged through the endoscopic image of the colorectum. It is difficult to distinguish, which makes it difficult to determine the specific area of ​​colorectal polyps, which in turn affects the segmentation accuracy of colorectal polyps

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Colorectal polyp segmentation method based on endoscopic image
  • Colorectal polyp segmentation method based on endoscopic image
  • Colorectal polyp segmentation method based on endoscopic image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The idea, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings, so as to fully understand the purpose, features and effects of the present invention.

[0058] figure 1 It is a schematic diagram of the overall flow of the method for segmenting colorectal polyps based on endoscopic images according to an embodiment of the present invention.

[0059] Such as figure 1 As shown, the endoscopic image-based colorectal polyp segmentation method of this embodiment is used to determine the polyp specific area of ​​colorectal polyps from the endoscopic image of the colorectum, especially to determine the edge area of ​​colorectal polyps , including the following steps:

[0060] Step S1: Correct and denoise the endoscopic image to obtain a bubble-free image. Before segmenting the endoscopic image into a polyp-specific region, it is necessary to preprocess the endoscopic image to eliminate t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a colorectal polyp segmentation method based on an endoscopic image, which is used for determining a polyp specific area of polyp in colorectum from the endoscopic image of thecolorectum, and comprises the following steps: correcting and denoising the endoscopic image; selecting a polyp suspected region and a colorectal polyp clustering center point; setting an image analysis scale, and carrying out region enhancement on the suspected polyp region; selecting an initial background pixel clustering center point; taking the colorectal polyp clustering center point and theinitial background pixel clustering center point as initial clustering centers; establishing a cost function according to a k-means clustering method, and performing iterative computation on the initial clustering center so as to continuously update the current clustering center; obtaining a final clustering center until iteration is finished; and clustering the to-be-classified pixel points according to the final clustering center to obtain a specific polyp region. The method can accurately distinguish the edge area of the colorectal polyp and improve the segmentation precision of the colorectal polyp.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a colorectal polyp segmentation method, in particular to a colorectal polyp segmentation method based on an endoscope image. Background technique [0002] A polyp is an abnormal growth of tissue that is usually benign but can sometimes become cancerous. Colorectal polyps are formed on the lining of the colon or rectum. They are abnormal growths that start on the inner wall of the colon or rectum. A history of polyps is one of the main risks of colorectal cancer. Therefore, changes in the size of polyps cannot be ignored. The larger the size of the polyp, the The possibility of canceration is greater. [0003] Colonoscopy is a common clinical polyp detection method, which can detect precancerous polyps and cancer at the earliest stage of treatment. Doctors can remove early polyps or early lesions during the detection period to prevent the development of cancer. During this ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/11G06T7/194G06T7/00G06T5/00G06K9/62
CPCG06T7/11G06T7/194G06T7/0012G06T2207/20024G06T2207/20036G06T2207/30032G06F18/23213G06T5/77
Inventor 聂生东段辉宏吴文浩高磊王旭
Owner UNIV OF SHANGHAI FOR SCI & TECH