Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Gastroscopy video-based real-time image segmentation method, system and device

A gastroscopic examination and real-time image technology, applied in the field of image processing, can solve the problems of poor efficiency of image analysis tools, inability to cope with high frame rate and large-scale video stream data processing requirements, low accuracy, etc., so as to improve the identification ability and reduce the The effect of scale, improved efficiency and accuracy

Pending Publication Date: 2022-02-25
合肥中纳医学仪器有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the image analysis tools used in the existing gastroscopy process have poor efficiency and low accuracy, and cannot cope with the high frame rate and large-scale video stream data processing requirements; the present invention provides a real-time image based on gastroscopy video Segmentation method, system, device

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
  • Gastroscopy video-based real-time image segmentation method, system and device
  • Gastroscopy video-based real-time image segmentation method, system and device
  • Gastroscopy video-based real-time image segmentation method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] This embodiment provides a real-time image segmentation method based on gastroscopy video, such as figure 1 As shown, the medical image segmentation method includes the following steps:

[0053] S1: Construct a lightweight image segmentation network model based on the Mask-RCNN framework. The input of the image segmentation network model is the medical image of gastroscopy, and the output is the segmentation result of the target area with lesion characteristics. The model building process includes the following steps:

[0054] S11: Obtain a traditional Mask-RCNN network including a backbone network and a ROI (Region of Interes, region of interest) part.

[0055] The so-called output of the segmentation result of the target area with lesion characteristics is to draw a polygonal frame in the target area of ​​the overall image, which is used to identify different cancerous individuals contained in the image. This processing is actually an image segmentation task in comp...

Embodiment 2

[0122] This embodiment also provides a real-time image segmentation system based on gastroscopy video, which uses the real-time image segmentation method based on gastroscopy video as in Embodiment 1 to process the video stream data of the gastroscopy process, and then segment the image Target regions containing cancerous features. like Figure 5 As shown, the real-time image segmentation system includes: a video framing module, an image segmentation network model, and an image display module.

[0123] Wherein, the video framing module is used to obtain the original video stream data obtained by the gastroscope inspection equipment, and then perform frame division processing on the video stream data to obtain the original gastroscope image of each frame.

[0124] The image segmentation network model takes the original gastroscope image output by the video framing module as output, and then extracts and segments the area with cancerous characteristics in the image. The image ...

Embodiment 3

[0128] This embodiment also provides a real-time image segmentation device based on gastroscopy video, which includes a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, the following steps are implemented: The steps of the real-time image segmentation method based on gastroscopy video in embodiment 1.

[0129] The computer device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a combination of multiple servers) that can execute programs. server cluster), etc. The computer device in this embodiment at least includes but is not limited to: a memory and a processor that can be communicatively connected to each other through a system bus.

[0130] In this embodiment, the memory (that is, the readable storage medium) includes a flash memory, a hard disk, a mu...

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 belongs to the field of image processing, and particularly relates to a gastroscopy video-based real-time image segmentation method, system and device. The method comprises the following steps: S1, constructing a lightweight image segmentation network model based on a Mask-RCNN framework; S2, acquiring gastroscopy images as samples to form an original data set; de-noising processing the image, and dividing an original data set into a training set and a test set; S3, replacing the IoU and GIoU of the original loss function with a CIoU-Loss function, and training the network model; S4, testing the network model by using the test set, and reserving the network model with the best performance; S5, acquiring video stream data of gastroscopy, carrying out framing processing on the video stream data, then carrying out real-time segmentation on a framed image, and outputting a segmentation result of the target area with the lesion features. The problems that an existing image analysis tool is poor in efficiency and low in accuracy and cannot meet the high-frame-rate large-scale video stream data processing requirement are solved.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a real-time image segmentation method, system and device based on video of gastroscopy examination. Background technique [0002] Early detection of gastric cancer needs to be done through gastroscopy. The probe of gastroscopy equipment can be inserted into the body of the examinee to take endoscopic images of the digestive tract and stomach wall. According to the endoscopic images, professional inspectors judge whether there are cancerous features in the tissue of the object to be inspected, and then give the corresponding inspection results. The image analysis process of the existing gastroscopy medical examination mainly relies on professional doctors to complete. However, some professional medical image analysis tools have gradually been applied in the process of gastroscopy. These medical image analysis tools can process the acquired original images, extract the ...

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
IPC IPC(8): G06T7/00G06T7/11G06T5/00G06N3/08G06N3/04G06K9/62G06V10/26G06V10/764G06V10/82
CPCG06T7/0012G06T7/11G06N3/08G06T2207/20104G06T2207/10024G06T2207/20081G06T2207/20032G06T2207/10016G06T2207/10068G06T2207/30092G06N3/045G06F18/2415G06T5/70
Inventor 孔德润董兰芳董天意马涛彭杰宋绍方吴艾久
Owner 合肥中纳医学仪器有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products