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

Mask RCNN-based gastric cancer early recognition method, system and device

A technology for early identification and gastric cancer, which is applied in the field of image processing, can solve the problems of poor efficiency of image analysis tools, inability to effectively distinguish cancerous and inflammatory features, and low accuracy, and achieve the effect of reducing the pressure on clinicians, fast speed, and high diagnosis

Pending Publication Date: 2022-04-05
合肥中纳医学仪器有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of poor efficiency and low accuracy of the image analysis tools used in the existing gastroscopy process, and the inability to effectively distinguish the characteristics of cancer and inflammation; the present invention provides a method, system and device for early identification of gastric cancer based on Mask RCNN

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
  • Mask RCNN-based gastric cancer early recognition method, system and device
  • Mask RCNN-based gastric cancer early recognition method, system and device
  • Mask RCNN-based gastric cancer early recognition method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment provides a method for early identification of gastric cancer based on Mask RCNN, such as figure 1 shown, including the following steps:

[0063] S1: Construct a gastric cancer recognition network for outputting cancerous or inflammatory feature regions. The input of the gastric cancer recognition network is gastroscopy images, and the output of the gastric cancer recognition network model includes inspection conclusions and image segmentation results of cancerous or inflammatory features.

[0064] The construction method of the gastric cancer recognition network includes the following process:

[0065] S11: Obtain the classic Mask RCNN network model, the backbone network of Mask RCNN is the ResNet50 network.

[0066] Such as figure 2 As shown, the Mask RCNN network model includes a feature extraction network, a region proposal network and a head network. The feature extraction network adopts the ResNet50 network, which is used to extract the features...

Embodiment 2

[0106] This embodiment provides an early identification system for gastric cancer based on Mask RCNN. The identification system uses the early identification method for gastric cancer based on Mask RCNN as in Example 1 to identify gastroscopy images, and gives the indications that there are "cancerous" and "inflammation". " or "normal" inspection conclusion, and give the image segmentation results of the identified cancerous or inflammatory features. Such as Figure 8 As shown, the gastric cancer early detection system includes:

[0107] The image acquisition unit is used to acquire video of gastroscopy examination, and divide the video data into image data for output; the image data is used as an input of a gastric cancer recognition network.

[0108] The gastric cancer recognition network includes a canceration recognition subunit, an inflammation recognition subunit, and a discrimination unit. The output image data of the image acquisition unit is simultaneously input int...

Embodiment 3

[0115] This embodiment provides a device for early detection of gastric cancer based on Mask RCNN, which includes a memory, a processor, and a computer program stored on the memory and operable on the processor. Steps of the system method for early detection of gastric cancer based on Mask RCNN.

[0116] 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.

[0117]In this embodiment, the memory (that is, the readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), random access memory (R...

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 Mask RCNN-based gastric cancer early recognition method, system and device. The recognition method comprises the following steps: S1, constructing a gastric cancer recognition network, including the following steps: S11, obtaining a Mask RCNN network model; and S12, the architecture of the CSP Net network is introduced into the Mask RCNN network model. S13, replacing an IoU Loss function with a CIoU Loss function to serve as a regression loss function of the network model; and S14, constructing a gastric cancer identification network comprising two CSP-ResNet networks and a discrimination module. S2, a plurality of real gastroscopy images are obtained and pre-marked to serve as a training data set; and S3, training the network model by using the training data set. And S4, inputting the gastroscopy image into the gastric cancer identification network to obtain an image segmentation result of the corresponding focus area. The problems that an image analysis tool used in an existing gastroscopy process is poor in efficiency and low in accuracy, and canceration and inflammation characteristics cannot be effectively distinguished are solved.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method, system and device for early identification of gastric cancer based on Mask RCNN. Background technique [0002] Gastric cancer is a malignant tumor with high morbidity and mortality; the number of patients who die from gastric cancer accounts for more than 8% of all cancer deaths every year. Gastric cancer is the fifth most common cancer after lung cancer, breast cancer, colorectal cancer and prostate cancer; early detection and early treatment are the key to improving the survival rate of gastric cancer patients. [0003] Gastroscopy plays an important clinical role in the diagnosis of gastric diseases. Due to the early atypical symptoms of gastric cancer and its advanced aggressive behavior, reducing recurrence and prolonging survival are increasingly dependent on advanced screening, diagnosis, treatment and other new technologies. Gastroscopy is a common ...

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): A61B1/00A61B1/04A61B1/273G06N3/04G06N3/08
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com