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

An image recognition method for early gastric cancer based on evolutionary neural network model compression

A neural network model, a technology for early gastric cancer, applied in biological neural network models, neural learning methods, character and pattern recognition, etc., can solve problems such as poor real-time performance, computational consumption, etc. The effect of model operation efficiency

Active Publication Date: 2021-08-13
SICHUAN UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an image recognition method for early gastric cancer based on evolutionary neural network model compression based on the deficiencies of the prior art. The method is based on an evolutionary algorithm and can efficiently and automatically discover Parameter redundancy, to solve the problem of poor real-time performance caused by the large computational consumption of the neural network model in the early gastric cancer recognition process

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
  • An image recognition method for early gastric cancer based on evolutionary neural network model compression
  • An image recognition method for early gastric cancer based on evolutionary neural network model compression
  • An image recognition method for early gastric cancer based on evolutionary neural network model compression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, the early gastric cancer identification method based on evolutionary neural network model compression provided in this embodiment includes the following steps:

[0049] (1) Collect and label early gastric cancer image datasets for training neural network models;

[0050] (2) Training the neural network model;

[0051] (3) Construct a binary encoding method to encode the parameters in the neural network model;

[0052] (4) Use evolutionary algorithms to compress the trained neural network model; reduce the amount of model calculation while maintaining network performance;

[0053] (5) Fine-tune the compressed neural network model and identify early gastric cancer lesion regions on newly input gastroscopy images.

[0054] Wherein, in the step (1), collecting and labeling the gastroscope image data set for training the neural network model includes the following steps:

[0055] (11) Record gastroscopy video streams, screen and cut out video c...

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 discloses an early gastric cancer image recognition method based on evolutionary neural network model compression, relates to the field of computer application technology, and solves the parameter redundancy in the existing convolutional neural network model and the large computational consumption of the neural network model in the early gastric cancer recognition process The problem of poor real-time performance caused by it; including the following steps: collecting an early gastric cancer image data set; training a neural network model; constructing a binary encoding method to encode parameters in the neural network model; using an evolutionary algorithm to train the neural network model Perform compression; fine-tune the compressed neural network model, and identify the early gastric cancer lesion area on the newly input gastroscopy image; the present invention can compress the neural network model for detection according to the collected gastroscopy image data, thereby improving early gastric cancer detection The efficiency of the neural network model in the task makes the deep neural network method have good real-time performance in early gastric cancer detection.

Description

technical field [0001] The invention relates to the technical field of computer applications, in particular to an early gastric cancer image recognition method based on evolutionary neural network model compression. Background technique [0002] Gastric cancer (GC) is the third most lethal malignancy worldwide. Due to the mild early symptoms, gastric cancer is usually diagnosed at an advanced stage, and its 5-year survival rate is less than 30%. If gastric cancer is detected early and treated accordingly, its 5-year survival rate can increase to over 95%. Therefore, the identification of early gastric cancer is of great significance to reduce the mortality rate of gastric cancer. Gastroscopy has been widely used in the diagnosis of early gastric cancer, which can provide guidance for early intervention and treatment. Since early gastric cancer usually only shows some subtle changes in the mucosa, the sensitivity of gastric cancer identification is generally relatively low...

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 Patents(China)
IPC IPC(8): G06K9/32G06K9/62G06T7/00G06N3/04G06N3/08
CPCG06T7/0012G06N3/084G06N3/086G06T2207/10068G06T2207/20081G06T2207/20084G06T2207/20104G06T2207/30096G06T2207/30092G06V10/25G06V2201/032G06N3/045G06F18/23213G06F18/241G06F18/214
Inventor 胡兵章毅张潇之周尧刘伟吴雨袁湘蕾
Owner SICHUAN UNIV
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