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

Gastrointestinal endoscopic image classification and early cancer detection system based on multi-task neural network

A neural network and digestive tract technology, applied in the field of digestive tract endoscopic image classification and early cancer detection system based on multi-task neural network, can solve problems such as single detection or identification, reduce morbidity and mortality, and reduce human factors , the effect of improving the efficiency of diagnosis

Inactive Publication Date: 2019-01-01
FUDAN UNIV
View PDF4 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Existing DCNN methods mainly focus on a single task of detection or recognition, and few works can simultaneously achieve these two closely related tasks

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
  • Gastrointestinal endoscopic image classification and early cancer detection system based on multi-task neural network
  • Gastrointestinal endoscopic image classification and early cancer detection system based on multi-task neural network
  • Gastrointestinal endoscopic image classification and early cancer detection system based on multi-task neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The embodiments of the present invention will be described in detail below, but the protection scope of the present invention is not limited to the examples.

[0040] use figure 1 Using the network structure in , 1332 abnormal images and 1096 normal images are used to train a multi-task neural network to obtain an automatic classification and detection model.

[0041] The specific implementation method is:

[0042] (1) Before training, initialize the network parameters with the pre-trained VGG-16 model, and adjust the images in the training set to a uniform size of 300×300;

[0043] (2) During training, the image is randomly cropped to 224×224, and the mean value is subtracted. Set the initial learning rate to 0.0001, the decay rate to 0.9, and decay once every two cycles. Minimize the loss function using mini-batch stochastic gradient descent. The batch size is set to 12. In order to prevent overfitting, randomly kill some neurons in the fully connected layer in 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 belongs to the technical field of medical image intelligent processing, in particular to a gastrointestinal endoscopic image classification and early cancer detection system based on a multi-task neural network. The system of the invention comprises: (1) a feature extraction backbone network; (2) Classification of gastrointestinal endoscopic images; (3) regional detection branch of early gastrointestinal cancer. The invention adopts a multi-task depth neural network structure, and classifies and detects two tasks to share a plurality of convolution layers. Endoscopic images are inputted into the neural network model, and the detection and classification results can be obtained simultaneously after a forward propagation, which can effectively reduce the computational load andimprove the classification and detection accuracy. The experimental results show that the invention can accurately classify the endoscopic images into normal and early cancers and detect the irregularlesion areas in the early cancers images, reduce the influence of human factors and improve the efficiency of clinical diagnosis.

Description

technical field [0001] The invention belongs to the technical field of medical image intelligent processing, and specifically relates to a digestive tract endoscopic image classification and early cancer detection system, more specifically, a multi-task neural network-based digestive tract endoscopic image classification and early cancer detection system. Background technique [0002] Esophageal cancer is a common upper gastrointestinal cancer in China and developing countries. The new cases of esophageal cancer in China account for more than 40% of the total number of cases in the world, and the morbidity and mortality are significantly higher than the world average. Precancerous lesions of the esophagus, such as intraepithelial neoplasia and Barrett's esophagus, are the main causes of esophageal cancer. Upper gastrointestinal endoscopy screening has been recommended as the primary diagnostic method for screening for precancerous lesions due to its remarkable efficacy in r...

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): G06T7/00G06K9/62G06N3/04
CPCG06T7/0012G06T2207/30028G06N3/045G06F18/241
Inventor 颜波钟芸诗牛雪静蔡世伦谭伟敏李冰
Owner FUDAN 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

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