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

Medical image classification method based on collaborative deep learning

A medical image and classification method technology, applied in the field of medical image classification based on collaborative deep learning, can solve problems such as poor classification accuracy, achieve the effect of strengthening feature representation, feature learning ability, and overcoming similar problems between classes

Active Publication Date: 2017-09-15
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of poor classification accuracy of existing medical image classification methods, the present invention provides a medical image classification method based on collaborative deep learning

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
  • Medical image classification method based on collaborative deep learning
  • Medical image classification method based on collaborative deep learning
  • Medical image classification method based on collaborative deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The specific steps of the medical image classification method based on collaborative deep learning in the present invention are as follows:

[0024] 1. Image pair input.

[0025] Using the input method of image pairs, two images are randomly sampled from the training images and input into two corresponding convolutional neural networks for training. Each pair of images has three supervision signals, which are the respective category labels of the two images and whether the pair of images belong to the same category. These three signals jointly supervise the training of the model.

[0026] 2. Dual deep convolutional neural network training.

[0027] The dual deep convolutional neural network module is the basic component of this algorithm, which includes two complete convolutional neural networks A and B with independent functions. In principle, convolutional neural networks of any structure can be applied to this algorithm module by deep feature extraction based on de...

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 a medical image classification method based on collaborative deep learning so as to solve the technical problem of poor classification accuracy of an existing medical image classification method. The technical scheme is characterized in that the method adopts a collaborative learning method between two deep convolution neural networks to carry out training in a mode of learning in pairs; each time, a model receives an image pair as input, and one pair of images are transmitted to the corresponding deep convolution neural networks respectively; the deep convolution neural networks are subjected to initialization and training through a pre-training model fine tuning method; a collaborative learning system is designed to allow the two deep networks to realize collaborative learning; and the collaborative learning is used for monitoring different or same attributes of the image pairs, that is, judging whether the image pair belongs to one category, and carrying out back propagation on collaborative errors generated by the two deep convolution neural networks in real time, and collecting network weight, so that the method can further enhance network learning feature representation capability, and can make an accurate judgment for easily-confused samples more effectively.

Description

technical field [0001] The present invention relates to a medical image classification method, in particular to a medical image classification method based on collaborative deep learning. Background technique [0002] Medical image classification methods play an extremely important role in medical retrieval, literature review and medical research, and have always been a hot research issue in the field of computer-aided diagnosis and medical research. In the past decades of research by countless researchers, a complete set of image classification techniques under the traditional model has been formed. Its core elements are two parts: manual feature extraction and classifier design. Although there is a very complete theoretical system, it is difficult for traditional image classification methods to achieve the seamless combination of optimal features and optimal classifiers, which leads to a great impact on their performance. In recent years, the emergence of deep learning t...

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): G06K9/62G06N3/08
CPCG06N3/082G06N3/084G06V2201/03G06F18/214G06F18/24
Inventor 夏勇张建鹏谢雨彤
Owner NORTHWESTERN POLYTECHNICAL 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