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

A medical image classification method based on a capsule theory and PLSA routing

A technology of medical imaging and classification methods, applied in the field of medical image analysis, can solve the problems of under-fitting and over-fitting, and achieve the effect of good processing

Inactive Publication Date: 2018-12-11
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Consistency routing simply uses the inner product between capsule vectors (ie, cosine similarity) as the contribution weight of the prediction results of low-level capsules to high-level capsules. The number of iterations depends on experience. Too many iterations can easily lead to overfitting, while Too few iterations can lead to underfitting

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
  • A medical image classification method based on a capsule theory and PLSA routing
  • A medical image classification method based on a capsule theory and PLSA routing
  • A medical image classification method based on a capsule theory and PLSA routing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A medical image classification method based on capsule theory and PLSA routing, please refer to figure 1 , Including the following steps:

[0048] S1: Input the original medical image;

[0049] S2: Construct a capsule-based convolutional neural network and perform classification prediction. The routing between the network capsule layers uses the probabilistic latent semantic analysis model PLSA for information transmission;

[0050] S3: Build a fully connected network for image reconstruction;

[0051] S4: Output the generated medical image.

[0052] In this embodiment, the capsule-based convolutional neural network described in step S2 includes the first layer of convolutional layer ReLUConv1, the second layer of PrimaryCaps layer and the third layer of ClassCaps, please refer to figure 2 ;

[0053] The first layer is the convolutional layer ReLU Conv1, which is a common convolutional layer. The input image size is 4×28×28, that is, the 3 RGB channel information of the original ...

Embodiment 2

[0078] Given a glaucoma medical image, after preprocessing, it is used as the input of the trained CapsNet network based on PLSA routing, and the glaucoma classification probability is output through calculation.

[0079] S1: Use the iMED-Origa650 data set to train the CapsNet classification network based on PLSA routing;

[0080] S2: Read the glaucoma medical image to be classified;

[0081] S3: Comprehensive use of image preprocessing technology, such as CLAHE to process the region of interest, and enhance the overall or local contrast of the image;

[0082] S4: Use the preprocessed image as the input of the trained network;

[0083] S5: The network outputs the classification probability value to determine whether the original image is glaucoma.

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 a capsule theory and PLSA routing. A PLSA probability model is introduced, a new capsule routing method is designed, and comparedwith consistent routing, this method uses a more reasonable soft clustering method to measure the consistency between capsules. Based on this, a medical image classification model is designed, whichcombines the capsule theory and PLSA routing, to better handle the task of medical image classification. The model framework consists of a convolutional neural network based on capsule and a fully connected network for image reconstruction. The convolutional neural network based on capsule uses PLSA routing to transfer the information between capsules, which not only can automatically learn the medical image features, but also can better find the size, position and direction of the features, and improve the classification accuracy. In order to improve the generalization ability of convolutional neural network based on capsule, full-connected image reconstruction network uses category capsule to recover original medical images.

Description

Technical field [0001] The present invention relates to the field of medical image analysis, and more specifically, to a medical image classification method based on capsule theory and PLSA routing. Background technique [0002] Medical imaging is an important part of medical data and has become an important basis for clinicians to diagnose. Clinicians need to perform various quantitative analysis on medical images to complete the diagnosis. Doctors viewing medical images are time-consuming and rely on personal experience, and the efficiency and accuracy of analysis are limited. Using computer technology to assist medical image analysis can effectively relieve the work pressure of clinicians and provide better medical services for patients. [0003] Medical image analysis includes image classification, target detection, image segmentation and retrieval, etc. The classification task is the most basic and can provide valuable judgment basis for disease screening. Computer technolo...

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): G06K9/62G06K9/34
CPCG06V10/267G06V2201/03G06F18/2415
Inventor 刘少鹏贾西平洪佳明林智勇马震远丘永发关立南廖秀秀高维奇
Owner GUANGDONG POLYTECHNIC NORMAL 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