Cell image segmentation method based on particle swarm neural network

A neural network and image segmentation technology, which is applied in the fields of biomedicine and image processing, can solve the problems of poor classification effect and time-consuming hidden layer neurons, and achieve the effect of facilitating subsequent processing, reducing blank points, and taking less time.

Inactive Publication Date: 2017-07-14
NANJING NORMAL UNIVERSITY
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although there are many segmentation methods for cell images, the existing methods have more or less defects. For example, the traditional setting of the number of neurons in the hidden layer is not only extremely time-consuming but also has many limitations, and it also affects the neurons in the hidden layer. The number of elements is only the number of samples in the traini...

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
  • Cell image segmentation method based on particle swarm neural network
  • Cell image segmentation method based on particle swarm neural network
  • Cell image segmentation method based on particle swarm neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] The cell image segmentation method based on the particle swarm neural network in this embodiment includes the following processes:

[0064] 1. Determine the number of neurons in the input layer: use the 9 pixels in the 3×3 window of the corresponding pixels as the input neurons.

[0065] 2. Determine the number of neurons in the output layer: if the expected number of classes is known and its value is greater than 2, the number of output neurons is equal to the number of expected classes; if its value is equal to 2, the number of output neurons is equal to 1 .

[0066]

[0067] Among them, C expects the number of classes; q the number of neurons;

[0068] In the case of q=C, if a certain sample is judged to be the mth class at this time, then n is the input sample and O(n) is the output label value.

[0069] 3. Use the estimation method based on information entropy to determine the number of neurons in the hidden layer:

[0070] a. Set the number of neurons 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 discloses a cell image segmentation method based on a particle swarm neural network. The method comprises following steps of inputting 3*3 windows to replace a traditional single pixel channel; adopting a method based on information entropy to determine the quantity of hidden layer neural elements; selecting activation functions of each layer; simplifying weight training to be an optimization problem; using an improved particle swarm to optimize and solve the problem; carrying out a network training; and analyzing test results. According to the invention, the method is improved based on the traditional BP neural network, so cell images can be well segmented; problems about how to determine the network structure and how to ensure that the network is converged to be overall optimal are solved; segmentation effects of the cell images are improved; and time loss in the cell segmentation process is relatively reduced.

Description

technical field [0001] The invention relates to biomedicine and image processing technology, in particular to a cell image segmentation method based on particle swarm neural network. Background technique [0002] Cell image is an important auxiliary research method for cell embryology and pathology, and plays an important role in the research of wound healing, autonomous defense mechanism, cancer cell metastasis mechanism, blood cell and immune cell statistical analysis, etc. The segmentation of cell images has important clinical application value and can improve the diagnosis and treatment of diseases. The segmentation of cell images is a key technology in the entire image processing and analysis, and the quality of segmentation has a very important impact on subsequent diagnosis. [0003] Although there are many segmentation methods for cell images, the existing methods have more or less defects. For example, the traditional setting of the number of neurons in the hidden l...

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): G06T7/11G06T7/136G06N3/08
CPCG06N3/08G06T2207/20081G06T2207/20084G06T2207/30004
Inventor 张煜东王水花刘方园周星星
Owner NANJING NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap