Unlock instant, AI-driven research and patent intelligence for your innovation.

Classification and setup of tumor cell images

A tumor cell and image technology, applied in the field of tumor cell image classification and devices, can solve the problems of time-consuming, energy-consuming, low efficiency, etc., and achieve the effects of improving robustness, individualized disease diagnosis, and assisting in guiding clinical decision-making

Active Publication Date: 2021-10-22
上海丹望医学检验实验室有限公司
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, by traversing all available models, it takes a lot of time and effort to approach the real optimal solution by trial and error, which shows that the traditional correlation classification scheme has low efficiency.

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
  • Classification and setup of tumor cell images
  • Classification and setup of tumor cell images
  • Classification and setup of tumor cell images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0028] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] Such...

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 present application relates to a classification and device of tumor cell images. Among them, the tumor cell image classification method trains m classifiers multiple times, determines L optimal projection matrices according to the objective function of the multi-classifier system including m classifiers, and obtains the image data of the cells to be tested. The characteristic data of the measured image data is projected into a new characteristic space through L optimal projection matrices to obtain L sets of characteristic data to be tested, and the L sets of characteristic data to be tested are input into m classifiers, and according to the output of m classifiers As a result, the category of the cells to be tested is determined, so as to realize accurate classification of the cells to be tested, and has high classification efficiency.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a classification and device of tumor cell images. Background technique [0002] The purpose of all decision support systems is to create a model that produces correct decisions. However, because different classification methods have their own advantages and limitations, when solving complex pattern recognition problems, it is difficult to select a classifier that can perform well in all applications and design a new classifier. more difficult. In this case, the multi-classifier system is designed as a method of combining multiple classifiers in a certain way without changing the structure of the original classifier, and has become a very popular tool in pattern recognition in recent years. At present, multi-classifier systems have been widely used in many fields such as bioinformatics, remote sensing science, network security, astrophysics, medical diagnosis,...

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): G06K9/62G06N3/12
CPCG06N3/126G06F18/241G06F18/214
Inventor 甄鑫梁芳蓉王琳婧
Owner 上海丹望医学检验实验室有限公司