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

Bone marrow cell proliferation degree automatic grading method and system

An automatic grading, bone marrow cell technology, applied in image analysis, image enhancement, instrumentation, etc., can solve complex problems and achieve the effect of overcoming complex problems

Active Publication Date: 2020-05-05
北京理工大学重庆创新中心 +1
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, in order to solve the above-mentioned problems in the prior art, the object of the present invention is to provide a method and system for automatically grading the degree of myeloid cell proliferation to overcome the complicated problems in manual counting and provide accurate cells for grading the degree of myeloid cell proliferation. purpose of counting

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
  • Bone marrow cell proliferation degree automatic grading method and system
  • Bone marrow cell proliferation degree automatic grading method and system
  • Bone marrow cell proliferation degree automatic grading method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] like figure 1 As shown, in this embodiment, a method for automatically grading the degree of myeloid cell proliferation is specifically disclosed, and the method includes the following steps:

[0036] Step A: The bone marrow smear is collected through a Fourier stack microscope to obtain an intensity map and a phase map, and the high-resolution intensity map and phase map characteristics can be obtained by using a Fourier stack microscope. Among them, the intensity map contains the information of nucleated cells and non-nucleated cells, while the phase map only contains the information of nucleated cells. Using this feature, when counting nucleated cells later, the phase map and the intensity map are combined to improve Accuracy of nucleated cell counts.

[0037] Step B: Input the intensity map and phase map into the convolutional neural network model, and count the nucleated cells and anucleated cells in the bone marrow smear respectively through the characteristics o...

Embodiment 2

[0043] In this embodiment, an automatic grading system for the degree of bone marrow cell proliferation is also disclosed. The system includes an image acquisition unit, an image processing unit, and an automatic grading unit. Intensity map and phase map of bone marrow smear, where the intensity map contains the information of nucleated cells and non-nucleated cells, while the phase map only contains the information of nucleated cells. Using this feature, when counting nucleated cells later, Combine the phase map with the intensity map to increase the accuracy of nucleated cell counts.

[0044] The intensity map and the phase map are transmitted to the image processing unit, and the image processing unit is used to input the intensity map and the phase map into the convolutional neural network model, and the nucleated cells in the bone marrow smear are analyzed by the convolutional neural network model and enucleated cells were counted separately; during the counting process, ...

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 bone marrow cell proliferation degree automatic grading method and system, and belongs to the technical field of computational microimaging. The method comprises the following steps: performing image acquisition on a bone marrow smear to obtain an intensity graph and a phase graph; inputting the intensity graph and the phase graph into a convolutional neural network model, and respectively counting nucleated cells and nucleless cells in the bone marrow smear through the convolutional neural network model; and calculating the ratio of nucleated cells to nucleless cellsaccording to the counting result, and obtaining the grade of the bone marrow cell proliferation degree, so as to overcome the complex problem in manual counting and provide accurate cell counting forgrading of the bone marrow cell proliferation degree.

Description

technical field [0001] The invention belongs to the technical field of computational microscopic imaging, and in particular relates to a method and system for automatically grading the degree of proliferation of bone marrow cells. Background technique [0002] Fourier stack microscopic imaging technology is a microscopic imaging technology developed in recent years with large field of view, high resolution, and quantitative phase calculation. This method integrates the concepts of phase recovery and synthetic aperture. Similar to other phase recovery methods, the processing process of Fourier stack microscopic imaging technology is also iterated alternately according to the light intensity information recorded in the spatial domain and a certain fixed mapping relationship in the frequency domain, so as to obtain Phase information of the sample. In the traditional Fourier stack microscopy imaging system, the sample is illuminated by plane waves from different angles and imag...

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): G06T7/00G06K9/62
CPCG06T7/0012G06T2207/10056G06T2207/30024G06T2207/30008G06T2207/20084G06T2207/30242G06F18/253
Inventor 许廷发汪心张继洲张一舟王舒珊
Owner 北京理工大学重庆创新中心
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