Nuclear staining cell counting method based on deep learning of incomplete marker, computer equipment and storage medium

A deep learning and cell counting technology, applied in the field of deep learning, can solve the problems of single color cells, difficult to complete intelligent learning, low accuracy, etc.

Active Publication Date: 2021-05-04
SHANDONG UNIV
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) Traditional cell counting based on methods such as threshold segmentation and color channel separation have disadvantages such as low accuracy, inability to be used universally, and manual adjustment of parameters under different types of cells.
[0008] (2) The cell counting method based on deep learning relies on accurate labeling data, but manual pixel-by-pixel labeling by

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
  • Nuclear staining cell counting method based on deep learning of incomplete marker, computer equipment and storage medium
  • Nuclear staining cell counting method based on deep learning of incomplete marker, computer equipment and storage medium
  • Nuclear staining cell counting method based on deep learning of incomplete marker, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] A method for counting nuclear stained cells based on deep learning of incomplete marking, comprising the following steps:

[0095] (1) Create annotation data

[0096] Aiming at the current problems of cell counting, the present invention is based on the artificial intelligence cell counting scheme based on deep learning, combined with the characteristics of counting, and proposes an efficient, robust and easy-to-apply cell labeling method.

[0097] Load the pathological image to the labeling software to obtain all sub-images and sub-mask image data pairs of positive cells;

[0098] (2) Training model

[0099] Obtain all subimages and the submask image data pair of positive cells by step (1) to be the positive cell training set; Obtain all subimages and the submask image data pair of negative cells by step (1) to be negative cell training set;

[0100] Train the convolutional neural network model of the same structure through the positive cell training set and the neg...

Embodiment 2

[0107] According to a kind of method for counting nuclear stained cells based on the deep learning of incomplete labeling described in Example 1, the difference is that:

[0108] In step (1), make label data, such as image 3 shown, including the following steps:

[0109] a. Load the pathological image to the labeling software; usually it is not necessary to label the whole pathological slice image, just take an image with a size of about 700 in a certain field of view.

[0110] b. Establish a positive cell label, and click on the individual center points of all positive cells in the pathological image, and use the individual center points of each positive cell as the center of the rectangle to mark a rectangular block to form a real mask image of positive cells;

[0111] c. Establish a negative cell label, and click on the individual center points of all negative cells in the pathological image, and use the individual center points of each negative cell as the center of the ...

Embodiment 3

[0131] According to a kind of method for counting nuclear stained cells based on the deep learning of incomplete labeling described in embodiment 2, the difference is:

[0132] like figure 2 As shown, the inference phase includes the following steps:

[0133] The DCP-Net provided by the present invention can input an image of any size, but when the input image is too large, one-time input is likely to cause insufficient computing resources. Input the complete cell image into the network for automatic and intelligent cell identification, or input identification and detection one by one in a block-by-block manner when computing resources are insufficient.

[0134] A. Divide the pathological image to be detected into several sub-images of equal size;

[0135] B. Carry out mirror filling to the lower border and the right border of the sub-image obtained after the processing in step A, so that the size of the sub-image after mirror filling is a multiple of the preset sub-image s...

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 relates to a nuclear staining cell counting method based on deep learning of an incomplete label, computer equipment and a storage medium, and the method comprises the following steps: (1) making label data: loading a pathological image to label software, and obtaining sub-mask image data pairs of all sub-images and positive cells; (2) model training: training a convolutional neural network model to respectively obtain a trained positive cell convolutional neural network model and a trained negative cell convolutional neural network model; (3) reasoning stage: inputting pathological images to be detected into the trained convolutional neural network model to obtain real mask images; and (4) post-treatment stage: calculating the number of positive cells and negative cells, and calculating to obtain the proportion p of the positive cells in all the cells. The method does not need extra parameters, is high in universality, greatly reduces manual adjustment, and effectively improves the recognition accuracy and robustness. The method is faster, more accurate and more effective in data marking.

Description

technical field [0001] The invention relates to a nuclear staining cell counting method, computer equipment and storage medium based on deep learning of incomplete markers, and belongs to the technical field of deep learning. Background technique [0002] Cancer is now the leading cause of death in the world. In addition to improving cancer treatment technology, early diagnosis and screening of cancer is also an important aspect of improving the survival rate of cancer patients. The auxiliary diagnosis of pathological sections is to carry out immunohistochemical typing according to the positive status of ER, PR and Ki-67, and to determine different diagnosis and treatment plans according to different types. This depends on calculating the proportion of negative cells and positive cells in the total cells in the pathological section. Usually, when a doctor judges a positive state, he needs to observe different fields of view in the magnified section of the microscope, and o...

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): G06T7/00G06T7/136G06T7/90G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/136G06T7/90G06N3/04G06N3/08G06T2207/30242G06T2207/10061G06T2207/30024G06F18/23213G06F18/2415
Inventor 付树军廖胜海张欣欣孙青陈晓蔺王建行李玉亮齐泽荣
Owner SHANDONG UNIV
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