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

Image processing method of cell smear

An image processing and cell smear technology, which is applied in the field of image processing of basal cell smears and can solve problems such as unsatisfactory sample staining.

Pending Publication Date: 2020-11-03
SHANDONG IND TECH RES INST OF ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In the first aspect, aiming at the problem of unsatisfactory staining of some areas of the sample or even the entire sample, an image processing method for automatically repairing stained images with unsatisfactory cell staining is proposed

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
  • Image processing method of cell smear
  • Image processing method of cell smear
  • Image processing method of cell smear

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] An image processing method for a cell smear, which performs the following operations: obtain an electronic image set of pathological pictures, construct an image training set, the image training set includes a cell image set and a stained image set, and the cell image set includes slice images marked with cells and Annotate slice images without cells, and the stained image set includes slice images marked with unsatisfactory staining and slice images marked with normal staining;

[0059] Construct a cell recognition neural network, input the cell image set into the cell recognition neural network to train the network until the cell recognition neural network can accurately identify whether there are cells in the image;

[0060] Constructing an image dyeing and repairing neural network, inputting the stained image set into the cell recognition neural network to train the network, until the dyeing and repairing neural network can output the input image as a dyed ideal imag...

Embodiment 2

[0075] The difference between this embodiment and Embodiment 1 lies in: preferably, the size of the slice image is the field of view under the microscope. All the other are identical with embodiment 1.

Embodiment 3

[0077]An image processing method for cell smears, which performs the following operations: collect fixed-size visual field pictures of cervical liquid-based cells, and construct a sharpness image data set. The sharpness image data set includes images with clear marks and images with blurred marks, and each An image marks its field of view size;

[0078] Construct a sharpness classification neural network, input the sharpness image data set into the fine definition classification neural network, until the sharpness classification neural network can accurately identify whether the image is a clear image or a blurred image;

[0079] Constructing the image definition restoration neural network, inputting the definition image set into the cell recognition neural network to train the network, until the image definition restoration neural network can output the input image as a clear image;

[0080] Obtain the current image to be processed, and slice the current image in the same way...

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

An image processing method of a cell smear comprises the following steps: collecting visual field pictures with fixed sizes of cervical liquid-based cells, and constructing a definition image data set, the definition image data set comprises images with clear marks and images with blurred marks, and the visual field size of each image is marked; the method has the advantages that for the problem of image blurring, the clearness condition of the visual field image is judged firstly, and when it is found that the image is blurred but can be restored, the clearness restoration neural network is started to restore the image. A definition classification neural network is used for screening blurred images, on one hand, images with restoration values are selected to improve the success rate of restoration, and on the other hand, repeated operation of the definition restoration neural network is avoided for clear images, operation time is saved, and operation efficiency is improved. Meanwhile,the definition restoration neural network method learns general features from a large number of actual images in an iterative mode, the strategy that a traditional method firstly estimates a fuzzy kernel and then estimates a clear image depends on artificial features is abandoned, and compared with the traditional method, the method has better adaptability.

Description

technical field [0001] The invention belongs to the field of image processing of medical pictures, in particular to an image processing method of a basal cell smear. Background technique [0002] In order to explore the disease process of organs, tissues or cells, some pathological and morphological examination methods are often used to check their lesions, discuss the causes, pathogenesis, and process of lesions, and finally make a pathological diagnosis. diagnosis. In the diagnosis of various diseases, the result of pathological diagnosis is recognized as the most accurate result of discrimination, and it is an important indicator for diagnosing disease in clinical diagnosis. [0003] For the examination of pathomorphology, first observe the pathological changes of the gross specimen, and then take a part of the sample to make a slide sample with histopathological method, and then use a microscope for further inspection. For example, a liquid-based thin-layer cytology de...

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 Applications(China)
IPC IPC(8): G06T7/00G06T5/00G06N3/08G06N3/04
CPCG06T7/0012G06N3/08G06T2207/10056G06N3/045G06T5/00
Inventor 吴健张久成吴边王文哲
Owner SHANDONG IND TECH RES INST OF ZHEJIANG UNIV