A method and system for identifying and organizing foreground segmentation of IHC digital preview images

A technology of foreground segmentation and preview image, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of incomplete foreground recognition, inconsistent effect, difficult to extract effect, etc., and achieve good recognition effect, improved accuracy rate, and accurate recognition high degree of effect

Active Publication Date: 2021-04-02
览思(宁波)智能科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The tissue presented by immunohistochemically stained digital slides is inconsistent with other digital slides; immunohistochemical staining is very light, and in many cases the color of the foreground tissue is almost close to the background of the slide, and many impurities are presented. All aspects of the color are basically consistent with the scene tissue, which makes it difficult to extract satisfactory results with general image processing methods. The conventional recognition process is either easy to process other impurities into the scene tissue, or it is the real tissue The foreground recognition is incomplete, and it is difficult to obtain effective recognition results
This shows that the traditional simple image processing is ineffective for the processing of immunohistochemical digital slides, and a more breakthrough thinking method is needed

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
  • A method and system for identifying and organizing foreground segmentation of IHC digital preview images
  • A method and system for identifying and organizing foreground segmentation of IHC digital preview images
  • A method and system for identifying and organizing foreground segmentation of IHC digital preview images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] like figure 1 As shown, the IHC digital preview image recognition and tissue foreground segmentation method of the present embodiment include:

[0032] 1) A preview of the IHC figures against the input (e.g. figure 2 shown), extract the binary mask map M1 containing the tissue part and the impurity part (such as image 3 shown); wherein, the input IHC digital preview image can be obtained by using a digital slide scanner to obtain digital slides of immunohistochemical tissue images;

[0033] 2) According to the preset area threshold T1, all connected domains in the binary mask map M1 are divided into large-area connected domain contour sets q b and the set of small-area connected domain contours q s ;

[0034] 3) Contour collections for large-area connected domains q b For each connected domain outline in , it is corresponding to the corresponding area in the original IHC digital preview image, the features of the corresponding area are extracted and the featu...

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 method and system for IHC digital preview image recognition and tissue foreground segmentation. The invention includes extracting a binary mask image M1 including tissue parts and impurity parts from an input IHC digital preview image; All connected domains in Figure M1 are divided into large-area connected domain contour sets q b and the set of small-area connected domain contours q s ;For large-area connected domain contour collection q b For each connected domain outline in , it is corresponding to the corresponding area in the original IHC digital preview image, the features of the corresponding area are extracted and the features are classified by the machine learning model to remove the connected domain outline of impurities and leave the connected domain outline of the organization . The invention can segment the foreground of the tissue from the IHC digital preview image with very light staining and the color of the foreground tissue is almost close to the background of the glass slide, and has the advantages of high recognition accuracy and good recognition effect.

Description

technical field [0001] The invention relates to the field of digital image processing, the field of biomedical engineering technology and the field of micropathological imaging, in particular to an IHC digital preview image recognition and tissue foreground segmentation method and system. Background technique [0002] In order to automatically scan the entire process of digital slides, minimize the travel of the scanner’s stage, and shorten the entire scanning time, the primary task of the scanner is to complete the preview and range confirmation of the tissue on the slide, and reduce the number of blank areas added to the slide. During the scanning process; this requires that the real tissue area should be identified as completely as possible, and the interference of artifacts caused by other impurities should be removed; therefore, the primary task of a digital slide scanner is to accurately preview and identify digital slides. Very important; for HE-stained digital slides...

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): G06T7/00G06T7/136G06T7/187G06T7/194G06T7/90
CPCG06T7/0012G06T2207/10056G06T7/136G06T7/187G06T7/194G06T7/90
Inventor 余莉韩方剑黄少冰
Owner 览思(宁波)智能科技有限公司
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