CN112270684B - Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system - Google Patents
Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system Download PDFInfo
- Publication number
- CN112270684B CN112270684B CN202011554677.1A CN202011554677A CN112270684B CN 112270684 B CN112270684 B CN 112270684B CN 202011554677 A CN202011554677 A CN 202011554677A CN 112270684 B CN112270684 B CN 112270684B
- Authority
- CN
- China
- Prior art keywords
- immunohistochemical
- microscopic
- image
- ihc
- positive cells
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a microscopic image immunohistochemical virtual multiple marking and analyzing method and system, which can realize virtual multiple marking on a plurality of groups of immunohistochemical microscopic panoramic pictures and automatic quantitative analysis on a specific area, and can compare and observe the expressions of a plurality of different antibodies (or antigens) at the same part by using the virtual multiple marking on the premise of ensuring the accurate results of various analysis and calculation indexes, and objectively judge the expression intensity of the antibodies (or antigens), thereby well solving the requirements of antibody (or antigen) multiple marking and reliable quantitative analysis in clinical pathological work and scientific research, subtracting the complex work of manual calculation and analysis of medical staff and scientific research personnel, and efficiently assisting the doctors and the scientific research personnel to finish the analysis of various immunohistochemical indexes after immunohistochemical multiple marking.
Description
Technical Field
The invention relates to the field of digital image processing, the technical field of biomedical engineering and the field of microscopic pathology automatic analysis, in particular to a microscopic image immunohistochemical virtual multiple labeling and analysis method and system.
Background
Immunohistochemistry (Immunohistochemistry) is also known as immunocytochemistry. It is a branch of histochemistry, and is a tissue and cell in situ detection technique for the distribution of antigen (or antibody) in tissue by using a labeled specific antibody (or antigen). As a mature, reliable, economical and widely applied technical means, the method is widely applied to clinical pathological diagnosis and scientific research at present, and has irreplaceable effects on judgment of tumor tissue sources, evaluation of tumor risks, selection of treatment methods and observation of tissue and cell antibody (or antigen) expression levels and distribution ranges in various experiments.
In the traditional immunohistochemistry, only one antibody (or antigen) can be marked at one time, and the existing interpretation of the immunohistochemistry is artificial semi-quantitative interpretation, the interpretation result is often strong in randomness, large in man-made interference and poor in objectivity, and considerable difficulty and great errors are brought to the marking and expression comparison of different antibodies (or antigens) in the same cell or the same region and the research of the correlation among the antibodies (or antigens). Comparing the expression of different antibody (or antigen) markers in the same site or in the same cell is very necessary and necessary in clinical and pathological diagnosis and many scientific experimental scenes, so how to perform multiple markers of antibodies (or antigens) and perform reliable quantitative analysis becomes a hot spot in current research.
The double-label immunohistochemistry is a better mode applied at present, has the capability of simultaneously marking two antibodies (or antigens), and is based on an intuitive multicolor positioning dyeing method established according to the difference of a positive expression part and a positive expression area. The labeling objects are two cell parts, including three combinations of membrane + plasma type, membrane + karyotype and plasma + karyotype, but the method has obvious limitation, firstly, the method cannot be used for labeling the membrane + membrane type, the nuclear + karyotype and the plasma + karyotype antibodies (or antigens), and the effect and the color overlap are influenced; secondly, the basic principle of immunohistochemistry is that antigen-antibody combination, and the simultaneous labeling of two antibodies (or antigens) is easy to generate cross reaction, which may cause false positive or false negative, which affects the dyeing effect and accuracy, and is also the reason that the method is mainly used for scientific research and is not widely applied in clinical pathological diagnosis for a while; finally, the method can only label two antibodies (or antigens) at the same time, cannot label a plurality of antibodies (or antigens) at the same time, and does not fundamentally solve the problem of immunohistochemical objective interpretation.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: aiming at the problems in the prior art, the invention provides a microscopic image immunohistochemical virtual multiple marking and analysis method and a microscopic image immunohistochemical virtual multiple marking and analysis system, which can realize the virtual multiple marking of a plurality of groups of immunohistochemical microscopic panoramic images and the automatic quantitative analysis of a specific area, on the premise of ensuring the accuracy of each analysis and calculation index result, the expression of a plurality of different antibodies (or antigens) at the same part is compared and observed by using virtual multiple markers, the expression intensity of the antibody (or antigen) is objectively interpreted, so that the requirements of multiple labeling of the antibody (or antigen) and reliable quantitative analysis in clinical pathological work and scientific research can be well met, the complicated work of manual and manual calculation analysis of medical staff and scientific research staff is reduced, and the analysis of various immunohistochemical indexes after immunohistochemical multiple labeling is efficiently assisted by doctors and scientific research staff.
In order to solve the technical problems, the invention adopts the technical scheme that:
a microscopic image immunohistochemical virtual multiple labeling and analysis method comprises the following steps:
1) scanning by a scanner to obtain corresponding continuous immunohistochemical sections to obtain each corresponding IHC microscopic panoramic image, wherein each IHC microscopic panoramic image is stored in a storage format of a multi-resolution pyramid file;
2) selecting one IHC microscopic panoramic image as a registration reference image, carrying out coarse registration of the organization level on the rest IHC microscopic panoramic images based on a multi-resolution pyramid file, and fusing to obtain a preliminary fusion model;
3) determining a target area of immunohistochemical index analysis in the registration reference image, calculating to obtain corresponding target areas in the rest IHC microscopic panoramic images according to the primary fusion model, and performing fine registration operation on all the target areas to obtain IHC cancer tissue image blocks;
4) statistical analysis of multiple immunohistochemical markers and corresponding indices were performed on IHC cancer tissue panels.
Optionally, when the corresponding continuous immunohistochemical sections are obtained by scanning with the scanner in step 1), the thickness of a single immunohistochemical section is 2-3 micrometers.
Optionally, the step of performing coarse tissue-level registration on the rest IHC micro-panoramas based on the multi-resolution pyramid file and performing fusion to obtain a preliminary fusion model in step 2) includes:
2.1) registering the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling;
2.2) the obtained registration parameters are applied to the images of the bottom layer in the multi-resolution pyramid file to complete a primary registration process of one-to-one pairing of each picture block in the registration reference image and each group of rest IHC microscopic panoramic images;
and 2.3) carrying out three-dimensional superposition on the preliminarily registered IHC microscopic panoramic image to obtain a preliminary fusion model.
Optionally, the step of performing a fine registration operation on all target regions in step 3) includes: performing cell-level registration on the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling; and (3) applying the obtained registration parameters to the images of the middle and bottom layers of the multi-resolution pyramid file to complete a one-to-one pairing fine registration process of all target areas in each of the registration reference image and each of the rest IHC microscopic panoramic images to obtain an IHC cancer tissue image block.
Optionally, the statistical analysis of multiple immunohistochemical markers and corresponding indicators for IHC cancer tissue patches in step 4) refers to counting the number of positive and non-positive cells in cancer cells for the target region.
Optionally, the step of performing statistics of the number of positive and non-positive cells in the cancer cells comprises: carrying out dye channel separation and color normalization processing by using a color deconvolution method aiming at IHC cancer tissue picture blocks obtained by fine registration; then, segmenting the preprocessed picture block by using a watershed algorithm, and separating to obtain a cancer tissue foreground and background area; then, after automatic threshold segmentation and image expansion corrosion operation, finding out the outline of each cell; then, according to the color and the shape, positive cells and non-positive cells are obtained by distinguishing; and finally, counting the number of the obtained positive cells and the number of the obtained non-positive cells respectively, wherein the positive cells comprise nuclear positive cells, plasma positive cells and membrane positive cells.
Optionally, the step 4) of performing a statistical analysis of multiple immunohistochemical markers and corresponding indicators on the IHC cancer tissue image block further comprises obtaining the number of positive cellsR i1,And number of non-positive cellsR i2,A step of calculating a positive rate, wherein i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
Alternatively, the said method is based on the number of positive cells obtainedR i1,And number of non-positive cellsR i2,The functional expression for calculating the positive rate is as follows:
in the above formula, the first and second carbon atoms are,H rate the positive rate is obtained by the method,R i1,the number of the positive cells is the number of the positive cells,R i2,the number of non-positive cells, where i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
In addition, the invention also provides a microscopic image immunohistochemical virtual multiple labeling and analysis system, which comprises a microprocessor and a memory which are connected with each other, wherein the microprocessor is programmed or configured to execute the steps of the microscopic image immunohistochemical virtual multiple labeling and analysis method, or the memory is stored with a computer program which is programmed or configured to execute the microscopic image immunohistochemical virtual multiple labeling and analysis method.
Furthermore, the present invention also provides a computer readable storage medium having stored therein a computer program programmed or configured to perform the foregoing microscopic image immunohistochemical virtual multiple labeling and analysis method.
Compared with the prior art, the invention has the following advantages: the invention can realize virtual multiple marking of a plurality of groups of immunohistochemical microscopic panoramas and automatic quantitative analysis of specific areas, on the premise of ensuring the accurate result of each analysis and calculation index, the expression of a plurality of different antibodies (or antigens) at the same part is compared and observed by using the virtual multiple marking, and the expression intensity is objectively interpreted, thereby well solving the requirements of antibody (or antigen) multiple marking and reliable quantitative analysis in clinical pathological work and scientific research, subtracting the complicated work of manual calculation and analysis of medical staff and scientific research staff, and efficiently assisting doctors and scientific research staff to finish the analysis of each immunohistochemical index after immunohistochemical multiple marking.
Drawings
FIG. 1 is a schematic diagram of a basic flow of a method according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a storage format of a multi-resolution pyramid file according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating coarse registration according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a preliminary fusion model obtained in an embodiment of the present invention.
Fig. 5 is a flowchart illustrating a fine registration operation according to an embodiment of the present invention.
FIG. 6 is a schematic diagram of a fine fusion model obtained in an embodiment of the present invention.
FIG. 7 is a statistical process for each cancer tissue image block according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, the method for immunohistochemical virtual multiple labeling and analysis of microscopic images of the present embodiment includes:
1) scanning by a scanner to obtain corresponding continuous immunohistochemical sections to obtain each corresponding IHC microscopic panorama, wherein each IHC microscopic panorama is stored in a storage format of a multi-resolution pyramid file, as shown in FIG. 2;
2) selecting one IHC microscopic panoramic image as a registration reference image, carrying out coarse registration of the organization level on the rest IHC microscopic panoramic images based on a multi-resolution pyramid file, and fusing to obtain a preliminary fusion model;
3) determining a target area of immunohistochemical index analysis in the registration reference image, calculating to obtain corresponding target areas in the rest IHC microscopic panoramic images according to the primary fusion model, and performing fine registration operation on all the target areas to obtain IHC cancer tissue image blocks;
4) statistical analysis of multiple immunohistochemical markers and corresponding indices were performed on IHC cancer tissue panels.
In this embodiment, when the corresponding continuous immunohistochemical sections are obtained by scanning with the scanner in step 1), the thickness of a single immunohistochemical section is 2 to 3 micrometers. The size of human cells is between 10 and 20 micrometers, the thickness of a single immunohistochemical section in the embodiment is 2 to 3 micrometers, and the same cells can exist in four to five sections simultaneously by adopting continuous sections. And the continuous sections are subjected to immunohistochemical marking (dual-label immunohistochemistry is used if necessary), then digital section scanning is carried out, precise overlapping and positioning are carried out on the sections through fine pairing, the expression of a plurality of different antibodies (or antigens) at the same part is compared and observed by using virtual multiple markers, and the expression intensity is objectively interpreted, so that the requirements of antibody (or antigen) multiple markers and reliable quantitative analysis in clinical pathological work and scientific research can be well met.
As shown in fig. 3, in step 2), the step of performing coarse tissue-level registration on the rest IHC microscopic panoramas based on the multi-resolution pyramid file and performing fusion to obtain a preliminary fusion model includes:
2.1) registering the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling;
2.2) the obtained registration parameters are applied to the images of the bottom layer in the multi-resolution pyramid file to complete a primary registration process of one-to-one pairing of each picture block in the registration reference image and each group of rest IHC microscopic panoramic images;
2.3) carrying out three-dimensional superposition on the preliminarily registered IHC microscopic panoramic images to obtain a preliminary fusion model, as shown in FIG. 4. Obtaining a preliminary fusion model may facilitate IHC labeling of these serial IHC slices by a physician or researcher.
Step 3) determining the target region for immunohistochemical index analysis in the registration reference map generally means that a doctor defines a specific region and performs immunohistochemical index analysis on the region. As shown in fig. 5, the step of performing the fine registration operation on all the target regions in step 3) of the present embodiment includes: performing cell-level registration on the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling; the registration parameters that have been obtained are applied to the images of the bottom layer in the multi-resolution pyramid file, and a one-to-one pairing fine registration process is completed as a registration reference map and each of all target regions in each of the remaining sets of IHC microscopic panoramas, resulting in IHC cancer tissue image blocks (cancer tissue image blocks), as shown in fig. 6. The fine registration operation is performed on the basis of the primary registration, so that the fine registration operation is equivalent to fine adjustment on the basis of the original primary registration, the correspondingly obtained registration parameters are small, and after the fine adjustment, the fine registration of cells and cells in a specific region can be completed; after the precise registration, the precise fusion process of the selected areas of the doctor is completed, so that the precise superposition and positioning of the specific areas are further completed, the doctor or the scientific research personnel can conveniently compare and observe the expressions of various antibodies (or antigens) at the same position by using the virtual multiple markers, and the expression intensity of the antibodies (or antigens) can be objectively interpreted. And for the area which is selected by the doctor and needs to be subjected to the IHC multiple-marker analysis, aiming at the reference IHC microscopic panoramic image and each group of IHC microscopic panoramic image, completing the automatic calculation of the corresponding immunohistochemical analysis index, such as counting the immunohistochemical positive rate of the corresponding area and the like.
In this embodiment, the statistical analysis of multiple immunohistochemical markers and corresponding indicators for IHC cancer tissue blocks in step 4) refers to counting the number of positive cells and the number of non-positive cells in cancer cells for the target region. Obtaining each picture block which needs to be subjected to positive rate statistics in each group of IHC microscopic panoramic pictures in a one-to-one correspondence manner through fine registration; and counting the number of positive cells and the number of non-positive cells in the cancer cells for each picture block needing positive rate counting, wherein the positive cells comprise nuclear positive cells, plasma positive cells and membrane positive cells.
As shown in fig. 7, the step of counting the number of positive cells and the number of non-positive cells in the cancer cells in this example includes: carrying out dye channel separation and color normalization processing by using a color deconvolution method aiming at IHC cancer tissue picture blocks obtained by fine registration; then, segmenting the preprocessed picture block by using a watershed algorithm, and separating to obtain a cancer tissue foreground and background area; then, after automatic threshold segmentation and image expansion corrosion operation, finding out the outline of each cell; then, according to the color and the shape, positive cells and non-positive cells are obtained by distinguishing; and finally, counting the number of the obtained positive cells and the number of the obtained non-positive cells respectively.
After the fine registration of the reference IHC microscopic panoramic image and each group of the rest IHC microscopic panoramic images is completed, the corresponding reference IHC microscopic panoramic image and the other IHC microscopic panoramic images can be obtained to obtain the fine matching on the cell level of the specific area, and a fusion model of the specific area is obtained; doctors or scientific researchers can use the precise fusion map of the specific region to carry out corresponding immunohistochemical marking and statistical analysis of indexes, such as the immunohistochemical positive rate of the corresponding region.
In this embodiment, the step 4) of performing the statistical analysis of the multiple immunohistochemical markers and corresponding indicators on the IHC cancer tissue image block further includes obtaining the number of positive cellsR i1,And number of non-positive cellsR i2,Step of calculating Positive RateA step, wherein i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
According to the number of positive cells obtainedR i1,And number of non-positive cellsR i2,The functional expression for calculating the positive rate is as follows:
in the above formula, the first and second carbon atoms are,H rate the positive rate is obtained by the method,R i1,the number of the positive cells is the number of the positive cells,R i2,the number of non-positive cells, where i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
In summary, in the present embodiment, a continuous slicing manner is adopted, and an accurate pairing technology is used to perform accurate registration and three-dimensional fusion on multiple immunohistochemical markers of a continuous slice, so as to perform three-dimensional reconstruction, complete multiple immunohistochemical index markers of corresponding regions, and analyze and interpret the positive rates of various markers, thereby performing objective evaluation and comparison on the expression and distribution of multiple immunohistochemical markers in the same region; in the embodiment, a SIFT rapid feature matching method based on a double multi-resolution pyramid model is adopted, coarse registration of a tissue level is gradually changed into fine registration of a cell level, and an analysis result of a specific area is obtained through automatic calculation; based on the original SIFT feature matching method, the registration speed is slow, especially if the registration is directly carried out on a bottom layer high-resolution panoramic image, the speed is extremely slow, based on the double multi-resolution SIFT registration method, firstly, the SIFT fast feature matching method based on a multi-resolution pyramid model is adopted, the registration is quickly completed by adopting an image with low high-layer resolution, then parameters such as translation amount, rotation angle, scaling ratio and the like obtained by registration extraction are directly drunk to a large image with high bottom layer resolution, the registration of the microscopic panoramic image on a tissue layer is completed, then, a corresponding area in the IHC microscopic panoramic image used as a reference is appointed, corresponding areas on other IHC images are obtained by corresponding calculation according to a coarse registration result, and further fine registration is carried out, so that the accurate registration on a cell level is completed; in the embodiment, when the identification statistics of the positive cells and the non-positive cells is carried out, channel separation and color normalization pretreatment is adopted, a tissue foreground part in a slice is obtained by segmentation through a region segmentation algorithm, then automatic threshold segmentation is carried out on the obtained tissue foreground part, then after morphological dilation corrosion operation is adopted, the outline of each cell is found, the positive cells and the non-positive cells are obtained by differentiation through characteristics such as color and shape, and finally the statistics of a positive cell region and a non-positive cell region of a cancer tissue region is rapidly completed, and the positive rate is calculated; the method can well meet the requirements of multiple labeling of antibodies (or antigens) and reliable quantitative analysis in clinical pathological work and scientific research, and can efficiently assist doctors and scientific research personnel in completing analysis of various immunohistochemical indexes after immunohistochemical multiple labeling by subtracting the complex work of manual calculation and analysis of medical personnel and scientific research personnel.
In addition, the present embodiment further provides a microscopic image immunohistochemical virtual multiple labeling and analyzing system, which includes a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the steps of the microscopic image immunohistochemical virtual multiple labeling and analyzing method, or the memory stores a computer program programmed or configured to execute the microscopic image immunohistochemical virtual multiple labeling and analyzing method.
In addition, the present embodiment also provides a computer readable storage medium, in which a computer program programmed or configured to execute the above-mentioned microscopic image immunohistochemical virtual multiple labeling and analysis method is stored.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is directed to methods, apparatus (systems), and computer program products according to embodiments of the application wherein instructions, which execute via a flowchart and/or a processor of the computer program product, create means for implementing functions specified in the flowchart and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (10)
1. A microscopic image immunohistochemical virtual multiple labeling and analysis method is characterized by comprising the following steps:
1) scanning by a scanner to obtain corresponding continuous immunohistochemical sections to obtain each corresponding IHC microscopic panoramic image, wherein each IHC microscopic panoramic image is stored in a storage format of a multi-resolution pyramid file;
2) selecting one IHC microscopic panoramic image as a registration reference image, carrying out coarse registration of the organization level on the rest IHC microscopic panoramic images based on a multi-resolution pyramid file, and fusing to obtain a preliminary fusion model;
3) determining a target area of immunohistochemical index analysis in the registration reference image, calculating to obtain corresponding target areas in the rest IHC microscopic panoramic images according to the primary fusion model, and performing fine registration operation of a cell layer on all the target areas to obtain an IHC cancer tissue image block;
4) statistical analysis of multiple immunohistochemical markers and corresponding indices were performed on IHC cancer tissue panels.
2. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 1, wherein, when the corresponding continuous immunohistochemical sections are obtained by scanning with the scanner in the step 1), the thickness of each single immunohistochemical section is 2 to 3 micrometers.
3. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 2, wherein the step of performing tissue-level coarse registration and fusion on the rest IHC microscopic panoramas based on the multi-resolution pyramid file in step 2) to obtain a preliminary fusion model comprises:
2.1) registering the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling;
2.2) the obtained registration parameters are applied to the images of the bottom layer in the multi-resolution pyramid file to complete a primary registration process of one-to-one pairing of each picture block in the registration reference image and each group of rest IHC microscopic panoramic images;
and 2.3) carrying out three-dimensional superposition on the preliminarily registered IHC microscopic panoramic image to obtain a preliminary fusion model.
4. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 3, wherein the step of performing the fine registration operation on all target regions in step 3) comprises: performing cell-level registration on the layer with lower high-layer resolution in the multi-resolution pyramid file based on an SIFT feature matching algorithm to obtain registration parameters including translation amount, rotation angle and scaling; and (3) applying the obtained registration parameters to the images of the middle and bottom layers of the multi-resolution pyramid file to complete a one-to-one pairing fine registration process of all target areas in each of the registration reference image and each of the rest IHC microscopic panoramic images to obtain an IHC cancer tissue image block.
5. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 1, wherein the statistical analysis of multiple immunohistochemical labeling and corresponding indexes for IHC cancer tissue image blocks in step 4) means that the statistics of the number of positive cells and the number of non-positive cells in cancer cells including nuclear positive cells, plasma positive cells and membrane positive cells are performed for the target region.
6. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 5, wherein said step of performing statistics of the number of positive cells and the number of non-positive cells in cancer cells comprises: carrying out dye channel separation and color normalization processing by using a color deconvolution method aiming at IHC cancer tissue picture blocks obtained by fine registration; then, segmenting the preprocessed picture block by using a watershed algorithm, and separating to obtain a cancer tissue foreground and background area; then, after automatic threshold segmentation and image expansion corrosion operation, finding out the outline of each cell; then, according to the color and the shape, positive cells and non-positive cells are obtained by distinguishing; and finally, counting the number of the obtained positive cells and the number of the obtained non-positive cells respectively.
7. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 6, wherein the statistical analysis of multiple immunohistochemical labeling and corresponding indicators for IHC cancer tissue image blocks in step 4) further comprises obtaining positive fine markersNumber of cellsR i1,And number of non-positive cellsR i2,A step of calculating a positive rate, wherein i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
8. The microscopic image immunohistochemical virtual multiple labeling and analysis method according to claim 7, wherein the number of positive cells obtained is the same as the number of positive cells obtainedR i1,And number of non-positive cellsR i2,The functional expression for calculating the positive rate is as follows:
in the above formula, the first and second carbon atoms are,H rate the positive rate is obtained by the method,R i1,the number of the positive cells is the number of the positive cells,R i2,the number of non-positive cells, where i =1,2,3, …,N，Nthe number of the cancer tissue image blocks needs to be counted.
9. A microscopic image immunohistochemical virtual multiple labeling and analysis system comprising a microprocessor and a memory interconnected, wherein the microprocessor is programmed or configured to perform the steps of the microscopic image immunohistochemical virtual multiple labeling and analysis method of any one of claims 1 to 8, or wherein the memory stores a computer program programmed or configured to perform the microscopic image immunohistochemical virtual multiple labeling and analysis method of any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program programmed or configured to perform the microscopic image immunohistochemical virtual multiple labeling and analysis method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554677.1A CN112270684B (en) | 2020-12-25 | 2020-12-25 | Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554677.1A CN112270684B (en) | 2020-12-25 | 2020-12-25 | Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112270684A CN112270684A (en) | 2021-01-26 |
| CN112270684B true CN112270684B (en) | 2021-04-06 |
Family
ID=74350200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011554677.1A Active CN112270684B (en) | 2020-12-25 | 2020-12-25 | Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112270684B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508952B (en) * | 2021-02-05 | 2021-05-04 | 宁波兰茜生物科技有限公司 | Pathological section double-objective lens self-adaptive scanning control method and system |
| CN117037149B (en) * | 2023-08-15 | 2024-03-22 | 华东师范大学 | Multi-immune-histochemical hyperspectral image unmixing method based on semi-supervised group optimization |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110088804A (en) * | 2016-12-22 | 2019-08-02 | 文塔纳医疗系统公司 | It is scored based on the computer of primary colors and immunohistochemistry image |
| CN111751371A (en) * | 2020-06-24 | 2020-10-09 | 武汉中纪生物科技有限公司 | Immunohistochemical digital slide reading system and method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2401438C (en) * | 2000-02-29 | 2011-11-29 | Institut National De La Sante Et De La Recherche Medicale (Inserm) | Novel human ulip/crmp protein and use thereof in diagnosis and treatment of cancers and paraneoplastic neurological syndromes |
| JP5784718B2 (en) * | 2010-06-15 | 2015-09-24 | コーニンクレッカ フィリップス エヌ ヴェ | Image processing method for microscopy |
| CN102184420B (en) * | 2011-04-18 | 2013-04-10 | 四川大学 | Method for processing immunohistochemical digital image |
| JP6499643B2 (en) * | 2013-10-01 | 2019-04-10 | ベンタナ メディカル システムズ， インコーポレイテッド | Line-based image registration and cross-image annotation device, system, and method |
| CN106802346B (en) * | 2017-01-19 | 2020-04-03 | 宁波江丰生物信息技术有限公司 | Pathological digital image analysis method based on immunohistochemical technology |
| CN109872335A (en) * | 2019-02-28 | 2019-06-11 | 志诺维思（北京）基因科技有限公司 | A kind of automatic read tablet method and its system for PD-L1 antibody stained slice |
| CN110400318B (en) * | 2019-06-14 | 2021-08-20 | 广东省人民医院(广东省医学科学院) | Immunohistochemical pathological image CD4 positive cell nucleus segmentation method and system |
| CN110763678A (en) * | 2019-09-12 | 2020-02-07 | 杭州迪英加科技有限公司 | Pathological section interpretation method and system |
| CN110853005A (en) * | 2019-11-06 | 2020-02-28 | 杭州迪英加科技有限公司 | Immunohistochemical membrane staining section diagnosis method and device |
-
2020
- 2020-12-25 CN CN202011554677.1A patent/CN112270684B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110088804A (en) * | 2016-12-22 | 2019-08-02 | 文塔纳医疗系统公司 | It is scored based on the computer of primary colors and immunohistochemistry image |
| CN111751371A (en) * | 2020-06-24 | 2020-10-09 | 武汉中纪生物科技有限公司 | Immunohistochemical digital slide reading system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112270684A (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Automatic segmentation of individual tooth in dental CBCT images from tooth surface map by a multi-task FCN | |
| CN109903284B (en) | HER2 immunohistochemical image automatic discrimination method and system | |
| EP3055835B1 (en) | Systems and methods for comprehensive multi-assay tissue analysis | |
| US20110286654A1 (en) | Segmentation of Biological Image Data | |
| CN112270684B (en) | Microscopic image immunohistochemical virtual multiple labeling and analyzing method and system | |
| CN109492706A (en) | A kind of chromosome classification prediction meanss based on Recognition with Recurrent Neural Network | |
| CN110796672A (en) | Breast cancer MRI segmentation method based on hierarchical convolutional neural network | |
| Nofallah et al. | Machine learning techniques for mitoses classification | |
| CN115546605A (en) | Training method and device based on image labeling and segmentation model | |
| CN111476794A (en) | UNET-based cervical pathological tissue segmentation method | |
| CN113011257A (en) | Breast cancer immunohistochemical artificial intelligence interpretation method | |
| Paulauskaite-Taraseviciene et al. | Deep learning-based detection of overlapping cells | |
| CN109993773B (en) | Multi-target tracking method and device for series section images | |
| CN117670895B (en) | Immunohistochemical pathological image cell segmentation method based on section re-staining technology | |
| Fu et al. | MSA-Net: Multiscale spatial attention network for medical image segmentation | |
| Li et al. | An automated pipeline for mitochondrial segmentation on atum-sem stacks | |
| CN112508860A (en) | Artificial intelligence interpretation method and system for positive check of immunohistochemical image | |
| Zhang et al. | Microscope based her2 scoring system | |
| CN113947599B (en) | Cytoplasmic positive immunohistochemical intelligent identification method, system and medium | |
| CN114926486B (en) | Thyroid ultrasound image intelligent segmentation method based on multi-level improvement | |
| Zhai et al. | Deep Neural Network Guided by Attention Mechanism for Segmentation of Liver Pathology Image | |
| Feng et al. | An advanced automated image analysis model for scoring of ER, PR, HER-2 and Ki-67 in breast carcinoma | |
| Sreelekshmi et al. | SwinCNN: An Integrated Swin Trasformer and CNN for Improved Breast Cancer Grade Classification | |
| Du et al. | Semi-Supervised Skin Lesion Segmentation via Iterative Mask Optimization | |
| Fuchs et al. | Weakly supervised cell nuclei detection and segmentation on tissue microarrays of renal clear cell carcinoma |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 6-1-604, No.55 Fuye street, Luotuo street, Zhenhai District, Ningbo City, Zhejiang Province Patentee after: Lansi (Ningbo) Intelligent Technology Co.,Ltd. Address before: Room 6-1-604, No.55 Fuye street, Luotuo street, Zhenhai District, Ningbo City, Zhejiang Province Patentee before: Ningbo Lanxi Biotechnology Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210126 Assignee: Changsha Lansi Intelligent Technology Co.,Ltd. Assignor: Lansi (Ningbo) Intelligent Technology Co.,Ltd. Contract record no.: X2023980033656 Denomination of invention: A virtual multiple labeling and analysis method and system for microscopic image immunohistochemistry Granted publication date: 20210406 License type: Common License Record date: 20230321 |