CN114299044A - Method and device for interpreting lymphocytes - Google Patents
Method and device for interpreting lymphocytes Download PDFInfo
- Publication number
- CN114299044A CN114299044A CN202111662822.2A CN202111662822A CN114299044A CN 114299044 A CN114299044 A CN 114299044A CN 202111662822 A CN202111662822 A CN 202111662822A CN 114299044 A CN114299044 A CN 114299044A
- Authority
- CN
- China
- Prior art keywords
- cell
- lymphocytes
- segmentation
- image
- cell segmentation
- 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.)
- Pending
Links
- 210000004698 lymphocyte Anatomy 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 28
- 210000004027 cell Anatomy 0.000 claims abstract description 84
- 230000011218 segmentation Effects 0.000 claims abstract description 41
- 230000001575 pathological effect Effects 0.000 claims abstract description 27
- 210000003171 tumor-infiltrating lymphocyte Anatomy 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- WZUVPPKBWHMQCE-UHFFFAOYSA-N Haematoxylin Chemical compound C12=CC(O)=C(O)C=C2CC2(O)C1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-UHFFFAOYSA-N 0.000 claims description 20
- 230000007170 pathology Effects 0.000 claims description 13
- 210000001519 tissue Anatomy 0.000 claims description 13
- 210000003855 cell nucleus Anatomy 0.000 claims description 10
- 210000000170 cell membrane Anatomy 0.000 claims description 8
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000010186 staining Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 5
- YQGOJNYOYNNSMM-UHFFFAOYSA-N eosin Chemical compound [Na+].OC(=O)C1=CC=CC=C1C1=C2C=C(Br)C(=O)C(Br)=C2OC2=C(Br)C(O)=C(Br)C=C21 YQGOJNYOYNNSMM-UHFFFAOYSA-N 0.000 claims description 4
- 206010028980 Neoplasm Diseases 0.000 description 10
- 238000001514 detection method Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 210000002865 immune cell Anatomy 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000004940 nucleus Anatomy 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 206010006187 Breast cancer Diseases 0.000 description 2
- 208000026310 Breast neoplasm Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 238000010827 pathological analysis Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 210000004881 tumor cell Anatomy 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 210000000805 cytoplasm Anatomy 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 102000052116 epidermal growth factor receptor activity proteins Human genes 0.000 description 1
- 108700015053 epidermal growth factor receptor activity proteins Proteins 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 238000007490 hematoxylin and eosin (H&E) staining Methods 0.000 description 1
- 230000028993 immune response Effects 0.000 description 1
- 230000037451 immune surveillance Effects 0.000 description 1
- 210000000987 immune system Anatomy 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000028709 inflammatory response Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 239000012128 staining reagent Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000030968 tissue homeostasis Effects 0.000 description 1
Images
Abstract
A method and a device for judging lymphocytes are provided, and the method for judging the lymphocytes comprises the following steps: a cell segmentation step, including cell segmentation of the pathological image; and a cell classification step, which comprises the step of identifying lymphocytes from the pathological image after cell segmentation. Cell segmentation and lymphocyte recognition are automatically completed through software, manual participation is not needed, and efficiency and accuracy of reading lymphocytes are effectively improved.
Description
Technical Field
The invention relates to the field of precise medical treatment, in particular to a method and a device for interpreting lymphocytes.
Background
1. Histopathology
Histopathology (histopathology) refers to the science of histologists examining tissue sections under a microscope and is considered the gold standard for clinical tumor diagnosis. Histopathological subjects are tissue sections, usually tissue samples collected during surgery or biopsy, which are prepared as thin slices of tissue of several microns thickness by the steps of fixing, embedding, sectioning and staining, which are attached to a slide. The pathologist observes these sections through a microscope to make a diagnosis. These diagnoses are highly dependent on the experience of the physician. Staining is an important step in preparing tissue sections, and different stains can reveal different cells and tissue structures. Hematoxylin and eosin (H & E) stains can stain with strong color contrast in the nucleus and cytoplasm, are the most widely used staining reagents, and can be applied to many different tissue types.
2.TILs
One of the essential roles of the immune system is to maintain tissue homeostasis by continuously initiating immune surveillance and inflammatory responses involving activation of innate and adaptive immune cells. Tumors alter the ordered structure of tissues and induce an immune response that can eliminate early stage tumors. However, partial incomplete elimination of tumor cells may escape immune control due to the immune editing mechanisms of the tumor cells.
With the development of clinical studies, morphological assessment of Tumor Infiltrating Lymphocytes (TILs) in breast cancer is of increasing interest. There is increasing evidence to assess the extent of lymphocyte infiltration in tumor tissues by hematoxylin and eosin (H & E) stained tumor sections and to demonstrate that TILs have prognostic and potentially predictive value, especially in triple negative and EGFR receptor 2 overexpressing breast cancers.
3. Digital pathological image analysis (DIA)
Pathological diagnosis is the final diagnosis of a disease, and is widely used in diagnosis and medication guidance of tumors. In practice, pathologists view pathological sections under a microscope, and identifying subtle lesions from complex tissue images is an essential step in diagnosis. The process is time-consuming and has strong subjectivity. Digital pathology based on the whole-slide digital scanning technique (WSI) enables us to obtain pathology images with histological features, mostly captured by high resolution. Histopathological image analysis algorithms are developed to efficiently capture useful information in images. Since the analysis of the algorithm is objective and stable, the result can be verified repeatedly. Therefore, classical cell segmentation algorithms and cell classification algorithms have been widely applied to digital pathology analysis platforms. The digital pathological technology is used for assisting a pathologist to make pathological diagnosis, so that the accuracy and efficiency of pathological physician diagnosis are obviously improved.
In the prior art, the problems include: 1) the efficiency of manual TILs interpretation of HE pathological images is low; 2) human subjective deviation, visual deviation and other reasons can cause poor repeatability between manual interpretation and even interpretation errors.
Disclosure of Invention
According to a first aspect, in an embodiment, there is provided a method of interpreting lymphocytes, comprising:
a cell segmentation step, including cell segmentation of the pathological image;
and a cell classification step, which comprises the step of identifying lymphocytes from the pathological image after cell segmentation.
According to a second aspect, in an embodiment, there is provided an apparatus for interpreting lymphocytes, comprising:
the cell segmentation module is used for carrying out cell segmentation on the pathological image;
and the cell classification module is used for identifying the lymphocytes from the pathological image after cell segmentation.
According to a third aspect, in an embodiment, there is provided an apparatus comprising:
a memory for storing a program;
a processor for implementing the method as described in the first aspect by executing the program stored by the memory.
According to a fourth aspect, in an embodiment, there is provided a computer readable storage medium having a program stored thereon, the program being executable by a processor to implement the method according to the first aspect.
According to the method and the device for judging the lymphocytes, the cell segmentation and the lymphocyte recognition are automatically completed through software without manual participation, and the efficiency and the accuracy of judging the lymphocytes are effectively improved.
Drawings
Fig. 1 is a flowchart of training the lymphocyte recognition algorithm and TILs calculation in example 1.
FIG. 2 is an exemplary illustration of the labeling of lymphocytes manually performed by the pathologist in example 1; (a) HE original pathology image, (b) blue dots are artificially labeled as lymphocytes.
Fig. 3 is a diagram of an example of detecting cells in an HE image by automatic segmentation using the watershed algorithm in example 1. (a) An original pathological image; (b) after cell detection is finished, cell detection result mask images are obtained; (c) area within the detection range, cell number, etc.
FIG. 4 is a graph showing the results of counting the attribute values of each of the detected cells in example 1, in which information on the partial attribute values of 4 exemplary cells is shown.
FIG. 5 is a diagram of an exemplary cell segmentation, lymphocyte detection and TILs calculation in one area of example 1. (a) Original pathological images of the selected area by a pathologist; (b) the algorithm performs the result image of cell segmentation and classification, each ellipse represents a cell, and the dark part represents the cell nucleus. Blue represents lymphocytes; (c) the number of lymphocytes detected in the circled Area (Numimune cells) was calculated from TILs (ImmuneCelarearea%).
FIG. 6 is a diagram showing an example of cell segmentation, lymphocyte detection and TILs calculation in another region of example 1. (a) Original pathological images of the selected area by a pathologist; (b) the algorithm carries out cell segmentation and classification to obtain a result image, each ellipse represents a cell, and the dark part represents a cell nucleus; blue represents lymphocytes. (c) The number of lymphocytes detected in the circled Area (Num immune cells) was calculated from TILs (imminecell Area%).
Fig. 7 is a graph of the correlation performance verification of the software analysis result and the manual interpretation result in example 1.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
As used herein, "tumor-infiltrating lymphocytes," also known as tumor-infiltrating lymphocytes (TILs ), are lymphocytes that migrate from the blood to the tumor tissue. In particular to lymphocytes which can migrate into the interior of a tumor or at the tumor margin, and the infiltrated lymphocytes are relevant to the prognosis of the tumor and the treatment effect.
According to a first aspect, in an embodiment, there is provided a method of interpreting lymphocytes, comprising:
a cell segmentation step, including cell segmentation of the pathological image;
and a cell classification step, which comprises the step of identifying lymphocytes from the pathological image after cell segmentation.
In one embodiment, in the cell classifying step, the attribute value of each cell is counted, and the lymphocyte is identified according to the attribute value.
In an embodiment, the property value comprises at least one of area, circumference, roundness, eccentricity, length, solidity, maximum diameter, minimum diameter, hematoxylin optical density value.
In an embodiment, the property values include all of area, perimeter, roundness, eccentricity, length, solidity, maximum diameter, minimum diameter, hematoxylin optical density values.
In one embodiment, the optimal parameter combinations for lymphocyte recognition are as follows: maximum tree depth: minimum number of supported samples per tree (artificially labeled cells): 20, number of features used per tree: 5, maximum tree number: 50.
in one embodiment, the pathology image comprises a region original pathology image circled by a pathologist.
In an embodiment, the pathology image includes a tissue slice treated by stain staining.
In one embodiment, the stain includes hematoxylin and eosin (H & E).
In one embodiment, the method further comprises a step of calculating the lymphocyte proportion according to the lymphocyte proportion [ (the area occupied by the lymphocytes in the identified pathological image)/(the total area of the case image or the total area of the circled areas in the case image) ]. the lymphocyte proportion is 100%.
In one embodiment, the lymphocytes comprise tumor infiltrating lymphocytes.
In one embodiment, in the cell segmentation step, after the pathological image is subjected to cell segmentation, the position information of the cell nucleus and the position information of the cell membrane of each cell are recorded.
In one embodiment, in the cell segmentation step, the cell nucleus and cell membrane contours of each cell are delineated by two contours, wherein the inner contour represents the cell nucleus contour and the outer contour represents the cell membrane contour.
In one embodiment, the algorithm for identifying lymphocytes in the cell classification step includes, but is not limited to, a random forest algorithm.
In one embodiment, the cell segmentation step includes, but is not limited to, a watershed algorithm.
According to a second aspect, in an embodiment, there is provided an apparatus for interpreting lymphocytes, comprising:
the cell segmentation module is used for carrying out cell segmentation on the pathological image;
and the cell classification module is used for identifying the lymphocytes from the pathological image after cell segmentation.
According to a third aspect, in an embodiment, there is provided an apparatus comprising:
a memory for storing a program;
a processor for implementing the method as described in the first aspect by executing the program stored by the memory.
According to a fourth aspect, in an embodiment, there is provided a computer readable storage medium having a program stored thereon, the program being executable by a processor to implement the method according to the first aspect.
In one embodiment, the present invention identifies lymphocytes as follows:
and a cell segmentation step, namely automatically completing the segmentation of the cells by using software based on a watershed algorithm.
And (4) a cell classification step, namely automatically identifying tumor infiltrating lymphocytes by using software and highlighting.
In one embodiment, the present invention develops an analysis process that allows software to automate cell segmentation, lymphocyte recognition and TILs. By providing automatic auxiliary counting, the efficiency and the accuracy of manual interpretation of a pathologist are improved.
In one embodiment, TILs refer to the area fraction of lymphocytes in the circled area.
In one embodiment, the lymphocytes comprise tumor infiltrating lymphocytes.
In one embodiment, the present invention uses Qupath as a digital pathology platform for development of TILs assisted interpretation algorithms.
In one embodiment, the present invention can greatly improve the efficiency and accuracy of TILs interpretation by automatically detecting lymphocytes and calculating the area ratio of the lymphocytes.
Example 1
The lymphocytes in this embodiment are specifically tumor infiltrating lymphocytes.
The embodiment comprises the following steps:
1. lymphocyte labeling and recognition algorithm training
In this embodiment, 7 HE-stained full-slide pathology images are randomly selected, and as shown in fig. 2, a professional pathologist manually marks lymphocytes in HE images by using a marking tool of Qupath, so as to mark more than 1000 lymphocytes.
As shown in fig. 3, the cells in the HE image are segmented using the watershed algorithm, and the position information of the cell nucleus and the cell membrane of each cell is recorded. The cell nucleus and membrane in each cell are outlined by two oval lines, where the inner oval is the nucleus and the outer oval is the membrane.
As shown in fig. 4, the attribute values such as diameter, roundness, area, color depth, etc. of each cell were counted. In order to enable lymphocyte detection to be more accurate and stable, the characteristics of lymphocytes and the HE staining principle are combined, and 9 cell attribute values are screened out, wherein the 9 cell attribute values are as follows: area (Area), circumference (Perimeter), roundness (circulation), Eccentricity (Eccentricity), Length (Length), Solidity (Solidity), maximum diameter (Max diameter), minimum diameter (Min diameter), Hematoxylin optical density value (Hematoxylin OD). Inputting the artificially marked lymphocytes and the screened attribute values into a random forest algorithm, training the random forest algorithm for recognizing the lymphocytes, and obtaining an optimal parameter combination for recognizing the lymphocytes through multi-test iterative optimization and adjustment, wherein the optimal parameter combination is as follows: maximum tree depth: minimum number of supported samples per tree (artificially labeled cells): 20, number of features used per tree: 5, maximum tree number: 50.
as shown in fig. 5 and 6, cell detection, cell attribute value statistics, and lymphocyte recognition are performed on the designated area of the HE pathology image by using a watershed algorithm and a trained random forest algorithm. Each ellipse represents a cell and the dark part represents the nucleus, where the blue label is a lymphocyte, and the TILs (ImmuneCell Area%) are calculated by combining the Area attribute value of each detected cell with the Area and cell number of the designated Area.
2. Lymphocyte detection and TILs (Linear arrays of cells) calculation software development
As shown in FIG. 1, the functions of cell detection, lymphocyte recognition and TILs ratio calculation are integrated into a software through Groovy language, and when a specified Region (ROI) is manually selected by using Qupath, the software can be used for automatically performing the lymphocyte detection and TILs ratio calculation of the ROI.
The TILs calculation formula is as follows:
TILs ═ Immune Cell Area/ROI Area. That is, the total area of the lymphocytes identified in the circled area is divided by the total area of the area, and the value is the TILs ratio.
3. Performance verification of software auto-computed TILs
To verify the performance of the software to calculate TILs, the pathologist randomly selected 32 Regions (ROIs) and manually interpreted the TILs for these regions. We detected TILs for these 32 ROIs using automated software developed earlier. As a result, as shown in FIG. 7, the correlation coefficient between the TILs automatically calculated by the software and the manually interpreted TILs reaches 0.82. We examined the interpretation region where the software interpretation and the manual interpretation have a deviation, and found that the interpretation deviation is mainly because the manual interpretation is affected by visual errors, and the area ratio of lymphocytes is estimated incorrectly. If the auxiliary interpretation software of the embodiment is used, the efficiency and the accuracy of TILs interpretation are improved.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (10)
1. A method of interpreting lymphocytes, comprising:
a cell segmentation step, including cell segmentation of the pathological image;
and a cell classification step, which comprises the step of identifying lymphocytes from the pathological image after cell segmentation.
2. The method of claim 1, wherein in the cell classifying step, the attribute value of each cell is counted, and the lymphocytes are identified based on the attribute values.
3. The method of claim 2, wherein the property values include at least one of area, perimeter, roundness, eccentricity, length, solidity, maximum diameter, minimum diameter, hematoxylin optical density values;
preferably, the property values include all of area, circumference, roundness, eccentricity, length, solidity, maximum diameter, minimum diameter, hematoxylin optical density values.
4. The method of claim 1, wherein the optimal parameters for lymphocyte recognition are combined as follows: maximum tree depth: 5, minimum number of supported samples per tree: 20, number of features used per tree: 5, maximum tree number: 50.
5. the method of claim 1, wherein the pathology image comprises a region raw pathology image circled by a pathologist;
and/or, the pathological image comprises a tissue section processed by staining by a staining agent;
and/or, the staining agent comprises hematoxylin and eosin.
6. The method of claim 1, further comprising a step of calculating a lymphocyte proportion, which comprises calculating the lymphocyte proportion according to [ (area occupied by lymphocytes in the identified pathology image)/(total area of case image or total area of circled regions in case image) ] 100%.
7. The method of claim 1, wherein said lymphocytes comprise tumor infiltrating lymphocytes;
and/or in the cell segmentation step, after cell segmentation is carried out on the pathological image, the cell nucleus position information and the cell membrane position information of each cell are recorded;
and/or in the cell segmentation step, the contour of the cell nucleus and the cell membrane in each cell is described through two contour lines, wherein the inner contour line represents the contour of the cell nucleus, and the outer contour line represents the contour of the cell membrane;
and/or in the cell classification step, the algorithm for identifying the lymphocytes comprises a random forest algorithm;
and/or in the cell segmentation step, the algorithm for carrying out cell segmentation on the pathological image comprises a watershed algorithm.
8. An apparatus for interpreting lymphocytes, comprising:
the cell segmentation module is used for carrying out cell segmentation on the pathological image;
and the cell classification module is used for identifying the lymphocytes from the pathological image after cell segmentation.
9. An apparatus, comprising:
a memory for storing a program;
a processor for implementing the method of any one of claims 1 to 7 by executing the program stored in the memory.
10. A computer-readable storage medium, characterized in that the medium has stored thereon a program which is executable by a processor to implement the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111662822.2A CN114299044A (en) | 2021-12-31 | 2021-12-31 | Method and device for interpreting lymphocytes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111662822.2A CN114299044A (en) | 2021-12-31 | 2021-12-31 | Method and device for interpreting lymphocytes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299044A true CN114299044A (en) | 2022-04-08 |
Family
ID=80974217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111662822.2A Pending CN114299044A (en) | 2021-12-31 | 2021-12-31 | Method and device for interpreting lymphocytes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299044A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570505A (en) * | 2016-11-01 | 2017-04-19 | 北京昆仑医云科技有限公司 | Method for analyzing histopathologic image and system thereof |
| CN108288265A (en) * | 2018-01-09 | 2018-07-17 | 东北大学 | A kind of segmentation and sorting technique towards HCC pathological image nucleus |
| CN109034208A (en) * | 2018-07-03 | 2018-12-18 | 怀光智能科技（武汉）有限公司 | A kind of cervical cell pathological section classification method of high-low resolution combination |
| CN110632069A (en) * | 2019-08-20 | 2019-12-31 | 西人马帝言(北京)科技有限公司 | Circulating tumor cell detection method, device, equipment and medium |
| CN113470041A (en) * | 2021-05-26 | 2021-10-01 | 透彻影像(北京)科技有限公司 | Immunohistochemical cell image cell nucleus segmentation and counting method and system |
-
2021
- 2021-12-31 CN CN202111662822.2A patent/CN114299044A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570505A (en) * | 2016-11-01 | 2017-04-19 | 北京昆仑医云科技有限公司 | Method for analyzing histopathologic image and system thereof |
| CN108288265A (en) * | 2018-01-09 | 2018-07-17 | 东北大学 | A kind of segmentation and sorting technique towards HCC pathological image nucleus |
| CN109034208A (en) * | 2018-07-03 | 2018-12-18 | 怀光智能科技（武汉）有限公司 | A kind of cervical cell pathological section classification method of high-low resolution combination |
| CN110632069A (en) * | 2019-08-20 | 2019-12-31 | 西人马帝言(北京)科技有限公司 | Circulating tumor cell detection method, device, equipment and medium |
| CN113470041A (en) * | 2021-05-26 | 2021-10-01 | 透彻影像(北京)科技有限公司 | Immunohistochemical cell image cell nucleus segmentation and counting method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7273215B2 (en) | Automated assay evaluation and normalization for image processing | |
| WO2019110583A1 (en) | Deep-learning systems and methods for joint cell and region classification in biological images | |
| US20110286654A1 (en) | Segmentation of Biological Image Data | |
| US20220351860A1 (en) | Federated learning system for training machine learning algorithms and maintaining patient privacy | |
| JP7422235B2 (en) | Non-tumor segmentation to aid tumor detection and analysis | |
| WO2014114612A1 (en) | Method and systems for cell-level fish dot counting | |
| GB2423150A (en) | Distinguishing layers of epithelial tissue | |
| CN107567631B (en) | Tissue sample analysis techniques | |
| Kanwal et al. | Quantifying the effect of color processing on blood and damaged tissue detection in whole slide images | |
| US20240079116A1 (en) | Automated segmentation of artifacts in histopathology images | |
| Scudamore | Practical approaches to reviewing and recording pathology data | |
| US9785848B2 (en) | Automated staining and segmentation quality control | |
| US10943350B2 (en) | Automated segmentation of histological sections for vasculature quantification | |
| Palokangas et al. | Segmentation of folds in tissue section images | |
| CN114299044A (en) | Method and device for interpreting lymphocytes | |
| Silva et al. | Development of a quantitative semi-automated system for intestinal morphology assessment in Atlantic salmon, using image analysis | |
| EP3757872A1 (en) | Scanning/pre-scanning quality control of slides | |
| JPH0694706A (en) | Pathology image inspection support device | |
| US11263781B2 (en) | Process for determining the infiltration of biological cells in a biological object of interest | |
| Satou et al. | Automatic analysis for neuron by confocal laser scanning microscope |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220408 |
|
| RJ01 | Rejection of invention patent application after publication |