A method and system for cell classification and function evaluation based on nucleolus morphology

Abstract

The present invention relates to the field of cell classification, and particularly relates to a method and system for cell classification and function evaluation based on nucleolus morphology. The method provided by the present invention includes: S101 obtaining microscopic image data of a biological sample; S102 obtaining a first region of interest, a second region of interest, and a third region of interest; S103 extracting nucleolus feature data; S104 performing a first classification on the cells in the biological sample; S105 performing a second classification on the C-type cells in the biological sample; S106 calculating the quantity and / or ratio of A-type cells and B-type cells in the biological sample, and further evaluating the functional state of the tissue or organ corresponding to the biological sample. The present invention can accurately and sensitively reflect and evaluate the functional state of the tissue or organ corresponding to the biological sample, and is particularly suitable for biological samples with strong heterogeneity lacking specific markers.

Description

Technical Field

[0001] The present invention relates to the field of cell classification, and particularly to a method and system for cell classification and function evaluation based on nucleolar morphology. Background Art

[0002] Traditional disease characterization methods rely on specific disease markers and are often limited by factors such as high tissue heterogeneity and low marker expression levels. Especially when screening the effectiveness of drugs and molecular targets, existing methods often can only evaluate toxicity indicators by detecting cell viability or apoptosis levels, and it is difficult to reflect the changes in the responses of key subpopulations of cells to drugs.

[0003] As an important subcellular structure within cells, the nucleolus undertakes multiple core functions such as rRNA transcription, ribosome biosynthesis, cellular stress and response, and cell cycle regulation. The nucleolus plays a key role in the process of cell growth and is closely related to cell growth, proliferation, differentiation, and dysfunction. In recent years, studies have shown that changes in nucleolar morphology can reflect the health status of cells, especially being closely related to the occurrence and development of cancers, immune diseases, and cardiovascular diseases.

[0004] Although there are certain evaluation criteria for changes in nucleolar morphology in the prior art, for example, the nucleoli of cancer cells may become larger, but there is a lack of clear judgment criteria, the evaluation of nucleolar morphology results is highly subjective, and the identification accuracy for relatively complex biological samples (such as tissue samples with ambiguous nucleolar phenotypes and high heterogeneity) is low and the repeatability is poor. For example, Chinese Patent Application CN112239455A discloses an RNA fluorescent probe for rapidly distinguishing cancer from normal tissues using changes in nucleolar morphology. The interpretation of the staining results of the nucleoli not only still relies on manual work but also can only distinguish breast tissues from normal tissues, and it is difficult to characterize the specific pathological states corresponding to biological samples. Chinese Patent Application CN111886630A discloses an automated method for analyzing biological tissues and cells. Based on three-dimensional images, while the imaging is difficult and complex, multiple geometric morphological features of the nucleoli need to be combined to achieve cell classification, and it is difficult to sensitively reflect the changing trends of the nucleoli, and thus it is difficult to be applied to application scenarios such as early diagnosis of diseases and high-throughput drug screening. Summary of the Invention

[0005] In a first aspect, the present invention provides a method for cell classification and function evaluation based on nucleolar morphology, including the following steps:

[0006] S101 Obtain microscopic image data of a biological sample;

[0007] In some embodiments, the microscopic image data includes optical microscope images with an objective lens magnification of more than 40 times and / or super-resolution microscopic image data.

[0008] In some embodiments, the biological sample includes a tissue or cell culture containing at least one cell.

[0009] In some embodiments, the biological sample is labeled with a nucleolus marker, and the nucleolus marker includes at least a dense fibrillar component marker and a granular component marker.

[0010] In some embodiments, the dense fibrillar component marker includes fibrillarin (FBL).

[0011] In some embodiments, the granular component marker includes nucleophosmin 1 (NPM1).

[0012] In some embodiments, the biological sample is also labeled with a cell nucleus marker.

[0013] In some embodiments, the cell nucleus marker includes 4',6-diamidino-2-phenylindole (DAPI).

[0014] S102 Obtain a first region of interest, a second region of interest, and a third region of interest in the microscopic image data;

[0015] In some embodiments, the first region of interest is a cell nucleus region demarcated using the fluorescence channel corresponding to the cell nucleus marker.

[0016] In some embodiments, the second region of interest is a nucleolus region demarcated using the fluorescence channel corresponding to the dense fibrillar component marker.

[0017] In some embodiments, the third region of interest is a nucleolus region demarcated using the fluorescence channel corresponding to the granular component marker.

[0018] S103 Extract nucleolus feature data of the second region of interest and the third region of interest, where the nucleolus feature data includes line scan data and region area data;

[0019] S104 Based on the line scan data, perform a first classification on the cells in the biological sample;

[0020] In some embodiments, the line scan data includes fluorescence intensity distribution curves of the second region of interest and the third region of interest.

[0021] In some embodiments, the method for the first classification includes:

[0022] When the fluorescence intensity distribution curve of the third region of interest surrounds the fluorescence intensity distribution curve of the second region of interest, classify the cell as a type A cell;

[0023] When the fluorescence intensity distribution curve of the second region of interest spills outside the fluorescence intensity distribution curve of the third region of interest, the cell is classified as a type C cell.

[0024] In some embodiments, the method for evaluating the spillover includes:

[0025] Analyze whether the change trends of the fluorescence intensities at the segments of the fluorescence intensity distribution curve of the second region of interest and the fluorescence intensity distribution curve of the third region of interest at the first non-overlapping region and the last non-overlapping region that first appear in the non-overlapping region formed outside the fluorescence intensity distribution curve of the third region of interest by the fluorescence intensity distribution curve of the second region of interest are the same; if not, there is spillover; if so, there is no spillover.

[0026] S105 Perform a second classification on the type C cells in the biological sample;

[0027] In some embodiments, the method for the second classification includes:

[0028] Analyze whether the ratio of the regional areas of the second region of interest and the third region of interest in the type C cells is abnormal to perform a second classification on the type C cells in the biological sample.

[0029] In some embodiments, if the ratio of the regional areas of the second region of interest and the third region of interest in the type C cells is abnormal, the classification of the type C cells is adjusted to type B cells; if not, the classification of the type C cells is adjusted to type A cells.

[0030] In some embodiments, when the ratio of the regional areas of the second region of interest and the third region of interest shows an increasing trend, it is regarded as abnormal.

[0031] S106 Calculate the quantity and / or proportion of the type A cells and the type B cells in the biological sample, and further evaluate the functional state of the tissue or organ corresponding to the biological sample.

[0032] In some embodiments, the biological sample includes a biologically treated sample and a non-biologically treated sample.

[0033] In some embodiments, the method further includes: S107 Analyze the average diameter of the spots formed by the dense fiber component markers in the second region of interest in the type B cells. When the average diameter is less than the first threshold, the biological sample is evaluated as being in a state of malignant proliferation.

[0034] In some embodiments, the first threshold includes 0.5 - 2 μm.

[0035] Second aspect, the present invention provides a cell classification and function evaluation system based on nucleolar morphology, the system comprising:

[0036] An image acquisition module 102, configured to acquire microscopic image data of a biological sample;

[0037] In some embodiments, the microscopic image data includes optical microscope images with an objective lens magnification of more than 40 times and / or super-resolution microscopic image data.

[0038] In some embodiments, the biological sample includes a tissue or cell culture containing at least one cell.

[0039] In some embodiments, the biological sample is labeled with a nucleolar marker, and the nucleolar marker includes at least a dense fibrillar component marker and a granular component marker.

[0040] In some embodiments, the dense fibrillar component marker includes fibrillarin (FBL).

[0041] In some embodiments, the granular component marker includes nucleophosmin 1 (NPM1).

[0042] In some embodiments, the biological sample is also labeled with a nuclear marker.

[0043] In some embodiments, the nuclear marker includes 4',6-diamidino-2-phenylindole (DAPI).

[0044] A first processing module, configured to obtain a first region of interest, a second region of interest, and a third region of interest in the microscopic image data.

[0045] In some embodiments, the first region of interest is a nuclear region delineated by the fluorescence channel corresponding to the nuclear marker.

[0046] In some embodiments, the second region of interest is a nucleolar region delineated by the fluorescence channel corresponding to the dense fibrillar component marker.

[0047] In some embodiments, the third region of interest is a nucleolar region delineated by the fluorescence channel corresponding to the granular component marker.

[0048] A second processing module, configured to extract nucleolar feature data of the second region of interest and the third region of interest, the nucleolar feature data including line scan data and regional area data;

[0049] A first classification module, configured to perform a first classification on the cells in the biological sample based on the line scan data;

[0050] In some embodiments, the line scan data includes fluorescence intensity distribution curves of the second region of interest and the third region of interest.

[0051] In some embodiments, the method of the first classification includes:

[0052] When the fluorescence intensity distribution curve of the third region of interest encloses the fluorescence intensity distribution curve of the second region of interest, classifying the cell as a type A cell;

[0053] When the fluorescence intensity distribution curve of the second region of interest spills over to the outside of the fluorescence intensity distribution curve of the third region of interest, classifying the cell as a type C cell.

[0054] In some embodiments, the method for evaluating the spillover includes:

[0055] Analyze whether the change trends of the fluorescence intensities at the segments of the fluorescence intensity distribution curve of the second region of interest and the fluorescence intensity distribution curve of the third region of interest at the first non-overlapping region and the last non-overlapping region that first appear in the non-overlapping region formed outside the fluorescence intensity distribution curve of the third region of interest by the fluorescence intensity distribution curve of the second region of interest are the same; if not, then there is spillover; if so, then there is no spillover.

[0056] A second classification module 110, configured to perform a second classification on the type C cells in the biological sample;

[0057] In some embodiments, the method of the second classification includes:

[0058] Analyze whether the ratio of the regional areas of the second region of interest and the third region of interest in the type C cells is abnormal to perform a second classification on the type C cells in the biological sample.

[0059] In some embodiments, if the ratio of the regional areas of the second region of interest and the third region of interest in the type C cells is abnormal, adjusting the classification of the type C cells to type B cells; if not abnormal, adjusting the classification of the type C cells to type A cells.

[0060] In some embodiments, when the ratio of the regional areas of the second region of interest and the third region of interest shows an increasing trend, it is regarded as abnormal.

[0061] An analysis module, configured to calculate the quantity and / or proportion of the type A cells and the type B cells in the biological sample, and further evaluate the functional state of the tissue or organ corresponding to the biological sample.

[0062] In some embodiments, the biological sample includes a biologically treated biological sample and a non-biologically treated biological sample.

[0063] In some embodiments, the analysis module is further configured to analyze the average diameter of the spots formed by the dense fibrillar component markers in the Class B cells. When the average diameter is less than a first threshold, the biological sample is evaluated as being in a state of malignant proliferation.

[0064] In some embodiments, the first threshold includes 0.5 - 2 μm.

[0065] Compared with the prior art, the beneficial effects of the present invention at least include the following aspects:

[0066] Conventional single nucleolus geometric morphology characteristic indexes are difficult to sensitively reflect the changing trend of the nucleolus. Therefore, the prior art usually needs to combine multiple geometric morphology characteristics of the nucleolus to classify cells in a biological sample. Even so, the existing methods for classifying cells based on nucleolus morphology usually can only achieve qualitative analysis.

[0067] The present invention discovers that the relative positions and distributions of the dense fibrillar component markers and the granular component markers in the nucleolus change with the functional state of the tissue or organ corresponding to the biological sample. And the line scan data (i.e., the distribution change of fluorescence intensity) of the second region of interest and the third region of interest defined based on the dense fibrillar component markers and the granular component markers can sensitively reflect the changing trend of the nucleolus (such as changing from regular to irregular). Furthermore, through the first classification method, the cell subsets in the biological sample can be accurately classified.

[0068] Furthermore, the present invention also discovers that although the nucleolus morphologies of non-tumor biological samples and tumor biological samples present different characteristics, when the nucleolus function is "abnormal", the changing trend of the ratio of the areas of the second region of interest and the third region of interest is similar. Therefore, using this changing trend, on the basis of the first classification, the present invention performs a second classification on the Class A cells and Class C cells classified in the first classification to obtain a more accurate quantity and / or ratio of Class A cells and Class B cells. Furthermore, cell quantitative and qualitative analysis can be carried out more effectively to accurately and sensitively reflect and evaluate the functional state of the tissue or organ corresponding to the biological sample, which is particularly suitable for biological samples with strong heterogeneity lacking specific markers.

[0069] The method and system provided by the present invention effectively overcome the limitations of the traditional method's dependence on markers, and can be combined with machine learning technology, improving the analysis speed while ensuring the accuracy and efficiency of cell classification. Furthermore, it can predict cell functions (such as hyperactive cell proliferation or cell exhaustion) and characterize changes in tissue health status (such as intimal hyperplasia, tumors, or degenerative changes, etc.) and the pathological state of diseased tissues by accurately and sensitively reflecting changes in nucleolus-related phenotypes at the early stage of the disease, thereby providing support for the early diagnosis of the disease.

[0070] In addition, since the method and system provided by the present invention can accurately classify cell subsets in biological samples with high repeatability, quantitative analysis can be performed based on the cell classification results of the present invention, which is applicable to application scenarios such as high-throughput drug screening and drug efficacy evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale. Obviously, the following-described drawings are some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0072] Figure 1 It is a flowchart of the method for Embodiment 1;

[0073] Figure 2 It is a schematic diagram of the modules of the system for Embodiment 2;

[0074] Figure 3 It is a result diagram of detecting a sample of rat vascular smooth muscle cell culture for Embodiment 3;

[0075] Figure 4 It is a result diagram of detecting a sample of neuroblastoma cell line SK-N-SH culture for Embodiment 4;

[0076] Figure 5 It is a result diagram of detecting a neuroblastoma tumor tissue for Embodiment 5.

[0077] 100 is a cell classification and function evaluation system, 102 is an image acquisition module, 104 is a first processing module, 106 is a second processing module, 108 is a first classification module, 110 is a second classification module, and 112 is an analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0078] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0079] In this document, suffixes such as "module", "component" or "unit" used to represent elements are only for facilitating the description of the present invention, and have no specific meaning in themselves. Therefore, "module", "component" or "unit" can be used interchangeably.

[0080] In this document, terms such as "upper", "lower", "inner", "outer", "front", "rear", "one end", "the other end", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for facilitating the description of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0081] In this document, unless otherwise clearly defined and limited, terms such as "install", "be provided with", "connect", etc. should be understood in a broad sense. For example, "connect" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, and can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0082] In this document, "and / or" includes any and all combinations of one or more of the listed related items.

[0083] In this document, "a plurality of" means two or more, that is, it includes two, three, four, five, etc.

[0084] It should be noted that in this document, the term "include", "comprise" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including that element.

[0085] As used in this specification, the term "about" typically means + / - 5% of the stated value, more typically + / - 4% of the stated value, more typically + / - 3% of the stated value, more typically + / - 2% of the stated value, even more typically + / - 1% of the stated value, and even more typically + / - 0.5% of the stated value.

[0086] In this specification, certain embodiments may be disclosed in a format that is within a certain range. It should be understood that this type of "within a certain range" description is merely for convenience and brevity and should not be construed as a rigid limitation on the disclosed range. Thus, the description of a range should be considered to have specifically disclosed all possible sub-ranges and individual numerical values within that range. For example, the description of the range 1 - 6 should be regarded as having specifically disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as the individual numbers within that range, such as 1, 2, 3, 4, 5, and 6. This rule applies regardless of the breadth of the range.

[0087] Example 1

[0088] As Figure 1 shown, this example provides a method for cell classification and function assessment based on nucleolar morphology, including the following steps:

[0089] S101 Obtain microscopic image data of a biological sample;

[0090] In some embodiments, the microscopic image data includes optical microscope images with an objective lens magnification of more than 40 times and / or super-resolution microscopic image data.

[0091] In some embodiments, immunofluorescence images of biological samples can be batch-collected through a high-throughput imaging system to obtain the microscopic image data. In some embodiments, the imaging requirements include: using an objective lens with a magnification of more than 40 times to image a well plate with a glass bottom or other ultra-thin bottom surfaces (such as 0.17 - 0.19 mm).

[0092] In some embodiments, the biological sample includes a tissue or cell culture containing at least one cell. In some embodiments, the biological sample can be any solid or fluid sample obtained from, excreted by, or secreted by any organism. In some embodiments, the organism includes a healthy or seemingly healthy human subject or a human patient affected by a condition or disease (such as cancer) to be diagnosed or studied. In some embodiments, the biological sample can be a biological fluid obtained from blood, plasma, serum, urine, bile, ascites, saliva, cerebrospinal fluid, aqueous humor, or vitreous humor, or any body secretion, exudate, effusion (e.g., a fluid obtained from an abscess or any other site of infection or inflammation), or a fluid obtained from a joint (e.g., a normal joint or a joint affected by a disease). In some embodiments, the biological sample can also be a sample obtained from any organ or tissue (including biopsy or autopsy specimens, such as tumor biopsies). In some embodiments, the biological sample can include cells (whether primary cells or cultured cells) or a medium regulated by any cell, tissue, or organ.

[0093] It should be understood that the same biological sample may be a mixture containing different cell subsets and have strong heterogeneity. For example, the same biological sample may simultaneously contain cells with "cancerous" and "non-cancerous" cell phenotypes. Therefore, the correct classification of each individual cell in the biological sample is very challenging.

[0094] In some embodiments, the biological sample is labeled with a nucleolus marker, and the nucleolus marker includes at least a dense fibrillar component marker and a granular component marker.

[0095] In some embodiments, the dense fibrillar component marker includes fibrillarin (FBL).

[0096] In some embodiments, the granular component marker includes nucleophosmin 1 (NPM1).

[0097] In this embodiment, FBL and NPM1 are used to label the nucleolus simultaneously, where FBL serves as the dense fibrillar component marker (the middle layer of the nucleolus) and NPM1 serves as the granular component protein marker (the outer layer of the nucleolus) to label the middle and outer layers of the nucleolus of the cells in the biological sample.

[0098] In some embodiments, the biological sample is also labeled with a cell nucleus marker.

[0099] In some embodiments, the cell nucleus marker includes 4',6-diamidino-2-phenylindole (DAPI).

[0100] In some embodiments, the above markers in the cells can be labeled by immunofluorescence staining or other suitable methods.

[0101] S102 Obtain a first region of interest, a second region of interest, and a third region of interest in the microscopic image data.

[0102] In some embodiments, the first region of interest is a nuclear region delineated by the fluorescence channel corresponding to the nuclear marker.

[0103] In some embodiments, the second region of interest is a nucleolus region delineated by the fluorescence channel corresponding to the dense fibrillar component marker.

[0104] In some embodiments, the third region of interest is a nucleolus region delineated by the fluorescence channel corresponding to the granular component marker.

[0105] S103 Extract nucleolus feature data of the second region of interest and the third region of interest, where the nucleolus feature data includes line scan data and regional area data;

[0106] S104 Based on the line scan data, perform a first classification on the cells in the biological sample;

[0107] In some embodiments, the line scan data includes fluorescence intensity distribution curves of the second region of interest and the third region of interest. Line scan is an image analysis method used to measure the change in fluorescence intensity in a specific region. For example, line scan can be used to measure the fluorescence intensity in a specific region by drawing a line and analyzing the fluorescence values along the line to quantitatively analyze the fluorescence intensity distribution in the specific region.

[0108] The prior art usually uses line scan to determine the relative position of the protein to be analyzed in a specific region. For example, a specific marker is selected as a reference, and the co-localization degree of the protein to be analyzed and the selected marker is evaluated by line scan. It should be understood that in this application scenario, the relative position and distribution of the selected marker in the specific region are assumed to be unchanged, so that the relative position of the protein to be analyzed can be determined.

[0109] In this embodiment, the nucleolus is labeled with both a dense fibrillar component marker and a granular component marker, which can not only more accurately locate the position of the nucleolus, but also, as found in this embodiment, different from the conventional idea, the relative positions and distributions of the dense fibrillar component marker and the granular component marker in the nucleolus change with the functional state of the tissue or organ corresponding to the biological sample. Moreover, the line scan data (i.e., the distribution change of fluorescence intensity) of the second and third regions of interest delineated based on the dense fibrillar component marker and the granular component marker can sensitively reflect the change trend of the nucleolus (e.g., from regular to irregular), thus contributing to the preliminary classification of cells in the biological sample.

[0110] It should be emphasized that conventional single nucleolus geometric morphology characteristic indexes are difficult to sensitively reflect the change trend of the nucleolus (e.g., from regular to irregular). Therefore, the prior art usually needs to combine multiple geometric morphology characteristics of the nucleolus to classify cells in a biological sample. In this embodiment, by adopting the first classification method, the change trend of the nucleolus can be quickly and accurately judged, and then the cells can be classified into type A cells and type C cells.

[0111] In some embodiments, the method of the first classification includes:

[0112] When the fluorescence intensity distribution curve of the third region of interest surrounds the fluorescence intensity distribution curve of the second region of interest, the cell is classified as a type A cell;

[0113] When the fluorescence intensity distribution curve of the second region of interest spills over to the outside of the fluorescence intensity distribution curve of the third region of interest, the cell is classified as a type C cell.

[0114] In some embodiments, the outside of the fluorescence intensity distribution curve of the third region of interest refers to the side where the fluorescence intensity is higher than the fluorescence intensity distribution curve of the third region of interest.

[0115] In some embodiments, "spill over" means that some sections of the fluorescence intensity distribution curve of the second region of interest are distributed outside the fluorescence intensity distribution curve of the third region of interest, and form one or more non-overlapping regions with the fluorescence intensity distribution curve of the third region of interest, and the change trend of the fluorescence intensity at the section where the fluorescence intensity distribution curve of the non-overlapping region corresponding to the second region of interest and the fluorescence intensity distribution curve of the third region of interest is different.

[0116] In some embodiments, the section of the fluorescence intensity distribution curve of the second region of interest corresponding to the overflow non-overlapping region generally has a "peak" shape (i.e., in this section, the fluorescence intensity first increases to a peak and then decreases), while the section of the fluorescence intensity distribution curve of the corresponding third region of interest generally has a non-"peak" shape (e.g., in this section, the fluorescence intensity first decreases and then increases, only increases, or only decreases, etc.).

[0117] In some embodiments, a "peak" refers to a point on the fluorescence intensity distribution curve where, as the curve rises and falls in the vertical direction, the curve changes direction from top to bottom along the mountain-shaped part.

[0118] In some embodiments, the method for evaluating the overflow includes:

[0119] Analyze whether the change trends of the fluorescence intensities at the first and last non-overlapping regions that first appear in the non-overlapping region formed outside the fluorescence intensity distribution curve of the third region of interest by the fluorescence intensity distribution curve of the second region of interest are the same; if not, there is overflow; if so, there is no overflow.

[0120] In some embodiments, the fluorescence intensity distribution curve of the third region of interest surrounding the fluorescence intensity distribution curve of the second region of interest (which can also be understood as the fluorescence intensity distribution curve of the third region of interest substantially surrounding the fluorescence intensity distribution curve of the second region of interest) can be: the fluorescence intensity distribution curve of the third region of interest completely surrounds the fluorescence intensity distribution curve of the second region of interest; it can also be: the fluorescence intensity distribution curve of the second region of interest and the fluorescence intensity distribution curve of the third region of interest mostly overlap, there are non-overlapping regions between the fluorescence intensity distribution curve of the second region of interest and the fluorescence intensity distribution curve of the third region of interest, but the change trends of the fluorescence intensities at the sections of the fluorescence intensity distribution curve of the second region of interest corresponding to the non-overlapping regions and the fluorescence intensity distribution curve of the third region of interest are the same (i.e., both have a "peak" shape) and / or the fluorescence intensities at the sections of the fluorescence intensity distribution curve of the second region of interest corresponding to the non-overlapping regions and the fluorescence intensity distribution curve of the third region of interest are substantially the same.

[0121] In some embodiments, when there is no overflow non-overlapping region outside the fluorescence intensity distribution curve of the second region of interest in the fluorescence intensity distribution curve of the third region of interest, it can be evaluated that the fluorescence intensity distribution curve of the third region of interest substantially surrounds the fluorescence intensity distribution curve of the second region of interest.

[0122] In some embodiments, a trained cell classification model can be used to perform a first classification (and subsequent second classification) on the cells in the biological sample.

[0123] In some embodiments, the cell classification model can be obtained by performing corresponding model training through a set of nucleolus morphological features related to cell types established, for example, by using labeled learning with cell data of known categories. The morphological differences of nucleoli in different cell types can be analyzed for linear relationships using machine learning, thereby improving the accuracy of classification.

[0124] In some embodiments, the cell classification model can perform image recognition on the microscopic image data to determine the cell types (such as vascular smooth muscle cells, neuroblastoma cells, etc.) of the cells in the biological sample and their corresponding nucleolus features.

[0125] To further ensure the accuracy of cell classification, a second classification can also be performed on the Class C cells:

[0126] In some embodiments, the method may further include: S105 performing a second classification on the Class C cells in the biological sample;

[0127] In some embodiments, the method for the second classification includes:

[0128] Analyzing whether the ratio of the regional areas of the second region of interest and the third region of interest in the Class C cells is abnormal to perform a second classification on the Class C cells in the biological sample.

[0129] In some embodiments, if the ratio of the regional areas of the second region of interest and the third region of interest in the Class C cells is abnormal, the classification of the Class C cells is adjusted to Class B cells; if not, the classification of the Class C cells is adjusted to Class A cells.

[0130] In some embodiments, when the ratio of the regional areas of the second region of interest and the third region of interest shows an increasing trend, it is regarded as abnormal.

[0131] This embodiment finds that when the nucleolus function is "abnormal" (such as impaired nucleolus function), the regional areas of the second region of interest and the third region of interest increase, and the ratio shows an increasing trend of change. By using this increasing trend of change, an accurate second classification of the Class C cells can be performed, and thus a more accurate number and / or ratio of Class A cells and Class B cells can be obtained, effectively performing quantitative and qualitative analysis of cells to accurately and sensitively reflect and evaluate the functional state of the tissue or organ corresponding to the biological sample, which is particularly suitable for biological samples with strong heterogeneity lacking specific markers.

[0132] In some embodiments, class A cells refer to cells with normal nucleolar function relative to the cells themselves.

[0133] In some embodiments, class B cells refer to cells with abnormal nucleolar function relative to the cells themselves.

[0134] In some embodiments, class C cells refer to cells with potentially abnormal nucleolar function relative to the cells themselves.

[0135] In other words, in some special application scenarios (such as when the accuracy requirement for classification results is relatively low or the requirement for classification speed is higher), based on the result of the first classification (i.e., treating class C cells as class B cells), subsequent S106 can be directly performed without performing step S105.

[0136] S106 Calculate the quantity and / or ratio of class A cells and class B cells in the biological sample, and then evaluate the functional state of the tissue or organ corresponding to the biological sample.

[0137] It should be emphasized that in this embodiment, it is found that the above-mentioned increasing change trend is applicable not only to non-tumor biological samples but also to tumor biological samples. That is, although the nucleolar morphologies of non-tumor biological samples and tumor biological samples show different characteristics, when their nucleolar functions are "abnormal", the change trend of the ratio of the area of the second region of interest to the area of the third region of interest is similar. Therefore, the method provided in this embodiment does not need to rely on specific cell activity markers and can achieve high-accuracy and high-precision cell classification only through nucleolus-related phenotypic characteristics, providing a new detection means for diseases lacking specific markers.

[0138] In addition, the method provided in this embodiment can predict cell functions (such as hyperactive cell proliferation or cell exhaustion) and characterize changes in tissue health status (such as intimal hyperplasia, tumors, or degenerative changes, etc.) and the pathological state of diseased tissues by accurately and sensitively reflecting changes in nucleolus-related phenotypes at the early stage of the disease, thereby providing support for the early diagnosis of the disease.

[0139] In some embodiments, the biological sample includes a biological sample treated with a drug and a biological sample not treated with a drug. It should be understood that different from the existing method of cell classification based on nucleolar morphology that can usually only achieve qualitative analysis, the method provided in this embodiment can accurately classify cell subsets in a biological sample with high repeatability. Therefore, quantitative analysis can be performed based on the cell classification results of this embodiment, which is particularly reflected in that the method provided in this embodiment can also be used for high-throughput drug screening and drug efficacy evaluation.

[0140] In some embodiments, the effectiveness of the drug (e.g., whether it has an anti-tumor effect) can be determined by comparing the number and / or ratio of type A cells and type B cells in a drug-treated biological sample and a non-drug-treated biological sample. In some embodiments, high-throughput drug screening can also be performed by comparing the number and / or ratio of type A cells and type B cells in biological samples treated with different concentration gradients of the drug and / or biological samples treated with different drugs.

[0141] In some embodiments, when the biological sample is a tumor sample (e.g., neuroblastoma), the method may further include: S107 analyzing the average diameter of the spots formed by the dense fibrillar component markers in the second region of interest in the type B cells, and when the average diameter is less than the first threshold, the biological sample is evaluated as being in a state of malignant proliferation.

[0142] In some embodiments, the first threshold includes 0.5 - 2 μm.

[0143] Embodiment 2

[0144] As Figure 2 shown, this embodiment provides a nucleolus morphology-based cell classification and function evaluation system 100 corresponding to the method of Embodiment 1, which includes:

[0145] An image acquisition module 102, configured to acquire microscopic image data of a biological sample;

[0146] In some embodiments, the microscopic image data includes optical microscope images with an objective lens magnification of more than 40 times and / or super-resolution microscopic image data.

[0147] In some embodiments, immunofluorescence pictures of biological samples can be batch-collected through a high-throughput imaging system to obtain the microscopic image data. In some embodiments, the imaging requirements include: using an objective lens with a magnification of more than 40 times to image a well plate with a glass bottom or other ultra-thin bottom surfaces (e.g., 0.17 - 0.19 mm).

[0148] In some embodiments, the biological sample includes a tissue or cell culture containing at least one cell.

[0149] In some embodiments, the biological sample is labeled with nucleolar markers, and the nucleolar markers at least include dense fibrillar component markers and granular component markers.

[0150] In some embodiments, the dense fibrillar component marker includes fibrillarin (FBL).

[0151] In some embodiments, the granular component marker includes nucleophosmin 1 (NPM1).

[0152] In some embodiments, the biological sample is further labeled with a nuclear marker.

[0153] In some embodiments, the nuclear marker includes 4',6-diamidino-2-phenylindole (DAPI).

[0154] The first processing module 104 is configured to obtain a first region of interest, a second region of interest, and a third region of interest in the microscopic image data.

[0155] In some embodiments, the first region of interest is a nuclear region delineated by a fluorescence channel corresponding to a nuclear marker.

[0156] In some embodiments, the second region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a dense fibrillar component marker.

[0157] In some embodiments, the third region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a granular component marker.

[0158] The second processing module 106 is configured to extract nucleolus feature data of the second region of interest and the third region of interest, where the nucleolus feature data includes line scan data and region area data;

[0159] The first classification module 108 is configured to perform a first classification on the cells in the biological sample based on the line scan data;

[0160] In some embodiments, the line scan data includes fluorescence intensity distribution curves of the second region of interest and the third region of interest.

[0161] In some embodiments, the method for the first classification includes:

[0162] When the fluorescence intensity distribution curve of the third region of interest encloses the fluorescence intensity distribution curve of the second region of interest, the cell is classified as a type A cell;

[0163] When the fluorescence intensity distribution curve of the second region of interest overflows to the outside of the fluorescence intensity distribution curve of the third region of interest, the cell is classified as a type C cell.

[0164] In some embodiments, the method for evaluating the overflow includes:

[0165] Analyze whether the change trends of the fluorescence intensities at the segments of the fluorescence intensity distribution curve of the second region of interest and the fluorescence intensity distribution curve of the third region of interest are the same in the non-overlapping region formed outside the fluorescence intensity distribution curve of the third region of interest; if not, then there is spillover; if so, then there is no spillover.

[0166] A second classification module 110, configured to perform a second classification on the type C cells in the biological sample;

[0167] In some embodiments, the method of the second classification includes:

[0168] Analyze whether the ratio of the area of the second region of interest to the area of the third region of interest in the type C cells is abnormal, so as to perform a second classification on the type C cells in the biological sample.

[0169] In some embodiments, if the ratio of the area of the second region of interest to the area of the third region of interest in the type C cells is abnormal, then adjust the classification of the type C cells to type B cells; if not abnormal, then adjust the classification of the type C cells to type A cells.

[0170] In some embodiments, when the ratio of the area of the second region of interest to the area of the third region of interest shows an increasing trend, it is regarded as abnormal.

[0171] In some embodiments, the first classification module 108 and the second classification module 110 may be based on a trained cell classification model.

[0172] In some embodiments, the cell classification model can be obtained by performing corresponding model training through a set of nucleolus morphological features related to cell types established, for example, by using cell data of known categories for labeled learning. The morphological differences of nucleoli in different cell types can be analyzed by machine learning for linear relationship analysis, thereby improving the accuracy of classification.

[0173] An analysis module 112, configured to calculate the quantity and / or proportion of type A cells and type B cells in the biological sample, and further evaluate the functional state of the tissue or organ corresponding to the biological sample.

[0174] In some embodiments, the biological sample includes a biological sample treated with a drug and a biological sample not treated with a drug.

[0175] In some embodiments, the analysis module 112 is further configured to analyze the average diameter of the spots formed by the dense fiber component markers in the class B cells. When the average diameter is less than the first threshold, the biological sample is evaluated as being in a state of malignant proliferation.

[0176] In some embodiments, the first threshold includes 0.5 - 2 μm.

[0177] Example III

[0178] Apply the method of Example I to detect a rat vascular smooth muscle cell culture. Figure 3 In a, the super-resolution microscopic images and line scan results of rat vascular smooth muscle cells in the normal group and the drug-treated group labeled with FBL and NPM1 are shown. The results show that in the fluorescence distribution curve of rat vascular smooth muscle cells in the normal group, the fluorescence distribution curve corresponding to NPM1 basically encloses the fluorescence distribution curve corresponding to FBL, representing the clear outer and middle layer partitions of the normal nucleoli of rat vascular smooth muscle cells. Adding drug intervention causes the fluorescence distribution curve corresponding to FBL to spill outside the fluorescence distribution curve corresponding to NPM1 (as indicated by the arrow in a typical case).

[0179] Figure 3 In b, the regional areas of rat vascular smooth muscle cells in the normal group and the drug-treated group labeled with FBL and NPM1 are shown. The regional areas of FBL and NPM1 and the ratio of the regional area of NPM1 to that of FBL in the drug-treated group of rat vascular smooth muscle cells both increase. Figure 3 In c, it is shown that the method and system provided by the present invention can be combined with machine learning (deep learning). Through the high efficiency of the machine learning algorithm, complex cell image data (microscopic image data) can be quickly processed and analyzed, improving the accuracy and precision of cell classification. As Figure 3 shown in c, the nucleoli of class A cells are regular, and the nucleoli of class B cells are irregular.

[0180] Figure 3 In d, the changes in the number and proportion of class A cells and class B cells in the rat vascular smooth muscle cell culture sample before and after drug intervention are shown. The results show that after drug intervention (as indicated by the yellow column in d), the number and proportion of class A cells in the rat vascular smooth muscle cell culture sample decrease, and the number and proportion of class B cells increase. The above results indicate that under the intervention of this drug, the nucleolar function is inhibited, thereby causing damage to cell function. Figure 3

[0181] Example IV

[0182] Figure 4 Apply the method of Example I to detect a neuroblastoma cell line SK-N-SH culture. Figure 4a in shows the super-resolution microscopic images of neuroblastoma cells in the normal group and the drug-treated group labeled with FBL and NPM1 fluorescence. Figure 4 b in shows the corresponding line scan results. The results show that the fluorescence distribution curve corresponding to NPM1 of neuroblastoma cells in the normal group basically surrounds the fluorescence distribution curve corresponding to FBL, representing the clear outer and middle layer partitions of the normal nucleoli of neuroblastoma cells. Adding drug intervention causes the fluorescence distribution curve corresponding to FBL to spill outside the fluorescence distribution curve corresponding to NPM1 (as typically indicated by the arrow).

[0183] Figure 4 c in shows the regional areas of neuroblastoma cells in the normal group and the drug-treated group labeled with FBL and NPM1 fluorescence. The regional areas of FBL and NPM1 and the ratio of the regional area of NPM1 to that of FBL in the drug-treated group of neuroblastoma cells both increase.

[0184] Figure 4 d in shows the changes in the number and proportion of type A cells and type B cells in the SK-N-SH culture sample before and after drug intervention. The results show that after drug intervention, the number and proportion of type A cells in the SK-N-SH culture sample decrease, and the number and proportion of type B cells (cells with "necklace"-like nucleoli in morphology) increase. The above results indicate that under the intervention of this drug, the nucleolar function is inhibited, and thus it can have an inhibitory effect on neuroblastoma cells.

[0185] Example 5

[0186] Using the method of Example 1, the neuroblastoma tumor tissue was detected. The tumor tissue was divided into three degrees of cell proliferation (~0%, 5.743%, 38.227%) using the cell proliferation marker Ki67. As Figure 5 shown, it can be seen that the FBL spot diameter is significantly smaller in highly proliferating neuroblastoma cells. The above results indicate that the malignancy degree of the tumor can be judged according to the FBL spot diameter.

[0187] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a computer terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0188] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit of the present invention and the scope protected by the claims. All of these fall within the protection scope of the present invention.

Claims

1. A method for cell classification and function evaluation based on nucleolar morphology, characterized in that: The following steps are involved: S101 Acquire microscopic image data of a biological sample, wherein the biological sample includes a tissue or a cell culture containing at least one cell; the biological sample is labeled with a nucleolar marker, and the nucleolar marker includes at least a dense fiber component marker and a granular component marker; S102 acquiring a first region of interest, a second region of interest, and a third region of interest in the microscopic image data; wherein the first region of interest is a cell nucleus region delineated by a fluorescence channel corresponding to a cell nucleus marker; the second region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a dense fiber component marker; and the third region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a particle component marker; S103 extracting nucleolus feature data of the second region of interest and the third region of interest, wherein the nucleolus feature data includes line scan data and region area data; S104 Based on the line scan data, a first classification is performed on the cells in the biological sample; the line scan data includes the fluorescence intensity distribution curves of the second region of interest and the third region of interest; the first classification method includes: when the fluorescence intensity distribution curve of the third region of interest is in a surrounding state with the fluorescence intensity distribution curve of the second region of interest, the cell is classified as a type A cell; when the fluorescence intensity distribution curve of the second region of interest overflows to the outside of the fluorescence intensity distribution curve of the third region of interest, the cell is classified as a type C cell; wherein overflow means that part of the section of the fluorescence intensity distribution curve of the second region of interest is distributed outside the fluorescence intensity distribution curve of the third region of interest, and forms one or more non-overlapping areas with the fluorescence intensity distribution curve of the third region of interest, and the fluorescence intensity change trend of the fluorescence intensity of the section of the fluorescence intensity distribution curve of the second region of interest corresponding to the non-overlapping area is different from that of the fluorescence intensity distribution curve of the third region of interest; S105 performing a second classification on the C-type cells in the biological sample, wherein the second classification method comprises: analyzing whether the ratio of the area of ​​the second region of interest to the area of ​​the third region of interest in the C-type cells is abnormal; if abnormal, adjusting the classification of the C-type cells to B-type cells; if normal, adjusting the classification of the C-type cells to A-type cells; S106 Calculate the number and / or ratio of the type A cells to the type B cells in the biological sample, and then evaluate the functional state of the tissue or organ corresponding to the biological sample.

2. The method according to claim 1, characterized in that The dense fiber component marker includes fibrillin, and the granular component marker includes nucleophosmin 1.

3. The method according to claim 1, characterized in that The cell nuclear marker includes 4',6-diamidino-2-phenylindole.

4. The method according to claim 1, characterized in that When the ratio of the area of ​​the second region of interest to the third region of interest shows an increasing trend, it is considered abnormal.

5. The method according to claim 1, characterized in that The biological samples include biological samples treated with drugs and biological samples not treated with drugs.

6. The method according to claim 1, wherein: The method further includes S107 analyzing an average diameter of spots formed by the dense fiber component marker in the second region of interest in the B-type cells, and when the average diameter is less than a first threshold, the biological sample is evaluated as being in a malignant proliferation state.

7. A cell classification and function evaluation system based on nucleolar morphology, characterized in that: The system comprises: An image acquisition module, configured to acquire microscopic image data of a biological sample; wherein the biological sample comprises a tissue or a cell culture comprising at least one cell; the biological sample is labeled with a nucleolar marker, and the nucleolar marker comprises at least a dense fiber component marker and a granular component marker; A first processing module is configured to obtain a first region of interest, a second region of interest, and a third region of interest in the microscopic image data; wherein the first region of interest is a cell nucleus region delineated by a fluorescence channel corresponding to a cell nucleus marker; the second region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a dense fiber component marker; and the third region of interest is a nucleolus region delineated by a fluorescence channel corresponding to a particle component marker; A second processing module is configured to extract nucleolus feature data of the second region of interest and the third region of interest, wherein the nucleolus feature data includes line scan data and region area data; A first classification module is configured to perform a first classification of cells in the biological sample based on the line scan data; the line scan data includes fluorescence intensity distribution curves of the second region of interest and the third region of interest; the first classification method includes: when the fluorescence intensity distribution curve of the third region of interest is in a surrounding state with respect to the fluorescence intensity distribution curve of the second region of interest, classifying the cells as type A cells; when the fluorescence intensity distribution curve of the second region of interest overflows to the outside of the fluorescence intensity distribution curve of the third region of interest, classifying the cells as type C cells; wherein overflow means that a part of the section of the fluorescence intensity distribution curve of the second region of interest is distributed outside the fluorescence intensity distribution curve of the third region of interest, and forms one or more non-overlapping areas with the fluorescence intensity distribution curve of the third region of interest, and the fluorescence intensity change trends at the sections of the fluorescence intensity distribution curve of the second region of interest corresponding to the non-overlapping areas are different from those of the fluorescence intensity distribution curve of the third region of interest; A second classification module is configured to perform a second classification on the C-type cells in the biological sample; the second classification method comprises: analyzing whether the ratio of the area of ​​the second region of interest to the third region of interest in the C-type cells is abnormal; if abnormal, adjusting the classification of the C-type cells to B-type cells; if not abnormal, adjusting the classification of the C-type cells to A-type cells; The analysis module is configured to calculate the number and / or ratio of the type A cells and the type B cells in the biological sample, and then evaluate the functional state of the tissue or organ corresponding to the biological sample.

8. The system according to claim 7, characterized in that The dense fiber component marker includes fibrillin, and the granular component marker includes nucleophosmin 1.

9. The system according to claim 7, characterized in that When the ratio of the area of ​​the second region of interest to the third region of interest shows an increasing trend, it is considered abnormal.

10. The system according to claim 7, characterized in that The biological samples include biological samples treated with drugs and biological samples not treated with drugs.

Images