Cell image processing system and cell image processing method

Abstract

The invention relates to a cell image processing system and a cell image processing method. A cell image processing system includes: an image acquisition unit configured to acquire a cell image including a plurality of cells as a subject; a cell region extraction unit configured to extract a plurality of cell regions from the cell image; a cell information acquisition unit configured to acquire characteristic information including morphological information on each cell region and pixel information on each cell region; a representative cell determination unit configured to determine a representative cell region from among the extracted plurality of cell regions based on at least one type of information constituting the characteristic information; and a display control unit configured to cause the display unit to display image information on a cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information on the cell region corresponding to the representative cell.

Description

Technical Field

[0001] The present invention relates to a cell image processing system and a cell image processing method. Background Art

[0002] Operations are often performed as follows: obtaining cell analysis data obtained by cell image analysis and having a user examine and analyze the obtained analysis data. Specifically, the analysis data distribution is visualized in a format such as a scatter plot so that the user can recognize an overall image of the analysis data distribution, thereby quantitatively recognizing a trend of a cell data group. In addition, operations are also performed as follows: while observing the state of each cell on an observation image, the user examines each cell data in the visualized data distribution, thereby examining the state of each living cell while recognizing an overview of the trend of the quantitative data.

[0003] In cell image analysis software that supports such operations, while examining cells in an observation image, the user sequentially picks up cells of interest. In addition, it is also possible to list a cropped image of a cell and cell data.

[0004] Japanese Patent Application Laid-Open No. 2016-90234 discusses an image processing apparatus that extracts feature values from a section image and causes a display unit to display a feature value image including information about the extracted feature values in such a manner that the feature value image is superimposed on the section image. Summary of the Invention

[0005] However, in many cases, a large number of cells (for example, thousands or more cells) are processed as cell data to be analyzed. In such a case, it is difficult for a user to manually find out main cells among the large number of cells. The user needs to select a section image, which increases the burden on the user.

[0006] According to an aspect of the present invention, a cell image processing system includes: an image acquisition unit configured to acquire a cell image of a sample including a plurality of cells as examinees; a cell region extraction unit configured to extract a plurality of cell regions respectively corresponding to the cells from the cell image; a cell information acquisition unit configured to acquire characteristic information including morphological information about each cell region and pixel information about each cell region; a representative cell determination unit configured to determine a representative cell region from the plurality of extracted cell regions based on at least one type of information constituting the characteristic information; and a display control unit configured to cause a display unit to display image information about a cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information about the cell region corresponding to the representative cell.

[0007] According to another aspect of the present invention, a method for processing cell images includes: acquiring a cell image of a sample including a plurality of cells as a subject to be examined; extracting a plurality of cell regions respectively corresponding to the cells from the cell image; acquiring characteristic information including morphological information about each cell region and pixel information about each cell region; determining a representative cell region from the plurality of extracted cell regions based on at least one type of information constituting the characteristic information; and controlling a display unit to display image information about the cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information about the cell region corresponding to the representative cell.

[0008] The further features of the present invention will become apparent from the following description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a block diagram showing a functional block of a cell image processing system according to a first exemplary embodiment of the present invention.

[0010] Figure 2 is a flowchart showing a cell image processing method according to a second exemplary embodiment of the present invention.

[0011] Figure 3 is a flowchart showing an example of a process for acquiring cell data in step S201 according to a second exemplary embodiment of the present invention.

[0012] Figure 4 shows an example of a defocused image acquired in step S301 according to a second exemplary embodiment of the present invention.

[0013] Figure 5 shows an example of a spontaneous fluorescence image acquired in step S302 according to a second exemplary embodiment of the present invention.

[0014] Figure 6 shows an example of a mask image generated in step S303 according to a second exemplary embodiment of the present invention.

[0015] Figure 7 shows tabular information as an example of cell data acquired in step S201 according to a second exemplary embodiment of the present invention.

[0016] Figure 8 is a conceptual diagram showing a method for determining a representative cell in step S202 according to a second exemplary embodiment of the present invention.

[0017] Figure 9 is a conceptual diagram showing a method for determining a representative cell in a fifth modification example according to a second exemplary embodiment of the present invention.

[0018] Figure 10 Shows an example of a graphical user interface (GUI) screen that displays information about representative cells in step S203 according to a second exemplary embodiment of the present invention.

[0019] Figure 11 Shows an example of a GUI screen that displays information about representative cells according to a sixth modification example of the second exemplary embodiment of the present invention.

[0020] Figure 12 Is a block diagram showing the functional blocks of a cell image processing system according to a third exemplary embodiment of the present invention.

[0021] Figure 13 Is a flowchart showing cell image processing according to a third exemplary embodiment of the present invention.

[0022] Figure 14 Shows an example of a GUI screen that displays information about representative cells in step S1304 according to a third exemplary embodiment of the present invention.

[0023] Figure 15 Is a block diagram showing a configuration example of an information processing system configured to execute a program according to an exemplary embodiment of the present invention. Detailed Description of the Invention

[0024] Exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following exemplary embodiments are not intended to limit the claimed invention. Multiple features are described in the exemplary embodiments, but not all of these features are required for the invention, and these multiple features can be appropriately combined. Further, in the drawings, the same or similar components are denoted by the same reference numerals, and redundant description thereof is omitted.

[0025] <Cell Image Processing System>

[0026] The cell image processing system according to a first exemplary embodiment of the present invention will be described below.

[0027] Figure 1 Is a block diagram showing the functional blocks of a cell image processing system according to a first exemplary embodiment. The cell image processing system 100 includes a cell data acquisition unit 110, a representative cell determination unit 120, a display control unit 130, and a storage unit 140. The cell data acquisition unit 110 includes an image acquisition unit 111, a cell region extraction unit 112, and a cell information acquisition unit 113. Although Figure 1 Each unit constituting the cell image processing system 100 is shown as an integrated device, some of these units may be configured as external devices (including objects on the cloud).

[0028] (Cell data acquisition unit)

[0029] The cell data acquisition unit 110 acquires a cell image and a set of cell data obtained by performing image analysis on the cell image. The set of cell data is a data set related to characteristic information about each cell region, the characteristic information including morphological information about the cell region and pixel information about the cell, and the set of cell data is obtained by performing image analysis on each cell region included in the cell image.

[0030] In the present exemplary embodiment, the position information about each cell region includes at least one of the following: a set of contour coordinates indicating the boundaries between cell regions in the cell image, and coordinates indicating the centroid position of each cell region in the cell image. The position information about each cell region according to the present exemplary embodiment is not particularly limited as long as the position information indicates the position of the cell region. Examples of the position information include information about the centroid coordinates of each cell region in the cell image and information about a set of contour coordinates indicating the boundaries between cell regions.

[0031] In the present exemplary embodiment, the morphological information about each cell region includes at least one of the following: the area of each cell region, the diameter (radius) of each cell region, the roundness of each cell region, and the perimeter of the contour of each cell region.

[0032] In the present exemplary embodiment, the pixel information about each cell region includes at least one of the following: the average value of the pixels (values) in each cell region, the integral value of the pixel values in each cell region, and the standard deviation of the pixel values in each cell region.

[0033] (Image acquisition unit)

[0034] The image acquisition unit 111 acquires at least one of the following cell images (cell image data): a bright-field image of each cell, a fluorescence image of each cell, and a phase-contrast image of each cell. The bright-field image is, for example, an image indicating the morphology of each cell, such as a bright-field image of each cell obtained at the focal position, or a bright-field image captured by shifting the focal position by a predetermined distance along the optical axis direction (this image is hereinafter referred to as a defocused image). The defocused image has the following characteristics: the contour part including the phase object of the cell is highlighted with a higher pixel value or a lower pixel value.

[0035] The fluorescence image is, for example, an image obtained by capturing the autofluorescence of each cell by applying light having a specific wavelength from an excitation light source to each cell (this image is hereinafter referred to as an autofluorescence image). The phase-contrast image is obtained by capturing an image of each cell with a phase-contrast microscope.

[0036] The cell image (cell image data) may be image data pre-stored in the storage unit 140, or may be acquired from an external storage area such as a hard disk drive (HDD) or cloud storage. The cell image processing system 100 according to the present exemplary embodiment may be connected to a cell image observation device (not shown) via a communication interface (I / F) to acquire an image captured by the cell image observation device.

[0037] (Cell Region Extraction Unit)

[0038] The cell region extraction unit 112 extracts cell regions from the cell images acquired by the image acquisition unit 111. Extracting cell regions means extracting and acquiring the morphologies of the individual cells discretely present within the cell observation field of view, or extracting and acquiring the morphologies of the individual cell groups and entire aggregates that exist in a state of being in close contact with each other or in an aggregated state. The software for extracting each cell region is not particularly limited, and known software may be used.

[0039] (Cell Information Acquisition Unit)

[0040] The cell information acquisition unit 113 acquires characteristic information including morphological information about the cell regions and pixel information about the cell regions based on the cell images acquired by the image acquisition unit 111 and the cell regions extracted by the cell region extraction unit 112.

[0041] (Representative Cell Determination Unit)

[0042] The representative cell determination unit 120 determines representative cells (main cells) constituting the cell data group based on the cell data acquired by the cell data acquisition unit 110. Specifically, the representative cell determination unit 120 determines representative cell regions from the extracted plurality of cell regions based on at least one type of information constituting the characteristic information.

[0043] The representative cell determination unit 120 according to the present exemplary embodiment may extract a plurality of subsets from a data set formed of characteristic information on a plurality of cell regions, and may determine a representative cell region from each of the plurality of subsets. Examples of the subset extraction method are as follows. That is, the method includes (1) calculating the occurrence probability of data on each cell region based on at least one type of information constituting the characteristic information, and (2) extracting, as subsets, data sets corresponding to each of a plurality of predetermined occurrence probability ranges from the data set formed of the characteristic information on the plurality of cell regions. Another example of the subset extraction method is as follows. That is, the method includes (a) calculating the distance between the data on each cell region and the centroid of the data on all cell regions based on at least one type of information constituting the characteristic information, and (2) extracting, as subsets, data sets corresponding to each of a plurality of predetermined distance ranges from the data set formed of the characteristic information on the plurality of cell regions. Still another example of the subset extraction method is as follows. That is, the method includes (i) dividing the data set constituting the subset into a plurality of clusters by unsupervised clustering, and (ii) determining, as the representative cell region in each of the data sets corresponding to these clusters, the cell region corresponding to the data closest to the centroid position of the data set. The process of determining the representative cell will be described in detail below.

[0044] (Display control unit)

[0045] The display control unit 130 displays information on the representative cell region determined by the representative cell determination unit 120. Specifically, the display control unit 130 causes the display unit to display image information on the cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information on the cell region corresponding to the representative cell. Hereinafter, "image information on the cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information on the cell region corresponding to the representative cell" may be referred to as information on the representative cell.

[0046] The image information on the cell region corresponding to the representative cell includes a magnified image of at least a small cutout region including the representative cell from the cell image acquired by the image acquisition unit 111. The characteristic information on the cell region corresponding to the representative cell includes measurement data of the representative cell obtained by measuring the cell image. The measurement data of the representative cell is characteristic information such as morphological information and pixel information corresponding to the representative cell determined by the representative cell determination unit 120 in the cell data set acquired by the cell data acquisition unit 110.

[0047] If at least one piece of information in the information about the representative cell is selected, the display control unit 130 may control the display unit to display the information other than the selected information together with the selected information synchronously and in a highlighted manner. Specifically, if at least one piece of information in the information about the representative cell displayed on the display is selected by a user operation, the display control unit 130 may control the display unit to synchronously and prominently display the information different from the selected information.

[0048] According to the present exemplary embodiment, a representative cell region (representative cell) may be determined from a cell image, and the display unit may be caused to display an image and characteristic information of the representative cell. This enables a user to simply identify information about the representative cell among a large number of cells within the cell image.

[0049] <Cell Image Processing Method>

[0050] Figure 2 is a flowchart showing a cell image processing method according to a second exemplary embodiment of the present invention. The cell image processing method according to the second exemplary embodiment includes a step of acquiring cell analysis data (step S201), a step of determining a representative cell (step S202), and a step of displaying information related to the representative cell (step S203).

[0051] Step S201 includes: an image acquisition step of acquiring a cell image of a sample including a plurality of cells as an examinee; and a cell region extraction step of extracting a plurality of cell regions corresponding to the cells from the cell image. Step S202 includes a representative cell determination step of determining a representative cell region from the plurality of extracted cell regions based on at least one type of information constituting the characteristic information. As used herein, the term "characteristic information" refers to information acquired in the cell information acquisition step and including morphological information about each cell region and pixel information about each cell region.

[0052] Step S203 includes a display control step of causing the display unit to display image information about the cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information about the cell region corresponding to the representative cell.

[0053] The following will refer to Figure 2 the flowchart shown to describe in detail each function of the cell image processing system 100.

[0054] (Acquisition of Cell Data)

[0055] In step S201, the cell data acquisition unit 110 acquires a cell image and a cell image data set by performing image analysis (image processing) on the cell image.

[0056] Figure 3 is a flowchart showing a process for analyzing cell images and obtaining cell data.

[0057] Hereinafter, with reference to Figure 3 an example of a process for obtaining a defocused image and an autofluorescence image and obtaining cell data through image analysis will be described.

[0058] (Acquisition of morphological cell images)

[0059] In step S301, the image acquisition unit 111 acquires a defocused image as a morphological cell image. Any image can be used as the image acquired in step S301 as long as the image has the following characteristics: the contrast of the contour portion of each cell is highlighted compared to the non-cell region. For example, an image captured by a phase contrast microscope can be used, or an image captured by an oblique illumination system or a telecentric optical system (double telecentric optical system) that is telecentric on the object side and the image side can be used. The position where the defocused image is captured can desirably be a position where the contrast of the contour portion of each cell is most prominently displayed.

[0060] (Acquisition of fluorescence images)

[0061] In step S302, the image data acquisition unit 101 acquires an autofluorescence image of each cell as a fluorescence image. As used herein, the term "autofluorescence image" refers to an image obtained by irradiating cells with excitation light having a predetermined wavelength to excite cell-intrinsic fluorescent substances and capturing the fluorescence through a filter for blocking the excitation light source wavelength.

[0062] The wavelength of the excitation light and the conditions of the cutoff filter can be selected according to the fluorescence characteristics of the endogenous component to be observed. As a combination of the wavelength of the excitation light and the cutoff filter, for example, when NAD(P)H is used as the endogenous component, excitation light with a wavelength of 360 nm and a long-pass filter of 430 nm are used. In the case of using flavin (FAD, etc.), excitation light with a wavelength of 450 nm and a long-pass filter of 530 nm can be used. Other examples of endogenous components for autofluorescence observation include autofluorescent molecules produced in cells, such as collagen, fibronectin, tryptophan, and folic acid. Fluorescent endogenous components other than these components can also be used. The autofluorescence image is an image including the same field of view as the morphological cell image acquired in step S301. In addition, any other image can be used as long as the image is captured by a camera including a two-dimensional image sensor (where two or more types of pixels having peak detection sensitivity in two or more different wavelength regions are regularly arranged).

[0063] For example, a red, green, blue (RGB) color camera can be used, which uses a complementary metal oxide semiconductor (CMOS) sensor as an optical sensor.

[0064] However, the optical sensor according to this exemplary embodiment is not limited to a CMOS sensor, and can also be a camera using a charge coupled device (CCD) sensor. It is desirable to use an appropriate sensor or a camera employing such a sensor depending on the wavelength of the light emitted from the cells to be observed.

[0065] Figure 4 An example of the defocused image acquired in step S301 is shown, and Figure 5 An example of the autofluorescence image acquired in step S302 is shown. Figure 4 The image 01 shown is an example of the acquired defocused image, and Figure 5 The image 02 shown is an example of the autofluorescence image captured within the same field of view as that of the image 01, using excitation light with a wavelength of 360 nm and a long pass filter with a wavelength of 430 nm. The images 01 and 02 are RGB color images captured by an RGB color camera using a CMOS sensor as an optical sensor.

[0066] The image 410 is an enlarged display image of a small area that is part of the image 01, and the image 510 is an enlarged display image of a small area that is part of the image 02. In the image 410, each region with a black highlighted outline corresponds to a cell region, and the image 410 was captured within a field of view where there are approximately three thousand cells.

[0067] As the autofluorescence image, two or more autofluorescence images can be acquired under different conditions of the combination of the excitation light wavelength and the observation side cut-off filter characteristics. The fluorescence image is not limited to the autofluorescence image, and a stained image obtained by observing a cell sample to which a staining reagent showing fluorescence characteristics for a specific wavelength has been added can be acquired.

[0068] (Cell region extraction process)

[0069] In step S303, the cell region extraction unit 112 extracts each cell region from the morphological cell image acquired in step S301.

[0070] The process of extracting each cell region can be performed by a known image analysis method. For example, as in Figure 4In the case of the acquired defocused image shown, the RGB image acquired by the RGB color camera is converted into a single channel and threshold processing is performed, so that cell contour information indicating the boundaries between cell regions can be extracted. Further, a mask image is created (wherein the inner region of the extracted cell contour is displayed with black pixels and the outer region of the extracted cell contour is displayed with white pixels), and an identifier is assigned to each isolated black pixel region by labeling processing, so that each cell region in the cell image can be identified.

[0071] Figure 6 An example of Figure 4 the mask image 01 created for the defocused image 01 shown is shown. The image 610 is an enlarged display image of a small region that is part of the mask image 01. The cell regions 00001 to 00003 each represent a partial cell region labeled based on the mask image 01.

[0072] Although the above-described exemplary embodiment shows an example of using a defocused image captured by an RGB color camera, the cell region extraction process can be applied to an image in which the contrast of the contour portion of a cell is highlighted compared to a non-cell region. For example, an image observed through a phase contrast microscope or an image subjected to image processing to highlight the contour portion of each cell can be used.

[0073] (Pixel information extraction process)

[0074] In step S304, the cell information acquisition unit 113 acquires pixel information corresponding to each cell region from the images acquired in steps S301 and S302 based on each cell region acquired in step S303.

[0075] An example of capturing an image by the RGB color camera in step S302 will be described.

[0076] First, the Bayer array data on the image is separated into images having three channels respectively corresponding to the RGB components. The Bayer array data is two-dimensional array data obtained by recording pixel values received by the CMOS color sensor.

[0077] Next, the pixel values of the Bayer array data are separated into components of color filters respectively corresponding to three wavelength regions, so that these components are separated into three RGB components. In the Bayer array data, each pixel includes information on the pixel value corresponding to any one of the RGB components. Interpolation processing can be performed so that each pixel has information on the pixel values corresponding to the three RGB components respectively. Further, preprocessing such as black level correction processing for subtracting the dark current value from each pixel value or filtering processing for reducing noise can be performed.

[0078] Next, extract the pixel information in each cell region obtained in step S303. The pixel information is a scalar value indicating the pixel statistics of each RGB component in each cell region. For example, the average value is calculated as the pixel information. An example of calculating the average value as the pixel value will be described below. However, the pixel information is not limited to this example, and one of the integral value and the standard deviation can be calculated, or multiple types of statistics can be calculated.

[0079] In the case of using a fluorescence image, according to the characteristics of the cutoff filter used during image capture, only the pixel statistics of the significant components in the RGB components are calculated. For example, in the case of using a spontaneous fluorescence image captured using excitation light with a wavelength of 360 nm and a 430 nm long-pass filter, only the pixel statistics of the G component and the B component are calculated.

[0080] The calculation of the pixel statistics as described above is repeatedly performed for each image and each cell region, so that a set of cell data can be obtained as a collection of pixel information regarding the cell regions.

[0081] In addition, morphological information indicating the morphological characteristics of each cell region can be obtained together with the pixel information. Specifically, scalar values such as area, diameter, roundness, or solidity are calculated.

[0082] Figure 7 Shown based on Figure 4 and Figure 5 Images 01 and 02 shown respectively in Figure 6 and the cell data set obtained from the cell regions shown in

[0083] is an example. Table 700 is a table in which each row corresponds to each cell region and each column represents the calculation results of the pixel information and the morphological information as described above.

[0084] The above describes an example of obtaining a defocused image and a spontaneous fluorescence image in step S201 and obtaining cell data through image processing.

[0085] In step S201, the cell data acquisition unit 110 acquires a set of cell data including both cell morphological characteristics and cell functional characteristics. The acquired set of cell data is used for the processing in step S202. As Figure 7As shown, the position information for each cell extracted from the cell image is also saved in association with the data of each cell region. Specifically, information on the coordinate group of the contour surrounding each cell region and information on the barycentric coordinates are saved as the position information for each cell.

[0086] Although the above-described exemplary embodiment shows an example of obtaining a cell data set using the defocused image 01 and the autofluorescence image 02 captured within a specific field of view, the cell data set obtaining method is not limited to this example. Images captured in multiple fields of view can be obtained. In this case, the process of step S201 is performed on each image among the images captured in multiple fields of view or on each captured image of multiple cell samples, thereby obtaining a cell data set.

[0087] (Determination of representative cells)

[0088] In step S202, the representative cell determination unit 120 determines the main cells constituting the cell data set based on the cell data set obtained in step S201.

[0089] First, the probability density distribution is estimated based on the obtained cell data set. The probability density distribution is a distribution for estimating the probability at which certain data may occur. The probability density distribution is estimated, for example, by kernel density estimation. Figure 8 Shows the use of Figure 7 The result of estimating the probability density distribution by kernel density estimation using two types of information, namely, the B component of the image 02 and the G component of the image 02, in the cell data set 700 shown. By plotting the normalized data of each cell region with the B component of the image 02 taken on the horizontal axis and the G component of the image 02 taken on the vertical axis, a scatter plot 801 is obtained. The probability density distribution 802 is a visualized probability density distribution estimated by kernel density estimation for the data set indicated by the scatter plot 801. The regions with darker colors indicate the regions of data that occur with a higher probability.

[0090] Next, in the probability density distribution 802, for example, a plurality of regions with a predetermined appearance probability are set. For example, three regions with appearance probabilities of 95 to 100%, 45 to 55%, and 0 to 5% are set respectively. These three regions correspond to regions D01, D02, and D03 in the probability density distribution 802 respectively. In this case, region D01 is the region that occupies most of the cell data and includes a large amount of cell data based on the cell group to be observed. Region D02 includes a large number of cell groups in which morphological features or functional features may have changed compared to the cells included in region D01. Region D03 is the region that includes cells that are very likely to be in an unexpected state. Examples of cells in an unexpected state include cells that have unexpectedly transformed, cells contaminated by other cells, cells in an abnormal state depending on the cell state (pathological condition), and non-cell objects similar to cells that appear during observation. The region setting method is not limited to the above method. For example, two regions with appearance probabilities of 95 to 100% and 0 to 5% respectively can be used, and the appearance probability range can be adjusted.

[0091] Next, data of representative cells are determined from each of regions D01 to D03. Specifically, first, a cell data group corresponding to region D01 is extracted as a subset S01 of the cell data group 700 for region D01. In addition, a number of cell data are extracted from the subset S01 as a representative cell group G01 in region D01. For example, four pieces of cell data can be extracted based on an unsupervised clustering method. As the cell data included in the representative cell group G01, cell data whose characteristics are not similar to any other data in the subset can be preferably extracted. For example, this process can be implemented using an unsupervised clustering method. More specifically, the data group is divided into four clusters by an unsupervised clustering method (such as K-means), and the data closest to the data centroid in each cluster is determined as the representative cell data. The above procedure is also applied to each of regions D02 and D03 to sequentially extract representative cell groups G02 and G03.

[0092] In the above step S202, representative cell groups G01, G02, and G03 are extracted as the main cells constituting the cell data group.

[0093] The above has been described with reference to step S202 using as Figure 7Examples of representative cells are determined using two types of data in the cell data group shown. However, the representative cell determination method is not limited to this example. In the case of using one or more types of data, a representative cell group can also be determined in the same manner. For example, only diameter data can be used or all types of data can be used. Specifically, if a high-quality data type for representing cell properties is known among multiple data types, this data type can be desirably selected by the user, and representative cells can be desirably determined using the selected data type. If the high-quality data type is unknown, it is also effective to perform the process of step S202 after converting each N-dimensional cell data formed by N types of scalar values into low-dimensional data by a dimensionality reduction method such as principal component analysis. For example, in Figure 7 the example shown, each cell data is ten-dimensional data formed by ten types of items, and principal component analysis is applied to the cell data group 700 to convert the data into two-dimensional data. Then, the representative cells are determined in step S202 using the two-dimensional data obtained after the conversion.

[0094] (Display of information about representative cells)

[0095] In step S203, the display control unit 130 displays information about the representative cells extracted in step S202 on the display. As described above, the information about the representative cells includes three types of information, namely, the representative cell image, the measurement data of the representative cells, and the position information about the representative cells.

[0096] Figure 10 An example of displaying information about representative cells is shown. A graphical user interface (GUI) screen 1000 is displayed on the display. Area 1010 shows an example of the image acquired in step S201. For example, the Figure 4 defocused image 01 shown is displayed. The position information about each representative cell extracted in step S202 is displayed on the defocused image 01 in a superimposed manner. For example, based on the contour coordinate information about the representative cells, a contour as indicated by the representative cell contour 02a shown in Figure 10 is drawn on the defocused image 01 as the position information.

[0097] Area 1020 displays the measurement data of each representative cell acquired in step S201. Considering the overview of the cell data group acquired in step S201, it is desirable to highlight the measurement data of each representative cell. For example, the Figure 8The scatter plot 801 shown in [description], and the plotted points corresponding to the representative cells are highlighted. The highlighting is, for example, plotting the data of each representative cell in a color different from the data in the regions outside the representative cell regions, or plotting the data of each representative cell with a larger marker size than the data in the regions outside the representative cell regions. The information to be displayed on the area 1020 is not limited to the two-dimensional scatter plot as shown in Figure 10 shown. Alternatively, a histogram, a box plot, a map obtained by visualizing the probability density distribution estimated in step S202, etc. can be used. Further, in this case, the data corresponding to each representative cell data is highlighted and plotted as a line or a point.

[0098] The area 1030 displays representative cell images based on the position information of each representative cell extracted in step S202. Figure 10 shows an enlarged display image of a sheared region having a predetermined size and centered on the center of gravity of the representative cell, which is sheared from the defocused image 01 as shown in Figure 4 shown.

[0099] The predetermined size can be determined by the user according to the size of the cells to be observed. As indicated by the representative cell groups G01, G02, and G03 shown in Figure 10 it is desirable to display each representative cell group in such a way that the user can identify the region to which each representative cell belongs in the probability density distribution. The area 1010 and the area 1030 correspond to the defocused image 01 and the representative cell image sheared from the defocused image 01, respectively. If a plurality of images are acquired as described above in step S201, these plurality of images can be switched. Specifically, the user selects the displayed image on the selection field 1040, thereby switching the image to be displayed on the area 1010 and the representative cell image to be displayed on the area 1030. The image switching process is not limited to this example, and the image can be switched by a mouse operation or a keyboard operation.

[0100] The display control unit 130 displays information about each representative cell on the GUI screen. Then, when the user selects any type of information about a representative cell, the display control unit 130 controls the display unit to display, in a synchronized and highlighted manner, other types of information about the representative cell. For example, if the user selects the representative cell image 02a from the representative cell images displayed on the area 1030 as shown in Figure 10 shown, the representative cell contour 02a and the representative cell data 02a corresponding to the representative cell image 02a are highlighted.

[0101] The method for determining representative cells in a cell data set obtained from a cell image and displaying information about the representative cells has been described above with reference to steps S201 to S203. According to this exemplary embodiment, a user can simply identify the main representative cells constituting the cell data set.

[0102] The processing of steps S201 to S203 according to a modified example of the second exemplary embodiment will be described below. Steps not mentioned in the modified example are similar to those of the second exemplary embodiment and thus their descriptions are omitted.

[0103] A first modified example of the second exemplary embodiment will be described. In step S302, if the morphological cell image and the fluorescence image are not captured in the same field of view, registration processing is performed on the morphological cell image and the fluorescence image data.

[0104] The registration processing is performed by a method based on marking by an operator or by using an image processing method.

[0105] In the method based on marking, the operator marks a plurality of points at the same cell positions in each of the morphological cell image and the autofluorescence image, and calculates an affine transformation matrix based on the coordinates of the marked points, thereby performing the registration processing. In this case, it may be preferable to mark nine or more points.

[0106] In the case of performing registration (alignment processing) by image processing, for example, alignment processing is performed using a mask image generated by performing threshold processing on the autofluorescence image and a non-cell region mask image generated from the defocused image in step S302. In this case, methods such as template matching or pure phase correlation can be used to perform alignment processing on the two mask images.

[0107] According to the first modified example, cell data including both cell morphological features and cell functional features can be obtained even when the morphological cell image and the fluorescence image are not captured in the same field of view.

[0108] [Second Modified Example of the Second Exemplary Embodiment]

[0109] A second modified example of the second exemplary embodiment will be described. The above second exemplary embodiment shows an example of acquiring a morphological image and a fluorescence image as a preferred example of acquiring cell data including both morphological features and functional features of each cell. The second exemplary embodiment is also applicable to the case where only a morphological image or a fluorescence image is used as an observation image of a target cell sample.

[0110] In the case of using only morphological images, the fluorescence image is not acquired in step S302 according to the second exemplary embodiment, and the process proceeds to step S303. The subsequent processing can be implemented in the same manner as in the second exemplary embodiment.

[0111] In the case of using only fluorescence images, the morphological image is not acquired in step S301 according to the second exemplary embodiment, and the process proceeds to step S302. To extract each cell region in step S303, known image processing methods can be used. For example, after converting the fluorescence image into a grayscale image, mask image creation processing and labeling processing as shown Figure 6 are performed through threshold processing.

[0112] The threshold used in the threshold processing can be determined by a known method such as Otsu's method. The subsequent processing can be executed in the same manner as in the above second exemplary embodiment.

[0113] A third modification example of the second exemplary embodiment will be described. In step S304, a method for extracting RGB components from Bayer array data is described. However, the components can be extracted after converting the RGB components to a different color space or a different color coordinate system. For example, color spaces such as sRGB and AdobeRGB and color coordinate systems such as Lab, XYZ, and HSV can be used.

[0114] A fourth modification example of the second exemplary embodiment will be described. The above second exemplary embodiment shows an example of a method for extracting autofluorescence information using a CMOS sensor as an RGB camera. Alternatively, images acquired by a camera other than an RGB camera can be used, such as a multi-band spectral camera including an optical sensor suitable for the observation wavelength or a spectral camera such as a hyperspectral camera. The optical sensor is, for example, a CMOS sensor, a CCD sensor, a Ge-type sensor, an InGaAs-type sensor, a bolometer-type sensor, or an avalanche photodiode array (APD)-type sensor.

[0115] In this case, in step S304, the image data is separated into images of a plurality of components corresponding to a plurality of wavelength filters included in the camera.

[0116] A fifth modification example of the second exemplary embodiment will be described. When there is a dense cell data distribution in the data space formed by the data types for estimation, the estimation of the probability density distribution according to the second exemplary embodiment is effective. On the other hand, in a cell data group where there is no dense cell data distribution, a representative cell group can be determined based on the distance between the data and the centroid of the cell data group.

[0117] Specifically, a plurality of data distribution regions are set based on the distance of the data from the centroid of the cell data group. Figure 9 An example of the set regions in the scatter plot 801 shown, for example, in Figure 8 is shown. With respect to the centroid C01 of the cell data group, three regions D04, D05, and D06 corresponding to distance ranges of 0.00 to 0.10, 0.45 to 0.55, and 0.95 to 1.00 are set, respectively. The distance from the centroid is normalized to a maximum of 1.00.

[0118] The method for determining the representative cells in each of the regions D04, D05, and D06 is similar to that of the second exemplary embodiment.

[0119] A known accuracy evaluation index for estimating the probability density distribution can be used to determine which of the probability density distribution estimation according to the second exemplary embodiment and the method according to this modified example is to be used. Specifically, the data occurrence probability is calculated, and the total value of the calculated data occurrence probability can be used as the value of the accuracy evaluation index. The evaluation value is a value in the range from 0.0 to 1.0. For example, if the evaluation value is less than or equal to 0.8, the method is switched to the determination of the representative cells based on this modified example.

[0120] It is possible to display Figure 8 the scatter plot 801 shown or the distribution plot representing the result of the probability density distribution 802, and the method to be adopted can be switched after the user checks the result.

[0121] A sixth modified example of the second exemplary embodiment will be described. The above second exemplary embodiment shows an example of displaying the representative cell images in a list format, as Figure 10 shown. However, at least two types of information among the three types of information, namely the representative cell image, the position information about the representative cell, and the measurement data of the representative cell, can be displayed, and the format for displaying such information is not limited to Figure 10 the example shown.

[0122] For example, the display control unit can cause the display unit to display the image information about the cell region corresponding to the representative cell and the position of the representative cell region in the cell image in an associated manner. Specifically, the following format can be used, in which the representative cell image is mapped and displayed at the coordinates on the image displayed in area 1010 or at the position corresponding to the data on the scatter plot shown in area 1020. Figure 11 An example of mapping and displaying the representative cell image based on the coordinates in area 1010 is shown. Each representative cell image is displayed on image 01 in area 1010, and each representative cell is displayed in association with the centroid position of the corresponding representative cell.

[0123] Instead of displaying the representative cell images on the same GUI screen 1000, the representative cell images can be displayed separately on regions 1010, 1020, and 1030, or displayed as separate GUI screens on one of regions 1010, 1020, and 1030.

[0124] The display formats described in the second exemplary embodiment and this modification example can be arbitrarily switched by the user. For example, an appropriate display format can be selected according to the type of device used for display (such as a desktop personal computer (PC), a laptop PC, a tablet PC, or a smartphone) and the resolution of the display.

[0125] The above second exemplary embodiment shows a method for determining representative cells in a cell data set obtained based on cell images and displaying information about the representative cells.

[0126] The third exemplary embodiment shows a method for performing cluster classification by unsupervised clustering of the obtained cell data set to determine representative cells in each cluster.

[0127] According to the third exemplary embodiment, even when the cell sample to be analyzed includes a large number of cell groups with different properties, the main cell data constituting each cell data set can be appropriately determined as representative cells.

[0128] The third exemplary embodiment is particularly effective when it can be estimated in advance that the target cell sample includes cell groups with different properties. Examples of such cases include images obtained by observing cell samples in which cells are co-cultured by adding two or more different types of cell stains or two or more different types of reagents, and cell samples in a state where there are a large number of live cells and a large number of dead cells.

[0129] Figure 12 is a block diagram showing the functional blocks of a cell image processing system according to the third exemplary embodiment. The cell image processing system 1200 includes a cell data acquisition unit 1210, a classification unit 1220, a representative cell determination unit 1230, a display control unit 1240, and a storage unit 1250. The cell data acquisition unit 1210 includes an image acquisition unit 1211, a cell region extraction unit 1212, and a cell information acquisition unit 1213.

[0130] The cell data acquisition unit 1210, the display control unit 1240, the image acquisition unit 1211, the cell region extraction unit 1212, and the cell information acquisition unit 1213 are similar to those in the first exemplary embodiment, and thus their descriptions are omitted.

[0131] (Taxonomic unit)

[0132] The taxonomic unit 1220 classifies the cell data group obtained by the cell data acquisition unit 1210 into a plurality of clusters by an unsupervised clustering method.

[0133] (Representative cell determination unit)

[0134] The representative cell determination unit 1230 determines representative cell data, which is the main cell data constituting each cluster in each cell data group classified by the taxonomic unit 1220.

[0135] Figure 13 is a flowchart showing the processing performed by the cell image processing system according to the third exemplary embodiment. The following will refer to Figure 13 the flowchart shown to describe in detail the functions of the cell image processing system 1200.

[0136] Step S1301 is similar to step S201 according to the second exemplary embodiment, and thus its description is omitted.

[0137] (Cluster classification)

[0138] In step S1302, the taxonomic unit 1220 classifies the cell data group obtained in step S1301 into a plurality of clusters.

[0139] For example, using the number of clusters "2", the cell data group is classified into two clusters CL01 and CL02 by an unsupervised clustering method such as K-means. In this case, the number of clusters can be set to any number by the user. For example, in the case of a cell image of a cell sample in which two different types of cell stains are co-cultured, two clusters are set.

[0140] (Determination of representative cells)

[0141] In step S1303, the representative cell determination unit 1230 determines the representative cells in each cell data group belonging to the corresponding cluster based on the classification result in step S1302. As in the second exemplary embodiment, as a method for determining the representative cells in each cluster, the probability density distribution can be estimated based on the cell data groups belonging to each cluster, and the subset and representative cell data can be extracted based on the data occurrence probability.

[0142] In the classification results, in some cell samples, only a small amount of cell data may belong to a specific classification result. For example, the number of cells belonging to a specific cluster may be less than 100. In such a case, it can be expected that the probability density distribution in the second exemplary embodiment is not estimated, and it can be expected that a predetermined region such as regions D01 and D02 based on the execution of probability density distribution estimation is not set, and it can also be expected that subsets corresponding to these regions are not extracted. Alternatively, all the data belonging to the cluster can be regarded as a data group equivalent to the subset according to the second exemplary embodiment, and the representative cell data can be determined based on this data.

[0143] For example, if a cell data group is classified into two clusters A and B, and regions with occurrence probabilities of 95 to 100% and 45 to 55% are set respectively, then the representative cell groups A01 and A02 of cluster A and the representative cell groups B01 and B02 of cluster B are extracted as representative cells.

[0144] As in this exemplary embodiment, in the case of classifying a cell data group into multiple clusters and determining the representative cells constituting each cluster, the cell data near the boundary between different clusters is also important cell data for the user to identify the state of each cell. For example, if the cell image of a cell sample in which two different types of cell stains are co-cultured is classified into two clusters, the data near the boundary between the clusters has similar characteristics between different types of cells. Therefore, this data is very likely to be important for the user to analyze the cell data.

[0145] Therefore, in this exemplary embodiment, the data near the boundary between the clusters is also extracted as representative cell data. Specifically, for the cell data belonging to any cluster, the occurrence probability on the probability density distribution estimated based on the cell data group in another cluster is calculated, and the cell data group with a certain occurrence probability or higher is extracted as a subset. Then, the representative cell data is determined from the subset by a method similar to the second exemplary embodiment. For example, if the cell image is classified into two clusters A and B, and the probability density distributions DA and DB are estimated for clusters A and B respectively, then the occurrence probability of the cell data belonging to cluster A on the probability density distribution DB is calculated. In addition, the data group with an occurrence probability of 50% or higher is extracted as a subset. Four representative cell data are extracted from the subset as a representative cell data group. An identifier (such as representative cell group A03b) is assigned so that the user can distinguish the extracted representative cell group from the representative cell group extracted by the method of the second exemplary embodiment, and the user can distinguish the probability density distribution in any one of the clusters based on which the representative cell group is extracted. In addition, in cluster B, the representative cell group B03a is extracted based on the probability density distribution DA.

[0146] (Display of Information on Representative Cells)

[0147] In step S1304, the display control unit 1240 displays, on the display, information on the representative cells in each cluster extracted in step S1303.

[0148] The representative cell images in each cluster may be displayed in a list format, where Figure 10 the area 1030 shown in is enlarged and each row represents the representative cell image in each cluster. Like Figure 14 the area 1450 shown in, a UI for selecting a cluster to be displayed may be provided to switch the representative cell image to be displayed on the area 1030 based on the selected cluster.

[0149] As described above, according to the present exemplary embodiment, even when the cell sample to be analyzed includes a large number of cell groups having different properties, the main cell data constituting the cell data group can be appropriately determined as representative cells.

[0150] As described above, when it can be estimated in advance that the target cell sample includes cell groups having different properties, the present exemplary embodiment is effective. However, if it is not known whether the target cell sample includes cell groups having different properties, the configuration in which the second exemplary embodiment and the third exemplary embodiment are sequentially performed is also effective. For example, the user determines the representative cells and checks Figure 10 the display result according to the second exemplary embodiment shown in, and then determines whether the cell sample includes a large number of cell groups having different properties. As a result, if the cell sample includes cell groups having different properties, the representative cell determination process including classification into clusters according to the third exemplary embodiment is performed.

[0151] <Program>

[0152] The program according to the present exemplary embodiment is a program for causing a computer to execute the cell image processing method according to the present exemplary embodiment described above.

[0153] Figure 15 is a block diagram showing an example of the hardware configuration of an information processing system configured to execute the program according to the present exemplary embodiment.

[0154] The information processing system includes the functions of a computer. For example, the information processing system may be integrally formed with a desktop computer PC, a laptop computer PC, a tablet PC, a smartphone, or the like.

[0155] To implement the functions of a computer for performing arithmetic processing and storage processing, an information processing system includes a central processing unit (CPU) 1501, a random access memory (RAM) 1502, a read-only memory (ROM) 1503, and an HDD 1504. The information processing system also includes a communication I / F 1505, a display device 1506, and an input device 1507. The CPU 1501, RAM 1502, ROM 1503, HDD 1504, communication I / F 1505, display device 1506, and input device 1507 are interconnected via a bus 1510. The display device 1506 and the input device 1507 may be connected to the bus 1510 via a driving device (not shown) for driving these devices.

[0156] Although Figure 15 the units constituting the information processing system are shown as integrated devices, some of these functions may be configured as external devices. For example, the display device 1506 and the input device 1507 may be external devices separated from a part of the functions constituting a computer including the CPU 1501.

[0157] The CPU 1501 includes the following functions: executing a predetermined operation based on a program stored in the RAM 1502, HDD 1504, etc., and controlling each unit of the information processing system. The RAM 1502 includes a volatile storage medium and provides a temporary storage area for the operation of the CPU 1501. The ROM 1503 includes a non-volatile storage medium and stores required information such as a program for the operation of the information processing system. The HDD 1504 is a storage device including a non-volatile storage medium and stores information such as the number and location of individual separated parts, fluorescence intensity, etc.

[0158] The communication I / F 1505 is a communication interface based on a standard such as or 4G, and is a module for communicating with another device. The display device 1506 is a liquid crystal display, an organic light-emitting diode (OLED) display, etc., and is used to display moving images, still images, characters, etc. The input device 1507 is a button, a touch panel, a keyboard, a pointing device, etc., and is used for a user to operate the information processing system. The display device 1506 and the input device 1507 may be integrally formed as a touch panel.

[0159] Figure 15The hardware configuration shown is merely an example. Devices other than those described above may be added, and some of the devices described above may be omitted. Some of these devices may be replaced by other devices including similar functions. In addition, some of these functions may be provided by another device via a network, and the functions constituting this exemplary embodiment may be implemented by being distributed to multiple devices. For example, the HDD 1504 may be replaced by a solid state drive (SSD) using semiconductor elements such as flash memory, or may be replaced by cloud storage.

[0160] The present disclosure described above includes the following configurations, methods, programs, and storage media.

[0161] (Configuration 1)

[0162] A cell image processing system, comprising: an image acquisition unit configured to acquire a cell image of a sample including a plurality of cells as examinees; a cell region extraction unit configured to extract a plurality of cell regions respectively corresponding to the cells from the cell image; a cell information acquisition unit configured to acquire characteristic information including morphological information about each cell region and pixel information about each cell region; a representative cell determination unit configured to determine a representative cell region from the plurality of extracted cell regions based on at least one type of information constituting the characteristic information; and a display control unit configured to cause a display unit to display image information about the cell region corresponding to the representative cell, position information corresponding to the representative cell region, and characteristic information about the cell region corresponding to the representative cell.

[0163] (Configuration 2)

[0164] The cell image processing system according to Configuration 1, wherein the position information includes at least one of the following: a set of contour coordinates indicating a boundary between cell regions in the cell image, and coordinates indicating a centroid position of a cell region in the cell image.

[0165] (Configuration 3)

[0166] The cell image processing system according to Configuration 1 or 2, wherein the morphological information about each cell region includes at least one of the following: an area of the cell region, a diameter of the cell region, a roundness of the cell region, and a perimeter of a contour of the cell region.

[0167] (Configuration 4)

[0168] The cell image processing system according to any one of Configurations 1 to 3, wherein the pixel information about each cell region includes at least one of the following: an average value of pixel values in the cell region, an integral value of pixel values in the cell region, and a standard deviation of pixel values in the cell region.

[0169] (Configuration 5)

[0170] The cell image processing system according to any one of Configurations 1 to 4, wherein the cell image includes at least one of the following: a fluorescence image, a bright field image, and a phase difference image.

[0171] (Configuration 6)

[0172] The cell image processing system according to any one of Configurations 1 to 5, wherein the representative cell determination unit extracts a plurality of subsets from a data set formed by characteristic information about the plurality of cell regions, and determines representative cell regions from each of the plurality of subsets.

[0173] (Configuration 7)

[0174] The cell image processing system according to Configuration 6, wherein the representative cell determination unit calculates the occurrence probability of data on each cell region based on at least one type of information constituting the characteristic information, and extracts a data set corresponding to each of a plurality of predetermined occurrence probability ranges from the data set formed by the characteristic information about the plurality of cell regions as a subset.

[0175] (Configuration 8)

[0176] The cell image processing system according to Configuration 6, wherein the representative cell determination unit calculates the distance between the data on each cell region and the centroid of the data on all cell regions based on at least one type of information constituting the characteristic information, and extracts a data set corresponding to each of a plurality of predetermined distance ranges from the data set formed by the characteristic information about the plurality of cell regions as a subset.

[0177] (Configuration 9)

[0178] The cell image processing system according to any one of Configurations 6 to 8, wherein the representative cell determination unit divides the data sets constituting the subsets into a plurality of clusters by unsupervised clustering, and determines the cell regions corresponding to the data closest to the centroid position of the data set as the representative cell regions in each of the data sets corresponding to the clusters.

[0179] (Configuration 10)

[0180] The cell image processing system according to any one of Configurations 1 to 9, further comprising a classification unit configured to classify a cell data set constituting a cell image into a plurality of clusters, wherein the representative cell determination unit determines representative cell regions in each of the plurality of clusters.

[0181] (Configuration 11)

[0182] The cell image processing system according to any one of Configurations 1 to 10, wherein, when any one of the image information regarding the cell region corresponding to the representative cell, the position information corresponding to the representative cell region, and the characteristic information regarding the cell region corresponding to the representative cell is selected, the display control unit controls the display unit to display the information other than the selected information together with the selected information synchronously and in a highlighted manner.

[0183] (Configuration 12)

[0184] The cell image processing system according to any one of Configurations 1 to 10, wherein the display control unit controls the display unit to display the image information regarding the cell region corresponding to the representative cell and the position of the representative cell region in the cell image in an associated manner.

[0185] (Method)

[0186] A cell image processing method, comprising: an image acquisition step of acquiring a cell image of a sample including a plurality of cells as an examinee; a cell region extraction step of extracting a plurality of cell regions respectively corresponding to the cells from the cell image; a cell information acquisition step of acquiring characteristic information including morphological information regarding each cell region and pixel information regarding each cell region; a representative cell determination step of determining a representative cell region from the extracted plurality of cell regions based on at least one type of information constituting the characteristic information; and a display control step of controlling the display unit to display the image information regarding the cell region corresponding to the representative cell, the position information corresponding to the representative cell region, and the characteristic information regarding the cell region corresponding to the representative cell.

[0187] (Program)

[0188] A program for causing a computer to execute the cell image processing method according to the method.

[0189] (Storage Medium)

[0190] A storage medium storing a program for causing a computer to execute the cell image processing method according to the method.

[0191] According to an aspect of the present invention, even when the cell image to be analyzed includes a large number of cells, the main cells (representative cells) can be extracted from the large number of cells, and the extracted representative cells can also be displayed together with the information regarding the representative cells.

[0192] Although the present invention has been described with reference to the exemplary embodiments, it is to be understood that the present invention is not limited to the disclosed exemplary embodiments. The scope of the following claims should be given the broadest interpretation to cover all such modifications as well as equivalent structures and functions.

Claims

1. A cell image processing system, comprising: an image acquisition unit configured to acquire a cell image of a sample including a plurality of cells as an object to be examined; a cell region extraction unit, the cell region extraction unit being configured to extract a plurality of cell regions respectively corresponding to cells from the cell image; a cell information acquisition unit configured to acquire characteristic information, wherein the characteristic information includes morphological information about each cell region in the cell regions and pixel information about each cell region in the cell regions; a representative cell determination unit configured to determine a representative cell region from among the extracted plurality of cell regions based on at least one type of information constituting the characteristic information; as well as A display control unit configured to cause a display unit to display image information about a cell region corresponding to a representative cell, position information corresponding to the representative cell, and characteristic information about the cell region corresponding to the representative cell.

2. The cell image processing system according to claim 1, wherein: The position information includes at least one of: a contour coordinate group indicating a boundary between cell regions in the cell image, and coordinates indicating a center of gravity position of a cell region in the cell image.

3. The cell image processing system according to claim 1, wherein: The morphological information about each of the cell regions includes at least one of the following: an area of ​​the cell region, a diameter of the cell region, a circularity of the cell region, and a perimeter of the cell region.

4. The cell image processing system according to claim 1, wherein: The pixel information about each of the cell regions includes at least one of: an average value of pixel values ​​in the cell region, an integrated value of pixel values ​​in the cell region, and a standard deviation of pixel values ​​in the cell region.

5. The cell image processing system according to claim 1, wherein: The cell image includes at least one of the following: a fluorescence image, a bright field image, and a phase contrast image.

6. The cell image processing system according to claim 1, wherein: The representative cell determination unit extracts a plurality of subsets from a data group formed of characteristic information on the plurality of cell regions, and determines a representative cell region from each of the plurality of subsets.

7. The cell image processing system according to claim 6, wherein: The representative cell determination unit calculates the occurrence probability of data on each cell region based on at least one type of information constituting the characteristic information, and extracts a data group corresponding to each predetermined occurrence probability range in a plurality of predetermined occurrence probability ranges as a subset from a data group formed by the characteristic information about the plurality of cell regions.

8. The cell image processing system according to claim 6, wherein: The representative cell determination unit calculates the distance between the data on each cell region and the center of gravity of the data on all cell regions based on at least one type of information constituting the characteristic information, and extracts a data group corresponding to each of a plurality of predetermined distance ranges as a subset from a data group formed by the characteristic information about the plurality of cell regions.

9. The cell image processing system according to any one of claims 6 to 8, wherein: The representative cell determination unit divides the data groups constituting the subset into multiple clusters through unsupervised clustering, and determines the cell region corresponding to the data closest to the centroid position of the data group as the representative cell region in each data group in the data groups corresponding to the cluster.

10. The cell image processing system according to claim 1, further comprising a classification unit configured to classify the cell data group constituting the cell image into a plurality of clusters, in, The representative cell determination unit determines a representative cell region in each of the plurality of clusters.

11. The cell image processing system according to claim 1, wherein: When any one of image information about a cell region corresponding to a representative cell, position information corresponding to a representative cell region, and characteristic information about a cell region corresponding to a representative cell is selected, the display control unit controls the display unit to display information other than the selected information synchronously with the selected information and in a highlighted manner.

12. The cell image processing system according to claim 1, wherein: The display control unit controls the display unit to display image information about a cell region corresponding to a representative cell and a position of the representative cell region in the cell image in a correlated manner.

13. A cell image processing method, comprising: acquiring a cell image of a sample including a plurality of cells as an object of examination; Extracting a plurality of cell regions respectively corresponding to the cells from the cell image; Acquire characteristic information, wherein the characteristic information includes morphological information about each cell region in the cell region and pixel information about each cell region in the cell region; determining a representative cell region from among the plurality of extracted cell regions based on at least one type of information constituting the characteristic information; as well as The display unit is controlled to display image information about a cell region corresponding to the representative cell, position information corresponding to the representative cell, and characteristic information about the cell region corresponding to the representative cell. 14 . A program for causing a computer to execute the cell image processing method according to claim 13 . 15 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute the cell image processing method according to claim 13 .

Images