Systems and methods for detecting and identifying cells

Abstract

The embodiments described herein provide systems and methods for quantifying cells. An exemplary method includes receiving at least one image, improving the contrast of at least one image to generate a contrast image, and performing a fit operation on the contrast image to generate a processed image. The method also includes applying a filter to the processed image to generate a filtered image, identifying cells in the filtered image, and providing an output image including a display of the cells.

Description

Technical Field

[0001] (Related Application) This application claims the benefit of U.S. Provisional Patent Application 63 / 517,052, filed on August 1, 2023, the entire content of which is incorporated herein by reference.

[0002] (Field of the Invention) This disclosure generally relates to microscopic image analysis. More specifically, this disclosure relates to detecting and identifying cells within microscopic images.

Background Art

[0003] Cell viability counting has conventionally been a manual and time-consuming process. Advancements in the field of image processing have enabled imaging systems to automate some of these manual tasks or otherwise reduce the amount of time and manual labor associated with determining the cell concentration in a sample. However, existing automated systems and methods for analyzing cell viability within a sample have many drawbacks. For example, many cell viability systems require the use of dyes, labels, or other compounds to determine the viability of cells within a sample. The use of many of these compounds often requires special, expensive, and / or bulky equipment to retrieve the results readout.

Summary of the Invention

[0004] The examples described herein receive a microscopic image of cells as input and output a list of cell locations. Images of cells can be associated with Raman measurements, fluorescence measurements, and the like. To convert an image of cells into a quantitative description of a list of cells, exemplary systems and methods include performing operations such as attributive morphology, exponential histogram fitting for image automatic thresholding, connected component identification, watershed segmentation, and combinations thereof.

[0005] One example provides a method for identifying cells. This method includes receiving at least one image, improving the contrast of at least one image to generate a contrast image, and performing a fit operation on the contrast image to generate a processed image. This method also includes applying a filter to the processed image to generate a filtered image, identifying cells in the filtered image, and providing an output image including a display of the cells.

[0006] Another example provides one or more hardware storage devices that store instructions executable by one or more processing devices of an imaging system, the instructions including receiving at least one image, improving the contrast of at least one image to generate a contrast image, and performing a fit operation on the contrast image to generate a processed image. The instructions also include applying a filter to the processed image to generate a filtered image, identifying cells in the filtered image, and providing an output image including a display of the cells.

[0007] Another example provides an imaging device comprising a stage assembly operable to receive a cell counting slide, and a controller including an electronic processor and memory. The controller is configured to capture the cell counting slide to generate at least one image, to improve the contrast of at least one image to generate a contrast image, and to perform a fit operation on the contrast image to generate a processed image. The controller is configured to apply a filter to the processed image to generate a filtered image, to identify cells in the filtered image, and to provide an output image including a display of the cells. [Brief explanation of the drawing]

[0008] The features and advantages of this technology will become clearer from the following detailed description of exemplary embodiments, in conjunction with the attached drawings. [Figure 1] This is a perspective view of an imaging system configured to perform one or more of the methods disclosed herein, according to one or more embodiments of the present disclosure. [Figure 2] This is a flowchart illustrating an exemplary method performed by the imaging system of Figure 1, according to one or more embodiments of the present disclosure. [Figure 3] This is a block diagram of various exemplary components within the imaging system of Figure 1, according to one or more embodiments of the present disclosure. [Figure 4] This is a flowchart of a cell viability counting method performed by the imaging system shown in Figure 1, according to one or more embodiments of the present disclosure. [Figure 5] Figure 4 is a flowchart of the cell viability counting method according to one or more embodiments of the present disclosure. [Figure 6A] The present disclosure provides exemplary input images captured by the imaging system of Figure 1 according to one or more embodiments thereof. [Figure 6B] The present disclosure provides exemplary input images captured by the imaging system of Figure 1 according to one or more embodiments thereof. [Figure 7A] One or more embodiments of this disclosure provide an exemplary image with increased contrast of the input image in Figure 6A. [Figure 7B] One or more embodiments of this disclosure provide an exemplary image with increased contrast of the input image in Figure 6A. [Figure 8A] This is a histogram of the image with increased contrast shown in Figure 7A, according to one or more embodiments of the present disclosure. [Figure 8B] This is a histogram of the image with increased contrast shown in Figure 7A, according to one or more embodiments of the present disclosure. [Figure 8C] This is a histogram of the image with increased contrast shown in Figure 7A, according to one or more embodiments of the present disclosure. [Figure 8D] This is a histogram of the image with increased contrast shown in Figure 7A, according to one or more embodiments of the present disclosure. [Figure 9A]One or more embodiments of the present disclosure provide an exemplary auto-threshold image of the contrast-enhanced image of Figure 7A, wherein the threshold is automatically defined by a histogram fit applied to the contrast-enhanced image of Figure 7A and has a highlighted region of interest. [Figure 9B] One or more embodiments of the present disclosure provide an exemplary auto-threshold image of the contrast-enhanced image of Figure 7A, wherein the threshold is automatically defined by a histogram fit applied to the contrast-enhanced image of Figure 7A and has a highlighted region of interest. [Figure 10A] The present disclosure provides an exemplary filtered image of the auto-thresholding image of Figure 9A according to one or more embodiments of this disclosure. [Figure 10B] The present disclosure provides an exemplary filtered image of the auto-thresholding image of Figure 9A according to one or more embodiments of this disclosure. [Figure 11A] One or more embodiments of this disclosure provide images having identified and separated cell candidates in the filtered image of Figure 10A. [Figure 11B] One or more embodiments of this disclosure provide images having identified and separated cell candidates in the filtered image of Figure 10A. [Figure 12A] One or more embodiments of this disclosure provide an output image containing an acceptable cell candidate in the image in Figure 11A. [Figure 12B] One or more embodiments of this disclosure provide an output image containing an acceptable cell candidate in the image in Figure 11A.

[0009] While this technology is open to various modifications and alternative forms, specific embodiments are shown in the drawings as examples and are described in detail herein. However, it should be understood that the present invention is not limited to the specific forms disclosed. Rather, the present invention encompasses all modifications, equivalents, and alternative forms that fall within the spirit and scope of the invention as defined by the appended claims. [Modes for carrying out the invention]

[0010] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. In case of conflict, the present document, including definitions, will control. Exemplary methods and systems are described below, but methods and systems similar or equivalent to those described herein can be used in the practice or testing of the present disclosure. All publications, patent applications, patents, and other references mentioned herein are incorporated by reference in their entirety. The systems, methods, and examples disclosed herein are illustrative only and not intended to be limiting.

[0011] As used herein, the terms "comprises," "comprising," "has," "having," "can," "including," and variations thereof are intended to be open transitional phrases, terms, or words that do not preclude the possibility of additional acts or structures. The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

[0012] As used herein, the term "or" is meant to be inclusive rather than exclusive. That is, unless otherwise specified or clear from the context, "X uses A or B" is intended to mean any natural inclusive permutation. That is, "X uses A or B" is satisfied under any of the preceding examples where X uses A, X uses B, or X uses both A and B. Further, the articles "a" and "an" as used in this specification and the appended drawings are generally to be construed to mean "one or more" unless otherwise specified or clear from the context that they are intended to refer to the singular form.

[0013] In addition, unless otherwise indicated, numbers expressing quantities, components, distances, or other measurements used in the specification and claims are to be understood as being modified by the term "about." As used herein, the terms "about," "substantially," or their equivalents still represent an amount or state close to a particular recited amount or condition that performs the desired function or achieves the desired result. For example, the terms "substantially," "about," and "essentially" may refer to an amount or state that deviates from the specifically recited amount or condition by less than 10%, or less than 5%, or less than 1%, or less than 0.1%, or less than 0.01%.

[0014] The present disclosure will be described with reference to the drawings, in which like reference numerals are used throughout to refer to like elements. In the following description, for purposes of explanation, many specific details are set forth in order to facilitate an understanding of the present disclosure. It will be apparent, however, that the systems and methods of the present disclosure may be practiced without one or more of these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate the description of the systems and methods of the present disclosure. There is no specific requirement that a system, method, or technology related to microscopic image analysis include all of the details characterized herein in order to obtain any benefits of the present disclosure. Thus, the specific examples characterized herein are illustrative applications of the technology being described, and alternative forms are possible.

[0015] Cell viability counting has conventionally been a manual and time-consuming process. Advances in the field of image processing have enabled imaging systems to automate some of these manual tasks or otherwise reduce the amount of time and manual labor associated with determining the cell concentration in a sample, particularly with regard to ascertaining the proportional number of live / dead cells in a given sample (or viability counting).

[0016] However, existing automated systems and methods for analyzing cell viability in samples have many drawbacks. For example, many cell viability systems require the use of dyes, labels, or other compounds to determine the viability of cells in a sample. The use of many of these compounds often requires specialized, expensive, and / or bulky equipment to retrieve the results. Consequently, the equipment is unlikely to be readily available and / or positioned within a laboratory space for easy access. Furthermore, systems and methods that utilize machine learning techniques may require large training datasets, leading to high computational costs.

[0017] Therefore, to address these and other issues, the systems and methods disclosed herein provide an accurate and automatic conversion of cell images to a quantitative description of a list of cells. In this way, cell viability counts are provided automatically and without time-consuming manual processes.

[0018] Figure 1 is a perspective view of an imaging system 100 configured to perform one or more of the methods disclosed herein. The imaging system 100 in Figure 1 is operable to facilitate a method related to the automated cell viability counting flowchart 200 disclosed by the exemplary flowchart in Figure 2. As shown, the imaging system 100 includes a housing 102 that encapsulates and protects a microscope and computing system used for cell viability counting. The housing 102 includes a slide port / stage assembly 106 operable to receive a cell counting slide into the imaging system (step 202). Upon receipt, the imaging system 100 determines a target focal position for imaging cells on the cell counting slide (step 204) and uses the target focal position to perform automated cell viability counting (step 206). The cell viability count representation is displayed in the imaging system 100, for example, using a display 104 (step 208). This representation and / or other data associated with the automated cell viability count may, in some embodiments, be removed from the imaging system 100 through user interaction with a communication module 108 which may include a USB port or other data exchange port as known in the art, and / or stored on a separate device.

[0019] In view of this disclosure, it will be understood that the principles described herein can be implemented using any suitable imaging system and / or any suitable imaging modality. Specific examples of imaging systems and imaging modalities discussed herein are provided as examples and as means of illustrating the features of the disclosed embodiments. Thus, the embodiments disclosed herein are not limited to any particular microscope system or microscopy application and may be implemented in a variety of contexts, such as bright-field imaging, fluorescence microscopy, flow cytometry, and confocal imaging (e.g., 3D confocal imaging, or any type of 3D imaging). For example, the principles discussed herein can be implemented using a flow cytometry system to provide or improve cell counting capabilities. As another example, cell count and / or viability data obtained according to the art of this disclosure may be used to complement fluorescence data to improve accuracy in distinguishing between different cells.

[0020] Furthermore, in consideration of this disclosure, it will be understood that any number of principles described herein can be implemented in various fields. For example, a system may implement the cell counting techniques discussed herein without necessarily implementing techniques such as cell viability determination.

[0021] Figure 3 is a schematic diagram of various exemplary components within the imaging system 100 of Figure 1 according to one or more embodiments of the present disclosure. As shown in Figure 3, the imaging system 100 may include a computer system 110 and a microscope system 120 contained therein. Figure 3 conceptually represents the computer system 110 and the microscope system 120 arranged within the housing 102 of the imaging system 100. However, in consideration of the present disclosure, it should be understood that any part of the computer system 110 or the microscope system 120 may be located at least partially outside the housing 102 within the scope of the disclosed embodiments.

[0022] Figure 3 shows that the computer system 110 of the imaging system 100 can include various components such as an electronic processor 112, a hardware storage device 114, a controller 116, and a communication module 108.

[0023] The electronic processor 112 may comprise one or more sets of electronic circuits, including any number of logic units, registers, and / or control units, to facilitate the execution of computer-readable instructions (e.g., instructions that form a computer program). Such computer-readable instructions may be stored in a hardware storage device 114, which may include physical system memory and may be volatile, non-volatile, or any combination thereof.

[0024] The controller 116 may include any suitable software components (e.g., a set of computer executable instructions) and / or hardware components (e.g., application-specific integrated circuits or other dedicated hardware components) that are capable of operating to control one or more physical devices of the imaging system 100, such as a part of the microscope system 120 (e.g., a positioning mechanism 128).

[0025] The communication module 108 may include any combination of software or hardware components that can operate to facilitate communication between on-system components / devices and / or with off-system components / devices. For example, the communication module 108 may include ports, buses, or other physical coupling devices for communicating with other devices (e.g., USB ports, SD card readers, and / or other devices). In addition, or alternatively, the communication module 108 may include, as a non-limiting example, a system that can operate to wirelessly communicate with external systems and / or devices through any suitable communication channel such as Bluetooth, ultra-wideband, WLAN, or infrared communication.

[0026] As shown in Figure 3, the imaging system 100 includes a microscope system 120 having an image sensor 122, an illumination source 124, an optical train 126, a slide port / stage assembly 106 for receiving a sample slide, and a positioning mechanism 128.

[0027] The image sensor 122 is positioned within the optical path of the microscope system and configured to capture an image of a sample, which will be used in the disclosed method to identify a target focal position and subsequently perform automated cell viability counting. As used herein, the terms “image sensor” or “camera” refer to any applicable image sensor that fits the apparatus, systems, and methods described herein, including but not limited to the aforementioned combinations such as charge-coupled devices, complementary metal-oxide-semiconductor devices, N-type metal-oxide-semiconductor devices, Quanta image sensors, and scientific complementary metal-oxide-semiconductor devices.

[0028] The optical train 126 may include one or more optical elements configured to facilitate the visibility of the cell counting slide by directing light from the illumination source 124 to the received cell counting slide. The optical train 126 may also be configured to direct light scattered, reflected, and / or emitted by the specimen in the cell counting slide towards the image sensor 122. The illumination source 124 may be configured to emit various types of light, such as white light or light in one or more specific wavelength bands. For example, the illumination source 124 may include an optical cube that can be installed and / or swapped within a housing for any desired set of illumination wavelengths.

[0029] The positioning mechanism 128 may include an x-axis motor, a y-axis motor, and a z-axis motor, which are operable to adjust the components of the optical train 126 and / or image sensor 122 as appropriate.

[0030] Figure 3 further shows that in some cases the imaging system 100 includes a display 104. Figure 3 shows that the display 104 can communicate directly or indirectly with various other components of the imaging system 100, such as the computer system 110 or its microscope system 120 (for example, as indicated by the triple-headed arrow in Figure 3). For example, the imaging system may use components of the microscope system 120 to capture images, the captured images may be processed and / or stored using components of the computer system 110 (e.g., an electronic processor 112, a hardware storage device 114, etc.), and the processed and / or stored images may be displayed on the display 104 for observation by one or more users.

[0031] As described herein, the components of the imaging system 100 can facilitate cell viability counting on a sample contained on a cell counting slide. In some examples, the representation of the cell viability counting results can be displayed on the display 104 of the imaging system 100 within a short time after initiating the cell viability counting process for the cell counting slide inserted into the imaging system 100 (for example, within a period of about 20 seconds or less, or about 10 seconds or less).

[0032] In light of this disclosure, it should be understood that the imaging system may include additional or alternative components beyond those illustrated and described with reference to Figure 3, and such components may be organized and / or distributed in various ways.

[0033] Figure 4 is a flowchart of an exemplary method 400 for performing automated cell viability counting. Method 400 can be performed, for example, by a controller 116, an electronic processor 112, or a combination thereof.

[0034] Method 400 includes receiving at least one image (e.g., an input image) (step 402). For example, an image sensor 122 captures an image of a sample. In another example, the image is acquired from, for example, a server or memory device. Thus, the image may be a previously captured image.

[0035] Method 400 includes, for example, improving the contrast of at least one image to generate a contrast image by performing region attribute operations (e.g., region attribute release, region attribute closure), grayscale operations, etc. (step 404).

[0036] Method 400 includes performing a fitting operation on a contrast image to produce a processed image (step 406). For example, an exponential histogram fitting operation may be performed on a contrast image (e.g., a contrast-improved image), as will be described in more detail below with respect to Figures 8A to 8D. Other fitting operations, such as a curve fitting operation, may be performed instead. In another example, a Gaussian function may be implemented for the histogram fitting operation, as defined by equation (1).

[0037]

number

[0038] Method 400 includes applying a filter to the processed image to generate a filtered image (step 408). For example, one or more binary open operations followed by binary closed operations using a 2x2 pixel square kernel, a binary mask, a median filter, a low-pass filter, etc., can be applied to the third image to remove noise, trim vines, and fill in small holes.

[0039] Method 400 includes identifying cells in the filtered image (step 410). For example, a binding component operation (e.g., an 8-binding component operation) may be performed to identify cells in the filtered image, as will be described in more detail below.

[0040] Method 400 includes providing an output image including a representation of cells (step 412). For example, the representation of cells in the input image is displayed on the imaging system 100 using, for example, a display 104. In this way, cell viability counting is performed.

[0041] Figure 5 is a flowchart of an exemplary implementation of method 400 for performing automated cell viability counting. Method 500 can be performed, for example, by a controller 116, an electronic processor 112, or a combination thereof.

[0042] Method 500 includes receiving an input image (step 502). For example, an image sensor 122 captures an image of a sample. Figure 6A shows an exemplary input image 600 described with respect to Method 500. Figure 6B shows a highlighted portion 650 of the input image 600 in more detail. The input image 600 may be received by a controller 116.

[0043] Method 500 includes performing a region attribute grayscale release operation on the input image 600 to generate a second image (step 504). In some implementations, the region attribute release is performed with a radius of 7.4 μm to 7.8 μm. In some implementations, the region attribute release is performed with a radius of 7.6 μm.

[0044] Method 500 includes performing a region attribute grayscale closure operation on a second image to generate a third image (step 506). In some implementations, the region attribute closure is performed using a region between 4 pixels and 6 pixels. In some implementations, the region attribute closure is performed using a region of 5 pixels.

[0045] Steps 504, 506, or a combination thereof, increase the contrast of the input image 600. For example, Figure 7A shows an exemplary third image 700. Figure 7B shows a highlighted portion 750 of the third image 700 in more detail. The third image 700 has increased contrast between the background and foreground compared to the input image 600.

[0046] Returning to Figure 5, Method 500 includes performing an exponential histogram fit operation on the third image 700 to generate a fourth image (step 508). For example, Figures 8A to 8D show histograms representing the third image 700 during the histogram fit operation. The histogram shows the relationship between pixel count and pixel intensity. Figure 8A shows the histogram of the third image 700 counting the number of pixels at each of several pixel intensity values ​​(grayscale). Figure 8B shows the histogram of Figure 8A normalized by the total number of pixels (i.e., dividing the number of pixels at each intensity value by the total number of pixels). Figure 8C shows the normalized histogram of Figure 8B with identified bin values ​​greater than the trimming rate. Figure 8D shows the histogram of Figure 8C normalized by the maximum bin value, with a superimposed exponential function. The exponential function is,

[0047]

number

[0048] In some implementations, the logarithmic trimming rate is a value between -1 and -2. In the examples in Figures 8A to 8D, the logarithmic trimming rate is -1.3. Therefore, to identify the trimming rate, Logarithmic trimming rate = -1.3

[0049]

number

[0050] The trimming rate restricts the bins used for analysis to the top bins of a selected number in the histogram (i.e., the intensity values ​​with the highest counts). For example, in the example above, a trimming rate of 0.05 indicates that 5% of the pixels in the lowest bin should be trimmed. Therefore, to apply the trimming rate, the normalized pixel counts in each bin (each intensity value), starting from the smallest bin (i.e., the intensity value with the lowest normalized count), are added up until the sum exceeds the trimming rate. As shown in the example bins in Figure 8C, the normalized pixel counts starting from bin 7 are added up. The sum of bins 7, 6, and 5 is less than the trimming rate (0.05), but the sum of bins 7, 8, 5, and 4 (0.09) is greater than the trimming rate (0.05). Therefore, in this example, bins 1, 2, 3, and 4 are retained, while bins 7, 6, and 5 are trimmed (ignored). As shown in Figure 8D, the retained bins are normalized by dividing each retained bin by the maximum value among the retained bins before performing the exponential histogram fitting operation. In some implementations, the exponential histogram fitting operation has a logarithmic false alarm rate between -1 and -7. In the examples in Figures 8A to 8D, the logarithmic false alarm rate is -4.2. The logarithmic false alarm rate is used to determine the global threshold. Logarithmic false alarm rate = -4.2 False alarm rate = 10 対数誤警報レート Global threshold = -tau*ln(false alarm rate) In the examples in Figures 8A to 8D, tau = 0.654612, and the global threshold is 6.3307.

[0051] Automatic thresholding using histogram fitting offers overall robustness compared to other methods. The histogram fit is unique for each input image, and therefore, a global threshold is fitted for each input image.

[0052] Returning to Figure 5, Method 500 includes generating a fifth image by applying a global threshold to the fourth image (step 510). For example, the global threshold may be applied to apply a binary mask to highlight a region of interest in the fourth image. In other words, all pixels with values ​​exceeding the threshold are set to one value, and all other pixels are set to different values. Figure 9A shows an exemplary fifth image 900 containing the highlighted region of interest. Figure 9B shows a more detailed view of the highlighted portion 950 of the fifth image 900.

[0053] As shown in Figure 5, Method 500 includes applying a small binary morphological operation to the fifth image 900 to generate a sixth image (step 512). For example, a small binary morphological operation may be performed to remove background noise in the fifth image 900, as well as to trim the vines around the region of interest and fill in small holes in the fifth image 900. Figure 10A shows an exemplary sixth image 1000 after a small binary morphological operation. Figure 10B shows a highlighted portion 1050 of the sixth image 1000 in more detail. An example of a binary morphological operation includes a morphological open and a subsequent morphological close, using a 2x2 pixel square kernel for both the open and close operators.

[0054] Small binary morphological operations are useful for removing foreground pores. Foreground pores may appear in the image based on the appearance of cells from different focal positions (e.g., different z-height focal positions from which the image is captured by the image sensor 122). Therefore, in some cases, foreground pore filling operations may be performed to expand the combined pixels to fill the foreground pores. In some examples, after performing a morphological operation on the image (e.g., small binary morphological operation), the imaging system 100 may define the combined components in the image in preparation for additional processing.

[0055] Method 500 includes applying a watershed action to a sixth image 1000 to generate a seventh image and candidate segment cells (step 514). For example, two or more cells in the sixth image 1000 may be in contact. The watershed action may be implemented to identify and logically separate the contacting cells.

[0056] Method 500 includes applying an eight-binding component operation to the seventh image to identify candidate cells (step 516). For example, candidate cells in the seventh image can be labeled by identifying binding components in the seventh image. In some implementations, a four-binding component operation is performed. Figure 11A shows an exemplary seventh image 1100 containing the identified candidate cells. Figure 11B shows a highlighted portion 1150 of the seventh image 1100 in more detail.

[0057] As used herein, "connectivity" in "connecting element" refers to which pixels are considered neighbors of a pixel of interest. A connecting element is a set of pixels with a single value, for example, a value representing black, and a path can be formed from any pixel in the set to any other pixel in the set without leaving the set, for example by traversing only black pixels. Generally speaking, a connecting element can be either a "4-connected" or an "8-connected." In the case of a 4-connected element, there are four possible directions, as paths can only move horizontally or vertically. In the case of an 8-connected element, paths between pixels may also move diagonally.

[0058] Method 500 includes determining acceptable cell candidates based on the contrast and length of the cell candidates (step 518). For example, the contrast and length of the cell candidates can be compared to a contrast threshold and a length threshold, respectively. The contrast threshold may be, for example, between 15 bytes and 25 bytes. The length threshold may be, for example, a short-axis length of 1.5 μm to 3.0 μm. Figure 12A shows an eighth image 1200 containing acceptable cell candidates. Figure 12B shows a highlighted portion 1250 of the eighth image 1200 in more detail. In the example of Figure 12A, the contrast threshold is 20 bytes and the length threshold is 2.3 μm.

[0059] Method 500 includes outputting an image containing the accepted cell candidates (e.g., an eighth image 1200) (step 520). For example, the display or representation of cells in the input image is displayed in the imaging system 100 (e.g., by the controller 116) using, for example, a display 104. Cell viability counting is performed in this manner. Cells may be identified by being highlighted, circled, or represented by an ellipse. The ellipse may be fitted to each connected component defined in the eighth image 1200. In some examples, the controller 116 provides data on the display 1104 regarding the accepted cell candidates, such as the ellipse center coordinates (in pixels), the ellipse semi-major axis (in pixels), the ellipse semi-minor axis (in pixels), the ellipse angle (in degrees), cell viability (e.g., whether the cell is dead or alive), cell brightness (e.g., the average grayscale intensity within the ellipse), and cell roundness (e.g., in the range of 0 to 1, where 1 is a perfect circle). It should be understood that identified cells and associated cell count information can be output in various formats and forms. For example, information about identified cells may be presented graphically, in text, or in a combination thereof (as schematically shown in Figures 12A-12B, for example).

[0060] As described above in the detailed description of the invention, the accompanying drawings forming part of this specification are referenced, similar figures throughout indicate similar parts, and illustrative examples of possible implementations are shown. It should be understood that other implementations may be used and structural or logical modifications may be made without departing from the scope of this disclosure. Therefore, the detailed description of the invention described above should not be construed as restrictive.

[0061] Various operations may be described sequentially as multiple separate actions or operations in a manner that is most helpful in understanding the subject matter disclosed herein. However, the order of the descriptions should be interpreted as suggesting that these operations are necessarily order-dependent. Specifically, these operations may not be performed in the order presented. The operations described may be performed in a different order than in the described implementation. Various additional operations may be performed, and / or the operations described may be omitted in additional implementations.

Claims

1. A method for identifying cells implemented via one or more electronic processors, wherein the method is Receiving at least one image, To generate a contrast image, improve the contrast of at least one of the images, The process involves performing a fitting operation on the aforementioned contrast image to generate a processed image, Applying a filter to the processed image to generate a filtered image, Identifying cells within the filtered image, A method comprising providing an output image including the display of the aforementioned cells.

2. To improve the contrast of the input image, The process involves performing a region attribute release operation on the aforementioned input image to generate an intermediate image, The method according to claim 1, comprising performing a region attribute closure operation on the intermediate image to generate the contrast image.

3. The method according to claim 2, wherein the region attribute release operation is performed with a radius of 7.4 μm to 7.8 μm.

4. The method according to claim 2, wherein the region attribute closing operation is performed in the region between the 4th pixel and the 6th pixel.

5. Performing the fitting operation on the contrast image means that The process involves generating a histogram representation of the input image based on the intensity values ​​of the pixels in the input image, The method according to claim 1, comprising normalizing the histogram representation using the total number of pixels in the input image to generate a normalized histogram representation.

6. Performing the fitting operation on the contrast image means that To generate a trimmed histogram representation, at least one bin included in the normalized histogram representation is trimmed based on the trimming rate. Determining an exponential function that fits the trimmed histogram representation, Determining a global threshold based on the aforementioned exponential function, The method according to claim 5, further comprising applying the global threshold to the contrast image to generate the processed image.

7. The method according to claim 1, wherein applying the filter to the processed image to generate the filtered image includes performing a small binary morphological operation on the processed image.

8. The method according to claim 1, wherein identifying cells in the filtered image comprises applying a watershed action to the filtered image.

9. The method according to claim 1, wherein identifying cells in the filtered image comprises performing an 8-component operation on the filtered image.

10. A computer system configured to identify cells, comprising: one or more electronic processors; and one or more hardware storage devices storing computer executable instructions that, when executed by the one or more electronic processors, constitute the computer system to perform the method according to any one of claims 1 to 9.

11. One or more hardware storage devices that store instructions that can be executed by one or more processing devices of an imaging system, wherein the instructions are: Receiving at least one image, To generate a contrast image, improve the contrast of at least one of the images, The process involves performing a fitting operation on the aforementioned contrast image to generate a processed image, Applying a filter to the processed image to generate a filtered image, Identifying cells within the filtered image, One or more hardware storage devices, including providing an output image that includes the display of the aforementioned cells.

12. An imaging device, A stage assembly capable of receiving cell counting slides, It is an electronic processor, The cell counting slide is captured and at least one image is generated. To generate a contrast image, improve the contrast of at least one of the images, The process involves performing a fitting operation on the aforementioned contrast image to generate a processed image, Applying a filter to the processed image to generate a filtered image, Identifying cells within the filtered image, An imaging device comprising an electronic processor configured to provide an output image including the display of the aforementioned cells.

13. The aforementioned electronic processor, The process involves performing a region attribute release operation on at least one of the aforementioned images to generate an intermediate image, The imaging apparatus according to claim 12, configured to improve the contrast of at least one image by performing a region attribute closure operation on the intermediate image to generate the contrast image.

14. The imaging apparatus according to claim 13, wherein the region attribute release operation is performed with a radius of 7.4 μm to 7.8 μm.

15. The imaging apparatus according to any one of claims 13 and 14, wherein the region attribute closing operation is performed in a region between 4 pixels and 6 pixels.

16. The aforementioned electronic processor, Based on the intensity values ​​of pixels in the at least one image, a histogram representation of the at least one image is generated. The imaging apparatus according to any one of claims 12 and 13, configured to perform the fitting operation on the contrast image by normalizing the histogram representation using the total number of pixels in at least one image to generate a normalized histogram representation.

17. The aforementioned electronic processor, To generate a trimmed histogram representation, at least one bin included in the normalized histogram representation is trimmed based on the trimming rate. Determining an exponential function that fits the trimmed histogram representation, Determining a global threshold based on the aforementioned exponential function, The imaging apparatus according to claim 16, further configured to perform the fitting operation on the contrast image by applying the global threshold to the contrast image to generate the processed image.

18. The imaging apparatus according to any one of claims 12 and 13, wherein the electronic processor is configured to apply the filter to the processed image by performing a small binary morphological operation on the processed image to generate the filtered image.

19. The imaging apparatus according to any one of claims 12 and 13, wherein the electronic processor is configured to identify cells in the filtered image by applying a watershed operation to the filtered image.

20. The imaging apparatus according to any one of claims 12 and 13, wherein the electronic processor is configured to identify cells in the filtered image by performing an eight-component operation on the filtered image.

Images