Image analysis method and image analysis system for gram-stained slide

Abstract

According to one embodiment of the present invention, when determining whether the bacteria are Gram-positive through Gram staining, analysis of a Gram-stained slide image enables automation of test results, including Gram-positivity determination. To this end, in particular, one embodiment of the present invention provides an image analysis method for a Gram-stained slide, the method comprising: a Gram staining step (S110) of Gram-staining a specimen slide; a low-magnification imaging step (S120) of imaging an ideal zone of the stained specimen slide by using a low-magnification imaging unit, thereby obtaining a low-magnification image; an object detecting step (S130) of detecting an object of interest from the obtained low-magnification image and identifying the location of the object of interest; a high-magnification imaging step (S140) of imaging, at the identified location of the object of interest, an object region including the detected object of interest by using a high-magnification imaging unit, thereby obtaining a high-magnification image; a first classification step (S150) of classifying, by a bacteria classification unit, bacteria among the objects to be observed as Gram-positive bacteria and Gram-negative bacteria on the basis of the high-magnification image; and a second classification step (S160) of classifying, by the bacteria classification unit, bacteria among the detected objects to be observed as at least one of cocci, bacilli, and spirilla.

Description

Image analysis method and image analysis system for Gram-stained slides

[0001] The present invention relates to an image analysis method and an image analysis system for a Gram stained slide.

[0002] The Gram stain is a bacterial staining method. It is a simple staining method and serves as an important indicator for identifying the causative agent and selecting antibiotics, making it an important staining method used on all bacteria. More specifically, the Gram stain is a staining method used in microbiology to classify bacteria into two major categories: Gram-positive and Gram-negative. Here, Gram-positive bacteria are bacteria whose cell walls stain purple when stained, while Gram-negative bacteria are bacteria whose cell walls stain red when stained.

[0003] Meanwhile, smear analysis can be performed on specimens that can be Gram stained, such as blood, sputum, throat swabs, feces, urine, cerebrospinal fluid and various puncture fluids, wound and soft tissue, and genital specimens.

[0004] In order to diagnose the infection of a patient or to examine bacteria in food, the aforementioned Gram staining was performed on a smeared slide specimen, or separately or in parallel with this, a method of preprocessing the specimen, inoculating it onto a medium, culturing it in an incubator, and then visually examining the medium was performed.

[0005] However, when there are multiple samples to be tested for positivity, assessing each one individually with limited resources can be time-consuming. Therefore, the need for automation in determining bacterial positivity using Gram staining is emerging.

[0006] The present invention was derived based on the above-mentioned necessity, and the purpose of the present invention is to provide a method and system for analyzing a Gram stain slide image that can automate the test results, such as whether or not a gram stain is positive, through image analysis of a Gram stain slide image in determining whether or not a gram stain is positive.

[0007] The purpose of the present invention as described above is a method for analyzing an image of a smeared slide image, comprising: a Gram staining step (S110) of staining a specimen slide with Gram; a low-magnification imaging step (S120) of capturing an ideal zone of the stained specimen slide with a low-magnification imaging unit to obtain a low-magnification image; an object detection step (S130) of detecting an object of interest in the acquired low-magnification image and searching for a location of the object of interest; a high-magnification imaging step (S140) of capturing an object area including the object of interest detected at the location of the searched object of interest with a high-magnification imaging unit to obtain a high-magnification image; a first discrimination step (S150) of distinguishing bacteria among the observation target objects into Gram-positive bacteria and Gram-negative bacteria based on the high-magnification image by a bacteria discrimination unit; And it can be achieved by providing a method for analyzing an image of a Gram stained slide, including a second differentiation step (S160) of differentiating bacteria among the observation target objects from which a bacterial differentiation section is detected as at least one of cocci, bacilli, and spiral bacteria.

[0008] The image analysis method of a Gram stain slide may further include, after step S160, an analysis result output step (S170) in which the analysis result output unit (240) outputs a cell grade based on a low-magnification image acquired for cells and outputs a bacteria grade based on a high-magnification image acquired for bacteria.

[0009] Here, the cell grade may be determined based on the number of cells detected within the acquired low-magnification image, and the bacteria grade may be determined based on the number of bacteria detected within the acquired high-magnification image.

[0010] Meanwhile, the image analysis method of a Gram-stained slide may further include a step (S115) of searching for an ideal zone based on the smear location and smear shape of the Gram-stained specimen slide between the Gram-staining step (S110) and the low-magnification imaging step (S120). Here, the ideal zone is an area where valid cells / bacteria (WBC, EP Cell, Yeast, fungi) exist.

[0011] And step S150 may be a step in which the bacterial discrimination unit discriminates between gram-positive bacteria and gram-negative bacteria based on the color detected for the bacteria in the high-magnification image.

[0012] Additionally, step S160 may be a step in which the bacterial discrimination unit discriminates bacteria in a high-magnification image as at least one of cocci, bacilli, and spiral bacteria in response to the shape detected.

[0013] Meanwhile, the purpose of the present invention can be achieved by providing an image analysis system of a Gram-stained slide, which comprises, as another category, a low-magnification imaging unit (210) for capturing an ideal zone of a Gram-stained specimen slide with a low-magnification imaging unit to obtain a low-magnification image; an object detection unit (215) for detecting an object of interest in the obtained low-magnification image and searching for the location of the object of interest; a high-magnification imaging unit (220) for obtaining a high-magnification image for an object region including the object of interest detected at the location of the searched object of interest; and a bacteria discrimination unit (230) for performing a first discrimination of distinguishing bacteria among the observation target objects as Gram-positive bacteria and Gram-negative bacteria based on the high-magnification image, and performing a second discrimination of distinguishing the detected bacteria among the observation target objects as at least one of cocci, bacilli, and spirilla.

[0014] According to one embodiment of the present invention as described above, in determining whether bacteria are positive through Gram staining, there is an effect of being able to automate the test results, such as whether positive or not, through image analysis of a Gram stain slide image.

[0015] In addition, the method and system of the present invention can be used to save time through automation and improve the convenience of inspection work.

[0016] Figure 1 is a configuration diagram of one embodiment of the Gram stain slide image analysis system of the present invention.

[0017] Figure 2 is a flowchart sequentially showing one embodiment of the method for analyzing a Gram stain slide image according to the present invention.

[0018] FIG. 3 is a drawing showing an image (a) of an ideal zone selected using an embodiment system of the present invention, a low-magnification image (b) of the ideal zone acquired by a low-magnification imaging unit, and an image (c) of a portion thereof enlarged.

[0019] Figure 4 is a drawing showing an image (a) showing the location of bacteria and cells and yeast searched using an embodiment system of the present invention and an enlarged image (b) of a portion thereof.

[0020] FIG. 5 is a drawing showing a high-magnification image (a) of a gram-positive bacterium obtained by a high-magnification imaging unit using an embodiment system of the present invention, and a high-magnification image (b) of a gram-negative bacterium obtained by a high-magnification imaging unit.

[0021] FIG. 6 is a drawing showing an example of a result report output by an analysis result output unit using an embodiment system of the present invention.

[0022] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings and the contents described therein. However, the present invention is not limited or restricted by these embodiments. Various modifications may be made to the embodiments described below. The embodiments described below are not intended to limit the embodiments, and should be understood to include all modifications, equivalents, and alternatives thereof.

[0023] Meanwhile, when describing the present invention, if a detailed description of a related known function or configuration is judged to unnecessarily obscure the gist of the present invention, such detailed description will be omitted. Furthermore, the terminology used in this specification is intended to appropriately express embodiments of the present invention and may vary depending on the intent of the user or operator, or the practices of the field to which the present invention pertains. Therefore, the definitions of these terms should be based on the contents throughout this specification.

[0024]

[0025] Image analysis system for Gram-stained slides

[0026] Figure 1 is a schematic diagram of one embodiment of a Gram stain slide image analysis system according to the present invention. Hereinafter, one embodiment of the Gram stain slide image analysis system according to the present invention will be described in detail with reference to Figure 1.

[0027] One embodiment of the Gram stain slide image analysis system of the present embodiment relates to an image analysis system of a Gram stained specimen slide, and includes a low magnification imaging unit (210), an object detection unit (215), a high magnification imaging unit (220), and a bacteria identification unit (230). The system may further include an analysis result output unit (240) for outputting image analysis results.

[0028] As illustrated in Fig. 1, the low-magnification imaging unit (210) captures an ideal zone on a Gram-stained specimen slide using the low-magnification imaging unit (210) to obtain a low-magnification image. In addition to the low-magnification microscope, the low-magnification imaging unit (210) may further include a control module for controlling imaging conditions and image acquisition, and a storage for storing image data. Here, the ideal zone is an area where valid cells / bacteria (e.g., WBC, EP Cell, Yeast, fungi) are expected to exist, and it is required that the smear is not too thick or too thin.

[0029] The object detection unit (215) detects an object of interest from an acquired low-magnification image and searches for the location of the object of interest. The object detection unit (215) may apply an algorithm that distinguishes between a background image and a target image to detect an object of interest (e.g., WBC, EP Cell, Yeast, bacteria) from a low-magnification image, and may be configured to include software implementing such an algorithm, a central processing unit (CPU) capable of executing the software, and a necessary memory device.

[0030] In addition, it is preferable that the object detection unit (215) divides the low-magnification image into appropriate segmented areas to search for the target object location and recognizes them as relative coordinates compared to the reference location.

[0031] The high-magnification imaging unit (220) acquires a high-magnification image of an object area containing an object of interest detected at the location of the searched object of interest. In addition to a high-magnification microscope, the high-magnification imaging unit (220) may further include a control module for controlling imaging conditions and image acquisition, and a storage unit capable of storing image data.

[0032] The bacteria discrimination unit (230) performs a first discrimination to discriminate bacteria among the observation target objects into Gram-positive bacteria and Gram-negative bacteria based on a high-magnification image, and a second discrimination to discriminate bacteria among the detected observation target objects into at least one of cocci, bacilli, and spiral bacteria. The bacteria discrimination unit (230) can primarily discriminate between Gram-positive bacteria and Gram-negative bacteria based on the colors detected for the bacteria in the color high-magnification image. That is, it can discriminate between Gram-positive bacteria whose cell walls are stained purple or Gram-negative bacteria whose cell walls are stained red.

[0033] In addition, the bacteria identification unit (230) can secondarily identify bacteria in a high-magnification image as at least one of coccus, bacillus, and spirochetes based on the shape detected (shape of the target image compared to the background image). Meanwhile, the bacteria identification unit (230) can additionally detect the amount, arrangement, size, presence of other cells, etc. of bacteria to identify diplococci, streptococci, and staphylococci, or to identify pathogenic bacteria (cholera bacteria, syphilis bacteria, etc.), molds, yeasts, etc.

[0034]

[0035] Image analysis method of Gram-stained slides

[0036] Figure 2 is a flowchart sequentially illustrating one embodiment of a method for analyzing a Gram stained slide image according to the present invention. Referring to Figure 2, in this embodiment, first, in the method for analyzing an image of a smeared slide image, a Gram staining step (S110) for staining a specimen slide is performed.

[0037] A step (S115) of searching for an ideal zone is performed based on the smear location and smear shape of the next Gram-stained specimen slide. Here, the ideal zone is an area where valid cells / bacteria (WBC, EP Cell, Yeast, fungi) exist.

[0038] Next, a low-magnification imaging step (S120) is performed to acquire a low-magnification image by capturing an ideal zone of the dyed specimen slide with a low-magnification imaging unit (210). Here, S110 and S120 are processes for acquiring an image (a) in which an ideal zone is selected, a segmented low-magnification image (b) of the ideal zone acquired by the low-magnification imaging unit, and an image (c) in which a portion is enlarged, as illustrated in FIG. 3, for example.

[0039] Next, an object detection step (S130) is performed to detect an object of interest in the acquired low-magnification image and search for the location of the object of interest. Here, S130 is a process of obtaining an image (a) showing the searched bacterial location and cells and yeast, and an image (b) magnified in part thereof, as illustrated in FIG. 4, for example.

[0040] A high-magnification imaging step (S140) is performed to acquire a high-magnification image by imaging an object area containing an object of interest detected at the location of the next searched object of interest using a high-magnification imaging unit (220).

[0041] The following bacteria discrimination unit (230) performs a first discrimination step (S150) in which it discriminates bacteria among the observation target objects into Gram-positive bacteria and Gram-negative bacteria based on a high-magnification image, and then performs a second discrimination step (S160) in which it discriminates bacteria among the observation target objects detected by the bacteria discrimination unit (230) into at least one of cocci, bacilli, and spiral bacteria. Here, S140 and S150 acquire and discriminate images (a) and (b) acquired by the high-magnification imaging unit (220), as illustrated in FIG. 5.

[0042] In particular, step S150 may be a step in which the bacteria identification unit (230) distinguishes between gram-positive bacteria and gram-negative bacteria based on the color detected for the bacteria in the high-magnification image. In addition, step S160 may be a step in which the bacteria identification unit (230) distinguishes between at least one of cocci, bacilli, and spiral bacteria based on the shape detected for the bacteria in the high-magnification image.

[0043] Finally, the method for analyzing images of a Gram stain slide can be implemented by performing an analysis result output step (S170) in which the analysis result output unit (240) outputs a cell grade based on a low-magnification image acquired for cells and outputs a bacteria grade based on a high-magnification image acquired for bacteria. Here, the cell grade may be determined based on the number of cells detected in the acquired low-magnification image, and the bacteria grade may be determined based on a relative amount compared to the number of cells.

[0044] And the analysis result output unit (240) can output a result report for image analysis, as illustrated in Fig. 6. This result report can define the result criteria as shown in Table 1 below.

[0045] [Table 1]

[0046]

[0047] Although the embodiments of the present invention have been described with reference to the attached drawings, it will be understood by those skilled in the art that the technical configuration of the present invention described above can be implemented in other specific forms without changing the technical spirit or essential characteristics of the present invention. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. In addition, the scope of the present invention is indicated by the claims described below rather than the detailed description above. Furthermore, all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included within the scope of the present invention.

[0048] [Explanation of symbols]

[0049] 210: Low magnification imaging unit

[0050] 215: Object detection unit

[0051] 220: High-magnification imaging unit

[0052] 230: Bacterial Identification Unit

[0053] 240: Analysis result output section

Claims

1. In the image analysis method of the smeared slide image, Gram staining step (S110) for staining the specimen slide; A low-magnification imaging step (S120) of capturing an ideal zone of the above-mentioned stained specimen slide using a low-magnification imaging unit to obtain a low-magnification image; An object detection step (S130) of detecting an object of interest in the acquired low-magnification image and searching for the location of the object of interest; A high-magnification imaging step (S140) of acquiring a high-magnification image by imaging an object area including the detected object of interest at the location of the searched object of interest using a high-magnification imaging unit; A first discrimination step (S150) in which a bacteria discrimination unit discriminates bacteria among the observation target objects into Gram-positive bacteria and Gram-negative bacteria based on the high-magnification image; and A method for analyzing an image of a Gram stained slide, comprising a second discrimination step (S160) in which the above-detected bacterial discrimination unit discriminates the bacteria among the detected observation target objects as at least one of cocci, bacilli, and spiral bacteria.

2. In paragraph 1, After the above step S160, A method for analyzing an image of a Gram stained slide, further comprising an analysis result output step (S170) in which the analysis result output unit outputs a cell grade based on the acquired low-magnification image for the cell and outputs a bacteria grade based on the acquired high-magnification image for the bacteria.

3. In paragraph 2, A method for analyzing an image of a Gram stained slide, characterized in that the cell grade is determined based on the number of cells detected in the acquired low-magnification image, and the bacteria grade is determined based on the number of bacteria detected in the acquired high-magnification image.

4. In paragraph 1, The above step S150 is, A method for analyzing an image of a Gram-stained slide, characterized in that the bacterial discrimination unit is a step of discriminating between Gram-positive bacteria and Gram-negative bacteria in response to the color detected for the bacteria in the high-magnification image.

5. In paragraph 1, The above step S160 is, A method for analyzing an image of a Gram stained slide, characterized in that the bacterial identification unit is a step of identifying the bacteria in the high-magnification image as at least one of cocci, bacilli, and spiral bacteria in response to the shape detected for the bacteria.

6. In the image analysis system of the smeared slide image, A low-magnification imaging unit (210) that acquires a low-magnification image by imaging the ideal zone of a Gram-stained specimen slide with a low-magnification imaging unit; An object detection unit (215) that detects an object of interest in the acquired low-magnification image and searches for the location of the object of interest; A high-magnification imaging unit (220) that acquires a high-magnification image of an object area including the detected object of interest at the location of the searched object of interest; and An image analysis system for a Gram stained slide, comprising a bacteria identification unit (230) that performs a first identification to identify bacteria among the observation target objects as Gram-positive bacteria and Gram-negative bacteria based on the high-magnification image, and performs a second identification to identify bacteria among the detected observation target objects as at least one of cocci, bacilli, and spiral bacteria.

Images