Method for generating images of tissue specimens and computing system for performing the same - Patents.com

Abstract

A method for generating a tissue image by removing tissue sample regions determined to be other tissue samples from a slide image of a tissue sample, and a computing system for performing the method are disclosed. According to one aspect of the present invention, a method for generating a tissue sample image is provided, comprising the steps of: extracting a plurality of contours corresponding to a plurality of tissue regions included in a tissue sample image, calculating the center point coordinates of each of the extracted contours, determining a main tissue contour among the contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the contours, and removing a region corresponding to at least a part of the remaining contours excluding the main tissue contour among the contours.

Description

[Technical field]

[0001] The present invention relates to a method for generating an image of a biological tissue sample and a computing system for performing the same, and more particularly to a method for generating a tissue image by removing tissue sample regions determined to be other tissue samples from a slide image of the tissue sample and a computing system for performing the same. [Background technology]

[0002] One of the main tasks of pathology or pathology department is to read slide images of patient's biological tissues and make a diagnosis to determine the condition or symptoms of a certain disease. In the conventional pathology diagnosis method, a pathologist visually observes and reads diagnostic pathology slide images made from a specimen through an optical microscope. The beginning of digital pathology is the method of converting a pathology slide into a digital image using a microscope camera connected to a computer, and then observing and reading it on a monitor. In recent years, with the emergence of digital slide scanners, the method of converting an entire pathology slide into a single digital image to create a pathology slide image, and then observing and reading it on a computer monitor has become widespread.

[0003] Recently, with the development of machine learning, there have been many attempts to automate tasks such as image recognition or classification using computer systems. In particular, attempts have been made to automate diagnoses that were previously performed by skilled medical personnel using neural networks (e.g., convolutional neural networks (CNNs) and the like), which are a type of machine learning, but generally, diagnoses via neural networks using biological tissue images use biological images. That is, for the corresponding biological images, skilled medical personnel annotate the state of a specific disease (e.g., whether or not the disease has manifested), and a plurality of such annotated images are used as training data to train the neural network.

[0004] On the other hand, as shown in FIG. 1, a pathology slide may be prepared by placing multiple tissue samples on one glass slide, and in the case of a pathology slide prepared in this manner, there is no significant problem in visually inspecting the pathology slide through an optical microscope. However, when the pathology slide is digitized and an algorithmic or artificial intelligence analysis is performed for each tissue sample, the image to be analyzed may contain other tissue samples, which may prevent the diagnostic model from learning correctly or may result in an inaccurate analysis. For example, in the case of a pathology slide image generated from a glass slide prepared with many biological tissues placed thereon, other tissue samples may be included in the process of automatically dividing the image into tissue sample units due to limitations or errors of the automatic division algorithm. Or, even if the image is divided manually into tissue sample units, if the tissue sample area can only be specified in a simple form such as a rectangle or ellipse, there is a problem that other tissue samples may be included.

[0005] Therefore, a method is needed that can check whether other tissue samples are included in an image segmented by tissue sample unit and can remove them. Summary of the Invention [Problem to be solved by the invention]

[0006] The technical problem to be solved by the present invention is to provide a method for generating a tissue sample image by inputting a slide image of a tissue sample and removing tissue sample areas determined to be other tissue samples, and a computing system for performing this method. [Means for solving the problem]

[0007] According to one aspect of the present invention, there is provided a method for generating a tissue sample image, comprising the steps of: extracting a plurality of contours corresponding to a plurality of tissue regions included in a tissue sample image; calculating the center point coordinates of each of the extracted contours; determining a main tissue contour from among the plurality of contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the plurality of contours; and removing an area from among the plurality of contours that corresponds to at least a portion of the remaining contours excluding the main tissue contour.

[0008] In one embodiment, the step of determining a main tissue contour from among the plurality of contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the plurality of contours may include the step of determining as the main tissue contour a contour from among the plurality of contours whose center point is closest to the center point of the tissue sample image.

[0009] In one embodiment, the step of removing an area of ​​the plurality of contours that corresponds to at least a portion of the remaining contours excluding the main tissue contour may include the steps of determining a boundary-adjacent contour of the plurality of contours that is adjacent to an outline of the tissue sample image, and removing an area of ​​the tissue sample image that corresponds to a contour to be removed (wherein the contour to be removed is a boundary-adjacent contour that is not a main tissue contour among the boundary-adjacent contours).

[0010] In one embodiment, the step of extracting a plurality of contours corresponding to each of a plurality of tissue regions included in the tissue sample image may include the steps of generating a binary mask image corresponding to the tissue sample image in which values ​​of a plurality of tissue regions and non-tissue regions included in the tissue sample image are divided by binary values, and extracting the plurality of contours based on the binary mask.

[0011] In one embodiment, removing an area of ​​the tissue sample image corresponding to the contour to be removed may include replacing the area of ​​the tissue sample image corresponding to the contour to be removed with a background color of the tissue sample image.

[0012] In one embodiment, the step of removing an area from the tissue sample image that corresponds to a contour to be removed may further include determining an average color of areas of the tissue sample image that do not correspond to any of the plurality of contours as a background color of the tissue sample image.

[0013] According to another aspect of the invention there is provided a computer program recorded on a medium for installing in a data processing device and for carrying out the method as described above.

[0014] According to another aspect of the present invention, there is provided a computer readable recording medium having recorded thereon a computer program for performing the method described above.

[0015] According to another aspect of the present invention, there is provided a system for generating an image of a tissue specimen, comprising:

[0016] A tissue sample image generation system is provided, comprising a processor and a memory for storing a computer program, which, when executed by the processor, causes the tissue sample image generation system to execute a tissue sample image generation method, the tissue sample image generation method including the steps of: extracting a plurality of contours corresponding to each of a plurality of tissue regions included in the tissue sample image; calculating the center point coordinates of each of the extracted plurality of contours; determining a main tissue contour from among the plurality of contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the plurality of contours; and removing an area from the plurality of contours that corresponds to at least a portion of the remaining contours excluding the main tissue contour.

[0017] In one embodiment, the step of determining a main tissue contour from among the plurality of contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the plurality of contours may include the step of determining as the main tissue contour a contour from among the plurality of contours whose center point is closest to the center point of the tissue sample image.

[0018] In one embodiment, the step of removing an area of ​​the plurality of contours that corresponds to at least a portion of the remaining contours excluding the main tissue contour may include the steps of determining a boundary-adjacent contour of the plurality of contours that is adjacent to an outline of the tissue sample image, and removing an area of ​​the tissue sample image that corresponds to a contour to be removed (wherein the contour to be removed is a boundary-adjacent contour that is not a main tissue contour among the boundary-adjacent contours).

[0019] In one embodiment, the step of extracting a plurality of contours corresponding to each of a plurality of tissue regions included in the tissue sample image may include the steps of generating a binary mask image corresponding to the tissue sample image in which values ​​of a plurality of tissue regions and non-tissue regions included in the tissue sample image are divided by binary values, and extracting the plurality of contours based on the binary mask.

[0020] In one embodiment, removing an area of ​​the tissue sample image corresponding to the contour to be removed may include replacing the area of ​​the tissue sample image corresponding to the contour to be removed with a background color of the tissue sample image. Effect of the Invention

[0021] According to the technical idea of ​​the present invention, a method for generating a tissue sample image by inputting a slide image of a tissue sample and removing tissue sample areas determined to be other tissue samples, and a computing system for performing this method can be provided.

[0022] In addition, the image generated by the method for generating a tissue sample image according to an embodiment of the present invention can be used to train an artificial neural network more accurately. [Brief description of the drawings]

[0023] In order to more fully understand the drawings referred to in the detailed description of the invention, a brief description of each of the drawings is provided.

[0024] [Figure 1] FIG. 1 shows an example of a glass slide on which a plurality of specimens are placed. [Diagram 2] 1 is a diagram for explaining a schematic system configuration for realizing a method for generating a tissue sample image according to an embodiment of the present invention. [Diagram 3] 4 is a flowchart illustrating a method for generating a tissue sample image according to an embodiment of the present invention. [Figure 4] 4 is a flowchart showing an example of step S100 in FIG. 3. [Diagram 5] 4 is a flowchart showing an example of step S120 in FIG. 3. [Figure 6] 4 is a flowchart showing an example of step S130 in FIG. 3. [Figure 7a] FIG. 13 is a diagram showing an example of a tissue sample image. [Figure 7b] FIG. 2 illustrates an example of a binary mask image corresponding to a tissue sample image. [Figure 7c] 7b shows a generated image after removing the area corresponding to the removal target contour from the tissue sample image of FIG. 7a. FIG. [Figure 8] 1 is a diagram showing a schematic configuration of a tissue sample image generating system according to an embodiment of the present invention; [Figure 9] 1 is a diagram for explaining a schematic configuration of a tissue sample image generating system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Since the present invention can be modified in various ways and can have various embodiments, a specific embodiment is shown in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to the specific embodiment, and it should be understood that the present invention includes all modifications, equivalents, and alternatives within the spirit and technical scope of the present invention. In the description of the present invention, if a detailed description of related publicly known technology is deemed to make the gist of the present invention unclear, the detailed description will be omitted.

[0026] Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. Terms such as first, second, etc. do not indicate a particular order, but are used only to distinguish one component from another component.

[0027] The terms used in this application are merely used to describe specific embodiments and are not intended to limit the present invention. The singular expressions include the plural expressions unless otherwise clearly meant in the context.

[0028] As used herein, terms such as "comprise" or "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described herein, and are to be understood as not precluding the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0029] In addition, in this specification, when a component "transmits" data to another component, it means that the component can transmit data directly to the other component, or can transmit data to the other component via at least one other component. Conversely, when a component "transmits" data to another component, it means that the component transmits data to the other component without via the other component.

[0030] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings, in which the same reference numerals indicate the same elements.

[0031] FIG. 2 is a diagram for explaining a schematic system configuration for implementing a method for generating a tissue sample image according to an embodiment of the present invention.

[0032] Referring to FIG. 2, a method for generating an image of a tissue sample according to the teachings of the present invention can be performed by a system 100 for generating an image of a tissue sample.

[0033] In one embodiment, the tissue sample image generating system 100 is installed in a predetermined server 10, and the technical idea of ​​the present invention can be realized. The server 10 means a data processing device having a computing capacity for realizing the technical idea of ​​the present invention, and an average expert in the technical field of the present invention can easily deduce that not only a data processing device to which a client can be connected via a network, but also any device capable of executing a specific service, such as a personal computer or a mobile terminal, can be defined as a server.

[0034] The tissue sample image generating system 100 inputs the generated tissue sample image into a predetermined neural network 200, so that the neural network 200 can learn, or a pre-trained neural network 200 can make a predetermined judgment from the tissue sample image. The neural network 200 may be an artificial neural network for providing diagnostic information, prognostic information, and / or reaction information to a treatment method for a pathological sample, and the results output by the neural network 200 can be used to make various judgments about the sample (e.g., the presence or absence of disease, prognosis, judgment about a treatment method, etc.).

[0035] The neural network 200 is an artificially constructed neural network based on the operating principle of human neurons, and may include a multi-layer perceptron model and may refer to a collection of information representing a set of design items that define an artificial neural network. The neural network 200 may include, but is not limited to, a convolutional neural network (CNN), which is widely known in the fields of artificial intelligence, machine learning, or deep learning.

[0036] The server 10 including the neural network 200 and the system 100 for generating tissue sample images may be a diagnostic system for diagnosing a disease, or a diagnostic support system for providing information necessary for a doctor to diagnose a disease. The neural network 200 and the system 100 for generating tissue sample images may be provided in one physical device, i.e., the server 10, but may also be provided in different physical devices depending on the embodiment, and various modifications are possible as needed, as can be easily deduced by an average expert in the technical field of the present invention.

[0037] The diagnostic system 10 can communicate with a predetermined terminal 20, 20-1 in order to train the neural network 200. The terminal 20, 20-1 can transmit a plurality of training data to the neural network 200 in order to train the neural network 200, and the neural network 200 can perform training using the received training data.

[0038] Furthermore, the terminals 20 and 20-1 can output a biological image to be diagnosed to the diagnostic system 10 in order to diagnose a disease using the trained neural network 200.

[0039] 2 shows an example in which the tissue sample image generating system 100 is realized in the form of a subsystem installed in the server 10, but it goes without saying that in some embodiments, the tissue sample image generating system 100 can be realized as an independent single system. In this case, the tissue sample image generating system 100 may be a computing system that is a data processing device having a computing capacity for realizing the technical idea of ​​the present invention, and may include not only a server that is a data processing device to which a client can be connected via a network, but also a computer device such as a personal computer or a mobile terminal.

[0040] The tissue specimen image generating system 100 is capable of generating a pathology specimen image.

[0041] The tissue or pathology specimen may be biopsies taken from various organs of the human body, and biological tissues excised by surgery. The tissue or pathology specimen image may be a slide image of the pathology specimen in the form of a glass slide, which is scanned and converted into a digital image, or may be an image obtained by segmenting the slide image using a predetermined automatic segmentation algorithm or manually.

[0042] In the process of preparing glass slides from pathological specimens, multiple specimens may be placed on one slide, and when such a prepared slide is converted into a digital image, multiple different tissues may be included in one image. Even if a slide prepared in this way is converted and then divided into images of multiple specimens, images of other tissues may be included in one image in addition to one main tissue. The tissue specimen image generating system 100 can generate a tissue image by a method of removing tissue specimen areas determined to be other tissue specimens.

[0043] FIG. 3 is a flow chart illustrating a method for generating a tissue sample image according to an embodiment of the present invention.

[0044] Referring to FIG. 3, the tissue sample image generating system 100 can extract a plurality of contours corresponding to a plurality of tissue regions included in the tissue sample image (S100).

[0045] In one embodiment, the tissue sample image generation system 100 can extract contours by binary masking, an example of which is shown in FIG.

[0046] 4, the tissue sample image generating system 100 can generate a binary mask image corresponding to a tissue sample image in which values ​​of a plurality of tissue regions and non-tissue regions included in the tissue sample image are divided by binary values ​​(S101). For example, the binary mask image may be an image in which parts of the tissue sample image that have tissue are composed of 1s and parts that do not have tissue are composed of 0s.

[0047] FIG. 7a shows an example of a tissue sample image, and FIG. 7b shows an example of a binary mask image corresponding to the tissue sample image.

[0048] In one embodiment, the tissue sample image generation system 100 can identify biological tissue regions using a pre-trained neural network for determining biological tissue regions, and generate a binary mask image by separating the identified biological tissue regions from non-biological tissue regions, or can identify biological tissue regions using various known methods.

[0049] If the tissue sample image is an image constructed using the HSV (Hue-Saturation-Value) color model, the tissue sample image generating system 100 according to one embodiment can generate a binary mask image based on the HSV color model in the following manner.

[0050] In one embodiment, the tissue sample image generating system 100 can generate a first binarization result by performing image binarization on an S-space corresponding to the tissue sample image. At this time, the S-space corresponding to the slide is a space consisting of saturation values ​​(Saturation) of an HSV model corresponding to the slide. As an image binarization method, Otsu's binarization process (Otsu Thresholding) can be used. Otsu's binarization process is a clustering-based image threshold processing method used in the fields of computer vision and image processing.

[0051] Furthermore, the tissue specimen image generating system 100 can generate a second binarization result by performing image binarization on the (1-V) space corresponding to the slide. At this time, the V space corresponding to the slide is a space consisting of brightness values ​​(Values) of the HSV model corresponding to the slide (i.e., a matrix (w is the image width and h is the image height) having a size of w×h and consisting of V channel values ​​(brightness values)), and the (1-V) space may be a space having a size of w×h and obtained by subtracting the V channel value from a matrix filled with 1s.

[0052] Thereafter, the tissue sample image generating system 100 can generate a binary mask image corresponding to the tissue sample image based on the first binarization result and the second binarization result. The first binarization result and the second binarization result can include a binary value (e.g., 0 or 1, or 0 or 255) corresponding to each pixel of the tissue sample image, and the tissue sample image generating system 100 can generate a binary mask image corresponding to the tissue sample image by determining, for each pixel of the tissue sample image, a pixel on the binary mask image corresponding to the pixel as a tissue pixel (a pixel corresponding to tissue) if the binary value of the first binarization result corresponding to the pixel or the binary value of the first binarization result corresponding to the pixel is 1 (or 255), and determining, otherwise (i.e., if the binary value is 0), the pixel on the binary mask image corresponding to the pixel as a non-tissue pixel (a pixel not corresponding to tissue). In summary, the tissue sample image generating system 100 can generate a binary mask image by performing a logical OR operation on the image binarization result for the S space and the image binarization result for the (1-V) space.

[0053] Meanwhile, the tissue sample image generating system 100 can extract a plurality of contours based on the binary mask (S102).

[0054] The tissue specimen image generating system 100 can extract multiple contours based on a binary mask using various known contour extraction methods, such as the contour extraction method proposed by Suzuki, S. and Abe, K. (Topological Structural Analysis of Digitized Binary Images by Border Following. CVGIP 30 1, pp32-46 (1985)), and can also use any other algorithm that can extract a contour composed of a set of coordinate sequences.

[0055] 3, the tissue sample image generating system 100 can calculate the center point coordinates of each of the extracted contours. If there are M tissues in the tissue sample image, the tissue sample image generating system 100 can calculate the center point coordinates of the first contour to the Mth contour (S110, S115).

[0056] The tissue sample image generating system 100 can determine a main tissue contour from among the multiple contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the multiple contours (S120).

[0057] A more detailed example of step S120 is shown in Fig. 5. Referring to Fig. 5, the tissue sample image generation system 100 can calculate the distance between the center point of the tissue sample image and each contour (i.e., the first contour to the Mth contour) (S121, S122).

[0058] Thereafter, the tissue sample image generating system 100 can determine, as a main tissue contour, a contour whose center point is closest to the center point of the tissue sample image among the multiple contours (S123).

[0059] Also, referring to FIG. 3, the system 100 for generating a tissue sample image may remove an area corresponding to at least a part of the remaining contours excluding the main tissue contour from among the plurality of contours (S130).

[0060] A specific example of step S130 is shown in Fig. 6. Referring to Fig. 6, the tissue sample image generation system 100 can determine a boundary adjacent contour that is adjacent to the outline of the tissue sample image among the multiple contours (S131).

[0061] Furthermore, the system 100 for generating tissue sample images can determine, among the boundary adjacent contours, those that are not main tissue contours as contours to be removed (S132).

[0062] Thereafter, the tissue sample image generating system 100 can remove the area corresponding to the removal target contour from the tissue sample image (S131).

[0063] In one embodiment, the tissue sample image generation system 100 can remove areas of the tissue sample image that correspond to the contours to be removed by replacing the areas of the tissue sample image that correspond to the contours to be removed with the background color of the tissue sample image, and at this time, the average color of the areas that do not correspond to any of the multiple contours can be determined as the background color of the tissue sample image.

[0064] FIG. 7c shows a generated image after removing the regions corresponding to the contours to be removed (boundary adjacent contours that are not the main tissue contours) from the tissue sample image of FIG. 7a.

[0065] In some embodiments, unlike FIG. 6, the tissue sample image generation system 100 may remove all remaining samples except the main tissue sample, or may compare the center point coordinates of the contour coordinates corresponding to the main tissue sample with the center point coordinates of the contours corresponding to each of the remaining samples and remove only those samples whose distance between the center point coordinates exceeds a predetermined limit value.

[0066] FIG. 8 is a diagram showing a schematic configuration of a tissue sample image generating system 100 according to an embodiment of the present invention.

[0067] The tissue sample image generating system 100 may refer to a logical configuration having hardware resources and / or software necessary to realize the technical idea of ​​the present invention, and does not necessarily refer to one physical component or one device. In other words, the tissue sample image generating system 100 may refer to a logical combination of hardware and / or software provided to realize the technical idea of ​​the present invention, and may be realized as a set of logical configurations that are installed in devices separated from each other as necessary and perform their respective functions to realize the technical idea of ​​the present invention. The tissue sample image generating system 100 may also refer to a set of configurations that are realized separately for each function or role to realize the technical idea of ​​the present invention. Each component of the tissue sample image generating system 100 may be located in different physical devices or in the same physical device. In addition, depending on the embodiment, the combination of software and / or hardware constituting each component of the tissue sample image generating system 100 may also be located in different physical devices, and the components located in the different physical devices may be organically combined with each other to realize each module.

[0068] In addition, in this specification, a module may refer to a functional and structural combination of hardware for carrying out the technical idea of ​​the present invention and software for driving the hardware. For example, a module may refer to a logical unit of a certain code and a hardware resource for executing the certain code, and does not necessarily refer to a physically connected code or a type of hardware, which can be easily inferred by an average expert in the technical field of the present invention.

[0069] 8, the tissue sample image generating system 100 may include an extraction module 110, a calculation module 120, a determination module 130, and a removal module 140. Depending on the embodiment of the present invention, some of the above-mentioned components may not necessarily correspond to components essential to realizing the present invention, and it goes without saying that the tissue sample image generating system 100 may include more components than the above. For example, the tissue sample image generating system 100 may further include a communication module (not shown) for communicating with an external device, a storage module (not shown) for storing data, a control module (not shown) for controlling the components and resources of the tissue sample image generating system 100, etc.

[0070] The extraction module 110 can extract a number of contours corresponding to a number of tissue regions included in the tissue sample image.

[0071] In one embodiment, the extraction module 110 can generate a binary mask image corresponding to the tissue sample image in which the values ​​of multiple tissue regions and non-tissue regions contained in the tissue sample image are divided by binary values, and extract multiple contours based on the binary mask.

[0072] The calculation module 120 can calculate the center point coordinates of each of the extracted contours.

[0073] The determination module 130 can determine a main tissue contour among the plurality of contours based on the center point coordinates of the tissue sample image and the center point coordinates of each of the plurality of contours.

[0074] In one embodiment, the determination module 130 may determine, among the multiple contours, a contour having a center point closest to a center point of the tissue sample image as the main tissue contour.

[0075] The removal module 140 can remove regions that correspond to at least a portion of the remaining contours, excluding the main tissue contour, among the plurality of contours.

[0076] In one embodiment, the removal module 140 may determine boundary-adjacent contours among the plurality of contours that are adjacent to an outline of the tissue sample image, and remove regions corresponding to the contours to be removed from the tissue sample image, where the contours to be removed may be boundary-adjacent contours that are not the main tissue contour.

[0077] In one embodiment, the removal module 140 may remove the area corresponding to the contour to be removed from the tissue sample image by replacing the area of ​​the tissue sample image corresponding to the contour to be removed with a background color of the tissue sample image, where the background color of the tissue sample image may be determined as an average color of the area of ​​the tissue sample image that does not correspond to any of the contours.

[0078] Meanwhile, according to an embodiment, the tissue sample image generating system 100 may include a processor and a memory for storing a program executed by the processor. In this case, the tissue sample image generating system 100 may have a configuration as shown in Fig. 9. Fig. 9 is a diagram for explaining a schematic configuration of the tissue sample image generating system 100 according to an embodiment of the present invention.

[0079] The tissue sample image generating system 100 may include a memory 102 in which a program for realizing the technical concept of the present invention is stored, and a processor 101 for executing the program stored in the memory 102 .

[0080] An average expert in the technical field of the present invention can easily deduce that the processor 101 can be named by various names such as a CPU, an APU, a mobile processor, etc., depending on the embodiment of the tissue sample image generating system 100. The processor may include a single-core CPU or a multi-core CPU. In addition, the tissue sample image generating system 100 can be realized by organically combining a plurality of physical devices, and in such a case, an average expert in the technical field of the present invention can easily deduce that at least one processor 101 is provided for each physical device to realize the tissue sample image generating system 100 of the present invention.

[0081] The memory 102 may be implemented as any form of storage device in which a program can be stored and which can be accessed by the processor to run the program. The memory 102 may include a high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Access to the memory by the processor and other components may be controlled by a memory controller. Depending on the hardware implementation, the memory 102 may be implemented as a single storage device or multiple storage devices. The memory 102 may also include not only a primary storage device but also a temporary storage device. The memory 102 may also be implemented as a volatile memory or a non-volatile memory, and may be defined to include all forms of information storage means in which a program can be stored and run by the processor.

[0082] When executed by the processor 101, the program can cause the tissue sample image generating system 100 to perform the tissue sample image generating method described above.

[0083] Meanwhile, the method according to the embodiment of the present invention may be realized in the form of computer readable program instructions and stored in a computer readable recording medium, and the control program and the target program according to the embodiment of the present invention may also be stored in a computer readable recording medium. The computer readable recording medium includes any kind of recording device in which data that can be read by a computer system is stored.

[0084] The program instructions contained on the recording media may be those specially designed and constructed for the purposes of the present invention, or they may be of the type commonly known and available to those having skill in the software arts.

[0085] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, etc. Also, computer-readable recording media can be distributed among computer systems connected via a network to store and execute computer-readable code in a distributed manner.

[0086] Examples of program instructions include not only machine code, such as produced by a compiler, but also high level language codes that may be executed by a device for processing information electronically, such as a computer, using an interpreter or the like.

[0087] The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

[0088] The above description of the present invention is for illustrative purposes only, and a person having ordinary skill in the art to which the present invention pertains can easily understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and are not limiting. For example, each component described in a single form can be implemented in a distributed manner, and similarly, components described as being distributed can be implemented in a combined form.

[0089] The scope of the present invention is indicated by the claims set forth below rather than by the above detailed description, and all modifications and variations that fall within the meaning and scope of the claims and their equivalent concepts should be construed as being included within the scope of the present invention. [Industrial Applicability]

[0090] The present invention may be used in a method for generating images of a tissue specimen, and in a computing system for doing so.

Claims

1. 1. A method for generating an image of a tissue specimen, comprising: extracting a plurality of contours corresponding to a plurality of tissue regions included in the tissue sample image; calculating center point coordinates of each of the extracted contours; determining a main tissue contour from among the plurality of contours based on a center point coordinate of the tissue sample image and center point coordinates of each of the plurality of contours; removing an area corresponding to at least a portion of the remaining contours excluding the main tissue contour from among the plurality of contours; The step of removing an area corresponding to at least a part of the remaining contours excluding the main tissue contour from among the plurality of contours includes: determining a boundary adjacent contour among the plurality of contours that is adjacent to an outline of the tissue sample image; removing an area corresponding to a contour to be removed from said tissue sample image, said contour to be removed being one of said boundary adjacent contours which is not a main tissue contour; 16. A method for generating an image of a tissue specimen, comprising:

2. determining a main tissue contour from among the plurality of contours based on a center point coordinate of the tissue sample image and center point coordinates of each of the plurality of contours, The method for generating a tissue sample image according to claim 1 , further comprising the step of determining, as the main tissue contour, a contour among the plurality of contours whose center point is closest to a center point of the tissue sample image.

3. The step of extracting a plurality of contours corresponding to a plurality of tissue regions included in the tissue sample image includes: generating a binary mask image corresponding to the tissue sample image, in which values ​​of a plurality of tissue regions and non-tissue regions included in the tissue sample image are divided by binary values; extracting the contours based on the binary mask image; The method of claim 1 , comprising:

4. The step of removing an area corresponding to a removal target contour from the tissue sample image includes:

2. The method of claim 1, further comprising replacing an area of ​​the tissue sample image that corresponds to the removal target contour with a background color of the tissue sample image.

5. The step of removing an area corresponding to a removal target contour from the tissue sample image includes:

5. The method of claim 4, further comprising the step of determining an average color of an area of ​​the tissue sample image that does not fall within any of the plurality of contours as a background color of the tissue sample image.

6. A computer program recorded on a recording medium for being installed in a data processing device and for carrying out the method according to any one of claims 1 to 5.

7. A computer-readable recording medium having a computer program recorded thereon for carrying out the method according to any one of claims 1 to 5.

8. 1. A system for generating a tissue sample image, comprising: A processor and a memory for storing a computer program, The computer program, when executed by the processor, causes the tissue sample image generation system to perform a tissue sample image generation method, The method for generating a tissue sample image comprises: extracting a plurality of contours corresponding to a plurality of tissue regions included in the tissue sample image; calculating center point coordinates of each of the extracted contours; determining a main tissue contour from among the plurality of contours based on a center point coordinate of the tissue sample image and center point coordinates of each of the plurality of contours; removing an area corresponding to at least a portion of the remaining contours excluding the main tissue contour from among the plurality of contours; The step of removing an area corresponding to at least a part of the remaining contours excluding the main tissue contour from among the plurality of contours includes: determining a boundary adjacent contour among the plurality of contours that is adjacent to an outline of the tissue sample image; removing an area corresponding to a contour to be removed from the tissue sample image, the contour to be removed being one of the boundary adjacent contours that is not a main tissue contour; A system for generating an image of a tissue specimen, comprising:

9. determining a main tissue contour from among the plurality of contours based on a center point coordinate of the tissue sample image and center point coordinates of each of the plurality of contours, The system for generating a tissue sample image according to claim 8 , further comprising a step of determining, as the main tissue contour, a contour among the plurality of contours whose center point is closest to a center point of the tissue sample image.

10. The step of extracting a plurality of contours corresponding to a plurality of tissue regions included in the tissue sample image includes: generating a binary mask image corresponding to the tissue sample image, in which values ​​of a plurality of tissue regions and non-tissue regions included in the tissue sample image are divided by binary values; extracting the contours based on the binary mask image; The system for generating a tissue specimen image according to claim 8 , comprising:

11. The step of removing an area corresponding to a removal target contour from the tissue sample image includes:

9. The system for generating a tissue sample image according to claim 8, further comprising a step of replacing an area of ​​the tissue sample image corresponding to the removal target contour with a background color of the tissue sample image.

Images