Inspection support device, inspection support method, and program

Abstract

Provided is a technique that suggests a testing region suited to dissection in genetic testing of somatic cells. An acquisition unit (11) acquires image data of a pathological specimen; an estimation unit (12) estimates the content ratio of tumor cells in each of individual regions in a focus region in the image data of the pathological specimen; a determination unit (13) determines a testing region in the focus region on the basis of the content ratio of tumor cells in each of the individual regions in the focus region; and an output unit (14) outputs information indicating the testing region.

Description

[Technical field]

[0001] The present invention relates to an examination support device, an examination support method, and a recording medium, and more particularly to an examination support device, an examination support method, and a recording medium that assist in the examination of a tumor using a pathology specimen. [Background technology]

[0002] To obtain a cell population for genetic testing of somatic cells, a microscope with a laser attached is used. In one method, a thin slice of tissue is attached to a special slide and stained, and then a laser is applied along the outline of the area to be examined while observing the tissue slice under a microscope. This allows the cell population within the area to be separated from the tissue and collected. This is an example of a technique called dissection.

[0003] In related technology, digitized pathological images are used to make diagnoses or assist in diagnosis. For example, in the related technology described in Patent Document 1, high-magnification and low-magnification pathological images are used to automatically identify pathological tissues. This technology is an example of digital pathology.

[0004] Patent Document 2 describes a method for identifying the state of cells or tissues in a pathological image using a learning model that has been machine-learned from a large number of pathological image samples, and for visualizing the results of the identification. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2010-203949 A [Patent Document 2] JP 2018-044806 A Summary of the Invention [Problem to be solved by the invention]

[0006] For accurate genetic testing, it is required to select a test area from tissue that contains a high proportion of tumor cells. However, it is difficult for a pathologist to properly determine the test area that contains a high proportion of tumor cells. In addition, an inexperienced pathologist may not be able to manually and accurately dissect the cell population in the test area.

[0007] The present invention has been made in consideration of the above problems, and has an object to provide a technique for proposing a test area suitable for dissection in genetic testing of somatic cells. [Means for solving the problem]

[0008] An examination support device according to one embodiment of the present invention includes an acquisition means for acquiring image data of a pathological specimen, an estimation means for estimating the tumor cell content ratio for each unit area in a region of interest in the image data of the pathological specimen, a determination means for determining an examination area within the region of interest based on the tumor cell content ratio within the region of interest, and an output means for outputting information indicating the examination area.

[0009] In one aspect of the present invention, an examination support method acquires image data of a pathological specimen, estimates the tumor cell content per unit area in a region of interest in the image data of the pathological specimen, determines an examination area within the region of interest based on the tumor cell content within the region of interest, and outputs information indicating the examination area.

[0010] A non-transient storage medium according to one embodiment of the present invention records a program for causing a computer to execute the following processes: acquiring image data of a pathological specimen; estimating the tumor cell content per unit area in a region of interest in the image data of the pathological specimen; determining an examination area within the region of interest based on the tumor cell content within the region of interest; and outputting information indicating the examination area. Effect of the Invention

[0011] According to one aspect of the present invention, it is possible to propose a test area suitable for dissection in genetic testing of somatic cells. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing an example of data transmission and reception within a system including a pathologist's terminal and a server. [Diagram 2] FIG. 2 is a diagram illustrating an example of image data of a pathological specimen. [Diagram 3] This is an example showing a screen of a pathologist's terminal, in which information indicating the tumor cell content rate for each unit area is added to one image data of a pathological specimen. [Figure 4] An examination region within a region of interest is indicated by a line on the image data of the pathological specimen shown in FIG. [Diagram 5] FIG. 1 is a schematic diagram showing a unit area containing normal cells and tumor cells. [Figure 6] 1 is a block diagram showing a configuration of an examination support device according to a first embodiment. [Figure 7] 4 is a flowchart showing the operation of the examination support device according to the first embodiment. [Figure 8] 1 is a diagram illustrating an example of a hardware configuration of an examination support device according to a first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] An embodiment of the present invention will be described with reference to the drawings.

[0014] (System 1) An example of the configuration of a system 1 to which a test support device 10 according to a first embodiment described below is applied will be described with reference to Fig. 1. Fig. 1 is a diagram illustrating an example of the system configuration.

[0015] As shown in FIG. 1, the system 1 includes a scanner 100 for a laboratory technician, a terminal 200 for a pathologist, and a server 300.

[0016] The laboratory technician prepares a pathology specimen of the cell tissue to be subjected to genetic testing. The laboratory technician prepares scan data of the pathology specimen using the scanner 100. The laboratory technician transmits the prepared scan data of the pathology specimen to the terminal 200 of the pathologist.

[0017] The pathologist processes the scan data of the pathological specimen received by the terminal 200 to generate image data of the pathological specimen to be transmitted to the server 300. For example, the pathologist determines a region of interest that is considered to have a high proportion of tumor cells.

[0018] The pathologist annotates the region of interest. For example, the pathologist may use general image editing software to add a marking to the region of interest that is considered to have a high tumor cell content. For example, the pathologist may use general image editing software running on the terminal 200 to input dots or lines to surround the region of interest on the image data of the pathological specimen. Alternatively, the pathologist may obtain the pathological specimen itself created by the laboratory technician, draw dots or lines on the pathological specimen with a marker or the like, and then scan the pathological specimen using the scanner 100. The pathologist's terminal 200 transmits the image data of the pathological specimen created in this way to the server 300.

[0019] FIG. 2 is a schematic diagram showing an example of image data of a pathological specimen. In the image data of the pathological specimen shown in FIG. 2, dots indicating an area of ​​interest are added to darker colored parts. Here, a case where an examination technician designates an area of ​​interest has been described. However, an area of ​​interest does not necessarily have to be designated. When an area of ​​interest is not designated, in the following description, the "area of ​​interest" is to be read as the entire image data of the pathological specimen.

[0020] The server 300 includes an examination support device 10 (FIG. 6) according to a first embodiment described later. As will be described in detail in the first embodiment, the examination support device 10 determines an examination region within a region of interest by analyzing image data of a pathological specimen.

[0021] The server 300 transmits information indicating the determined examination region to the pathologist's terminal 200. For example, the server 300 may add a line indicating the examination region proposed to the pathologist on the image data of the pathological specimen (FIG. 4).

[0022] The pathologist's terminal 200 displays the information indicating the examination area received from the server 300. Note that the detailed configuration and operation of the examination support device 10 included in the server 300 will be described in the first embodiment.

[0023] FIG. 3 is an example showing one screen of the pathologist's terminal 200. FIG. 3 shows the tumor cell content ratio for each unit area in a pathological specimen. More specifically, in FIG. 3, the magnitude of the tumor cell content ratio for each unit area in a region of interest is expressed as a pattern on one image data of the pathological specimen. In FIG. 3, the tumor cell content ratio for each unit area is classified in 10% increments. A unit area is an area within a rectangle when one image data of a pathological specimen is divided into rectangles having a certain size. The unit area is sufficiently large compared to the size of a cell. Therefore, a large number of cells and / or tumor cells are present in the unit area. Hereinafter, the ratio of tumor cells in one unit area of ​​interest is referred to as the tumor cell content ratio. In other words, the tumor cell content ratio is the ratio of the number of tumor cells to the total number of cells and tumor cells contained in one unit area of ​​interest.

[0024] In Fig. 4, an examination area within a region of interest is illustrated by a line on the image data of the pathological specimen shown in Fig. 3. The line of the examination area in the image data of the pathological image shown in Fig. 4 is an example of information indicating the examination area described above.

[0025] (Explanation of how to calculate the tumor cell content rate) A method for calculating the tumor cell content ratio will be described with reference to Fig. 5. The tumor cell content ratio is the ratio of tumor cells to a unit area. Fig. 5 shows a schematic diagram of normal cells and tumor cells in a unit area. In the example shown in Fig. 5, five of the seven cells contained in the unit area are tumor cells, so the tumor cell content ratio is approximately 71% (=5 / 7 x 100).

[0026] [Embodiment 1] The first embodiment will be described with reference to Figures 6 to 7. In the first embodiment, the "tumor cell content ratio" refers to the ratio of tumor cells to the total cells contained in a region of interest (unit region).

[0027] (Inspection support device 10) The components of the test support device 10 according to the present embodiment 1 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing the configuration of the test support device 10. As shown in Fig. 6, the test support device 10 includes an acquisition unit 11, an estimation unit 12, a determination unit 13, and an output unit 14.

[0028] The acquiring unit 11 acquires image data of a pathological specimen. The acquiring unit 11 is an example of an acquiring means. In one example, the acquiring unit 11 acquires image data of a pathological specimen transmitted from a pathologist's terminal 200 (FIG. 1) to a server 300 (FIG. 1). The acquiring unit 11 outputs the acquired image data of the pathological specimen to the estimation unit 12.

[0029] The estimation unit 12 estimates the tumor cell content rate for each unit area in the region of interest in the image data of the pathological specimen. The region of interest is a region on the image data of the pathological specimen that the pathologist judges to have a higher tumor cell content rate compared to normal cells. In one example, the estimation unit 12 identifies the region of interest based on dots on the image data added by image editing software running on the pathologist's terminal 200 (FIG. 2). In this case, the estimation unit 12 may determine, as the region of interest, a region surrounded by lines that is created by connecting adjacent (i.e., nearest) dots with lines.

[0030] Furthermore, the estimation unit 12 estimates the tumor cell content ratio for each unit area in the region of interest in the image data using a classifier that has machine-learned the characteristics of cells. For example, the estimation unit 12 estimates the tumor cell content ratio in each unit area using a neural network that has learned a model of tumor cells, etc. Here, the estimation unit 12 may estimate the tumor cell content ratio using a related technology described in Patent Document 2.

[0031] The estimation unit 12 outputs, to the determination unit 13, information indicating the tumor cell content rate for each unit region in the region of interest in the image data.

[0032] The determining unit 13 determines an examination area within the region of interest based on the tumor cell content rate for each unit area within the region of interest. The determining unit 13 is an example of a determining means.

[0033] In one example, the determination unit 13 determines the examination area in the region of interest such that the sum average of the tumor cell content ratios of all unit areas included in the examination area is equal to or greater than a first threshold. In one specific example, the determination unit 13 determines the examination area in the region of interest such that the sum average of the tumor cell content ratios of all unit areas included in the examination area is equal to or greater than 30%. However, the first threshold may be determined arbitrarily.

[0034] In another example, the determination unit 13 determines the examination area within the region of interest such that the sum average of the indices of all unit areas included in the examination area is equal to or greater than a second threshold value. The "indices" here represent the magnitude of the tumor cell content rate of the unit area.

[0035] An example of the index will be described with reference to FIG. 3. In the example shown in FIG. 3, the unit areas are classified according to ranks corresponding to the magnitude of the tumor cell content ratio. Specifically, the unit areas are divided into six ranks: "0-10%", "10-20%, "20-30%, "30-40%, "40-50%", and "50-100%". "~%" represents the tumor cell content ratio. In this example, the rank corresponding to the tumor cell content ratio of the unit area corresponds to the index of the unit area.

[0036] In one specific example, the determination unit 13 may determine the inspection area within the region of interest such that the total average of the indices of all unit areas included in the inspection area is 4 or more out of 6. However, the second threshold value may be arbitrarily determined independently of the first threshold value.

[0037] In one variant, the determination unit 13 determines the inspection area based on at least one of a first condition regarding the proportion of tumor cells in the area of ​​interest, a second condition regarding the size of the area of ​​the inspection area, and a third condition regarding the shape of the contour of the inspection area.

[0038] For example, the second condition is that the area of ​​the inspection region is greater than the first lower limit, and the third condition is that the contour of the inspection region is a smooth curve. However, the second and third conditions are not limited to these.

[0039] The determining unit 13 outputs information indicating the inspection region within the region of interest to the output unit 14.

[0040] The output unit 14 outputs information indicating the inspection region. The output unit 14 is an example of an output means.

[0041] In one example, the output unit 14 receives information indicating an examination area within the region of interest from the determination unit 13. Then, the output unit 14 outputs the information indicating the examination area to the pathologist's terminal 200 (FIG. 1) via a local network or the Internet. In one example, the output unit 14 outputs image data of a pathological specimen indicating the tumor cell content rate per unit area within the region of interest to the pathologist's terminal 200. The output unit 14 adds a line indicating the examination area onto the output image data (FIG. 4). In this example, the line indicating the examination area added onto the image data of the pathological specimen corresponds to the information indicating the examination area. Alternatively, the output unit 14 may transmit information indicating the examination area to the pathologist's terminal 200 via a wireless or wired network, and cause the terminal 200 to display an image of the examination area exemplified in FIG. 4.

[0042] (Operation of the inspection support device 10) The operation of the test support device 10 according to the first embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the flow of execution number processing performed by each unit of the test support device 10.

[0043] 7, the acquisition unit 11 acquires image data (FIG. 2) of the pathological specimen (S1). The acquisition unit 11 outputs the image data of the pathological specimen to the estimation unit 12.

[0044] The estimation unit 12 estimates the tumor cell content rate for each unit area in the region of interest in the image data of the pathological specimen (S2). The estimation unit 12 outputs information indicating the tumor cell content rate in the region of interest to the determination unit 13.

[0045] The determination unit 13 determines an examination area within the region of interest based on the tumor cell content rate for each unit area within the region of interest (FIG. 3) (S3). The determination unit 13 outputs information indicating the examination area to the output unit 14.

[0046] The output unit 14 outputs information indicating the examination area (S4). The output unit 14 displays the information indicating the examination area on the screen of the pathologist's terminal. In one example, the output unit 14 displays a screen on the pathologist's terminal in which the examination area is illustrated by lines in the image data of the pathological specimen, as shown in FIG.

[0047] This completes the operation of the test support device 10.

[0048] (Effects of this embodiment) According to the configuration of this embodiment, the acquisition unit 11 acquires image data of a pathological specimen. The estimation unit 12 estimates the tumor cell content rate for each unit area in the region of interest in the image data of the pathological specimen. The determination unit 13 determines an examination area in the region of interest based on the tumor cell content rate for each unit area in the region of interest. The output unit 14 outputs information indicating the examination area. The examination area to be output is determined based on the tumor cell content rate for each unit area in the region of interest. In general, the higher the tumor cell content rate in the examination area, the more suitable the examination area is for dissection. Therefore, in genetic testing of somatic cells, an examination area suitable for dissection can be proposed.

[0049] (Hardware configuration) Each component of the test support device 10 described in the first embodiment is shown as a functional block. Some or all of these components are realized by an information processing device 900 as shown in Fig. 8. Fig. 8 is a block diagram showing an example of the hardware configuration of the information processing device 900.

[0050] As shown in FIG. 8, an information processing device 900 includes, for example, the following configuration.

[0051] ·CPU(Central Processing Unit)901 ROM (Read Only Memory) 902 ·RAM(Random Access Memory)903 Program 904 loaded into RAM 903 A storage device 905 for storing a program 904 A drive device 907 for reading and writing data from the recording medium 906 A communication interface 908 for connecting to a communication network 909 An input / output interface 910 for inputting and outputting data Bus 911 connecting each component Each of the components of the test support device 10 described in the first embodiment is realized by the CPU 901 reading and executing a program 904 that realizes these functions. The program 904 that realizes the functions of each component is, for example, stored in advance in the storage device 905 or the ROM 902, and is loaded into the RAM 903 and executed by the CPU 901 as necessary. The program 904 may be supplied to the CPU 901 via the communication network 909, or may be stored in advance in the recording medium 906, and the drive device 907 may read out the program and supply it to the CPU 901.

[0052] According to the above configuration, the test support device 10 described in the first embodiment is realized as hardware, and therefore it is possible to achieve the same effects as those described in the first embodiment.

[0053] Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above-mentioned embodiments (and examples). Various modifications that can be understood by a person skilled in the art can be made to the configurations and details of the above-mentioned embodiments (and examples) within the scope of the present invention.

[0054] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.

[0055] [Additional Notes] (Appendix 1) An acquisition means for acquiring image data of a pathological specimen; an estimation means for estimating a tumor cell content ratio for each unit area in a region of interest in the image data of the pathological specimen; a determining means for determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; an output means for outputting information indicating the inspection area; An inspection support device equipped with the above.

[0056] (Appendix 2) The determining means is The test area is determined based on a first condition regarding a tumor cell content rate in the test area. 2. The inspection support device according to claim 1,

[0057] (Appendix 3) The determining means is The test area is determined so that an average of an index based on a tumor cell content rate in the test area exceeds a first threshold value according to the first condition. 3. The inspection support device according to claim 2,

[0058] (Appendix 4) The determining means is The inspection area is determined based on at least one of a second condition related to the size of the area of ​​the inspection area and a third condition related to the shape of the outline of the inspection area in addition to the first condition. 4. The inspection support device according to claim 2 or 3.

[0059] (Appendix 5) The estimation means includes: Calculate an index based on the tumor cell content rate within the region of interest. 5. The inspection support device according to claim 1,

[0060] (Appendix 6) The output means includes: The tumor cell content rate for each unit area in the region of interest is displayed on the image. 6. The inspection support device according to claim 1,

[0061] (Appendix 7) The acquiring means acquires image data of the pathological specimen to which information indicating the region of interest has been added, The output means outputs information indicating the region of interest together with information indicating the inspection region. 7. The inspection support device according to claim 1,

[0062] (Appendix 8) The estimation means estimates the tumor cell content ratio for each unit area in the region of interest using a neural network that has learned a tumor model. 8. The inspection support device according to claim 1,

[0063] (Appendix 9) The information indicating the region of interest is added by an annotation. 8. The inspection support device according to claim 7,

[0064] (Appendix 10) The second condition is that the area of ​​the inspection region is greater than a second threshold value. 5. The inspection support device according to claim 4,

[0065] (Appendix 11) The third condition is that the contour of the inspection area is a smooth curve. 5. The inspection support device according to claim 4,

[0066] (Appendix 12) Acquire image data of the pathological specimen; Estimating a tumor cell content ratio for each unit area in a region of interest in the image data of the pathological specimen; determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; Outputting information indicating the inspection area Inspection support methods.

[0067] (Appendix 13) A process of acquiring image data of a pathological specimen; A process of estimating a tumor cell content ratio for each unit area in a region of interest in the image data of the pathological specimen; A process of determining an examination area within the region of interest based on the tumor cell content ratio within the region of interest; A process of outputting information indicating the inspection area; A non-transitory recording medium that records a program for causing a computer to execute the above. [Explanation of symbols]

[0068] 10. Inspection support equipment 11 Acquisition Department 12 Estimation part 13 Decision Section 14 Output section

Claims

1. An acquisition means for acquiring image data of a pathological specimen; an estimation means for estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; a determining means for determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; an output means for outputting information indicating the inspection area; Equipped with The determining means is The test area is determined based on a first condition related to the tumor cell content rate in the test area such that an average of an index based on the tumor cell content rate in the test area exceeds a first threshold value according to the first condition. Inspection support equipment.

2. An acquisition means for acquiring image data of a pathological specimen; an estimation means for estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; a determining means for determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; an output means for outputting information indicating the inspection area; Equipped with The determining means is The inspection area is determined based on at least one of a first condition related to the tumor cell content rate in the inspection area, a second condition related to the size of the area of ​​the inspection area, and a third condition related to the shape of the outline of the inspection area. Inspection support equipment.

3. The determining means is The examination area is determined so that an average of an index based on the tumor cell content rate in the examination area exceeds a first threshold value according to the first condition.

3. The inspection support device according to claim 2.

4. The determining means is The inspection area is determined based on at least one of a second condition related to the size of the area of ​​the inspection area and a third condition related to the shape of the outline of the inspection area in addition to the first condition.

2. The inspection support device according to claim 1.

5. The estimation means estimates the tumor cell content ratio for each unit area in a region of interest in image data of the pathological specimen.

5. The inspection support device according to claim 1,

6. The output means includes: The tumor cell content ratio in the region of interest is displayed on the image.

6. The inspection support device according to claim 1,

7. The acquiring means acquires image data of the pathological specimen to which information indicating the region of interest has been added, The output means outputs information indicating the region of interest together with information indicating the inspection region.

7. The inspection support device according to claim 1,

8. The estimation means estimates the tumor cell content ratio in the region of interest using a neural network that has learned a tumor model.

8. The inspection support device according to claim 1,

9. Acquire image data of the pathological specimen; Estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; An inspection support method for outputting information indicating the inspection area, When determining the inspection area, The test area is determined based on a first condition related to the tumor cell content rate in the test area such that an average of an index based on the tumor cell content rate in the test area exceeds a first threshold value according to the first condition. Inspection support methods.

10. Acquiring image data of a pathological specimen, Estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; determining an examination area within the region of interest based on the tumor cell content rate within the region of interest; An inspection support method for outputting information indicating the inspection area, When determining the inspection area, The inspection area is determined based on at least one of a first condition related to the tumor cell content rate in the inspection area, a second condition related to the size of the area of ​​the inspection area, and a third condition related to the shape of the outline of the inspection area. Inspection support methods.

11. A process of acquiring image data of a pathological specimen; A process of estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; A process of determining an examination area within the region of interest based on the tumor cell content ratio within the region of interest; A process of outputting information indicating the inspection area; A program for causing a computer to execute the above, In the process of determining the inspection area, the computer The inspection area is determined based on a first condition related to the tumor cell content rate in the inspection area such that an average of an index based on the tumor cell content rate in the inspection area exceeds a first threshold value according to the first condition. program.

12. A process for acquiring image data of a pathological specimen; A process of estimating a tumor cell content ratio in a region of interest in the image data of the pathological specimen; A process of determining an examination area within the region of interest based on the tumor cell content ratio within the region of interest; A process of outputting information indicating the inspection area; A program for causing a computer to execute the above, The inspection area is determined based on at least one of a first condition related to the tumor cell content rate in the inspection area, a second condition related to the size of the area of ​​the inspection area, and a third condition related to the shape of the outline of the inspection area. program.

Images