JP2018185265A - Information processing apparatus, control method, and program - Google Patents

Abstract

A new index that can be used for pathological diagnosis is obtained from pathological image data.
An information processing apparatus 2000 includes a layer (first layer 22) composed of normal gland ducts and a tumor gland duct from an image area (tissue area 20) representing a tissue included in pathological image data 10. The layer to be constructed (second layer 24) is detected. The information processing apparatus 2000 calculates an index value based on the detected first layer 22 and second layer 24. For example, the information processing apparatus 2000 calculates an index value based on the thicknesses of the first layer 22 and the second layer 24 or the detected areas of the first layer 22 and the second layer 24.
[Selection] Figure 1

Description

  The present invention relates to image analysis of pathological images.

  As one of methods for diagnosing humans and animals, pathological diagnosis using pathological images is performed. A pathological image is an image obtained by capturing a tissue of a human or animal body with a camera.

  A technique for detecting a lesion by performing image analysis on pathological image data (hereinafter referred to as pathological image data) has been developed. For example, Patent Document 1 discloses a technique for evaluating a deformity of a gland duct by the distribution of nuclei in the gland duct and outputting the evaluation result.

JP 2010-281636 A

  The index that can be used for pathological diagnosis is not only the deformity of the duct. The present inventor has found a new index that can be used for pathological diagnosis. One of the objects of the present invention is to provide a technique for obtaining a new index that can be used for pathological diagnosis from pathological image data.

  The information processing apparatus according to the present invention includes 1) a first layer composed of normal gland ducts and a tumor gland duct from a tissue region included in the pathological image data by performing image processing on the pathological image data. Detecting means for detecting the second layer; and 2) calculating means for calculating an index value based on the thickness or area of the first layer and the second layer.

  The control method of the present invention is executed by a computer. The control method includes: 1) image processing of pathological image data, so that a first layer composed of normal gland ducts and a second layer composed of tumor gland ducts from a tissue region included in the pathological image data And 2) a calculation step of calculating an index value based on the thickness or area of the first layer and the second layer.

  The program of this invention makes a computer perform each step which the control method of this invention has.

  According to the present invention, a technique for obtaining a new index that can be used for pathological diagnosis from pathological image data is provided.

FIG. 2 is a diagram conceptually illustrating an operation of the information processing apparatus according to the first embodiment. 2 is a block diagram illustrating a functional configuration of the information processing apparatus according to the first embodiment. FIG. It is a figure which illustrates the computer for implement | achieving information processing apparatus. 3 is a flowchart illustrating a flow of processing executed by the information processing apparatus according to the first embodiment. It is a flowchart which illustrates the flow of the process which detects the 1st layer and the 2nd layer from a tissue region. It is a figure which illustrates the effect of an expansion process. It is a figure which illustrates notionally pathological image data after determination whether it is a gland duct area | region is performed. It is a figure which illustrates the peripheral region of a closed region. It is a figure which illustrates notionally the method of detecting the pixel of the gland duct area | region of a tumor gland duct farthest from the surface of a tissue. It is a figure which illustrates the 1st layer. It is a figure which illustrates the 2nd layer. 6 is a diagram illustrating a functional configuration of an information processing apparatus according to a second embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same reference numerals are given to the same components, and the description will be omitted as appropriate. In each block diagram, unless otherwise specified, each block represents a functional unit configuration, not a hardware unit configuration.

[Embodiment 1]
FIG. 1 is a diagram conceptually illustrating the operation of the information processing apparatus 2000 according to the first embodiment. FIG. 1 merely shows an example of the operation for facilitating the understanding of the information processing apparatus 2000, and does not limit the functions of the information processing apparatus 2000 at all.

  The information processing apparatus 2000 performs image processing on the pathological image data 10. The pathological image data 10 is image data obtained by imaging a tissue in the body of a person to be diagnosed or another animal (hereinafter referred to as a patient) with a camera. More specifically, for example, the pathological image data 10 is obtained by collecting a tissue from a patient's body, enlarging the tissue with a microscope, and imaging the enlarged tissue with a camera.

  The information processing apparatus 2000 includes an image region (hereinafter referred to as a tissue region) representing a tissue included in the pathological image data 10, a layer composed of normal gland ducts (hereinafter referred to as a first layer), and a tumor gland duct. Layer (hereinafter referred to as second layer) is detected. For example, in the pathological image data 10 of FIG. 1, the first layer 22 and the second layer 24 are detected from the tissue region 20. Here, the tumor gland duct is defined as, for example, “a gland duct in which tumor cells have grown out of the proliferation part located in the gland neck”. In addition, because it is difficult to distinguish whether the gland duct is a tumor or non-tumor in the proliferative part, not all gland ducts containing tumors are treated as tumor gland ducts, but gland ducts containing many tumors are treated as tumor gland ducts. Good. Normal ducts are ducts other than tumor ducts.

  The information processing apparatus 2000 calculates an index value based on the detected first layer 22 and second layer 24. For example, the information processing apparatus 2000 calculates an index value based on the thicknesses of the first layer 22 and the second layer 24 or the detected areas of the first layer 22 and the second layer 24.

  Thus, according to the information processing apparatus 2000 of the present embodiment, the first layer 22 composed of normal gland ducts and the second layer 24 composed of tumor gland ducts are detected from the pathological image data 10, An index value based on the detected first layer 22 and second layer 24 is calculated. Thus, according to the information processing apparatus 2000 of the present embodiment, a new index that can be used for pathological diagnosis is provided.

  For example, the above index value can be used as an index for quantitatively expressing to what extent the tumor has infiltrated from the tissue surface (depth of infiltration). The depth of invasion is an important factor in evaluating the risk of metastasis / recurrence and selecting a treatment method, and it is clinically meaningful to express this quantitatively.

  Hereinafter, the present embodiment will be described in further detail.

<Example of functional configuration>
FIG. 2 is a block diagram illustrating the functional configuration of the information processing apparatus 2000. The information processing apparatus 2000 includes a detection unit 2020 and a calculation unit 2040. The detection unit 2020 performs image processing on the pathological image data 10, thereby causing the first layer 22 configured with normal gland ducts and the second layer configured with tumor gland ducts from the tissue region 20 included in the pathological image data 10. The layer 24 is detected. The calculation unit 2040 calculates an index value based on the detected first layer 22 and second layer 24.

<Example of Hardware Configuration of Information Processing Device 2000>
Each functional component of the information processing apparatus 2000 may be realized by hardware (eg, a hard-wired electronic circuit) that implements each functional component, or a combination of hardware and software (eg: It may be realized by a combination of an electronic circuit and a program for controlling it). Hereinafter, the case where each functional component of the information processing apparatus 2000 is realized by a combination of hardware and software will be further described.

  FIG. 3 is a diagram illustrating a computer 1000 for realizing the information processing apparatus 2000. The computer 1000 is an arbitrary type of computer. For example, the computer 1000 is a personal computer (PC), a server machine, a tablet terminal, or a smartphone. The computer 1000 may be a dedicated computer designed for realizing the information processing apparatus 2000 or a general-purpose computer.

  The computer 1000 includes a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. The bus 1020 is a data transmission path through which the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 transmit / receive data to / from each other. The processor 1040 is an arithmetic processing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 1060 is a main storage device realized by a RAM (Random Access Memory) or the like. The storage device 1080 is an auxiliary storage device realized by a hard disk, an SSD (Solid State Drive), a ROM, a memory card, or the like. However, the storage device 1080 may be realized by hardware similar to the hardware used for realizing the main storage device such as RAM.

  The input / output interface 1100 is an interface for connecting the computer 1000 and an input / output device. For example, a keyboard, a mouse, a display device, or the like is connected to the input / output interface 1100.

  The network interface 1120 is an interface for connecting to a communication network such as a WAN (Wide Area Network) or a LAN (Local Area Network).

  The storage device 1080 stores program modules that implement the functions of the information processing apparatus 2000. The processor 1040 reads each program module into the memory 1060 and executes it, thereby realizing each function corresponding to the program module.

<Process flow>
FIG. 4 is a flowchart illustrating the flow of processing executed by the information processing apparatus 2000 according to the first embodiment. The information processing apparatus 2000 acquires the pathological image data 10 (S102). The detection unit 2020 performs image processing on the pathological image data 10, thereby causing the first layer 22 configured with normal gland ducts and the second layer configured with tumor gland ducts from the tissue region 20 included in the pathological image data 10. The layer 24 is detected (S104). The calculation unit 2040 calculates an index value based on the detected first layer 22 and second layer 24 (S106).

<Acquisition of pathological image data 10: S102>
The information processing apparatus 2000 acquires the pathological image data 10 to be subjected to image analysis (S102). The method by which the information processing apparatus 2000 acquires the pathological image data 10 is arbitrary. For example, the information processing apparatus 2000 acquires the pathological image data 10 by accessing a storage device in which the pathological image data 10 is stored. The storage device in which the pathological image data 10 is stored may be provided inside the camera that generates the pathological image data 10 or may be provided outside the camera. Further, for example, the information processing apparatus 2000 may acquire the pathological image data 10 by receiving the pathological image data 10 transmitted from the camera.

<Detection of the first layer 22 and the second layer 24: S104>
The detection unit 2020 detects the first layer 22 and the second layer 24 from the tissue region 20 included in the pathological image data 10 (S104). The detection of the first layer 22 and the second layer 24 is performed, for example, according to the flow shown in FIG. FIG. 5 is a flowchart illustrating the flow of processing for detecting the first layer 22 and the second layer 24 from the tissue region 20.

  The detection unit 2020 extracts the tissue region 20 from the pathological image data 10 (S202). The detection unit 2020 extracts a region representing a gland duct (hereinafter referred to as a gland duct region) from the tissue region 20 (S204). The detection unit 2020 classifies each gland duct area extracted from the tissue area 20 into a gland duct area of a normal gland duct and a gland duct area of a tumor gland duct (S206). The detection unit 2020 detects the first layer 22 and the second layer 24 from the tissue region 20 based on the classification result in S206 (S208).

  Hereinafter, each step in the flowchart of FIG. 5 will be described in more detail.

<Extraction of tissue region 20: S202>
The detection unit 2020 extracts the tissue region 20 from the pathological image data 10 (S202). Here, it is assumed that the tissue included in the pathological image data 10 is stained with hematoxylin and eosin.

  In the pathological image data 10, image regions other than the tissue region 20 are portions that do not include stained tissue, and can be treated as so-called background regions. On the other hand, in the pathological image data 10, the tissue region 20 can be treated as a foreground region. Therefore, the detection unit 2020 performs background separation on the pathological image data 10 and extracts a foreground region obtained as a result as the tissue region 20.

  First, the detection unit 2020 performs color correction (for example, gamma correction) on the pathological image data 10 so that the variation in staining is reduced. Then, the detection unit 2020 divides the pathological image data 10 into a foreground region and a background region, and extracts the foreground region as the tissue region 20. Various existing methods can be used as a specific method of background separation. Note that color correction of the pathological image data 10 is not necessarily performed.

  Here, the detection unit 2020 preferably performs an expansion process on the pathological image data 10 when performing background separation. FIG. 6 is a diagram illustrating the effect of the expansion process. In FIG. 6, when the background separation is performed without performing the expansion process, the recessed portion around the tissue surface is not included in the tissue region 20. On the other hand, when background separation is performed after the expansion process, a recessed portion around the tissue surface is also included in the tissue region 20. Therefore, by performing the expansion process, it is possible to prevent the ductal region existing in the recessed portion around the tissue surface from being excluded from the extraction target of the tubular region described later. That is, the ductal region on the tissue surface can be extracted by the processing described later.

<Extraction of gland duct region: S204>
The detection unit 2020 extracts a gland duct region from the tissue region 20 (S204). For this purpose, the detection unit 2020 first extracts a line (hereinafter referred to as a candidate boundary line) that is presumed to be a boundary line of the ductal region from the tissue region 20. The tissue region 20 includes one or more closed regions surrounded by the candidate boundary lines extracted here. Therefore, the detection unit 2020 determines whether each of the one or more closed regions is a gland duct region. Then, the detection unit 2020 extracts the closed area determined to be a ductal duct area as the ductal duct area.

<< Extraction of candidate boundary lines >>
The detection unit 2020 performs edge detection for detecting an edge included in the tissue region 20 and extracts the detected edge as a candidate boundary line. Here, an image region stained with hematoxylin is treated as an edge. For example, the detection unit 2020 converts the pathological image data 10 into an image composed of four values of hematoxylin, eosin, white, and red (four values), thereby staining the pathological image data 10 with hematoxylin. Get the image area. An existing technique can be used as a specific method of edge detection.

  At the time of edge detection, the detection unit 2020 may perform processing for enhancing an edge using an edge enhancement filter. As a result, for example, even when a part of the borderline of the ductal region is cut off, it is possible to connect the disconnected part. It can be detected from the data 10.

  The strength of edge enhancement (parameter of edge enhancement filter) may be statically determined in advance or may be dynamically determined by the detection unit 2020. In the latter case, the detection unit 2020 uses the information obtained from the pathological image data 10 to determine the strength of edge enhancement. For example, the detection unit 2020 determines the strength of edge enhancement based on the area Sh of the region stained with hematoxylin and the area Se of the region stained with eosin. More specifically, the strength of edge enhancement is increased as the value of Sh / (Sh + Se) is smaller. By doing so, the pathological image data 10 is corrected so that the smaller the portion stained with hematoxylin in the pathological image data 10, the larger the portion (the edge is emphasized).

  Here, it is preferable that the detection unit 2020 performs a process of removing an image region (hereinafter, a lymphocyte region) represented by a lymphocyte region from the tissue region 20 before extracting candidate boundary lines. This is because lymphocytes are also stained with hematoxylin, and the lymphocyte region may be extracted as an edge by the edge detection process.

  Various methods can be used for detecting the lymphocyte region from the pathological image data 10. For example, the detection unit 2020 detects a lymphocyte region from the pathological image data 10 using machine learning. Specifically, a detector that detects a lymphocyte region from image data is created in advance by using teacher data obtained by labeling the lymphocyte region. Then, the detection unit 2020 removes the lymphocyte region obtained by inputting the pathological image data 10 to the detector from the pathological image data 10. It is preferable to use deep learning for the machine learning.

<<< Determination of whether or not it is a gland duct area >>>
The detection unit 2020 determines whether each of the closed regions surrounded by the candidate boundary lines is a gland duct region. FIG. 7 is a diagram conceptually illustrating the pathological image data 10 after the determination as to whether or not the region is a gland duct region. In FIG. 7, the closed region 30 is a region surrounded by a dotted line frame, and the gland duct region 32 is a region surrounded by a solid line frame. In FIG. 7, a part of the closed region 30 included in the pathological image data 10 is detected as a gland duct region 32.

  The determination as to whether or not the closed region 30 is the gland duct region 32 is realized using, for example, machine learning. For example, a discriminator for identifying whether or not the closed region is a gland duct region is created by using image data obtained by labeling the gland duct region as teacher data. The discriminator is realized as a support vector machine, for example.

  The discriminator discriminates whether or not the closed region 30 is a gland duct region based on the feature amount obtained from inside or around the closed region 30. For example, the feature amount includes 1) a ratio of the area of the lymphocyte region in the closed region 30, 2) a ratio of the area of the white region in the closed region 30, and 3) a ratio of the area of the interstitial region in the closed region 30. 4) Proportion of cytoplasm area in the closed region 30 5) Proportion of area of the gray region in the white region in the closed region 30 6) Proportion of area of the lymphocyte region in the peripheral region of the closed region 30 and 7 ) Any one or more of the ratios of the area of the cell nucleus region in the peripheral region of the closed region 30 can be used. The peripheral area will be described later.

  Here, the white region in the closed region 30 is an image region composed of pixels having a luminance equal to or higher than a predetermined first threshold among the pixels included in the closed region 30. For example, the detection unit 2020 uses the pathological image data 10 that has been subjected to the quaternarization described above, and extracts an area composed of white pixels included in the quaternarized closed area 30 as a white area. The first threshold value can be an arbitrary value. The first threshold value may be set in advance in the detection unit 2020 or may be stored in a storage device accessible from the detection unit 2020.

  The gray region in the closed region 30 is an image region composed of pixels having luminances equal to or higher than the first threshold and lower than or equal to the second threshold among the pixels included in the closed region 30. That is, the gray area is an image area composed of pixels with relatively low luminance among the pixels constituting the white area. The second threshold value can be any value equal to or greater than the first threshold value. The second threshold value may be set in advance in the detection unit 2020 or may be stored in a storage device accessible from the detection unit 2020.

  The interstitial region in the closed region 30 is, for example, a region obtained as follows. First, the detection unit 2020 obtains an image region stained with eosin from the pathological image data 10 by binarizing the pathological image data 10 into an image including four values of hematoxylin, eosin, white, and red. . However, when an image obtained by converting the pathological image data 10 into a four-value has already been generated, the image can be used. Then, the detection unit 2020 selects an image area whose hue value is equal to or greater than a predetermined threshold among the image areas stained with eosin, and which is in the closed area 30, as an interstitial area in the closed area 30. Get as.

  The threshold value may be a predetermined value or a dynamically determined value. In the latter case, for example, the detection unit 2020 determines the threshold value as follows. First, the detection unit 2020 calculates an average color of a plurality of pixels (for example, 100 pixels) in the cell nucleus region. The average color is a color composed of an average value of R values, an average value of G values, and an average value of B values of a plurality of pixels in the cell nucleus region. The detection unit 2020 calculates the Euclidean distance in the three-dimensional coordinates composed of the R value, the G value, and the B value for the color of each pixel of the pathological image data 10 and the average color. Then, normalization is performed so that the Euclidean distance is in the range of 0 to 255. Image data composed of values obtained by normalizing the Euclidean distance calculated for each pixel in this way is referred to as distance image data. The detection unit 2020 identifies an image region S composed of pixels smaller than a predetermined value for the distance image data.

  Furthermore, the detection unit 2020 identifies an image region R that is stained with eosin and whose hue is greater than the threshold value t for the pathological image data 10. The detection unit 2020 repeatedly specifies the image region R while reducing the threshold value t so that the image regions R and S overlap each other. Then, the threshold value t when the image regions R and S overlap or the threshold value t just before the overlap are set as threshold values for obtaining the interstitial region in the closed region 30. The initial value of the threshold value t is, for example, the maximum hue value.

  Here, the image area S obtained from the distance image data represents a roughly estimated gland duct area. Therefore, according to the above-described method, an eosin region having a high hue and a region that does not overlap with the roughly estimated gland duct region can be obtained as the stroma region.

  The cytoplasm region in the closed region 30 is a portion of the region in the closed region 30 excluding the stroma region.

  The peripheral region of the closed region 30 is defined as a region having a predetermined width surrounding the closed region 30, for example. FIG. 8 is a diagram illustrating a peripheral region of the closed region 30. In FIG. 8, the peripheral region 40 is a region having a width d surrounding the closed region 30.

  The method for specifying the lymphocyte region is as described above. The cell nucleus region in the peripheral region 40 is a region obtained by removing the lymphocyte region from the peripheral region 40.

<Classification of gland duct area: S206>
The detection unit 2020 classifies the extracted duct area 32 into a normal duct area and a tumor duct area (S206). Therefore, the detection unit 2020 determines whether each cell nucleus included in the peripheral region 40 of one gland duct region 32 is a normal cell nucleus or a tumor cell nucleus. Based on the number of cell nuclei of normal cells and the number of cell nuclei of tumor cells contained in the peripheral region 40 of a certain duct region 32, the detection unit 2020 determines that the duct region 32 is a normal duct region. Identify which is the tumor ductal area.

  Various methods can be used as a method for discriminating the nucleus of normal cells from the nucleus of tumor cells. For example, machine learning can be used for this identification. In this case, for example, by using each of the image data representing the cell nucleus of the normal cell and the image data representing the cell nucleus of the tumor cell as teacher data, a discriminator for discriminating between the cell nucleus of the normal cell and the cell nucleus of the tumor cell in advance is used. Make up. Then, the detection unit 2020 inputs the peripheral region 40 of the gland duct region 32 to the discriminator, so that each cell nucleus included in the peripheral region 40 is either a normal cell nucleus or a tumor cell nucleus. An identification result is obtained. It is preferable to use deep learning for the machine learning.

  Here, the discriminator not only discriminates cell nuclei into normal cell nuclei and tumor cell nuclei, but also cell nuclei 1) nuclei of lymphocytes, 2) nuclei of normal cells other than lymphocytes, 3) It may be identified as one of tumor cell nuclei. In this case, the discriminator can also be used to remove the lymphocyte region described above.

  Note that the method for identifying cell nuclei is not limited to a method using machine learning, and various existing methods can also be used.

  As described above, the detection unit 2020 determines that the gland duct region 32 is a normal gland duct based on the number of cell nuclei of normal cells and the number of cell nuclei of tumor cells included in the peripheral region 40 of the gland duct region 32. Identify whether the region is a tumor ductal region. There are various specific methods. For example, the detection unit 2020 calculates the ratio of the number of cell nuclei of normal cells included in the peripheral region 40 to the total number of cell nuclei included in the peripheral region 40 of the gland duct region 32. And the detection part 2020 discriminate | determines that the gland duct area | region 32 is a normal gland duct area | region, when the calculated ratio is more than predetermined value. On the other hand, when the calculated ratio is less than the predetermined value, the detection unit 2020 determines that the gland duct region 32 is a tumor gland duct region. Note that the number of cell nuclei of lymphocytes may be excluded from the “total number of cell nuclei contained in the peripheral region 40 of the gland duct region 32”.

  There are various methods for determining the predetermined value. For example, the predetermined value is manually set based on the experience of a doctor. In addition, for example, the predetermined value is set using machine learning. In the latter case, for example, image data obtained by labeling whether the normal duct area or the tumor duct area is included in the image data of the duct area is used as teacher data, and the duct area included in the image data is The predetermined value for discriminating between the normal gland duct area and the tumor gland duct area is determined by counting the number of normal cell nuclei and the number of tumor cell nuclei detected from the surrounding area. .

<Detection of first layer 22 and second layer 24: S208>
The detection unit 2020 detects the first layer 22 and the second layer 24 from the tissue region 20 based on the classification result in S206 (S208). As described above, the first layer 22 is an image region composed of regions of normal gland ducts. On the other hand, the second layer 24 is an image region composed of a tumor gland duct region.

<< Detection of the first layer 22 >>
The detection unit 2020 identifies a boundary line between the normal gland duct area and the tumor gland duct area (hereinafter referred to as a first boundary line). The first boundary line is specified by the following method, for example.

  First, the detection unit 2020 determines, for each column of the pixel matrix constituting the pathological image data 10, pixels of the gland duct region of the tumor gland that are farthest from the tissue surface (the boundary line between the tissue region 20 and the background region). To detect. FIG. 9 is a diagram conceptually illustrating a method for detecting a pixel in a ductal region of a tumor duct that is farthest from the surface of a tissue. In FIG. 9, in the matrix of pixels constituting the pathological image data 10, there are three tumor gland duct areas and one normal gland duct area on the same column. Therefore, the detection unit 2020 determines the pixel at the lower end of the gland duct region (third gland duct region from the top) of the tumor gland farthest from the tissue surface as “the gland duct of the tumor gland farthest from the tissue surface”. This is detected as “region pixel”.

  The detection unit 2020 connects the pixels detected from each column by the above-described method, and identifies the first boundary line. For example, this connection is performed by linear interpolation.

  Here, it is preferable that the detection unit 2020 performs a process of smoothing the generated first boundary line. For example, this smoothing can be performed using various smoothing filters such as a Lowess filter.

  The detection unit 2020 includes an image region closed by the identified first boundary line and the outer frame of the tissue region 20 (boundary line between the tissue region 20 and the background region) as a gland duct region of a tumor gland duct. Detected as one layer 22. FIG. 10 is a diagram illustrating the first layer 22.

<< Detection of Second Layer 24 >>
In order to detect the second layer 24, the detection unit 2020 detects a boundary line between the gland duct region of the normal gland duct and the image region other than the gland duct region included in the tissue region 20 (hereinafter, the second boundary line). ) Is generated. The second boundary line can be generated by the following method, for example, in the same manner as the first boundary line. Specifically, the detection unit 2020 detects a pixel in the gland duct region of the normal gland duct that is farthest from the surface of the tissue for each column of the pixel matrix constituting the pathological image data 10. Next, the detection unit 2020 connects the pixels detected from each column to generate a second boundary line. Note that, similarly to the first boundary line, it is preferable to smooth the second boundary line.

  The detection unit 2020 detects the first boundary line, the second boundary line, and the image region closed by the outer frame of the tissue region 20 as the second layer 24. FIG. 11 is a diagram illustrating the second layer 24.

<Calculation of index value: S104>
The calculation unit 2040 calculates an index value based on the first layer 22 and the second layer 24 detected by the detection unit 2020. Various index values can be used. For example, the calculation unit 2040 calculates an index value based on the areas of the first layer 22 and the second layer 24 or the detected thicknesses of the first layer 22 and the second layer 24. In the former case, for example, the calculation unit 2040 calculates, as an index value, the ratio of the area of the first layer 22 to the area of the entire layer of the gland duct area (the area where the first layer 22 and the second layer 24 are combined). For example, if the area of the first layer 22 is S1, and the area of the second layer 24 is S2, the index value is S1 / (S1 + S2). In addition, for example, the calculation unit 2040 may use the ratio (S1 / S2) of the area of the first layer 22 to the area of the second layer 24 as an index value.

  On the other hand, when calculating the index value from the thicknesses of the first layer 22 and the second layer 24, for example, the information processing apparatus 2000 uses the thickness of the first layer 22 relative to the thickness of the entire layer of the gland duct region as the index value. calculate. For example, if the thickness of the first layer 22 is T1, and the thickness of the entire gland duct region is Ta, the index value is T1 / Ta. In addition, for example, the calculation unit 2040 may use the ratio (T1 / T2) of the thickness T1 of the first layer 22 to the thickness T2 of the second layer 24 as an index value.

  Here, there are various methods for determining the thickness of the layer. For example, the calculation unit 2040 calculates the thickness of the first layer 22 for each column in the pixel matrix constituting the pathological image data 10, and calculates a statistical value (average value, maximum value, or thickness) of each calculated column. The minimum value is set as the thickness of the first layer 22. The same applies to the thickness of the second layer 24 and the thickness of the entire layer of the ductal region.

  The index value does not necessarily have to be expressed as a ratio or a ratio. For example, the information processing apparatus 2000 may use the area and thickness of the first layer 22 and the first layer 22 as an index value.

[Embodiment 2]
FIG. 12 is a block diagram illustrating an information processing apparatus 2000 according to the second embodiment. Except for the items described below, the information processing apparatus 2000 according to the second embodiment is the same as the information processing apparatus 2000 according to the first embodiment.

  The information processing apparatus 2000 according to the second embodiment includes an output control unit 2060. Based on the index value calculated by the calculation unit 2040, the output device is caused to perform a predetermined output.

  The output control unit 2060 may always output the index value calculated by the calculation unit 2040, or may output the index value only when the calculated index value satisfies a predetermined condition. For example, the predetermined condition is when the index value is equal to or greater than a predetermined threshold, or when the index value is equal to or less than the predetermined threshold.

  The relationship between the index value and the threshold value depends on what value the index value is calculated as. For example, when the area or thickness of the layer (first layer 22) of the gland duct region of the tumor gland duct is used as the index value with respect to the area or thickness of the whole layer of the gland duct region, the tumor gland duct is used as the tissue region 20 The index value tends to increase as the amount of increases. Therefore, for example, when the condition that “the index value is equal to or greater than a predetermined threshold” is satisfied, the output control unit 2060 outputs the index value.

  The predetermined threshold value may be set in advance in the output control unit 2060 or may be stored in a storage device accessible from the output control unit 2060.

  There are various modes in which the output control unit 2060 outputs the index value. For example, the output control unit 2060 displays the index value on the display screen of the display device. In this case, the output control unit 2060 controls the display device. In addition, for example, the output control unit 2060 outputs an index value with sound from a speaker. In this case, the output control unit 2060 controls the speaker. In addition, for example, the output control unit 2060 stores the index value in the storage device. In this case, the output control unit 2060 controls the storage device.

  The index value may be output as it is as raw data, or may be processed and output. In the latter case, for example, the output control unit 2060 collectively outputs a plurality of calculated index values in the form of a table or a graph. For example, it is assumed that the calculation unit 2040 calculates an index value using each of a plurality of pathological image data 10 obtained from the same patient. In this case, the output control unit 2060 creates a table or a graph with each index value calculated using the plurality of pathological image data 10. In addition, for example, the output control unit 2060 creates a table or a graph with one or more index values calculated in the past for the same patient.

  In addition, for example, the output control unit 2060 may be configured to output a predetermined message (for example, a warning message) when the index value satisfies the predetermined condition described above.

<Hardware configuration>
The hardware configuration of a computer that implements the information processing apparatus 2000 according to the second embodiment is represented by, for example, FIG. However, the storage device 1080 of the computer 1000 that implements the information processing apparatus 2000 of this embodiment further stores a program module that implements the functions of the information processing apparatus 2000 of this embodiment. In addition, various hardware (display device, speaker, etc.) controlled by the output control unit 2060 may be connected to the input / output interface 1100 of the computer 1000 that implements the information processing apparatus 2000 of the present embodiment.

  As mentioned above, although embodiment of this invention was described with reference to drawings, these are illustrations of this invention, The combination of said each embodiment or various structures other than the above can also be employ | adopted.

A part or all of the above-described embodiment can be described as in the following supplementary notes, but is not limited thereto.
1. Detecting means for detecting a first layer composed of normal gland ducts and a second layer composed of tumor gland ducts from a tissue region included in the pathological image data by performing image processing on the pathological image data; ,
An information processing apparatus comprising: calculation means for calculating an index value based on the thickness or area of the first layer and the second layer.
2. The detection means includes
Extracting a plurality of gland duct regions from the tissue region, and determining whether each of the plurality of gland duct regions extracted is a normal gland duct region or a tumor gland duct region;
1. Calculate the boundary between the first layer and the second layer using the position of each normal gland duct area and the position of each tumor gland duct area; The information processing apparatus described in 1.
3. 1. The process of determining whether the gland duct area is a normal gland duct area or a tumor gland duct area is performed using deep learning. The information processing apparatus described in 1.
4). The tissue region is an image region of a tissue stained with hematoxylin,
The detection means extracts a closed region surrounded by an image region stained with hematoxylin from the tissue region, and determines whether the closed region is the gland duct region based on the feature of the closed region To extract the gland duct region. Or 3. The information processing apparatus described in 1.
5. The characteristics of the closed region are the ratio of the lymphocyte region in the closed region, the ratio of the white region in the closed region, the ratio of the gray region in the white region, the ratio of the stroma region in the closed region, the cytoplasm in the closed region 3. including any one or more of a region ratio, a lymphocyte region ratio around the closed region, and a cell nucleus region ratio around the closed region; The information processing apparatus described in 1.
6). 3. The detection means removes a lymphocyte region from the tissue region and extracts the closed region from the tissue region from which the lymphocyte region has been removed. Or 5. The information processing apparatus described in 1.
7). 5. The process of removing the lymphocyte region is performed using deep learning. The information processing apparatus described in 1.
8). The tissue region is an image region of a tissue subjected to hematoxylin and eosin staining,
The detection means includes
Based on the ratio of the image area stained with hematoxylin and the image area stained with eosin, the enhancement of the image area stained with hematoxylin is performed,
3. Extracting the closed region from the pathological image data after the enhancement processing is performed. To 7. The information processing apparatus according to any one of the above.
9. 1. Output control means for performing a predetermined output when the index value calculated by the calculation means satisfies a predetermined condition. To 8. The information processing apparatus according to any one of the above.

10. A control method executed by a computer,
A detection step of detecting a first layer composed of a normal gland duct and a second layer composed of a tumor gland duct from a tissue region included in the pathological image data by performing image processing on the pathological image data; ,
A control method comprising: calculating an index value based on a thickness or an area of the first layer and the second layer.
11. In the detection step,
Extracting a plurality of gland duct regions from the tissue region, and determining whether each of the plurality of gland duct regions extracted is a normal gland duct region or a tumor gland duct region;
9. Calculate the boundary between the first layer and the second layer by using the position of each normal duct and the position of each tumor duct. The control method described in 1.
12 10. The process of determining whether the gland duct area is a normal gland duct area or a tumor gland duct area is performed using deep learning. The control method described in 1.
13. The tissue region is an image region of a tissue stained with hematoxylin,
In the detection step, a closed region surrounded by an image region stained with hematoxylin is extracted from the tissue region, and whether or not the closed region is the gland duct region is determined based on the feature of the closed region. 10. to extract the gland duct region. Or 12. The control method described in 1.
14 The characteristics of the closed region are the ratio of the lymphocyte region in the closed region, the ratio of the white region in the closed region, the ratio of the gray region in the white region, the ratio of the stroma region in the closed region, the cytoplasm in the closed region 12. One or more of a region ratio, a lymphocyte region ratio around the closed region, and a cell nucleus region ratio around the closed region are included. The control method described in 1.
15. 12. In the detection step, a lymphocyte region is removed from the tissue region, and the closed region is extracted from the tissue region from which the lymphocyte region has been removed; Or 14. The control method described in 1.
16. 15. The process of removing the lymphocyte region is performed using deep learning. The control method described in 1.
17. The tissue region is an image region of a tissue subjected to hematoxylin and eosin staining,
In the detecting step,
Based on the ratio of the image area stained with hematoxylin and the image area stained with eosin, the enhancement of the image area stained with hematoxylin is performed,
12. extracting the closed region from the pathological image data after the enhancement processing; To 16. The control method as described in any one.
18. 10. an output control step of performing a predetermined output when the index value calculated in the calculation step satisfies a predetermined condition; To 17. The control method as described in any one.

19. 10. To 18. A program for causing a computer to execute each step of the control method according to any one of the above.

10 pathological image data 20 tissue region 22 first layer 24 second layer 30 closed region 32 gland duct region 40 peripheral region 1000 computer 1020 bus 1040 processor 1060 memory 1080 storage device 1080 storage device 1100 input / output interface 1120 network interface 2000 information processing Device 2020 Detection unit 2040 Calculation unit 2060 Output control unit

Claims (11)

Detecting means for detecting a first layer composed of normal gland ducts and a second layer composed of tumor gland ducts from a tissue region included in the pathological image data by performing image processing on the pathological image data; ,
An information processing apparatus comprising: calculation means for calculating an index value based on the thickness or area of the first layer and the second layer. The detection means includes
Extracting a plurality of gland duct regions from the tissue region, and determining whether each of the plurality of gland duct regions extracted is a normal gland duct region or a tumor gland duct region;
The information processing apparatus according to claim 1, wherein a boundary between the first layer and the second layer is calculated using a position of each normal gland duct region and a position of each tumor gland duct region.   The information processing apparatus according to claim 2, wherein the process of determining whether the gland duct area is a normal gland duct area or a tumor gland duct area is performed using deep learning. The tissue region is an image region of a tissue stained with hematoxylin,
The detection means extracts a closed region surrounded by an image region stained with hematoxylin from the tissue region, and determines whether the closed region is the gland duct region based on the feature of the closed region The information processing apparatus according to claim 2, wherein the gland duct region is extracted.   The characteristics of the closed region are the ratio of the lymphocyte region in the closed region, the ratio of the white region in the closed region, the ratio of the gray region in the white region, the ratio of the stroma region in the closed region, the cytoplasm in the closed region The information processing apparatus according to claim 4, comprising any one or more of a region ratio, a lymphocyte region ratio around the closed region, and a cell nucleus region ratio around the closed region.   The information processing apparatus according to claim 4, wherein the detection unit removes a lymphocyte region from the tissue region and extracts the closed region from the tissue region from which the lymphocyte region has been removed.   The information processing apparatus according to claim 6, wherein the process of removing the lymphocyte region is performed using deep learning. The tissue region is an image region of a tissue subjected to hematoxylin and eosin staining,
The detection means includes
Based on the ratio of the image area stained with hematoxylin and the image area stained with eosin, the enhancement of the image area stained with hematoxylin is performed,
The information processing apparatus according to claim 4, wherein the closed region is extracted from the pathological image data after the enhancement process is performed.   The information processing apparatus according to claim 1, further comprising: an output control unit that performs a predetermined output when the index value calculated by the calculation unit satisfies a predetermined condition. A control method executed by a computer,
A detection step of detecting a first layer composed of a normal gland duct and a second layer composed of a tumor gland duct from a tissue region included in the pathological image data by performing image processing on the pathological image data; ,
A control method comprising: calculating an index value based on a thickness or an area of the first layer and the second layer.   The program which makes a computer perform each step of the control method of Claim 10.

Images