JP6059444B2 - Image processing apparatus and method, and program - Google Patents

Description

  The present technology relates to an image processing apparatus and method, and a program, and more particularly, to an image processing apparatus and method, and a program that enable more accurate diagnosis.

  Conventionally, there is an image recognition technique for detecting a lesion site such as a tumor from a pathological image obtained by imaging a human organ or the like.

  For example, a technique for accurately detecting a notable cell tissue region by setting a cell tissue region using a pre-learned cell tissue detector based on the luminance difference feature amount of each pixel of a pathological image (See Patent Document 1).

JP 2011-215061 A

  By the way, pathological images obtained by tomographic imaging of a three-dimensional human body are different images depending on how to take a cross section (angle and depth).

  For example, the cross-sectional image 2A of the cross-section A of the cell tissue 1 shown in FIG. It may be visible.

  In FIG. 1, it is assumed that a cross-sectional image 2A is an image that is determined not to have cancer (malignant tumor), and a cross-sectional image 2B is an image that is determined to have cancer. Even if a certain cross section of the cellular tissue in the same part is a cross section like the cross sectional image 2B, if the other cross section is a cross section like the cross sectional image 2A, the doctor may indicate that the cellular tissue is cancerous. Can be diagnosed as not.

  However, when the doctor observes only the cross-sectional image 2B, the cell tissue makes a diagnosis that there is a possibility of cancer.

  Thus, depending on how the cross-section of the pathological image is taken, there is a risk that the doctor makes an apologetic diagnosis.

  This technique is made in view of such a situation, and makes it possible to perform a more accurate diagnosis.

An image processing apparatus according to an aspect of the present technology provides a plurality of cross-sectional images each representing a cross-section in a plurality of directions with respect to one predetermined region selected by a user in a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space. An evaluation value acquisition unit that acquires an evaluation value representing the likelihood of cancer of the cross-sectional image , and a display control unit that controls display so as to display a predetermined cross-sectional image among the plurality of cross-sectional images according to the evaluation value with the door, the display control unit, said three-dimensional image wherein the predetermined cross-section on one of the predetermined region selected by the user, of a plurality of said cross-sectional images, the evaluation value is highest rather most Ganrashii a first cross-sectional image, the evaluation value is displayed alternately and second cross-sectional image implausible low Ku most cancers.

From the 3-dimensional image, wherein further provided block extraction section for extracting a pixel block including a predetermined area, the evaluation value acquiring unit, the cross-sectional image representing a plurality of cross-section of the pixel block, thereby obtaining the evaluation value be able to.

  The display control unit can display a third cross-sectional image among the plurality of cross-sectional images between the first cross-sectional image and the second cross-sectional image.

  The third cross-sectional image may be an interpolation image that interpolates between the first cross-sectional image and the second cross-sectional image.

The evaluation value acquisition unit can acquire the evaluation value for the cross-sectional image representing an arbitrary cross-section included in the pixel block.

  Based on the evaluation value acquired by the evaluation value acquisition unit, a cross-section estimation unit that estimates a cross-sectional image of a cross-section from which the evaluation value has not been acquired is further provided, and the display control unit includes the cross-section estimation unit. A predetermined cross-sectional image of the estimated cross-sectional images can be displayed.

  The evaluation value can represent the cancer-likeness of the cellular tissue in an image targeting cellular tissue of a predetermined part of the human body.

An image processing method according to an aspect of the present technology evaluates each cross-sectional image of a plurality of cross-sectional images representing cross-sections in a plurality of directions with respect to a predetermined region of a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space. An image of an image processing apparatus comprising: an evaluation value acquisition unit that acquires an evaluation value of the image; and a display control unit that controls display so as to display a predetermined cross-sectional image of the plurality of cross-sectional images according to the evaluation value A processing method, wherein the image processing apparatus is configured to obtain a plurality of cross-sectional images representing cross sections in a plurality of directions for one predetermined area selected by a user in a predetermined cross section of a three-dimensional image representing an object in a three-dimensional space. each obtains an evaluation value representing the cancer likelihood of cross-sectional images, on one of the predetermined region selected by the user in the predetermined cross-section of the three-dimensional image, double Wherein one of the cross-sectional image, the step of displaying the first sectional image seems highest rather most cancer the evaluation value, and a second cross-sectional images the evaluation value is not plausible low Ku most cancers in alternating including.

A program according to an aspect of the present technology is provided for a plurality of cross-sectional images representing a plurality of cross-sectional images representing a cross-section in a plurality of directions for one predetermined region selected by a user in a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space An evaluation value acquisition step for acquiring an evaluation value representing the cancer-likeness of the image , and a display control step for controlling display so as to display a predetermined cross-sectional image among the plurality of cross-sectional images according to the evaluation value. The display control step is configured such that the evaluation value of the plurality of cross-sectional images is calculated on one predetermined area selected by the user in the predetermined cross-section of the three-dimensional image. highest rather the most cancers seems first cross-sectional image, the evaluation value is displayed alternately and second cross-sectional image implausible low Ku most cancers.

In one aspect of the present technology, each of the cross- sectional images representing a plurality of cross-sectional images representing a cross-section in a plurality of directions with respect to one predetermined region selected by the user in a predetermined cross-section of the three-dimensional image representing the object in the three-dimensional space. An evaluation value representing the likelihood of cancer is acquired, a predetermined cross-sectional image of a plurality of cross-sectional images is displayed according to the evaluation value, and on one predetermined area selected by the user in a predetermined cross-section of the three-dimensional image in, of the plurality of cross-sectional images, a first cross-sectional image seems highest rather most cancer evaluation value, a second cross-sectional image evaluation value is not plausible low Ku most cancers are alternately displayed .

  According to one aspect of the present technology, more accurate diagnosis can be performed.

It is a figure which shows the example of the cross-sectional image of a cell tissue. It is a block diagram which shows the structural example of the information processing apparatus to which this technique is applied. It is a block diagram which shows the functional structure of CPU. It is a flowchart explaining a cross-section display process. It is a figure explaining selection of a field. It is a figure explaining selection of a field. It is a figure explaining a pixel block. It is a figure explaining the cross section of a pixel block. It is a figure explaining the example of a display of a section picture. It is a figure explaining the example of a display of a section picture. It is a figure explaining the example of a display of a section picture. It is a figure explaining the example of a display of a section picture. It is a block diagram which shows the other functional structure of CPU. It is a flowchart explaining a cross-section display process. It is a block diagram which shows the further another functional structure of CPU. It is a flowchart explaining a cross-section display process.

  Hereinafter, embodiments of the present technology will be described with reference to the drawings.

[Configuration of image processing device]

  FIG. 2 is a block diagram illustrating a configuration example of the image processing apparatus. The image processing apparatus 11 is configured by a personal computer, for example.

  In the image processing apparatus 11, a CPU (Central Processing Unit) 21, a ROM (Read Only Memory) 22, and a RAM (Random Access Memory) 23 are connected to each other by a bus 24.

  An input / output interface 25 is further connected to the bus 24. An input unit 26, an output unit 27, a storage unit 28, a communication unit 29, and a drive 30 are connected to the input / output interface 25.

  The input unit 26 includes a keyboard, a mouse, a microphone, and the like. The output unit 27 includes a display, a speaker, and the like. The storage unit 28 includes a hard disk, a nonvolatile memory, and the like. The communication unit 29 includes a network interface or the like. The drive 30 drives a removable medium 31 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

  In the image processing apparatus 11 configured as described above, the CPU 21 loads, for example, a program stored in the storage unit 28 to the RAM 23 via the input / output interface 25 and the bus 24 and executes the program. A predetermined process is executed.

  In the image processing apparatus 11, for example, the program can be installed in the storage unit 28 via the input / output interface 25 by mounting the removable medium 31 as a package medium or the like on the drive 30. The program can be received by the communication unit 29 via a wired or wireless transmission medium and installed in the storage unit 28. In addition, the program can be installed in the ROM 22 or the storage unit 28 in advance.

  Next, the functional configuration of the CPU 21 will be described. FIG. 3 is a block diagram showing a functional configuration of the CPU 21.

  As shown in FIG. 3, the CPU 21 includes a cross-section setting unit 51, a region selection unit 52, a block extraction unit 53, an evaluation value calculation unit 54, and a display control unit 55. Each unit has a function of exchanging information as necessary.

  The cross section setting unit 51 sets a predetermined cross section for a three-dimensional image representing an object in a three-dimensional space.

  The region selection unit 52 selects a predetermined region in the cross section set for the three-dimensional image by the cross section setting unit 51.

  The block extraction unit 53 extracts a three-dimensional pixel block corresponding to the region selected by the region selection unit 52 from the three-dimensional image.

  The evaluation value calculation unit 54 calculates an evaluation value for evaluating each of the cross-sectional images representing a predetermined cross-section of the pixel block extracted by the block extraction unit 53. In other words, the evaluation value calculation unit 54 calculates evaluation values for a plurality of images targeting a predetermined portion (portion included in the pixel block) of the object in the three-dimensional space.

  The display control unit 55 controls display on the display as the output unit 27. In particular, the display control unit 55 controls the display of a predetermined image among the plurality of cross-sectional images for which the evaluation value is calculated according to the evaluation value by the evaluation value calculation unit 54.

[Cross-section display processing by image processing device]
Next, the cross-sectional display process by the image processing apparatus 11 will be described with reference to the flowchart of FIG. According to this cross-sectional display processing, for example, a predetermined three-dimensional image of a human body such as a CT image obtained by a CT (Computerized Tomography) scanner or an MRI (Magnetic Resonance Imaging) image supplied via the communication unit 29 is used. A section of the cell tissue is displayed on the display as the output unit 27.

  In step S11, the cross section setting unit 51 sets a predetermined cross section for the three-dimensional image of the human body. The cross section set here may be a cross section at the time of tomography in which a three-dimensional image is obtained, or may be a cross section on a plane determined in advance in a three-dimensional space. Moreover, the cross section selected by the user (doctor) may be sufficient. The set cross-sectional image is displayed on a display as the output unit 27.

  In step S <b> 12, the region selection unit 52 selects a region including a cancerous (malignant) cell tissue in the cross section of the three-dimensional image set by the cross section setting unit 51.

  For example, as shown in FIG. 5, the region selected by the region selection unit 52 is an input unit for a cell tissue that the user has determined to be cancerous in the cross-sectional image 81 set by the cross-section setting unit 51. The area 83 is formed by the mouse pointer 82 in response to the user's operation (drag) on the mouse 26.

  In addition, as shown in FIG. 6, the region selected by the region selection unit 52 includes a cellular tissue having the highest score calculated by using a cancer detector learned in advance in the cross-sectional image 81. The region 83 may be used. In this case, the region 83 is selected by the mouse pointer 82 in response to a user operation (click) on the mouse as the input unit 26. In this case, the size of the region 83 may be determined by a cancer detector or may be determined by a user operation. In addition, the calculation of the score using a cancer detector shall use the method currently disclosed by patent document 1, for example.

  5 and 6, the region 83 is rectangular, but may be another shape such as a circle or an ellipse.

  Returning to the flowchart of FIG. 4, in step S <b> 13, the block extraction unit 53 extracts a pixel block including the region selected by the region selection unit 52 from the three-dimensional image. That is, the block extraction unit 53 extracts a pixel block including a cancerous cell tissue from the three-dimensional image.

  Specifically, for example, as shown in FIG. 7, a rectangular parallelepiped 91 obtained by extending a region 83 in a cross-sectional image 81 of a three-dimensional image in the normal direction on the upper surface side and the lower surface side of the cross-sectional image 81 A block (hereinafter referred to as a pixel block 91) is extracted from the three-dimensional image. Here, the three-dimensional image is a set of tomographic images obtained by tomography, and all the pixels of each tomographic image are elements of a three-dimensional matrix. This element is a pixel (so-called voxel) on the three-dimensional image, and has coordinates in the three-dimensional space. That is, the pixel block is also composed of voxels, and the pixel block is designated and extracted by the position (coordinates) in the three-dimensional space of the pixel (voxel) constituting the pixel block.

  Note that the shape of the pixel block is not limited to a rectangular parallelepiped, and may be a sphere or an ellipsoid depending on the shape of the region 83.

  In step S <b> 14, the evaluation value calculation unit 54 calculates an evaluation value representing the likelihood of cancer for a cross-sectional image representing an arbitrary cross-section of the pixel block extracted by the block extraction unit 53. Specifically, in the pixel block 91, the evaluation value calculation unit 54 represents a cross section representing a cross section in a plurality of directions with the region 83 as a reference (in other words, with a cancerous cell tissue included in the pixel block 91 as a reference). An evaluation value is calculated for the image. An arbitrary cross section in the pixel block 91 is designated by the position of a voxel constituting the pixel block, and is set using, for example, an arbitrary cross section reconstruction (MPR) technique in a CT image.

  Specifically, in the pixel block 91 shown in FIG. 8, when the image of the region 83 is a cross-sectional image S0 representing a reference cross-section, the evaluation value calculation unit 54 determines the midpoint of the two long sides of the region 83. Evaluation values are calculated for the cross-sectional image Sm and the cross-sectional image Sn obtained by rotating the cross-sectional image S0 around the connected line segment L. The number of cross-sectional images obtained by rotating the cross-sectional image S0 can be arbitrarily set. For example, it may be 4 (including the cross-sectional image S0) obtained by rotating the cross-sectional image S0 by 45 degrees. However, it may be 6 (including the cross-sectional image S0) obtained by rotating the cross-sectional image S0 by 30 degrees. The evaluation value representing the likelihood of cancer can be obtained as a score using the cancer detector described above.

  In FIG. 8, the evaluation value is calculated for the cross-sectional image obtained by rotating the cross-sectional image S0 about the line segment L. However, the cross-sectional image S0 is used about the line segment orthogonal to the line segment L as an axis. An evaluation value may be calculated for a cross-sectional image obtained by rotating. When the pixel block is a sphere or an ellipsoid, an evaluation value may be calculated for a cross-sectional image obtained using the center point of the reference cross-sectional image as a rotation center.

  In step S <b> 15, the display control unit 55 alternately displays the cross-sectional image with the highest evaluation value and the cross-sectional image with the lowest evaluation value among the cross-sectional images for which the evaluation value is calculated by the evaluation value calculation unit 54.

  Specifically, in the cross-sectional image 81 shown in the upper left of FIG. 9, when a region 83 containing cell tissue that seems to be cancerous is selected, the region 83 of the cross-sectional image 81 has the most as shown in the upper right of FIG. 9. A cross-sectional image Smax (for example, cross-sectional image 2B in FIG. 1) having a high evaluation value (most likely cancer) is displayed. 9, for example, when the user operates (clicks) the mouse as the input unit 26, the region 83 of the cross-sectional image 81 has the highest evaluation value as shown in the lower part of FIG. A low (most unlikely) cross-sectional image Smin (for example, cross-sectional image 2A in FIG. 1) is displayed. Further, when the mouse as the input unit 26 is operated (clicked) by the user in the lower state of FIG. 9, the state returns to the upper right state of FIG. That is, in the region 83 of the cross-sectional image 81, the cross-sectional image Smax having the highest evaluation value and the cross-sectional image Smin having the lowest evaluation value are alternately displayed for each user operation.

  In addition, in the cross-sectional image 81 shown in the upper left of FIG. 9, when a region 83 containing cell tissue that seems to be cancerous is selected, the cross-sectional image Smax having the highest evaluation value and the highest evaluation value are not required without user operation. The low cross-sectional images Smin may be alternately and continuously displayed.

  According to the above processing, an evaluation value representing the likelihood of cancer is calculated for a plurality of cross-sectional images of the same part of cellular tissue, and according to the evaluation value, the cross-sectional image with the highest evaluation value and the highest evaluation value Low cross-sectional images are displayed alternately. Therefore, the user can confirm the most cancerous cross section and the least cancerous cross section for the same part of the cell tissue, and by referring to those cross sections, the user can perform a more accurate diagnosis. It becomes possible.

  In the above, the two cross-sectional images having the highest evaluation value and the cross-sectional image having the lowest evaluation value are alternately displayed. However, the cross-sectional image having the highest evaluation value and the lowest evaluation value are displayed. You may make it display the interpolation image which interpolates between between cross-sectional images. Here, the interpolated image is, for example, an image that is generated by a morphing method and interpolates between two different images, and the pixel values of the two images are synthesized (blended) at a predetermined ratio. can get. As a result, when the display of one image is switched to the display of another image, the display is naturally switched.

  As an interpolated image, for example, a cross-sectional image obtained with the line segment L described with reference to FIG. 8 as a rotation axis, between the cross-sectional image with the highest evaluation value and the cross-sectional image with the lowest evaluation value. A cross-sectional image can be used. Note that there may be one or more interpolated images. Thereby, compared with the case where the two cross-sectional images having the highest evaluation value and the cross-sectional image having the lowest evaluation value are alternately displayed, the larger the number of interpolation images, the smoother the display can be performed. .

  Further, as the interpolation image, a cross-sectional image whose evaluation value is a value between the highest value and the lowest value may be used, or a cross-sectional image having the highest evaluation value and a cross-sectional image having the lowest evaluation value are used. An interpolation image may be newly generated by using this.

  Further, the plurality of cross-sectional images for which the evaluation values are calculated may be ranked according to the evaluation values, and any one of the upper cross-sectional images having the highest evaluation value and the cross-sectional image having the lowest evaluation value may be alternately displayed. .

  Specifically, for example, as shown in FIG. 10, on the display 101 serving as the output unit 27, the top three cross sections having the highest evaluation value among the plurality of cross sectional images whose evaluation values are calculated together with the cross sectional image 81. Images S1, S2, and S3 are displayed.

  In FIG. 10, when the cross-sectional image S1 is selected from the cross-sectional images S1, S2, and S3 by the user's operation, the region 83 of the cross-sectional image 81 is evaluated first as shown in FIG. The cross-sectional image S1 having a high value and the cross-sectional image Smin having the lowest evaluation value are alternately displayed. Even in this case, an interpolation image may be displayed between two cross-sectional images displayed alternately. Further, in the lower part of FIG. 11, a reference cross-sectional image S0 may be displayed instead of the cross-sectional image Smin having the lowest evaluation value.

  In the above description, the cross-sectional image whose evaluation value is calculated is displayed in the region 83 of the cross-sectional image 81. However, as shown in FIG. 12, the evaluation is performed in the display region 111 different from the cross-sectional image 81. You may make it display the cross-sectional image which calculated the value. Of course, even in this case, an interpolation image may be displayed between two cross-sectional images displayed alternately.

  In the above description, the image processing apparatus 11 calculates evaluation values for cross sections in a plurality of directions of a predetermined cellular tissue. However, an unillustrated server or the like connected to the outside is arbitrary. The evaluation value for the cross section may be calculated, and the image processing apparatus 11 may acquire the evaluation value from the server and display a predetermined cross-sectional image according to the acquired evaluation value.

[Other functional configuration of CPU]
FIG. 13 is a block diagram showing another functional configuration of the CPU 21.

  As shown in FIG. 13, the CPU 21 includes an evaluation value acquisition unit 151 and a display control unit 55. In FIG. 13, the display control unit 55 is the same as the display control unit 55 in the CPU 21 in FIG.

  The evaluation value acquisition unit 151 acquires an evaluation value for a cross-sectional image representing a predetermined cross section of a pixel block in a three-dimensional image from a server connected to the outside via the communication unit 29.

  The external server has functions similar to those of the cross-section setting unit 51, the region selection unit 52, the block extraction unit 53, and the evaluation value calculation unit 54 in the CPU 21 in FIG. 3, and the region set in the three-dimensional image An evaluation value is calculated for an arbitrary cross section in the pixel block including.

[Cross-section display processing by image processing device]
Next, with reference to the flowchart of FIG. 14, the cross-section display processing by the image processing apparatus 11 having the function described in FIG. 13 will be described.

  In the external server, the evaluation value is calculated for an arbitrary cross section of the pixel block including the region set for a predetermined cellular tissue in the three-dimensional image of the human body.

  In step S <b> 31, the evaluation value acquisition unit 151 performs a cross-sectional image representing an arbitrary cross section of a pixel block including a predetermined cellular tissue in a three-dimensional image of a human body from a server connected to the outside via the communication unit 29. Get the evaluation value.

  In step S32, the display control unit 55 alternately displays the cross-sectional image having the highest evaluation value and the cross-sectional image having the lowest evaluation value among the cross-sectional images for which the evaluation value is acquired by the evaluation value acquiring unit 151. Note that the two cross-sectional images may be displayed as described with reference to FIG. 9, or may be displayed as described with reference to FIG. 11 or FIG. 12.

  Also by the above process, it is possible to obtain the same effects and operations as those of the cross-section display process described with reference to the flowchart of FIG.

  In the above description, only the cross-sectional image from which the evaluation value has been acquired (calculated) is the display target. For example, the cross-section of the cross-section not designated as the cross-section in the method of taking the cross-section described with reference to FIG. There is also a possibility that the evaluation value of the image is the highest (or lower).

  Therefore, in the following, a configuration for estimating the evaluation value of a cross section other than the designated cross section will be described.

[Further functional configuration of CPU]
FIG. 15 is a block diagram showing still another functional configuration of the CPU 21.

  As shown in FIG. 15, the CPU 21 includes an evaluation value acquisition unit 151, a cross section estimation unit 211, and a display control unit 55. In FIG. 15, the evaluation value acquisition unit 151 and the display control unit 55 are the same as the evaluation value acquisition unit 151 and the display control unit 55 in the CPU 21 of FIG.

  Based on the evaluation value acquired by the evaluation value acquisition unit 151, the cross-section estimation unit 211 estimates a cross-sectional image of a cross section for which the evaluation value has not been acquired (calculated).

[Cross-section display processing by image processing device]
Next, with reference to the flowchart of FIG. 16, the cross-section display processing by the image processing apparatus 11 having the function described in FIG. 15 will be described.

  In step S <b> 51, the evaluation value acquisition unit 151 performs a cross-sectional image representing an arbitrary cross-section of a pixel block including a predetermined cellular tissue in a three-dimensional image of a human body from a server connected to the outside via the communication unit 29. Get the evaluation value.

  In step S <b> 52, the cross-section estimation unit 211 estimates the cross-sectional image of the cross section with the highest evaluation value and the cross-sectional image of the cross section with the lowest evaluation value based on the evaluation value acquired by the evaluation value acquisition unit 151. Specifically, the cross section estimation unit 211 estimates the distribution of evaluation values in the rotation direction of the cross section from the evaluation values for each cross section acquired by the evaluation value acquisition unit 151 by linear interpolation or the like. Then, the cross-sectional estimation unit 211 generates a cross-sectional image with the highest evaluation value and a cross-sectional image with the lowest evaluation value based on the estimated distribution of evaluation values. For example, when it is estimated that the evaluation value is the highest between two cross-sectional images, the ratio according to the difference between the evaluation value of each of the two cross-sectional images and the estimated highest evaluation value, By combining (blending) the pixel values of the two cross-sectional images, a cross-sectional image with the highest evaluation value is obtained.

  In step S53, the display control unit 55 alternately displays the cross-sectional image with the highest evaluation value and the cross-sectional image with the lowest evaluation value estimated by the cross-section estimation unit 211. Note that the two cross-sectional images may be displayed as described with reference to FIG. 9, or may be displayed as described with reference to FIG. 11 or FIG. 12.

  Also by the above process, it is possible to obtain the same effects and operations as those of the cross-section display process described with reference to the flowchart of FIG.

  Further, the cross section estimating unit 211 in the CPU 21 in FIG. 15 may be provided in the CPU 21 in FIG. In this case, a cross-sectional image estimation process (the process of step S51 of the flowchart of FIG. 16) by the cross-section estimation unit 211 is executed between step S14 and step S15 of the flowchart of FIG.

  In the above, the case where the present technology is applied to a configuration for displaying a cross section of a cellular tissue of a human body has been described. However, the cross section of food such as vegetables, fruits, meat, electronic devices, structures, and strata By applying it to the display configuration, it becomes possible to more accurately detect foreign matter and analyze parts and deposits.

[Application of this technology to programs]
The series of processes described above can be executed by hardware or can be executed by software.

  When a series of processing is executed by software, a program constituting the software executes various functions by installing a computer incorporated in dedicated hardware or various programs. For example, a general-purpose personal computer is installed from a network or a recording medium.

  As shown in FIG. 2, the recording medium including such a program is distributed to provide a program to the user separately from the apparatus main body, and a magnetic disk (including a floppy disk) on which the program is recorded. It is not only composed of removable media 31 consisting of optical disks (including CD-ROM (compact disk-read only memory) and DVD), magneto-optical disks (including MD (mini-disk)), or semiconductor memory. The program includes a flash ROM 22 in which a program is recorded, a hard disk included in the storage unit 28, and the like provided to the user in a state of being preinstalled in the apparatus main body.

  In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in chronological order according to the order, but is not necessarily performed in chronological order, either in parallel or individually. The process to be executed is also included.

  Further, the program executed by the computer may be a program that is processed in time series in the order described in this specification, or in parallel or at a necessary timing such as when a call is made. It may be a program for processing.

  The embodiments of the present technology are not limited to the above-described embodiments, and various modifications can be made without departing from the gist of the present technology.

  In addition, the present technology can take a configuration of cloud computing in which one function is shared by a plurality of devices on a network and is jointly processed.

  Furthermore, each step described in the above flowchart can be executed by one apparatus or can be shared by a plurality of apparatuses.

  In addition, when a plurality of processes are included in one step, the plurality of processes included in the one step can be executed by being shared by a plurality of apparatuses in addition to being executed by one apparatus.

  DESCRIPTION OF SYMBOLS 11 Image processing apparatus, 21 CPU, 51 Section setting part, 52 Area selection part, 53 Block extraction part, 54 Evaluation value calculation part, 55 Display control part, 151 Evaluation value acquisition part, 211 Section estimation part

Claims (9)

An evaluation value representing the likelihood of cancer of each cross-sectional image for a plurality of cross-sectional images representing cross-sections in a plurality of directions for one predetermined region selected by the user in a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space An evaluation value acquisition unit for acquiring
A display control unit that controls display so as to display a predetermined cross-sectional image of the plurality of cross-sectional images according to the evaluation value;
The display controller, the three-dimensional image wherein the predetermined cross-section on one of the predetermined region selected by the user, of a plurality of said cross-sectional image, likely the evaluation value highest rather most cancers first a first cross-sectional image, the image processing apparatus for displaying alternately a second cross-sectional images the evaluation value is not plausible low Ku most cancers. A block extraction unit for extracting a pixel block including the predetermined region from the three-dimensional image;
The image processing apparatus according to claim 1, wherein the evaluation value acquisition unit acquires the evaluation value for cross-sectional images representing a plurality of cross sections of the pixel block. The image processing apparatus according to claim 2, wherein the display control unit displays a third cross-sectional image among the plurality of cross-sectional images between the first cross-sectional image and the second cross-sectional image. The image processing apparatus according to claim 3, wherein the third cross-sectional image is an interpolation image that interpolates between the first cross-sectional image and the second cross-sectional image. The image processing apparatus according to claim 2, wherein the evaluation value acquisition unit acquires the evaluation value for the cross-sectional image representing an arbitrary cross-section included in the pixel block. Based on the evaluation value acquired by the evaluation value acquisition unit, further comprising a cross-section estimation unit that estimates a cross-sectional image of a cross-section from which the evaluation value has not been acquired,
The image processing apparatus according to claim 1, wherein the display control unit displays a predetermined cross-sectional image among the cross-sectional images estimated by the cross-sectional estimation unit. The image processing apparatus according to any one of claims 1 to 6, wherein the evaluation value represents a cancerousness of the cellular tissue in an image targeted for cellular tissue of a predetermined part of a human body. An evaluation value acquisition unit that acquires an evaluation value for evaluating each cross-sectional image for a plurality of cross-sectional images representing a cross-section in a plurality of directions for a predetermined region of a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space; ,
An image processing method of an image processing apparatus comprising: a display control unit that controls display so as to display a predetermined cross-sectional image of the plurality of cross-sectional images according to the evaluation value;
The image processing apparatus is
An evaluation value representing the likelihood of cancer of each cross-sectional image for a plurality of cross-sectional images representing cross-sections in a plurality of directions for one predetermined region selected by the user in a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space Get
It said one on the predetermined region selected by the user in the predetermined cross-section of the three-dimensional image, a first cross-sectional image plausible cancer, the evaluation value is rather highest among the plurality of cross-sectional images, an image processing method comprising the step of displaying a second cross-sectional images the evaluation value is not plausible low Ku most cancer alternately. An evaluation value representing the likelihood of cancer of each cross-sectional image for a plurality of cross-sectional images representing cross-sections in a plurality of directions for one predetermined region selected by the user in a predetermined cross-section of a three-dimensional image representing an object in a three-dimensional space An evaluation value acquisition step for acquiring
According to the evaluation value, the computer executes a process including a display control step of controlling display so as to display a predetermined cross-sectional image of the plurality of cross-sectional images,
Wherein the display control step, the three-dimensional image wherein the predetermined cross-section on one of the predetermined region selected by the user, of a plurality of said cross-sectional image, likely the evaluation highest rather most cancers value the a first cross-sectional image, a program for displaying alternately a second cross-sectional images the evaluation value is not plausible low Ku most cancers.

Images