Information processing device, method and program

Abstract

An information processing device, method, and program prevent diagnosis from being made using an inappropriate image. [Solution] A processor acquires a medical image and imaging conditions associated with the medical image before acquiring the medical image, and derives validity information indicating the validity of the medical image with respect to the imaging conditions based on the medical image and the imaging conditions.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, a method, and a program. [Background technology]

[0002] In recent years, advances in medical equipment such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) have led to the use of higher quality, higher resolution, and smaller slice thickness images for diagnostic imaging.

[0003] When imaging a subject using an imaging device such as a CT device or an MRI device, in order to determine imaging conditions including the imaging range, scout imaging is performed prior to the actual imaging to obtain images with a small slice thickness (or small slice interval), and positioning images (scout images) with a relatively larger slice thickness (or larger slice interval) than the images in the actual imaging are obtained.The operator of the imaging device, such as a technician, sets the imaging conditions for the actual imaging while looking at the scout image and taking into consideration the purpose of the examination specified by the doctor, etc.

[0004] On the other hand, setting the imaging conditions while viewing the scout image requires the operator, such as a technician, to manually set them, which takes time. Furthermore, the accuracy of the settings varies because they depend on the operator's ability and experience. For this reason, various methods have been proposed for automatically setting the imaging range from the scout image (see Patent Document 1 and Non-Patent Document 1). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-121598 [Non-patent literature]

[0006] [Non-Patent Document 1] Laurent Itti et. al, Automatic scan prescription for brain MRI, Magnetic Resonance in Medicine 45:486-494, 28 February 2001 Summary of the Invention [Problem to be solved by the invention]

[0007] On the other hand, there are cases where the set imaging range is inappropriate, such as when the imaging range set by the operator or the automatically set imaging range does not include the target region. Even if the imaging range is appropriate, if the subject moves after the scout imaging, the target region may not be included in the image acquired by the actual imaging. In such cases, the operator may end the examination without noticing after the actual imaging, resulting in an inappropriate image being used for diagnosis.

[0008] The present disclosure has been made in consideration of the above circumstances, and aims to prevent diagnosis from being made using inappropriate images. [Means for solving the problem]

[0009] An information processing device according to the present disclosure includes a processor, The processor Acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; Based on the medical image and the imaging conditions, validity information indicating the validity of the medical image with respect to the imaging conditions is derived.

[0010] The information processing method according to the present disclosure includes a step of: acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; Based on the medical image and the imaging conditions, validity information indicating the validity of the medical image with respect to the imaging conditions is derived.

[0011] The information processing program according to the present disclosure includes a procedure for acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; The computer is caused to execute a procedure of deriving validity information representing the validity of the medical image with respect to the imaging conditions, based on the medical image and the imaging conditions. [Effects of the Invention]

[0012] According to the present disclosure, the imaging range can be set with high precision. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a perspective view showing an overview of an MRI apparatus to which an information processing apparatus according to a first embodiment of the present disclosure is applied; [Figure 2] FIG. 1 is a diagram showing a hardware configuration of an information processing apparatus according to a first embodiment; [Figure 3] FIG. 1 is a diagram showing a functional configuration of an information processing apparatus according to a first embodiment; [Figure 4] A diagram showing the shooting range set for the scout image [Figure 5] FIG. 1 is a diagram showing a functional configuration of a second derivation unit in the first embodiment; [Figure 6] FIG. 10 is a diagram showing a display screen of validity information in the first embodiment. [Figure 7] 1 is a flowchart showing the processing performed in the first embodiment. [Figure 8] FIG. 10 is a diagram showing the functional configuration of a second derivation unit in the second embodiment. [Figure 9] FIG. 10 is a diagram for explaining a process performed by a validity determination unit in the second embodiment. [Figure 10] 10 is a flowchart showing the processing performed in the second embodiment. [Figure 11] FIG. 10 is a diagram showing a functional configuration of a second derivation unit in the third embodiment. [Figure 12] FIG. 10 is a diagram for explaining derivation of actual shooting conditions in the third embodiment. [Figure 13] 10 is a flowchart showing the processing performed in the third embodiment. [Figure 14] FIG. 10 is a diagram showing another example of a validity information display screen. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Fig. 1 is a perspective view showing an overview of an imaging device to which an information processing device according to a first embodiment of the present disclosure is applied. As shown in Fig. 1, the imaging device according to this embodiment is an MRI device 1, which includes a gantry 2, a bed 3, and a console 4.

[0015] The gantry 2 has a tunnel-like structure with an opening 5 in its center. Inside the gantry 2, a magnetic field generating unit consisting of a static magnetic field magnet, a high-frequency magnetic field coil, and a gradient magnetic field coil (none of which are shown) is built in. A receiving coil (not shown) is arranged on the bed 3. The receiving coil receives nuclear magnetic resonance signals emitted from the imaging region of the subject H by the high-frequency magnetic field. A nuclear magnetic resonance image, i.e., an MRI image, is generated based on the nuclear magnetic resonance signals received by the receiving coil.

[0016] The bed 3 has a bed section 3A on which the subject lies, a base section 3B that supports the bed section 3A, and a drive section 3C that moves the bed section 3A back and forth in the direction of arrow A. The bed section 3A can be slid relative to the base section 3B in the direction of arrow A by the drive section 3C. When an MRI image is to be taken, the subject H lying on the bed section 3A is transported into the opening 5 of the gantry 2 by sliding the bed section 3A.

[0017] The imaging of the subject by driving the gantry 2 and the bed 3 is performed by an operator's input via a console 4. The console 4 includes an information processing device 10 according to the first embodiment.

[0018] Next, an information processing device according to a first embodiment included in the console 4 will be described. First, a hardware configuration of the information processing device according to the first embodiment will be described with reference to FIG. 2. As shown in FIG. 2, the information processing device 10 includes a CPU (Central Processing Unit) 11, a display 14, an input device 15, a memory 16, and an I / F (Interface) 17 connected to the MRI apparatus 1. The CPU 11, the display 14, the input device 15, the memory 16, and the I / F 17 are connected to a bus 19. The CPU 11 is an example of a processor in the present disclosure.

[0019] The memory 16 includes the storage unit 13 and a RAM (Random Access Memory) 18. The RAM 18 is a memory for primary storage, and is, for example, a RAM such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory).

[0020] The storage unit 13 is a non-volatile memory, and is realized by, for example, at least one of a hard disk drive (HDD), a solid state drive (SSD), an electrically erasable and programmable read only memory (EEPROM), and a flash memory. The storage unit 13, which serves as a storage medium, stores an information processing program 12 according to this embodiment. The CPU 11 reads the information processing program 12 from the storage unit 13, loads it into the RAM 18, and executes the loaded information processing program 12.

[0021] The display 14 is a device for displaying various screens, such as a liquid crystal display or an EL (Electro Luminescence) display. The input device 15 is a device for a user to input, such as at least one of a keyboard, a mouse, a microphone for voice input, a touchpad for proximity input including contact, and a camera for gesture input. The I / F 17 is an interface for connecting the MRI apparatus 1 to an external network.

[0022] The information processing program 12 is stored in a state accessible from the outside in a storage device of a server computer connected to a network or in a network storage, and is downloaded and installed in a computer constituting the information processing device 10 in response to a request. Alternatively, the information processing program 12 is recorded on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) and distributed, and is installed from the recording medium into a computer constituting the information processing device 10.

[0023] Next, a functional configuration of the information processing device according to the first embodiment will be described. Fig. 3 is a diagram showing the functional configuration of the information processing device according to the first embodiment. As shown in Fig. 3, the information processing device 10 includes an imaging control unit 21, an information acquisition unit 22, a first derivation unit 23, a second derivation unit 24, and a display control unit 25. When the CPU 11 executes the information processing program 12, the CPU 11 functions as the imaging control unit 21, the information acquisition unit 22, the first derivation unit 23, the second derivation unit 24, and the display control unit 25.

[0024] The imaging control unit 21 controls the magnetic field generating unit provided on the gantry 2 and the receiving coil provided on the bed 3 in response to instructions from the input device 15 to perform imaging of the subject H. During MRI imaging, scout imaging is performed prior to the actual imaging to set the imaging range for the actual imaging to acquire MRI images with a small slice thickness. The scout imaging is performed by imaging the subject H to acquire several (e.g., three) tomographic images along a predetermined imaging direction of the subject H. The scout images acquired by the scout imaging have a relatively larger slice thickness than the MRI images acquired by the actual imaging. In this embodiment, coronal, sagittal, and axial images, which are tomographic images of the coronal, sagittal, and axial planes of the subject H, are acquired as scout images. The scout image is an example of a basic image in the present disclosure. The scout image may be at least one of the coronal, sagittal, and axial images. For example, when imaging a subject H on a bed, since organs are unlikely to move on the axial plane, either a sagittal image or a coronal image may be acquired as a scout image.

[0025] For scout imaging, the operator sets the imaging range so that the area to be included in the MRI image is included. For example, if the purpose of imaging is to examine the lumbar vertebrae, the imaging range for scout imaging is set so that the lumbar vertebrae are included.

[0026] In this embodiment, the imaging range for the actual imaging is set automatically based on the scout image. Setting the imaging range will be described later. After setting the imaging range, the operator issues an instruction for the actual imaging via the input device 15, and the imaging control unit 21 performs the actual imaging. This results in an MRI image of the subject H. The MRI image acquired by the actual imaging includes multiple tomographic images with slice thicknesses relatively smaller than those of the scout image. For example, the slice thickness of the scout image is 3 mm or more, and the slice thickness of the MRI image for the actual imaging is approximately 1 mm. The scout image acquired by the scout imaging and the MRI image acquired by the actual imaging are acquired by the information acquisition unit 22 and stored in the storage unit 13.

[0027] The information acquisition unit 22 acquires scout images acquired by scout imaging and MRI images acquired by main imaging. The information acquisition unit 22 also acquires information on the imaging range derived as described below. Furthermore, the information acquisition unit 22 also acquires examination information. The examination information includes information on the subject H and the imaging purpose. The imaging purpose is specified by a doctor and includes information such as vertebral body examination, knee examination, upper abdominal examination, liver examination, and chest examination. The examination information is input to the information processing device 10 by the operator via the input device 15.

[0028] The first derivation unit 23 sets the imaging range and the like for actual imaging using the scout image. In this embodiment, an imaging angle and an imaging cross section are set in addition to the imaging range, and the imaging angle and the imaging cross section are collectively referred to as the imaging range. Here, in this embodiment, the imaging purpose is, for example, a detailed examination of the lumbar vertebrae. Therefore, the scout image includes the lumbar vertebrae of the subject H. The first derivation unit 23 sets the imaging range for each of the scout images (i.e., coronal image, sagittal image, and axial image).

[0029] Specifically, the first derivation unit 23 extracts lumbar vertebrae from a scout image and sets a centerline between the two lumbar vertebrae. The centerline is the centerline of the intervertebral disc between the two lumbar vertebrae, and the first derivation unit 23 derives the centerline as an imaging cross section. The first derivation unit 23 may, for example, identify an intervertebral disc or lumbar vertebra region and perform a thinning process on the region to determine the centerline. Alternatively, the first derivation unit 23 may derive four feature points from two lumbar vertebrae or one intervertebral disc and use the line segment connecting the midpoints of the line segment connecting two of the feature points as the centerline. The coordinate axes of the scout image coincide with the coordinate axes of the three-dimensional space in which the subject H is imaged. Therefore, the first derivation unit 23 derives, for example, the inclination of the centerline with respect to the horizontal axis (or vertical axis) of the scout image as the imaging angle. The first derivation unit 23 sets the imaging range to a range in which a predetermined number of tomographic images are captured at slice intervals for main imaging with the center line as the reference and which includes the entire width of the lumbar vertebrae. Note that since there are multiple lumbar vertebrae, the first derivation unit 23 sets multiple imaging ranges. The number of tomographic images included in the imaging range is set to an odd number, such as three or five, with the center line as the reference.

[0030] FIG. 4 is a diagram showing imaging ranges set in a scout image. As shown in FIG. 4, multiple imaging ranges are set in each of a coronal image 30 and a sagittal image 31 included in the scout image. Here, there are five lumbar vertebrae, L1 to L5, and a total of six imaging ranges A1 to A6 are set between the five lumbar vertebrae L1 to L5, between the thoracic vertebra Th12 and the lumbar vertebra L5, and between the lumbar vertebra L1 and the sacrum. Here, using imaging range A1 as an example, imaging range A1 includes a center line A1a and an outer frame A1b of the imaging range. Note that an imaging range A7 is set for axial image 32 in accordance with the inclination of subject H.

[0031] When the first derivation unit 23 derives the imaging range, the imaging control unit 21 instructs the MRI apparatus 1 to perform actual imaging of the subject H based on the set imaging range. As a result, the MRI apparatus 1 performs actual imaging of the subject H and generates an MRI image G0 having a slice thickness smaller than that of the scout image. The information acquisition unit 22 acquires the MRI image G0 and stores it in the storage unit 13. The MRI image G0 is an example of a medical image of the present disclosure.

[0032] The second derivation unit 24 derives validity information representing the validity of the MRI image G0 with respect to the imaging conditions, based on the MRI image G0 and the imaging conditions. In this embodiment, the imaging conditions include the imaging range (including the imaging angle and imaging cross section) derived by the first derivation unit 23 and the imaging purpose included in the examination information. The validity information also includes at least one of an index value representing validity and a reason for determining the validity.

[0033] 5 is a diagram showing the functional configuration of the second derivation unit 24 in the first embodiment. As shown in FIG. 5, the second derivation unit 24 in the first embodiment has a first identification unit 41, a second identification unit 42, and a validity determination unit 43.

[0034] The first identification unit 41 identifies anatomical structures to be included in the MRI image G0 based on the imaging purpose included in the examination information. If the imaging purpose is a detailed examination of the lumbar vertebrae, the first identification unit 41 identifies the lumbar vertebrae as the anatomical structure. If the imaging purpose is a detailed examination of the liver, brain, and lungs, the first identification unit 41 identifies the liver, brain, and lungs as the anatomical structures. If the imaging purpose is a detailed examination of the upper abdomen, the first identification unit 41 identifies the liver, kidneys, pancreas, spleen, and related blood vessels, etc., located between the diaphragm and the lower end of the kidney, as the anatomical structures.

[0035] The second identification unit 42 identifies anatomical structures included in the MRI image G0. For example, the second identification unit 42 has a learning model 42A that has undergone machine learning to recognize anatomical structures included in the MRI image G0, and identifies anatomical structures included in the tomographic image of the imaging range using the learning model 42A. For example, if the imaging range of the MRI image G0 includes the lumbar vertebrae, the second identification unit 42 identifies the lumbar vertebrae as anatomical structures. Also, if the MRI image G0 includes the liver, lungs, and brain, the second identification unit 42 identifies the liver, lungs, and brain as anatomical structures, respectively. Note that if multiple imaging ranges are set and the MRI image G0 is acquired, the second identification unit 42 identifies anatomical structures for each of the multiple imaging ranges.

[0036] The validity determination unit 43 determines the validity of the imaging conditions of the MRI image G0 based on the anatomical structure (referred to as the first anatomical structure) identified by the first identification unit 41 and the anatomical structure (referred to as the second anatomical structure) identified by the second identification unit 42. Specifically, the validity determination unit 43 derives the distance between the ideal position of the first anatomical structure to be included in the MRI image G0 and the second anatomical structure identified in the MRI image G0. The derived distance is the distance between landmarks included in the first anatomical structure and the second anatomical structure. For example, if the anatomical structure is a lumbar vertebra, examples of the landmarks include the center of gravity of the lumbar vertebrae and points at the four corners of the lumbar vertebrae, but are not limited thereto.

[0037] Here, if the derived distance is relatively small, the set shooting conditions are valid, and if the derived distance is relatively large, the shooting conditions are invalid. Therefore, the validity determination unit 43 derives the reciprocal of the derived distance and normalizes the reciprocal of the derived distance to a range of 0 to 1 to derive an index value representing validity. Then, if the index value is equal to or greater than a predetermined threshold value Th1, the validity determination unit 43 derives validity information indicating that the index value is valid. If the index value is less than the threshold value Th1, the validity determination unit 43 derives validity information indicating that the index value is invalid. Note that the validity information may include the index value representing validity.

[0038] Instead of deriving the distance, the validity determination unit 43 may superimpose the first anatomical structure at an ideal position on the MRI image G0 and determine the validity based on the degree of overlap between the superimposed first anatomical structure and the second anatomical structure. In this case, the index value representing the validity becomes higher as the degree of overlap increases. Alternatively, the validity may be determined based on the area ratio between the ideal first anatomical structure and the second anatomical structure. Alternatively, the validity may be determined by determining whether the first anatomical structure and the second anatomical structure match.

[0039] The validity determination unit 43 also has a learning model 43A that has been machine-learned to output a reason for determining validity when the first anatomical structure and the second anatomical structure are input. The validity determination unit 43 uses the learning model 43A to output the reason for determining validity. For example, if the first anatomical structure and the second anatomical structure match, validity information indicating validity is derived, and the learning model 43A outputs text such as "structures match" as the reason for determining validity. On the other hand, if the first anatomical structure and the second anatomical structure do not match, validity information indicating invalidity is derived, and the learning model 43A outputs text such as "structures do not match" as the reason for determining validity.

[0040] The display control unit 25 presents the validity information derived by the second derivation unit 24. Specifically, the display control unit 25 displays the tomographic images and validity information for each of the imaging ranges on the display 14. FIG. 6 is a diagram showing a display screen for validity information in the first embodiment. As shown in FIG. 6, tomographic images 51A to 51F for each of the six imaging ranges A1 to A6 are displayed on the display screen 50, and validity information 52A to 52F is displayed for each of the tomographic images 51A to 51F. Note that the contents of the tomographic images are omitted in FIG. 6. Since each imaging range includes multiple tomographic images, one of the multiple tomographic images, for example, at the position of the center line, is displayed. Note that the tomographic image to be displayed can be switched by operating the input device 15.

[0041] The validity information 52A-52F is marked with a circle when the MRI image G0 is valid for the imaging conditions, and marked with an × when it is not valid. The validity information 52A-52F also includes an index value representing validity. Because the index value is normalized to 0-1, the index value is multiplied by 100 on the display screen 50 to display a score out of 100. Furthermore, the validity information 52A-52F includes a reason for the determination that "the structures match" when the image is valid, and a reason for the determination that "the structures do not match" when the image is not valid. In FIG. 6, it can be seen that the tomographic images 51A, 51B, 51E, and 51F of the imaging ranges A1, A2, A5, and A6 are valid, and the tomographic images 51C and 51D of the imaging ranges A3 and A4 are invalid.

[0042] In addition, when invalid validity information is derived, a warning may be issued on the display screen 50. For example, among the displayed validity information 52A to 52F, the invalid validity information 52C and 52D may be displayed separately from the valid validity information 52A, 52B, 52E, and 52F to issue a warning. In this case, for example, the color of the text and the background color of the text of the invalid validity information 52C and 52D may be different from those of the valid validity information 52A, 52B, 52E, and 52F, or the invalid validity information 52C and 52D may be framed or flashed. Also, the inclusion of invalid validity information may be notified by audio. In FIG. 6, the warning is issued by surrounding the invalid validity information 52C and 52D with a frame 60.

[0043] Next, the processing performed in the first embodiment will be described. Fig. 7 is a flowchart showing the processing performed in the first embodiment. First, the imaging control unit 21 causes the MRI apparatus 1 to perform scout imaging to generate a scout image, and the information acquisition unit 22 acquires the scout image (step ST1). Next, the first derivation unit 23 sets an imaging range based on the scout image (step ST2). Subsequently, the imaging control unit 21 causes the MRI apparatus 1 to perform main imaging based on the set imaging range, and the information acquisition unit 22 acquires an MRI image G0 (step ST3).

[0044] Next, the second derivation unit 24 derives validity information representing the validity of the MRI image G0 with respect to the imaging conditions based on the MRI image G0 and the imaging conditions (step ST4).Then, the display control unit 25 presents the validity information derived by the second derivation unit 24 (step ST5), and the process ends.

[0045] In this way, in the first embodiment, validity information indicating the validity of the MRI image G0 with respect to the imaging conditions is derived. Therefore, by checking the validity information, the operator can confirm whether the MRI image G0 has been appropriately acquired. Furthermore, if the MRI image G0 is inappropriate, the operator can take measures such as re-imaging. Therefore, according to the first embodiment, it is possible to prevent a diagnosis from being made using an inappropriate image.

[0046] Next, a second embodiment of the present disclosure will be described. Note that the functional configuration of the information processing device in the second embodiment is the same as the functional configuration of the information processing device according to the first embodiment, so a detailed description of the configuration will be omitted here. In the second embodiment, the process of deriving validity information in the second derivation unit 24 is different from that in the first embodiment.

[0047] Fig. 8 is a diagram showing the functional configuration of the second derivation unit in the second embodiment. As shown in Fig. 8, the second derivation unit 24A in the second embodiment includes a provisional medical image derivation unit 45 and a validity determination unit 46.

[0048] The provisional medical image derivation unit 45 derives a provisional medical image based on the imaging conditions and a scout image. In this embodiment, since the medical image is an MRI image G0, the provisional medical image is a provisional MRI image G1 that conforms to the imaging conditions. Therefore, when the imaging conditions and the scout image are input, the provisional medical image derivation unit 45 derives the provisional MRI image G1 using a learning model 45A that has been machine-learned to output a provisional MRI image G1 that conforms to the imaging conditions. The learning model 45A is constructed by using the learning imaging conditions, the learning scout image, and the learning MRI images acquired by performing imaging based on the learning imaging conditions as training data.

[0049] The learning model 45A may be constructed so that when only the imaging conditions are input, the learning model 45A outputs a provisional MRI image G1 that conforms to the imaging conditions. In this case, the provisional medical image derivation unit 45 derives the provisional MRI image G1 based only on the imaging conditions.

[0050] The learning model 45A may take as input only the shooting range (including the shooting angle and shooting cross section) included in the shooting conditions, may take as input only the shooting purpose, or may take as input both the shooting range and the shooting purpose.

[0051] The validity determination unit 46 derives validity information based on the similarity of the anatomical structures included in the MRI image G0 and the provisional MRI image G1. FIG. 9 is a diagram for explaining the processing performed by the validity determination unit 46 in the second embodiment. The validity determination unit 46 extracts the anatomical structures K0 and K1 included in the MRI image G0 and the provisional MRI image G1, respectively. For example, if the MRI image G0 and the provisional MRI image G1 each include lumbar vertebrae, the validity determination unit 46 extracts the lumbar vertebrae as the anatomical structures K0 and K1 from the MRI image G0 and the provisional MRI image G1, respectively.

[0052] The validity determination unit 46 then derives the similarity between the extracted anatomical structures K0 and K1 as an index value representing validity, which is one piece of validity information. The similarity may be, for example, a correlation value between the anatomical structures K0 and K1, but is not limited to this. Note that the validity determination unit 46 may derive an index value indicating validity based on the distance or overlapping area between the anatomical structures K0 and K1, as in the first embodiment.

[0053] The validity determination unit 46 also has a learning model 46A that has been machine-learned to output a reason for determining validity when the anatomical structures K0 and K1 are input. The validity determination unit 46 uses the learning model 46A to output the reason for determining validity. For example, if the anatomical structures K0 and K1 match, the index value representing validity will be large, and the learning model 46A will output text such as "structures match" as the reason for determining validity. On the other hand, if the anatomical structures K0 and K1 do not match, the index value representing validity will be small, and the learning model 46A will output text such as "structures do not match" as the reason for determining validity.

[0054] In the second embodiment, the display control unit 25 presents the validity information derived by the second derivation unit 24A. Note that the presentation of the validity information in the second embodiment is the same as the display screen 50 shown in Fig. 6, and therefore detailed description thereof will be omitted here.

[0055] Next, the processing performed in the second embodiment will be described. Fig. 10 is a flowchart showing the processing performed in the second embodiment. First, the imaging control unit 21 causes the MRI apparatus 1 to perform scout imaging to generate a scout image, and the information acquisition unit 22 acquires the scout image (step ST11). Next, the first derivation unit 23 sets an imaging range based on the scout image (step ST12). Subsequently, the imaging control unit 21 causes the MRI apparatus 1 to perform main imaging based on the set imaging range, and the information acquisition unit 22 acquires an MRI image G0 (step ST13).

[0056] Next, the provisional medical image derivation unit 45 of the second derivation unit 24A derives a provisional MRI image G1 based on the imaging conditions and the scout image (step ST14). Then, the validity determination unit 46 derives an index value representing validity from the validity information based on the similarity between the anatomical structures included in the MRI image G0 and the provisional MRI image G1 (step ST15). Furthermore, the validity determination unit 46 derives a reason for determining the validity from the validity information (step ST16). Then, the display control unit 25 presents the validity information derived by the second derivation unit 24 (step ST17), and the process ends.

[0057] Next, a third embodiment of the present disclosure will be described. Note that the functional configuration of the information processing device in the third embodiment is the same as the functional configuration of the information processing device according to the first embodiment, so detailed description of the configuration will be omitted here. In the third embodiment, the process of deriving validity information in the second derivation unit is different from that in the first embodiment.

[0058] Fig. 11 is a diagram showing the functional configuration of the second derivation unit in the third embodiment. As shown in Fig. 11, the second derivation unit 24B in the third embodiment includes an actual shooting condition derivation unit 48 and a validity determination unit 49.

[0059] The actual imaging condition deriving unit 48 derives the actual imaging conditions (hereinafter referred to as actual imaging conditions) when the MRI image G0 was acquired, based on the MRI image G0 acquired by the actual imaging. Fig. 12 is a diagram for explaining the derivation of the actual imaging conditions. The MRI image G0 is derived in the imaging ranges A1 to A6 set as shown in Fig. 4. Therefore, the actual imaging condition deriving unit 48 compares the MRI image G0 of the imaging ranges A1 to A6 with the scout image, thereby specifying the corresponding ranges in the scout image of the MRI image G0 in each of the imaging ranges A1 to A6.

[0060] If the MRI image G0 has been acquired within the imaging ranges A1 to A6, actual imaging ranges (hereinafter referred to as actual imaging ranges) A11 to A16 that are substantially the same as the imaging ranges A1 to A6 are set for the coronal image G11 and sagittal image G12 derived from the MRI image G0, as shown in Fig. 12. On the other hand, if the MRI image G0 has not been acquired within all of the imaging ranges A1 to A6, the actual imaging ranges for the MRI image G0 that has not been acquired will not be set for the coronal image G11 and sagittal image G12.

[0061] The validity determination unit 49 derives the similarity between the imaging ranges A1 to A6 set based on the scout image and the actual imaging range set based on the MRI image G0 as an index value representing validity, which is one piece of validity information. As the similarity, for example, a correlation value between the imaging ranges A1 to A6 set on the scout image and the actual imaging range set based on the MRI image G0 can be used, but is not limited to this. Note that, for example, as in the first embodiment, the validity determination unit 46 may derive an index value indicating validity according to the distance or overlapping area between the imaging ranges A1 to A6 set based on the scout image and the actual imaging range set based on the MRI image G0.

[0062] The validity determination unit 49 also has a learning model 49A that has been machine-learned to output a reason for determining validity when the shooting ranges A1 to A6 and the actual shooting range are input. The validity determination unit 49 uses the learning model 49A to output the reason for determining validity. For example, if the shooting ranges A1 to A6 match the actual shooting range, the index value representing validity will be large, and the learning model 49A will output text such as "Structure matches" as the reason for determining validity. On the other hand, if the shooting ranges A1 to A6 do not match the actual shooting range, the index value representing validity will be small, and the learning model 49A will output text such as "Structure does not match" as the reason for determining validity.

[0063] In the third embodiment, the display control unit 25 presents the validity information derived by the second derivation unit 24B. Note that the presentation of the validity information in the third embodiment is the same as the display screen 50 shown in Fig. 6, and therefore detailed description thereof will be omitted here.

[0064] Next, the processing performed in the third embodiment will be described. Fig. 13 is a flowchart showing the processing performed in the third embodiment. First, the imaging control unit 21 causes the MRI apparatus 1 to perform scout imaging to generate a scout image, and the information acquisition unit 22 acquires the scout image (step ST21). Next, the first derivation unit 23 sets an imaging range based on the scout image (step ST22). Subsequently, the imaging control unit 21 causes the MRI apparatus 1 to perform main imaging based on the set imaging range, and the information acquisition unit 22 acquires an MRI image G0 (step ST23).

[0065] Next, the actual imaging condition derivation unit 48 of the second derivation unit 24B derives the actual imaging conditions when the MRI image G0 was acquired based on the MRI image G0 acquired by the actual imaging (step ST24). Then, the validity determination unit 49 derives an index value representing the validity of the validity information based on the similarity between the imaging conditions and the actual imaging conditions (step ST25). Furthermore, the validity determination unit 49 derives a reason for determining the validity of the validity information (step ST26). Then, the display control unit 25 presents the validity information derived by the second derivation unit 24B (step ST27), and the process ends.

[0066] In each of the above embodiments, the first derivation unit 23 derives the imaging range based on a scout image, but this is not limited to this. A scout image may be displayed on the display 14, and the imaging range may be set manually by the operator via the input device 15. In this case, the threshold value Th1 used when determining validity based on the index value representing validity derived in each of the above embodiments may be different between when derived by the first derivation unit 23 and when received through manual operation by the operator. Specifically, the threshold value when the first derivation unit 23 derives the imaging range may be larger than the threshold value when set through manual operation by the operator. Specifically, the scout image and whether the imaging range associated with the scout image is the first setting set by the first derivation unit 23 or the second setting set through operation by the operator are recorded in association with each other. The validity determination unit 49 determines whether the shooting range associated with the scout image is the first setting or the second setting, and based on the determination result, reads out the threshold value associated with the first setting or the threshold value associated with the second setting from the memory 16 and determines whether it is valid or not.

[0067] In addition, in the above-described embodiments, an MRI image G0 is used as the medical image of the present disclosure, but the present disclosure is not limited to this. The technology of the present disclosure can also be applied when acquiring a CT image, a PET (Positron Emission Tomography) image, a SPECT (Single Photon Emission CT) image, an X-ray image, and an ultrasound image.

[0068] In addition, in each of the above embodiments, the information processing device according to the present disclosure is applied to an MRI device, but the present disclosure is not limited to this. The information processing device according to the present disclosure may be applied to a CT device or the like as long as the MRI device acquires a scout image for setting the imaging range before the actual imaging.

[0069] In addition, in each of the above embodiments, the information processing device is provided with the photographing control unit 21, but this is not limitative. The photographing control unit 21 may be provided separately from the information processing device.

[0070] In addition, in each of the above embodiments, the console 4 includes the information processing device according to the present embodiment, but this is not limited to this. The information processing device according to the present embodiment may be a device connected to the console 4 via a network. In other words, the information processing device does not need to be connected to the gantry 2 and the bed 3, and does not need to control the gantry 2 and the bed 3.

[0071] Furthermore, although the above embodiments have been described with reference to cases where the lumbar vertebrae are the subject of examination, the present disclosure is not limited to this case and can be applied to cases where any anatomical structure is the subject of examination depending on the purpose of imaging.

[0072] In the above embodiment, the validity information is displayed as shown in Fig. 6, but the present invention is not limited to this. As shown in Fig. 14, a sagittal image 56 including imaging ranges A1 to A6 may be displayed on the display screen 55, and a circle and an x ​​may be displayed adjacent to each of the imaging ranges A1 to A6 as validity information. In Fig. 14, only the imaging range A4 is marked with an x. Then, by selecting a circle or an x, a tomographic image 57 of the selected imaging range may be displayed on the display screen 55.

[0073] Furthermore, in each of the above embodiments, the following various processors can be used as the hardware structure of a processing unit that performs various processes, such as the imaging control unit 21, the information acquisition unit 22, the first derivation unit 23, the second derivation unit 24, and the display control unit 25. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a GPU (Graphics Processing Unit), a Programmable Logic Device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0074] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0075] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of an entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0076] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0077] The following are appendices to the present disclosure. (Additional note 1) a processor; The processor: acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; an information processing device that derives validity information indicating validity of the medical image with respect to the imaging conditions based on the medical image and the imaging conditions; (Additional note 2) 2. The information processing device according to claim 1, wherein the processor presents the validity information. (Additional note 3) 3. The information processing device according to claim 1, wherein the validity information includes at least one of an index value representing the validity and a reason for determining the validity. (Additional note 4) The information processing device described in Appendix 3, wherein the processor derives the reason for determining the validity by using a learning model that has been trained to output the reason for determining the validity when the medical image and the shooting conditions are input. (Additional note 5) the validity information includes an index value representing the validity, The processor derives a comparison result between the index value and a predetermined threshold value; 3. The information processing device according to claim 1 or 2, which presents the comparison result. (Additional note 6) The information processing device according to claim 5, wherein, when the shooting conditions are derived based on a basic image for determining the shooting conditions that is acquired before acquiring the medical image, the threshold value is larger than when the shooting conditions are set by manual input by an operator. (Additional note 7) The imaging conditions include an imaging purpose, 7. The information processing device according to any one of claims 1 to 6, wherein the processor derives the validity information based on the medical image and the imaging purpose. (Additional note 8) The processor derives a virtual medical image based on the imaging conditions; 7. The information processing device according to any one of appended items 1 to 6, wherein the validity information is derived based on a comparison result between the medical image and the provisional medical image. (Additional note 9) The processor derives the imaging conditions based on a basic image for determining the imaging conditions, which is acquired before acquiring the medical image; The information processing device according to supplementary item 8, wherein the provisional medical image is derived based on the basic image in addition to the imaging conditions. (Additional note 10) The information processing device described in Appendix 9, wherein the processor derives the provisional medical image by using a learning model that has been trained to output the provisional medical image when the shooting conditions and the basic image are input. (Additional note 11) The imaging conditions include an imaging purpose, The information processing device according to claim 8, wherein the processor derives the provisional medical image by using a learning model that has been trained to output the provisional medical image when the imaging purpose is input. (Additional note 12) 12. The information processing device according to any one of appendices 8 to 11, wherein the processor derives the validity information based on a similarity between anatomical structures included in the medical image and the provisional medical image. (Additional note 13) The processor derives actual imaging conditions when the medical image was acquired based on the medical image; 7. The information processing device according to any one of appended items 1 to 6, wherein the validity information is derived based on a comparison result between the photographing conditions and the actual photographing conditions. (Additional note 14) 14. The information processing device according to any one of appendixes 1 to 13, wherein the imaging conditions include an imaging range, an imaging angle, and an imaging cross section. (Additional note 15) The information processing device according to any one of appendices 1 to 7, 13, and 14, wherein the processor derives the imaging conditions based on a basic image for determining the imaging conditions that is acquired before acquiring the medical image. (Additional note 16) a computer acquires a medical image and an imaging condition associated with the medical image before acquiring the medical image; An information processing method for deriving validity information representing validity of the medical image with respect to the imaging conditions based on the medical image and the imaging conditions. (Additional note 17) a step of acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; and a procedure for deriving validity information representing the validity of the medical image with respect to the imaging conditions, based on the medical image and the imaging conditions. [Explanation of symbols]

[0078] 1 MRI machine 2 Gantry 3 berths 3A Sleeper Section 3B base 3C Drive Unit 4 Console 10. Information processing equipment 11 CPU 12 Information Processing Program 13 Storage section 14 Display 15 Input Devices 16 memory 17 Interfaces 18 Bus 20 Information processing equipment 21 Imaging control unit 22 Information Acquisition Department 23 First derivation part 24,24A,24B 2nd derivation part 25 Display control unit 30 Coronal Images 31 Sagittal Images 32 Axial Images 41 1st Specific Part 42 Second Specific Part 42A Learning Model 43,46,49 Validity judgment unit 43A Learning Model 45 Temporary medical image derivation unit 45A Learning Model 46A Learning Model 48 Actual shooting condition derivation part 48A Learning Model 49A Learning Model 50, 55 display screen 51A~51F Tomographic images 52A~52F Validity Information 56 Sagittal Images 57 Tomographic images 60 slots A1~A6, A11~A16 shooting range G0 MRI image G1 provisional MRI image G11 Coronal Image G12 Sagittal Image

Claims

1. a processor; The processor: acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; an information processing device that derives validity information indicating validity of the medical image with respect to the imaging conditions based on the medical image and the imaging conditions;

2. The information processing device according to claim 1 , wherein the processor presents the validity information.

3. The information processing apparatus according to claim 1 , wherein the validity information includes at least one of an index value representing the validity and a reason for determining the validity.

4. The information processing device according to claim 3 , wherein the processor derives the reason for determining the validity by using a learning model that has been trained to output a reason for determining the validity when the medical image and the imaging conditions are input.

5. the validity information includes an index value representing the validity, The processor derives a comparison result between the index value and a predetermined threshold value; The information processing device according to claim 1 or 2, wherein the comparison result is presented.

6. 6. The information processing device according to claim 5, wherein when the imaging conditions are derived based on a basic image for determining the imaging conditions that is acquired before acquiring the medical image, the threshold value is larger than when the imaging conditions are set by manual input by an operator.

7. The imaging conditions include an imaging purpose, The information processing device according to claim 1 , wherein the processor derives the validity information based on the medical image and the imaging purpose.

8. The processor derives a virtual medical image based on the imaging conditions; The information processing apparatus according to claim 1 , wherein the validity information is derived based on a comparison result between the medical image and the provisional medical image.

9. The processor derives the imaging conditions based on a basic image for determining the imaging conditions, which is acquired before acquiring the medical image; The information processing apparatus according to claim 8 , wherein the provisional medical image is derived based on the basic image in addition to the imaging conditions.

10. The information processing device according to claim 9 , wherein the processor derives the provisional medical image by using a learning model that has been trained to output the provisional medical image when the imaging conditions and the basic image are input.

11. The imaging conditions include an imaging purpose, The information processing apparatus according to claim 8 , wherein the processor derives the provisional medical image by using a learning model that has been trained to output the provisional medical image when the imaging purpose is input.

12. The information processing device according to claim 8 , wherein the processor derives the validity information based on a similarity between anatomical structures included in the medical image and the provisional medical image.

13. The processor derives actual imaging conditions when the medical image was acquired based on the medical image; The information processing apparatus according to claim 1 , wherein the validity information is derived based on a result of comparison between the photographing conditions and the actual photographing conditions.

14. The information processing apparatus according to claim 1 , wherein the imaging conditions include an imaging range, an imaging angle, and an imaging cross section.

15. The information processing apparatus according to claim 1 , wherein the processor derives the imaging conditions based on a basic image for determining the imaging conditions that is acquired before acquiring the medical image.

16. a computer acquires a medical image and an imaging condition associated with the medical image before acquiring the medical image; An information processing method for deriving validity information representing validity of the medical image with respect to the imaging conditions based on the medical image and the imaging conditions.

17. a step of acquiring a medical image and imaging conditions associated with the medical image before acquiring the medical image; and a procedure for deriving validity information representing the validity of the medical image with respect to the imaging conditions, based on the medical image and the imaging conditions.

Images