Information processing device, information processing method, and information processing program

Abstract

This invention provides an information processing device, an information processing method, and an information processing program that can support the diagnosis of arterial dissection. [Solution] The information processing device 10 includes a processor, which acquires an input image including blood vessels, generates path information indicating the blood flow path based on the input image, identifies at least the starting position of the arterial dissection based on the path information, and determines the true lumen and false lumen of the arterial dissection based on the path information within a range set according to the starting position.

Description

Technical Field

[0004] , , , , , , , , , , ,

[0005] , , , , , , , , ,

[0003]

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] In recent years, by performing CPR (Curved Planer Reconstruction) processing on three-dimensional images acquired by a CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, etc., the visibility of the observation site is enhanced to improve the efficiency of diagnosis. The CPR process is to reconstruct a CPR image, which is a two-dimensional image or a three-dimensional image, with an arbitrarily set curve direction in the three-dimensional image as one coordinate axis. By using the CPR image, for example, a cross-section in the running direction of a blood vessel can be displayed on one screen. For example, Patent Document 1 discloses creating a straightened CPR image and a volume rendering image from three-dimensional medical image data and displaying them side by side vertically on a display screen.

[0003] Also, for example, Patent Document 2 discloses generating a surface mesh of a dissected blood vessel using a 3D geometric model of the dissected blood vessel, determining local deformation using the surface mesh, and generating a strain map of the dissected blood vessel using the local deformation and the surface mesh.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] In recent years, there has been a growing demand for technologies that can support the diagnosis of arterial dissection. Arterial dissection is a disease in which a tear occurs in the intima, one of the three layers of the blood vessel wall consisting of the intima, media, and adventitia, and blood flows through the tear into the media. In arterial dissection, in addition to the true lumen, which is the original vessel lumen, a false lumen is created by the dissection.

[0006] Generally, in diagnosing arterial dissection, treatment plans are formulated by observing the location and extent of the dissection, as well as the blood flow status of the false lumen, using images including blood vessels, such as CT scans. For this purpose, it is necessary to distinguish between the true lumen and the false lumen from the images, but it has been difficult to distinguish between the true lumen and the false lumen from localized images, such as cross-sectional views perpendicular to the direction of the blood vessel's course.

[0007] This disclosure provides an information processing device, an information processing method, and an information processing program that can support the diagnosis of arterial dissection. [Means for solving the problem]

[0008] A first aspect of this disclosure is an information processing device comprising a processor, the processor acquires an input image including blood vessels, generates path information indicating a blood flow path based on the input image, identifies at least the starting position of arterial dissection based on the path information, and determines the true lumen and false lumen of arterial dissection based on the path information within a range set according to the starting position.

[0009] The processor may distinguish between true lumens and false lumens based on the spatial continuity of the blood flow pathway indicated by the pathway information.

[0010] The processor may distinguish between true lumens and false lumens based on a feature that represents at least one of the following: the shape and pixel values ​​of the blood vessels shown in the input image, and the spatial continuity of the blood flow path shown in the path information.

[0011] The processor may further identify the termination position of the arterial dissection based on the path information, and may distinguish between true and false lumens based on the path information within a range set according to the termination position, in addition to the starting position.

[0012] The processor may determine, based on the path information, whether the true lumen and false lumen are continuous at the end position. If it determines that the true lumen and false lumen are discontinuous at the end position, it may distinguish between the true lumen and false lumen based on spatial continuity. If it determines that the true lumen and false lumen are continuous at the end position, it may distinguish between the true lumen and false lumen based on feature quantities.

[0013] The processor may estimate the centerline of the blood flow region in the blood vessels based on the input image, and generate path information based on the centerline.

[0014] The processor may interpolate the centerline if it is interrupted, based on the distance between the centerlines before and after the interruption.

[0015] The processor may acquire a 3D image including blood vessels as an input image, obtain a coordinate system for the direction of the blood vessels' course from the 3D image, generate a CPR (Curved Planer Reconstruction) image along the direction of the blood vessels' course based on the coordinate system, and generate path information based on the CPR image.

[0016] The processor may acquire a CPR (Curved Planer Reconstruction) image along the direction of the blood vessel's course as the input image.

[0017] The processor may display the starting position in the CPR image on the display.

[0018] The processor may display the regions of the true lumen and the false lumen in the CPR image on a display so that they can be identified, based on the results of the determination of true lumen and false lumen.

[0019] The processor may accept corrections to the classification result, and if the classification result is corrected, it may display the true lumen and false lumen regions in the CPR image on the display in an identifiable manner based on the corrected classification result.

[0020] The processor may display the starting position in the input image on the display.

[0021] Based on the discrimination result between the true lumen and the false lumen, the processor may display the regions of the true lumen and the false lumen in the input image on the display in a distinguishable manner.

[0022] The processor may accept the correction of the discrimination result. When the discrimination result is corrected, based on the corrected discrimination result, the processor may display the regions of the true lumen and the false lumen in the input image on the display in a distinguishable manner.

[0023] A second aspect of the present disclosure is an information processing method, which includes: acquiring an input image including blood vessels; generating path information indicating a blood flow path based on the input image; specifying at least the starting position of arterial dissection based on the path information; and the computer executing a process of discriminating the true lumen and the false lumen of arterial dissection based on the path information within a range set according to the starting position.

[0024] A third aspect of the present disclosure is an information processing program, which causes a computer to: acquire an input image including blood vessels; generate path information indicating a blood flow path based on the input image; specify at least the starting position of arterial dissection based on the path information; and execute a process of discriminating the true lumen and the false lumen of arterial dissection based on the path information within a range set according to the starting position.

Advantages of the Invention

[0025] According to the above aspects, the information processing apparatus, information processing method, and information processing program of the present disclosure can assist in the diagnosis of arterial dissection.

Brief Description of the Drawings

[0026] [Figure 1] It is a diagram showing the schematic configuration of an information processing system. [Figure 2] It is a block diagram showing an example of the hardware configuration of an information processing apparatus. [Figure 3] It is a block diagram showing an example of the functional configuration of an information processing apparatus. [Figure 4] This figure shows an example of a 3D image. [Figure 5] This figure shows an example of a 3D image. [Figure 6] This figure shows an example of a CPR image. [Figure 7] This figure shows an example of a cross-section of a CPR image. [Figure 8] This is a diagram illustrating the route information for Example 1. [Figure 9] This is a diagram illustrating the route information for Example 2. [Figure 10] This figure shows an example of a screen displayed on a display. [Figure 11] This is a flowchart illustrating an example of information processing. [Modes for carrying out the invention]

[0027] The following describes an example of an embodiment of the disclosed technology with reference to the drawings. In each drawing, identical or equivalent components and parts are given the same reference numerals, and redundant descriptions are omitted. Furthermore, the dimensional ratios in the drawings are exaggerated for illustrative purposes and may differ from actual ratios.

[0028] Referring to Figure 1, an example of the configuration of the information processing system 100 according to this embodiment will be described. The information processing system 100 is a system for supporting the diagnosis of arterial dissection occurring in the aorta, coronary arteries, and carotid arteries, etc. Arterial dissection is a disease in which a crack occurs in the intima, one of the three layers of the blood vessel wall consisting of the intima, media, and adventitia, and blood flows from the crack into the media. In arterial dissection, in addition to the true lumen, which is the original blood vessel lumen, a false lumen is created by the dissection. In general, in the diagnosis of arterial dissection, a treatment plan is made by observing the location and extent of the arterial dissection, as well as the state of blood flow in the false lumen, using images including the blood vessel. The information processing system 100 supports the diagnosis of arterial dissection by distinguishing between the true lumen and the false lumen in this arterial dissection.

[0029] The information processing system 100 includes an information processing device 10, a camera 12, and an image server 14. The information processing device 10, the camera 12, and the image server 14 are connected to each other via a wired or wireless network 18, enabling them to communicate with one another. The network 18 is, for example, a LAN (Local Area Network) and a WAN (Wide Area Network).

[0030] Furthermore, each device included in the information processing system 100 may be located in the same facility (e.g., a hospital) or in different facilities. Also, the number of devices included in the information processing system 100 is not particularly limited, and each device may consist of multiple devices having similar functions.

[0031] The imaging device 12 is a modality that generates a medical image T showing the area of ​​a subject to be diagnosed by imaging that area. In this embodiment, the medical image T is a three-dimensional image including the blood vessels of the area to be diagnosed. Examples of imaging devices 12 include CT (Computed Tomography) devices, MRI (Magnetic Resonance Imaging) devices, PET (Positron Emission Tomography) devices, and ultrasound diagnostic devices. The medical image T generated by the imaging device 12 is transmitted to the image server 14.

[0032] The image server 14 is a computer that stores and manages various types of data, including medical images T, and is equipped with a storage device and database management software. Specifically, the image server 14 acquires medical images T generated by the imaging device 12 via the network 18, stores them in its storage device, and manages them. When the image server 14 receives a request to acquire medical images T from the information processing device 10, it transmits the requested medical images T to the information processing device 10. The storage format of various types of data, including medical images T, and communication between each device are based on predetermined protocols such as DICOM (Digital Imaging and Communications in Medicine).

[0033] The information processing device 10 is a device for supporting the diagnosis of arterial dissection by distinguishing between the true lumen and false lumen in arterial dissection based on the medical image T acquired by the imaging device 12. An example of the configuration of the information processing device 10 according to this embodiment will be described below.

[0034] Referring to Figure 2, an example of the hardware configuration of the information processing device 10 according to this embodiment will be described. The information processing device 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage unit 22, and a memory 23 as a temporary storage area. The information processing device 10 also includes a display 24, an input unit 25, and a communication interface (I / F) 26. The CPU 21, storage unit 22, memory 23, display 24, input unit 25, and communication interface 26 are connected to each other via a bus 28, such as a system bus and a control bus, enabling the exchange of various types of information.

[0035] The storage unit 22 is implemented by a storage medium such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and flash memory. The information processing program 27 of the information processing device 10 is stored in the storage unit 22. The CPU 21 reads the information processing program 27 from the storage unit 22, expands it into memory 23, and executes the expanded information processing program 27. The CPU 21 is an example of the processor of this disclosure.

[0036] The display 24 is, for example, a liquid crystal display and displays various information. The input unit 25 includes a pointing device such as a mouse and a keyboard, and is used to input various information to the device. The display 24 may be configured as a touch panel and used in conjunction with the input unit 25.

[0037] Communication I / F26 is an interface for communicating with other devices, including the image server 14. For this communication, wired communication standards such as Ethernet® or FDDI (Fiber Distributed Data Interface), or wireless communication standards such as 4G, 5G, or Wi-Fi® can be used. The information processing device 10 can appropriately include, for example, a server computer, a personal computer, a smartphone, a tablet terminal, and a wearable terminal.

[0038] Referring to Figure 3, an example of the functional configuration of the information processing device 10 according to this embodiment will be described. The information processing device 10 includes, as a functional configuration, an acquisition unit 30, a CPR processing unit 32, a generation unit 34, a discrimination unit 36, and a control unit 38. The CPU 21 executes the information processing program 27, thereby enabling the acquisition unit 30, CPR processing unit 32, generation unit 34, discrimination unit 36, and control unit 38 to function.

[0039] The acquisition unit 30 acquires an input image that includes the blood vessels to be diagnosed. Specifically, the acquisition unit 30 acquires a three-dimensional medical image T generated by the imaging device 12 from the image server 14. Figure 4 schematically shows an example of a medical image T represented in a three-dimensional XYZ coordinate system. The medical image T is, for example, a CT image in which multiple tomographic images T1 to Tm (where m is 2 or more), each representing the XY tomographic plane from the head to the waist of a single subject (human body), are stacked in the Z direction. The CT image also includes blood vessels. That is, the acquisition unit 30 acquires a medical image T (three-dimensional image) including blood vessels as the input image.

[0040] The CPR processing unit 32 obtains a coordinate system representing the direction of blood vessel course from the medical image T (3D image) and generates a CPR (Curved Planer Reconstruction) image along the direction of blood vessel course based on this coordinate system. A CPR image is a 2D or 3D image reconstructed using an arbitrarily set curve direction as one coordinate axis in a 3D image. The "coordinate system representing the direction of blood vessel course" is a 2D or 3D coordinate system that includes the direction of blood vessel course as one coordinate axis. In other words, the CPR processing unit 32 reconstructs a CPR image based on the medical image T using the direction of blood vessel course as one coordinate axis.

[0041] While any known method can be appropriately applied to generate CPR images, one example is described below. First, the CPR processing unit 32 extracts the blood vessels to be diagnosed from the medical image T (3D image). Any known method can be appropriately applied to extract the blood vessels. For example, the CPR processing unit 32 may extract the blood vessels by thresholding using pixel values ​​in the medical image T. Alternatively, the CPR processing unit 32 may extract the blood vessels by template matching using a template representing the shape of the blood vessels. Alternatively, the CPR processing unit 32 may extract the blood vessels using a machine learning model that has been pre-trained to extract blood vessels from the medical image T.

[0042] Next, the CPR processing unit 32 sets the core line of the extracted blood vessel. The core line indicates the direction of the blood vessel's course and is, for example, the centerline of the blood vessel. The core line can be generated, for example, by identifying the center (or centroid) of the blood vessel from each of the tomographic images T1 to Tm and connecting those centers. Figure 5 shows the blood vessel 90 extracted from medical image T, and the core line C0 of the blood vessel 90 is shown as a dashed line.

[0043] Next, the CPR processing unit 32 samples cross-sections perpendicular to the core wire C0 at predetermined intervals (e.g., 1 mm intervals) based on the medical image T (3D image). Figure 5 shows cross-sections AA and BB as examples of cross-sections perpendicular to the core wire C0. In this specification, "perpendicular" does not mean intersecting at exactly 90 degrees, but rather intersecting at angles within a predetermined range including 90 degrees.

[0044] Next, the CPR processing unit 32 generates a CPR image 52 aligned with the direction of the blood vessel's course (i.e., the direction of the core wire C0) by stacking the sampled cross-sectional groups. Figure 6 shows the CPR image 52 generated from the blood vessel 90 in Figure 5. In Figure 6, the CPR image 52 is represented in an αβγ coordinate system, where the direction of the blood vessel 90's course is the γ direction and the direction perpendicular to the direction of the blood vessel 90's course is the αβ direction. Figure 6 also shows the positions corresponding to the AA and BB cross-sections in Figure 5. The CPR processing unit 32 generates a CPR image 52 in which the blood vessel 90 is displayed as a straight line by stacking the cross-sectional groups sampled from the medical image T, such as the AA and BB cross-sections, in the γ direction parallel to the αβ direction.

[0045] The generation unit 34 generates route information indicating the blood flow path based on the input image. Specifically, the generation unit 34 generates route information based on the CPR image 52 generated by the CPR processing unit 32. Normally, blood flows only in the true lumen, but in the case of arterial dissection, blood also flows in the false lumen. Therefore, the generation unit 34 estimates the blood flow path including the true lumen and false lumen from the input image and generates route information.

[0046] Specifically, first, the generation unit 34 extracts the blood flow region of the blood vessels based on the input image (CPR image). Figure 6 shows the first lumen 91 and the second lumen 92 as examples of blood flow regions. For example, the generation unit 34 may extract the blood flow region by thresholding using the pixel values ​​in the CPR image 52. Alternatively, for example, the generation unit 34 may extract the blood flow region using a machine learning model that has been pre-trained to extract the blood flow region from the CPR image 52.

[0047] Next, the generation unit 34 estimates the centerlines of the extracted blood flow regions. In Figure 6, the centerline C1 of the first lumen 91 and the centerline C2 of the second lumen 92 are shown as dashed lines. The centerlines can be generated, for example, by identifying the center (or centroid) of each blood flow region from each cross section (e.g., cross section AA and cross section BB) perpendicular to the direction of course of the blood vessel 90 in the CPR image 52, and connecting those centers. Figure 7 shows an example of a cross section 54 perpendicular to the direction of course of the blood vessel 90 in the CPR image 52. Figure 7 shows the centerline C1 of the first lumen 91 and the centerline C2 of the second lumen 92 in cross section 54.

[0048] Next, the generation unit 34 generates path information based on the estimated centerlines. For example, the generation unit 34 generates a graph represented by multiple nodes as path information by sampling the centerline C1 of the first cavity 91 and the centerline C2 of the second cavity 92 at predetermined intervals (e.g., 1 mm intervals) (see Figures 8 and 9).

[0049] In some cases, the centerline may be interrupted, for example, if the blood flow region is not properly extracted in certain cross-sections. If the centerline is interrupted, the generation unit 34 may interpolate the centerline based on the distance between the centerlines before and after the interruption. For example, if multiple centerlines are estimated, the generation unit 34 may estimate that they are interrupted centerlines if the Euclidean distance between them is below a predetermined threshold. In this case, the generation unit 34 may linearly interpolate the centerline of the interrupted portion and generate path information (graph) using the linearly interpolated centerline.

[0050] The discrimination unit 36 ​​identifies at least the starting position of the arterial dissection based on the path information, and distinguishes between the true lumen and the false lumen of the arterial dissection based on the path information within the range set according to the starting position. The method for distinguishing between the true lumen and the false lumen will be described below with reference to an example.

[0051] (Example 1) In this embodiment, the discrimination unit 36 ​​distinguishes between true lumen and false lumen based on the spatial continuity of the blood flow path indicated by the path information. This embodiment is suitable, for example, when the true lumen and false lumen are continuous (entry) at the starting position of arterial dissection, but are not continuous at the ending position.

[0052] Figure 8 shows an example of the graph 60 generated in this case. Nodes N11 to N17 are sampled from the centerline C1 of the first lumen 91. Nodes N21 to N25 are sampled from the centerline C2 of the second lumen 92. Nodes N01 to N02 are sampled from the overlapping portion of centerlines C1 and C2. Nodes N11, N21, N15, and N25, which correspond to the start and end positions of arterial dissection, will be hereinafter referred to as branch nodes.

[0053] The discrimination unit 36 ​​identifies branching nodes N11 and N21 corresponding to the starting position of arterial dissection based on the path information (graph 60). Next, for each of the branching nodes N11 and N21, the discrimination unit 36 ​​tracks the connected nodes until one of them is interrupted. In other words, the range from the starting position of arterial dissection to the point where the node connection is interrupted corresponds to the "range set according to the starting position".

[0054] If the true lumen and false lumen are not continuous at the end position, it is assumed that the true lumen is longer than the false lumen. Therefore, the discrimination unit 36 ​​determines that the branch node corresponding to the true lumen is the one with the longer path starting from each branch node N11 and N21 (i.e., the one with more continuous nodes).

[0055] In the example shown in Figure 8, branch node N11 is continuous with six nodes from N12 to N17, and branch node N21 is continuous with four nodes from N22 to N25. Therefore, the discrimination unit 36 ​​determines that branch node N11, which is continuous with more nodes, is the branch node N11 corresponding to the true lumen. That is, the discrimination unit 36 ​​determines that the first lumen 91, which has the center line C1 that is the sampling source for branch node N11, is the true lumen, and the other second lumen 92 is a false lumen.

[0056] (Example 2) In this embodiment, the discrimination unit 36 ​​distinguishes between true lumens and false lumens based on a feature quantity that indicates at least one of the following: the shape and pixel values ​​of the blood vessels shown in the input image (CPR image 52), and the spatial continuity of the blood flow path shown in the path information (graph 60). Furthermore, the discrimination unit 36 ​​identifies the end position of the arterial dissection based on the path information, and distinguishes between true lumens and false lumens based on the path information within a range set according to the end position in addition to the start position. This embodiment is suitable, for example, when the true lumen and false lumen are continuous (re-enter) not only at the start position of the arterial dissection but also at the end position.

[0057] Figure 9 shows an example of the graph 60 generated in this case. Nodes N11 to N15 are sampled from the center line C1 of the first cavity 91. Nodes N21 to N25 are sampled from the center line C2 of the second cavity 92. Nodes N01 to N02 and nodes N31 to N32 are sampled from the overlapping portion of center lines C1 and C2.

[0058] The discrimination unit 36 ​​identifies branching nodes N11 and N21 corresponding to the start position of arterial dissection and branching nodes N15 and N25 corresponding to the end position of arterial dissection based on the path information (graph 60). Next, the discrimination unit 36 ​​derives a feature vector for at least one node (node ​​N02) located within a predetermined range from branching nodes N11 and N21 corresponding to the start position. Similarly, the discrimination unit 36 ​​derives a feature vector for at least one node (node ​​N31) located within a predetermined range from branching nodes N15 and N25 corresponding to the end position. In other words, the predetermined range from the start position of arterial dissection and the predetermined range from the end position correspond to the "range set according to the end position in addition to the start position".

[0059] If the true lumen and false lumen are continuous (re-entry) at the end position, the true lumen is not necessarily longer than the false lumen; it may be of equal length or even shorter. Therefore, the discrimination unit 36 ​​improves the accuracy of discrimination by using the various features described above. Specifically, it is preferable for the discrimination unit 36 ​​to use a multidimensional feature vector that includes multiple of the various features described above. These various features or feature vectors can be derived for each arbitrary point in the vascular lumen, for example, by a feature extractor that takes the CPR image 52 and graph 60 as input.

[0060] Feature vectors have the property that the distance between points contained in the same vascular lumen (true lumen or false lumen) is small, and the distance between points contained in different vascular lumens is large. Therefore, the discrimination unit 36 ​​calculates the distance between the feature vectors of branching node N11 and node N02 corresponding to the start position of arterial dissection, and the distance between the feature vectors of branching node N15 and node N31 corresponding to the end position of arterial dissection, with respect to the first lumen 91. Next, the discrimination unit 36 ​​calculates a score for discriminating between true lumen and false lumen using the distance of the feature vectors related to at least one of the start position and end position of arterial dissection. For example, the discrimination unit 36 ​​may calculate representative values ​​such as the average value, sum, minimum value, and maximum value of the distance of the feature vectors related to the start position and end position of arterial dissection as the score. Alternatively, for example, the discrimination unit 36 ​​may calculate the distance of the feature vectors related to either the start position or end position of arterial dissection as the score.

[0061] Similarly, the discrimination unit 36 ​​calculates the distance between the feature vectors of branching node N21 and node N02 corresponding to the start position of arterial dissection, and the distance between the feature vectors of branching node N25 and node N31 corresponding to the end position of arterial dissection, with respect to the second lumen 92. Then, the discrimination unit 36 ​​calculates a score for the second lumen 92 in the same manner as the score for the first lumen 91.

[0062] Next, the discrimination unit 36 ​​compares the score for the first lumen 91 with the score for the second lumen 92 and determines that the vascular lumen with the smaller score (i.e., the closer distance between the feature vectors) is the true lumen. In other words, the discrimination unit 36 ​​determines that the vascular lumen with the larger score (i.e., the farther distance between the feature vectors) is the false lumen.

[0063] Furthermore, the discrimination method using feature quantities as in this embodiment may also be applied to cases where the true lumen and false lumen are not continuous at the end position, as illustrated in Example 1. In this case, the accuracy of discrimination may be further improved.

[0064] Furthermore, for example, the choice of which discrimination method to use, Example 1 or Example 2, may be switched depending on whether the true lumen and false lumen are continuous at the termination point of the arterial dissection. Specifically, the discrimination unit 36 ​​may determine whether the true lumen and false lumen are continuous at the termination point based on the path information (graph 60). If it is determined that the true lumen and false lumen are discontinuous at the termination point, as in the example in Figure 8, the discrimination unit 36 ​​may distinguish between the true lumen and false lumen based on spatial continuity, as in Example 1. On the other hand, if it is determined that the true lumen and false lumen are continuous at the termination point, as in the example in Figure 9, the discrimination unit 36 ​​may distinguish between the true lumen and false lumen based on feature quantities, as in Example 2.

[0065] The control unit 38 controls the display 24 to display the results of the determination of true lumen and false lumen. Figure 10 shows an example of screen D displayed on the display 24 by the control unit 38. Screen D includes a volume rendering image 50 (hereinafter referred to as VR image 50) of the blood vessel 90 extracted from the input CT image, a CPR image 52, and an AA cross-section 54.

[0066] For example, as shown in Figure 10, the control unit 38 may control the display 24 to display the regions of the true lumen and false lumen in the CPR image 52 in a distinguishable manner, based on the determination result of true lumen and false lumen. In the example in Figure 10, the region of the true lumen is made distinguishable by enclosing it with a dotted line. Also in the example in Figure 10, the region of the true lumen is also enclosed with a dotted line in the cross-section 54. The method of making them distinguishable is not particularly limited, and may include color coding, marking, or displaying text such as "The left side of the CPR image is the true lumen."

[0067] For example, as shown in Figure 10, the control unit 38 may be controlled to display at least one of the start and end positions of arterial dissection in the CPR image 52 on the display 24. This makes it easier for the user to understand the state of arterial dissection.

[0068] Furthermore, for example, the control unit 38 may accept a correction of the determination result of true lumen and false lumen. In the example of Figure 10, the control unit 38 changes the true lumen region to the specified region when a region different from the currently determined true lumen region is specified on the CPR image 52 or cross-section 54, and the correction button 80 is pressed. Also, if the determination result is corrected, it is preferable that the control unit 38 controls the display 24 to display the true lumen region and the false lumen region in the CPR image 52 in a way that allows identification based on the corrected determination result. In other words, it is preferable that the user be able to confirm the corrected determination result.

[0069] In the example shown in Figure 10, a configuration was described in which the results of distinguishing between true and false lumens were displayed using a CPR image 52. However, the method is not limited to this, and the results of distinguishing between true and false lumens may also be displayed using other CT images, VR images 50, and cross-sections 54, etc.

[0070] For example, the control unit 38 may control the display 24 to display at least one of the start position and end position in the input image. Alternatively, the control unit 38 may control the display 24 to display the regions of the true lumen and false lumen in the input image in a way that allows for identification, based on the determination result of true lumen and false lumen. Alternatively, the control unit 38 may accept a correction of the determination result of true lumen and false lumen, and if the determination result is corrected, it may control the display 24 to display the regions of the true lumen and false lumen in the input image in a way that allows for identification, based on the corrected determination result.

[0071] Next, the operation of the information processing device 10 will be explained with reference to Figure 11. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the information processing shown in Figure 11. This processing is executed, for example, when the user issues an instruction to start execution.

[0072] In step S10, the acquisition unit 30 acquires a three-dimensional image (medical image T) generated by the imaging device 12 from the image server 14. In step S12, the CPR processing unit 32 generates a CPR image along the direction of blood vessel course from the three-dimensional image acquired in step S10. In step S14, the generation unit 34 generates route information indicating the blood flow path based on the CPR image generated in step S12.

[0073] In step S16, the discrimination unit 36 ​​identifies at least the start position of the arterial dissection and, if necessary, the end position, based on the path information generated in step S14. In step S18, the discrimination unit 36 ​​determines the true lumen and false lumen of the arterial dissection based on the path information within the range set according to the start position (and end position) identified in step S16. In step S20, the control unit 38 controls the display 24 to display the determination result of the true lumen and false lumen determined in step S18, and terminates this information processing.

[0074] As described above, the information processing device 10 according to this embodiment includes a processor. The processor acquires an input image including blood vessels, generates path information indicating the blood flow path based on the input image, identifies at least the starting position of the arterial dissection based on the path information, and determines the true lumen and false lumen of the arterial dissection based on the path information within a range set according to the starting position.

[0075] In other words, according to the information processing device 10 of this embodiment, by identifying the starting position of arterial dissection, it is possible to distinguish between the true lumen and false lumen of arterial dissection from an input image including blood vessels with good accuracy. Therefore, it can support the diagnosis of arterial dissection.

[0076] In the above embodiment, the CPR processing unit 32 was described as generating CPR images from, for example, three-dimensional images such as CT images, but this is not limited to this. For example, the CPR processing may be performed by an external device such as an image server 14. In this case, the acquisition unit 30 acquires CPR images along the direction of blood vessel course as input images from the external device performing the CPR processing, such as the image server 14. In this case, the information processing device 10 may omit the function of the CPR processing unit 32.

[0077] Furthermore, although the above embodiment describes a configuration in which the input image is a three-dimensional image, it is not limited to this. The input image can be any image capable of generating vascular pathway information, such as a two-dimensional angiographic image.

[0078] In this embodiment, each process is executed on any computer. Furthermore, any computer may execute these processes using a processor as hardware, a program as software, or a combination thereof. In that case, the processor is configured to work in cooperation with the program to execute the various processes in this embodiment, and can function as a unit or means in this embodiment. Also, the execution order of the processes by the processor is not limited to the order described and may be changed as appropriate. Any computer may be a general-purpose computer, a computer designed for a specific purpose, a workstation, or any other system capable of executing each process.

[0079] A processor may consist of one or more hardware components, and the type of hardware is not limited. For example, a processor may consist of a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a programmable logic device such as an FPGA (Field Programmable Gate Array), a dedicated circuit for executing a specific process such as an ASIC (Application Specific Integrated Circuit), a GPU (Graphic Processing Unit), or an NPU (Neural Processing Unit). Furthermore, the type of hardware may be a combination of different types of hardware. When multiple hardware components are configured to execute one or more processes of a given processor, these components may reside in physically separate devices or in the same device. Also, in any embodiment, the order of each process performed by the processor is not limited to the order described above and may be changed as appropriate. Hardware is composed of electrical circuits (circuitry) that combine circuit elements such as semiconductor elements.

[0080] Furthermore, the program may be firmware or software such as microcode. Alternatively, the program may be, for example, a set of program modules, each function of which may be implemented by a processor configured to perform its respective function. The program may be program code or multiple code segments stored on one or more non-temporary computer-readable media (e.g., storage media or other storage). The program may be divided and stored on multiple non-temporary computer-readable media located on physically separate devices. Program code or code segments may represent any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. Program code or code segments may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0081] Furthermore, although the above embodiment describes an embodiment in which the information processing program 27 is pre-stored (installed) in the storage unit 22, the invention is not limited to this. The information processing program 27 may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the information processing program 27 may be provided in the form of a download from an external device via a network.

[0082] The technology disclosed herein extends to all program products. A program product includes all forms of products for providing programs. For example, a program product includes programs provided via a network such as the Internet, as well as non-temporary computer-readable recording media such as CD-ROMs, DVD-ROMs, and USB memory sticks on which programs are stored.

[0083] The technology of this disclosure can also be appropriately combined with the above-described embodiments and modifications. The descriptions and illustrations shown above are detailed explanations of the parts relating to the technology of this disclosure and are merely examples of the technology of this disclosure. For example, the above descriptions of the configuration, function, operation, and effect are examples of the configuration, function, operation, and effect of the parts relating to the technology of this disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements added, or replaced from the descriptions and illustrations shown above, as long as they do not deviate from the spirit of the technology of this disclosure.

[0084] The following additional information is disclosed regarding the above embodiments. [Note 1] The processor comprises, Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. Information processing device. [Note 2] The aforementioned processor, Based on the spatial continuity of the blood flow pathway indicated by the aforementioned pathway information, the true lumen and the false lumen are distinguished. The information processing device described in Appendix 1. [Note 3] The aforementioned processor, Based on the shape and pixel values ​​of the blood vessels shown in the input image, and a feature quantity that indicates at least one of the spatial continuity of the blood flow path shown in the path information, the true lumen and the false lumen are distinguished. The information processing device described in Appendix 1 or Appendix 2. [Note 4] The aforementioned processor, Based on the aforementioned pathway information, the termination position of the arterial dissection is further identified. Based on the path information within a range set according to the start position and the end position, the true lumen and the false lumen are determined. The information processing device described in Appendix 3. [Note 5] The aforementioned processor, Based on the aforementioned path information, it is determined whether the true lumen and the false lumen are continuous at the termination position. If it is determined that the true lumen and the false lumen are discontinuous at the aforementioned termination position, the true lumen and the false lumen are distinguished based on the spatial continuity. If it is determined that the true lumen and the false lumen are continuous at the aforementioned termination position, the true lumen and the false lumen are distinguished based on the feature quantity. The information processing device described in Appendix 4. [Note 6] The aforementioned processor, Based on the input image, the centerline of the blood flow region through the blood vessel is estimated. Based on the aforementioned center line, the route information is generated. An information processing device as described in any one of the appendices 1 through 5. [Note 7] The aforementioned processor, If the aforementioned center line is interrupted, the center line is interpolated based on the distance between the center line before and after the interruption. The information processing device described in Appendix 6. [Note 8] The aforementioned processor, As the input image, a three-dimensional image including the blood vessels is acquired. From the aforementioned three-dimensional image, the coordinate system of the direction of the blood vessel's course is obtained. Based on the aforementioned coordinate system, a CPR (Curved Planer Reconstruction) image is generated along the direction of the blood vessel's course. Based on the CPR image, the route information is generated. An information processing device as described in any one of the appendices 1 through 7. [Note 9] The aforementioned processor, As the input image, a CPR (Curved Planer Reconstruction) image is acquired along the direction of the blood vessel's course. An information processing device as described in any one of the appendices 1 through 7. [Note 10] The aforementioned processor, The starting position in the CPR image is displayed on the display. The information processing device described in Appendix 8 or Appendix 9. [Note 11] The aforementioned processor, Based on the determination result of the true lumen and the false lumen, the regions of the true lumen and the false lumen in the CPR image are displayed on the display in a way that allows for identification. An information processing device as described in any one of the appendices 8 to 10. [Note 12] The aforementioned processor, We accept requests to correct the aforementioned determination results. If the aforementioned determination result is corrected, the display will show the areas of the true lumen and the false lumen in the CPR image in a way that allows for identification based on the corrected determination result. The information processing device described in Appendix 11. [Note 13] The aforementioned processor, The starting position in the input image is displayed on the display. An information processing device as described in any one of the appendices 1 through 12. [Note 14] The aforementioned processor, Based on the determination result of the true lumen and the false lumen, the regions of the true lumen and the false lumen in the input image are displayed on the display in a way that allows for identification. An information processing device as described in any one of the appendices 1 through 13. [Note 15] The aforementioned processor, We accept requests to correct the aforementioned determination results. If the judgment result is corrected, the display will show the regions of the true lumen and the false lumen in the input image in a way that allows for identification, based on the corrected judgment result. The information processing device described in Appendix 14. [Note 16] Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. An information processing method in which a computer performs the processing. [Note 17] Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. An information processing program that instructs a computer to perform a task. [Explanation of symbols]

[0085] 10 Information Processing Devices 12. Imaging device 14 Image Server 18 Network 21 CPU 22 Memory section 23 memory 24 displays 25 Input section 26 Communication I / F 27 Information Processing Programs 28 buses 30 Acquisition Department 32 CPR Processing Unit 34 Generation part 36 Discrimination part 38 Control Unit 50 Volume Rendered Images 52 CPR images 60 Graphs 80 Edit button 90 Blood vessels 91 First cavity 92 Second cavity 100 Information Processing Systems C0 core wire C1, C2 center line D screen Nodes N01-N32 T Medical Images T1-Tm fault images

Claims

1. The processor comprises, Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. Information processing device.

2. The aforementioned processor, Based on the spatial continuity of the blood flow pathway indicated by the aforementioned pathway information, the true lumen and the false lumen are distinguished. The information processing apparatus according to claim 1.

3. The aforementioned processor, Based on the shape and pixel values ​​of the blood vessels shown in the input image, and a feature quantity that indicates at least one of the spatial continuity of the blood flow path shown in the path information, the true lumen and the false lumen are distinguished. The information processing apparatus according to claim 1.

4. The aforementioned processor, Based on the aforementioned pathway information, the termination position of the arterial dissection is further identified. Based on the path information within a range set according to the start position and the end position, the true lumen and the false lumen are determined. The information processing apparatus according to claim 3.

5. The aforementioned processor, Based on the aforementioned path information, it is determined whether the true lumen and the false lumen are continuous at the termination position. If it is determined that the true lumen and the false lumen are discontinuous at the aforementioned termination position, the true lumen and the false lumen are distinguished based on the spatial continuity. If it is determined that the true lumen and the false lumen are continuous at the aforementioned termination position, the true lumen and the false lumen are distinguished based on the feature quantity. The information processing apparatus according to claim 4.

6. The aforementioned processor, Based on the input image, the centerline of the blood flow region through the blood vessel is estimated. Based on the aforementioned center line, the route information is generated. The information processing apparatus according to claim 1.

7. The aforementioned processor, If the aforementioned center line is interrupted, the center line is interpolated based on the distance between the center line before and after the interruption. The information processing apparatus according to claim 6.

8. The aforementioned processor, As the input image, a three-dimensional image including the blood vessels is acquired. From the aforementioned three-dimensional image, the coordinate system of the direction of the blood vessel's course is obtained. Based on the aforementioned coordinate system, a CPR (Curved Planer Reconstruction) image is generated along the direction of the blood vessel's course. Based on the CPR image, the route information is generated. The information processing apparatus according to claim 1.

9. The aforementioned processor, As the input image, a CPR (Curved Planer Reconstruction) image is acquired along the direction of the blood vessel's course. The information processing apparatus according to claim 1.

10. The aforementioned processor, The starting position in the CPR image is displayed on the display. The information processing apparatus according to claim 8 or claim 9.

11. The aforementioned processor, Based on the determination result of the true lumen and the false lumen, the regions of the true lumen and the false lumen in the CPR image are displayed on the display in a way that allows for identification. The information processing apparatus according to claim 8 or claim 9.

12. The aforementioned processor, We accept requests to correct the aforementioned determination results. If the aforementioned determination result is corrected, the display will show the areas of the true lumen and the false lumen in the CPR image in a way that allows for identification based on the corrected determination result. The information processing apparatus according to claim 11.

13. The aforementioned processor, The starting position in the input image is displayed on the display. The information processing apparatus according to claim 1.

14. The aforementioned processor, Based on the determination result of the true lumen and the false lumen, the regions of the true lumen and the false lumen in the input image are displayed on the display in a way that allows for identification. The information processing apparatus according to claim 1.

15. The aforementioned processor, We accept requests to correct the aforementioned determination results. If the judgment result is corrected, the display will show the regions of the true lumen and the false lumen in the input image in a way that allows for identification, based on the corrected judgment result. The information processing apparatus according to claim 14.

16. Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. An information processing method in which a computer performs the processing.

17. Acquire an input image that includes blood vessels, Based on the input image, route information indicating the blood flow path is generated. Based on the aforementioned pathway information, at least the starting position of the arterial dissection is identified, Based on the path information within the range set according to the starting position, the true lumen and false lumen of the arterial dissection are determined. An information processing program that instructs a computer to perform a task.

Images