Information processing method, program and information processor

Abstract

To provide an information processing method, etc. capable of removing noise included when detecting a detection target area from a transverse tomographic image of a blood vessel.SOLUTION: An information processing method includes the following steps of: acquiring a plurality of transverse tomographic images of a cross section intersecting an axial direction of a blood vessel, which are continuously photographed along the axial direction; inputting each of the acquired transverse tomographic images to a model learned so as to detect a detection target area when inputting the transverse tomographic images, and thereby detecting the detection target area from each transverse tomographic image; generating a longitudinal tomographic image showing a cross section along the axial direction of the blood vessel from the plurality of transverse tomographic images; determining whether or not the transverse tomographic image including the detection target area contains a threshold or more within a scanning range along the axial direction; and when determining that the transverse tomographic image including the detection target area contains the threshold or more, allowing the computer to perform processing for displaying a marker indicating that the detection target area is present at a position corresponding to the longitudinal tomographic image.SELECTED DRAWING: Figure 5

Description

[Technical field]

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

[0002] There is a technology that uses machine learning to support image diagnosis related to vascular treatment such as PCI (Percutaneous Coronary Intervention). For example, Patent Literature 1 discloses a system that uses a neural network to segment a region of interest from a polar image of a coronary artery. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2022-522960 Summary of the Invention [Problem to be solved by the invention]

[0004] In one aspect, an object of the present invention is to provide an information processing method and the like that can suitably remove noise that is included when detecting a detection target region from a transverse layer image of a blood vessel. [Means for solving the problem]

[0005] In one aspect, (1) an information processing method includes acquiring a plurality of transverse cross-sectional images of a cross section intersecting an axial direction of a blood vessel, capturing the cross section along the axial direction of the blood vessel in succession, inputting each of the acquired transverse cross-sectional images into a model that has been trained to detect a detection target region when a transverse cross-sectional image is input, thereby detecting the detection target region from each of the transverse cross-sectional images, generating a longitudinal cross-sectional image showing a cross-section along the axial direction of the blood vessel from the plurality of transverse cross-sectional images, determining whether the transverse cross-sectional image including the detection target region is contained within a scanning range along the axial direction by a threshold value or more, and if it is determined that the transverse cross-sectional image including the detection target region is contained within a scanning range along the axial direction by a computer, the computer executes a process of displaying a marker indicating the presence of the detection target region at a corresponding position on the longitudinal cross-sectional image.

[0006] (2) In the information processing method described above in (1), the detection target region includes a side branch of a blood vessel.

[0007] (3) The information processing method of (1) or (2) above calculates a diameter value of a blood vessel from the transverse slice image, and determines the scanning range in accordance with the diameter value.

[0008] (4) The information processing method described in any one of (1) to (3) above displays the cross-sectional image showing the detected detection target area, and updates the display of the detection target area on the cross-sectional image depending on the result of determining whether the cross-sectional image including the detection target area contains a threshold value or more.

[0009] (5) In the information processing method of (4) above, when the detection target area is not detected from the first transverse layer image at a position corresponding to the scanning range in which it is determined that the transverse layer image including the detection target area contains a threshold value or more, the detection result of the detection target area in the first transverse layer image is updated based on the detection result of the detection target area in second transverse layer images existing before and after the first transverse layer image.

[0010] (6) The information processing method described in any one of (1) to (5) above generates distribution data indicating the presence or absence of the detection target area along the axial direction with a binary value depending on whether the detection target area has been detected from each of the transverse cross-sectional images, and determines whether the moving average of the distribution data is equal to or greater than a threshold value, thereby determining whether the transverse cross-sectional image including the detection target area contains a threshold value or more.

[0011] (7) When the information processing method of (6) above determines that the moving average is greater than or equal to a threshold, it identifies from the distribution data a continuous area that is greater than or equal to the threshold, including the area where the moving average is greater than or equal to the threshold, and displays the marker at a position on the longitudinal tomographic image that corresponds to the identified area.

[0012] (8) The information processing method of (6) or (7) above identifies an angle of the detection target area detected from each of the transverse cross-sectional images in a circumferential direction of the blood vessel, and determines the presence or absence of the detection target area in each of the transverse cross-sectional images according to the angle, thereby generating the distribution data.

[0013] (9) The information processing method described in any one of (1) to (8) above calculates features relating to the detection target area detected from each of the transverse slice images, groups the transverse slice images including the detection target area based on the features, and determines whether the transverse slice images of each group are contained within a scanning range along the axial direction at a threshold value or more.

[0014] (10) The information processing method described in any one of (1) to (9) above identifies an angle that the detection target area detected from each transverse slice image occupies in the circumferential direction of the blood vessel, and when adjacent markers along the axial direction are separated by a predetermined distance or more, or when the detection target areas corresponding to adjacent markers along the axial direction are separated by a predetermined angle or more in the circumferential direction, displays the markers in a different display mode.

[0015] In one aspect, (11) a program causes a computer to execute a process of acquiring a plurality of transverse cross-sectional images of a cross section intersecting with an axial direction of a blood vessel, capturing the cross-section along the axial direction of the blood vessel in succession, inputting each of the acquired transverse cross-sectional images into a model that has been trained to detect a detection target area when a transverse cross-sectional image is input, thereby detecting the detection target area from each of the transverse cross-sectional images, generating a longitudinal cross-sectional image showing a cross-section along the axial direction of the blood vessel from the plurality of transverse cross-sectional images, determining whether the transverse cross-sectional image including the detection target area is included within a scanning range along the axial direction by a threshold value or more, and displaying a marker indicating the presence of the detection target area at a corresponding position on the longitudinal cross-sectional image if it is determined that the transverse cross-sectional image including the detection target area is included within a scanning range along the axial direction by a threshold value or more.

[0016] In one aspect, (12) an information processing device includes a control unit, wherein the control unit acquires a plurality of transverse cross-sectional images of a cross section intersecting an axial direction of a blood vessel, the cross-sectional images being successively captured along the axial direction, and detects the detection target area from each of the acquired transverse cross-sectional images by inputting each of the acquired transverse cross-sectional images into a model that has been trained to detect a detection target area when a transverse cross-sectional image is input, and generates a longitudinal cross-sectional image showing a cross-section along the axial direction of the blood vessel from the plurality of transverse cross-sectional images, determines whether the transverse cross-sectional image including the detection target area is included within a scanning range along the axial direction by a threshold value or more, and when it is determined that the transverse cross-sectional image including the detection target area is included within a scanning range along the axial direction by a threshold value or more, displays a marker indicating the presence of the detection target area at a corresponding position on the longitudinal cross-sectional image. Effect of the Invention

[0017] According to one aspect, noise contained in a detection target region is detected from a transverse cross-sectional image of a blood vessel can be suitably removed. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of the configuration of an image diagnostic system. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of a server. [Diagram 3] FIG. 1 is a block diagram showing an example of the configuration of an image diagnostic apparatus. [Figure 4] FIG. 1 is an explanatory diagram of a detection model. [Diagram 5] FIG. 11 is an explanatory diagram regarding a noise removal process. [Figure 6] 11 is an explanatory diagram relating to a determination process according to a moving average. FIG. [Figure 7] FIG. 13 is an explanatory diagram showing an example of an analysis screen for a vascular tomographic image. [Figure 8] 11 is a flowchart showing an example of a processing procedure executed by an imaging diagnostic apparatus. [Figure 9] 13 is an explanatory diagram relating to a determination process according to a moving average according to a modified example. FIG. [Figure 10] FIG. 11 is an explanatory diagram showing an overview of a second embodiment. [Figure 11] 11 is a flowchart showing an example of a processing procedure executed by the imaging diagnostic apparatus according to the second embodiment. [Figure 12] FIG. 11 is an explanatory diagram showing an overview of a third embodiment. [Figure 13] 13 is a flowchart showing an example of a processing procedure executed by an imaging diagnostic apparatus according to the third embodiment. [Figure 14] FIG. 13 is an explanatory diagram showing an overview of a fourth embodiment. [Figure 15] FIG. 13 is an explanatory diagram showing an overview of a fourth embodiment. [Figure 16] FIG. 13 is an explanatory diagram showing an overview of a fourth embodiment. [Figure 17] FIG. 13 is an explanatory diagram showing an overview of a fourth embodiment. [Figure 18] 13 is a flowchart showing an example of a processing procedure executed by an imaging diagnostic apparatus according to the fourth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] The present invention will now be described in detail with reference to the drawings showing embodiments thereof. (Embodiment 1) Fig. 1 is an explanatory diagram showing an example of the configuration of an image diagnostic system. In this embodiment, an image diagnostic system is described that detects a detection target region such as a side branch of a blood vessel from a transverse cross-sectional image of the blood vessel and displays the detection result on a longitudinal cross-sectional image of the blood vessel. The image diagnostic system includes a server 1 and an image diagnostic device 2. Each device is communicatively connected via a network N.

[0020] The server 1 is a server computer capable of various information processing and transmitting and receiving information. The device equivalent to the server 1 may be a personal computer or other device. The server 1 performs machine learning to learn from predetermined training data, and generates a detection model 50 (see FIG. 4) that detects detection target regions such as side branches of blood vessels using a transverse layer image of a blood vessel as an input.

[0021] The image diagnostic device 2 is an imaging device that captures medical images of a patient's blood vessels, and is, for example, an IVUS (Intravascular Ultrasound) device that performs ultrasound examinations using a catheter 201. The catheter 201 is a medical instrument that is inserted into a patient's blood vessels, and transmits ultrasound signals from an ultrasound probe attached to the tip of the catheter 201 and receives reflected waves. The image diagnostic device 2 generates and displays an ultrasound tomographic image based on the reflected waves received by the catheter 201.

[0022] In this embodiment, the image diagnostic device 2 is described as an IVUS device, but it may be an optical imaging device using OFDI (Optical Frequency Domain Imaging), etc. The transverse slice image may be captured by a method other than IVUS or OFDI.

[0023] Data of the detection model 50 generated by the server 1 is installed in the image diagnostic device 2, and the image diagnostic device 2 inputs a transverse slice image captured using the catheter 201 to the detection model 50, and detects a detection target region such as a side branch. As will be described later, the image diagnostic device 2 detects a side branch, etc. from each transverse slice image captured continuously along the axial direction of the blood vessel, generates (reconstructs) a longitudinal slice image of the blood vessel from the multiple transverse slice images, and displays the detection result of the side branch, etc. on the longitudinal slice image (see FIG. 7).

[0024] In this embodiment, the image diagnostic device 2 detects the detection target region using the detection model 50, but the server 1 on the cloud may execute the processing using the detection model 50. Also, for example, a general-purpose computer connected to the image diagnostic device 2 may execute the processing. In this way, the processing entity that executes the series of processes is not particularly limited.

[0025] In this embodiment, when the image diagnostic device 2 detects a detection target area such as a side branch from each transverse slice image along the axial direction as described above, the image diagnostic device 2 judges whether the detection target area exists by judging whether the transverse slice image including the detection target area is included within a scanning range of a predetermined length along the axial direction by a threshold value or more. When it is judged that the detection target area exists, the image diagnostic device 2 displays a marker 741 indicating the presence of the detection target area at a position on the longitudinal slice image corresponding to the scanning range (see FIG. 7). This process will be described in detail later.

[0026] 2 is a block diagram showing an example of the configuration of the server 1. The server 1 includes a control unit 11, a main storage unit 12, a communication unit 13, and an auxiliary storage unit . The control unit 11 has one or more arithmetic processing devices such as a central processing unit (CPU), a micro-processing unit (MPU), a graphics processing unit (GPU), etc., and performs various information processing, control processing, etc. by reading and executing a program P1 stored in the auxiliary storage unit 14. The main storage unit 12 is a temporary storage area such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), and temporarily stores data required for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing processing related to communication, and transmits and receives information to and from the outside. The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory or a hard disk, and stores the program P1 (program product) and other data required for the control unit 11 to execute processing.

[0027] The auxiliary storage unit 14 may be an external storage device connected to the server 1. The server 1 may be a multi-computer consisting of a plurality of computers, or may be a virtual machine virtually constructed by software.

[0028] In the present embodiment, the server 1 is not limited to the above configuration, and may include, for example, an input unit for accepting operation input, a display unit for displaying images, etc. The server 1 may also include a reading unit for reading a portable storage medium 1a such as a CD (Compact Disk)-ROM or a DVD (Digital Versatile Disc)-ROM, and may read and execute the program P1 from the portable storage medium 1a.

[0029] 3 is a block diagram showing an example of the configuration of the image diagnostic apparatus 2. The image diagnostic apparatus 2 includes a control unit 21, a main storage unit 22, a communication unit 23, a display unit 24, an input unit 25, an image processing unit 26, and an auxiliary storage unit 27. The control unit 21 has one or more arithmetic processing devices such as CPUs, and performs various information processing, control processing, etc. by reading and executing a program P2 stored in the auxiliary storage unit 27. The main storage unit 22 is a temporary storage area such as RAM, and temporarily stores data necessary for the control unit 21 to execute arithmetic processing. The communication unit 23 is a communication module for performing processing related to communication, and transmits and receives information to and from the outside. The display unit 24 is a display screen such as a liquid crystal display, and displays images. The input unit 25 is an operation interface such as a keyboard or mouse, and accepts operation input from the user. The image processing unit 26 is an image processing module that processes signals transmitted and received via the catheter 201, and generates a vascular tomographic image.

[0030] The auxiliary storage unit 27 is a non-volatile storage area such as a hard disk or a large-capacity memory, and stores a program P2 (program product) and other data necessary for the control unit 21 to execute processing. The auxiliary storage unit 27 also stores a detection model 50. The detection model 50 is a machine learning model generated by learning predetermined training data, and is a trained model that detects detection target regions such as side branches of blood vessels using a transverse slice image captured by the image diagnostic device 2 as an input.

[0031] The image diagnostic apparatus 2 may include a reading unit for reading a portable storage medium 2a such as a CD-ROM, and may read and execute the program P2 from the portable storage medium 2a.

[0032] Fig. 4 is an explanatory diagram of the detection model 50. Fig. 4 illustrates how detection target regions such as the lumen of the main trunk of the blood vessel, the external elastic membrane (EEM) of the main trunk, (the lumen and external elastic membrane of) the side branch, and plaque are detected when a transverse slice image capturing a cross section intersecting the axial direction of the blood vessel is input to the detection model 50. The detection model 50 will be described with reference to Fig. 4.

[0033] The detection model 50 is a model that has been trained to detect a detection target region indicating a predetermined detection target when a cross-sectional image of a blood vessel is input. For example, the detection model 50 is a CNN (Convolutional Neural Network) related to semantic segmentation such as U-net, and identifies the detection target region on a pixel-by-pixel basis.

[0034] The detection model 50 may be a neural network other than the CNN. The detection model 50 may be a machine learning model other than the neural network, such as a decision tree or a Support Vector Machine (SVM).

[0035] The detection target regions include, but are not limited to, the lumen of the main trunk of a blood vessel, the external elastic lamina of the main trunk, the lumen of a side branch, the external elastic lamina of a side branch, plaque (attenuating plaque, etc.), calcified tissue, thrombus, hematoma, dissected blood vessel wall, cracks, extravascular tissue (epicardium, vein, etc.), and devices inserted into a blood vessel (guide wire, stent, guiding catheter, microcatheter, etc.). The detection model 50 detects these multiple detection target regions from the transverse slice image. In addition, in the transverse slice image of FIG. 4, the side branch region is not completely separated from the main trunk of the blood vessel, but the side branch in the transverse slice image in which the main trunk of the blood vessel and the side branch are completely separated may be detected.

[0036] The server 1 generates a detection model 50 by using training data to which a label indicating the position of the correct detection target region is added to a training cross-sectional image. The server 1 detects the detection target region by inputting the training cross-sectional image to the detection model 50. The server 1 compares the detected detection target region with the correct label, and optimizes parameters such as weights between neurons so that the two are similar. In this way, the server 1 generates the detection model 50.

[0037] The diagnostic imaging device 2 detects detection target regions from a transverse cross-sectional image of the patient's blood vessel using the detection model 50 generated as described above. The diagnostic imaging device 2 captures transverse cross-sectional images at each position along the axial direction of the blood vessel in response to the pull-back operation of the catheter 201. The diagnostic imaging device 2 inputs each captured transverse cross-sectional image to the detection model 50, thereby detecting each detection target region, such as a side branch of the blood vessel, the lumen of the main trunk, and the external elastic lamina of the main trunk, from each transverse cross-sectional image.

[0038] The image diagnostic device 2 displays a vascular tomographic image showing the detection result of the detection target region. As will be described in detail later, the image diagnostic device 2 generates (reconstructs) a longitudinal tomographic image showing a cross section along the axial direction of the blood vessel from a plurality of transverse cross-sectional images captured continuously along the axial direction, and displays a marker 741 indicating the presence of a side branch of the blood vessel superimposed on the longitudinal tomographic image (see FIG. 7).

[0039] In this way, the detection model 50 detects detection target regions such as side branches from each transverse slice image along the axial direction of the blood vessel, but depending on the detection model 50, if the detection result is displayed as is, a lot of noise may be mixed in. Therefore, the image diagnostic device 2 displays the detection target regions (side branches in this embodiment) detected from each transverse slice image after removing noise.

[0040] Fig. 5 is an explanatory diagram regarding noise removal processing. Fig. 5 conceptually illustrates a state in which noise is removed from the detection result of side branches of blood vessels. An outline of this embodiment will be described based on Fig. 5.

[0041] The upper part of Fig. 5 shows a schematic longitudinal tomographic image of a blood vessel. In the longitudinal tomographic image shown in the upper part of Fig. 5, vertical bars (markers) shown in the lumen indicate the presence or absence of side branches. As shown in Fig. 5, when the output of the detection model 50 is displayed as is, a large number of side branches are displayed as the detection result, but there is a lot of noise among them. Therefore, the image diagnostic device 2 corrects the detection result of the side branches by the detection model 50 and removes noise.

[0042] Specifically, the image diagnostic device 2 scans along the axial direction of the blood vessel within a scanning range of a predetermined length (for example, 1 to 1.5 mm) and determines whether or not a transverse slice image including a side branch (detection target region) is included within the scanning range at a threshold value or more. If it is determined that a transverse slice image including a side branch is included at a threshold value or more, the image diagnostic device 2 determines that a side branch exists and displays a marker at the position of the longitudinal slice image corresponding to the scanning range.

[0043] More specifically, the image diagnostic device 2 generates distribution data indicating the presence or absence of a side branch along the axial direction with a binary value of 1 or 0 depending on whether a side branch is detected from each transverse slice image. The distribution data is illustrated in the middle part of Fig. 5. The image diagnostic device 2 calculates a moving average of the distribution data. Then, the image diagnostic device 2 determines whether the calculated moving average is equal to or greater than a threshold value, thereby determining whether the number of transverse slice images including a side branch is equal to or greater than the threshold value.

[0044] Fig. 6 is an explanatory diagram regarding the judgment process according to the moving average. In the graph of Fig. 6, the horizontal axis indicates the position of the transverse slice image in the axial direction, and the vertical axis indicates the value of the distribution data. In addition, the thin line in the graph indicates the above-mentioned distribution data (output by the detection model 50), and the thick line indicates the moving average. As shown in Fig. 6, the image diagnostic device 2 calculates the moving average from the distribution data, and judges whether or not the moving average is equal to or greater than a threshold value (0.5 in Fig. 6).

[0045] When it is determined that the moving average is equal to or greater than the threshold, the image diagnostic device 2 determines that a side branch exists in the region equal to or greater than the threshold. As a result, the image diagnostic device 2 generates distribution data from which noise with a moving average less than the threshold has been removed, as shown in the lower part of FIG.

[0046] For example, the image diagnostic device 2 considers side branches that are within a specified value in the anterior-posterior direction in the axial direction to be the same side branch. Also, the image diagnostic device 2 extracts only side branches whose diameter is a specified value (e.g., 1.5 mm) or more, and displays them as detection results.

[0047] In the above description, the scanning range when scanning the distribution data is a constant value (1 to 1.5 mm), but the present embodiment is not limited to this. For example, the image diagnostic device 2 may calculate the diameter value of the blood vessel (its lumen or external elastic lamina) from the transverse slice image, and determine the scanning range according to the calculated diameter value. This allows the scanning range to be determined in consideration of the size of the blood vessel, and side branches to be suitably extracted.

[0048] Fig. 7 is an explanatory diagram showing an example of an analysis screen of a vascular tomographic image. Fig. 7 illustrates an analysis screen showing the detection result of the detection target region by the detection model 50. The analysis screen includes a first image display field 71, a second image display field 72, a third image display field 73, and a fourth image display field 74. The first image display field 71 and the second image display field 72 are display fields that display transverse layer images according to the positions of cursors 742 and 743, which will be described later.

[0049] The third image display field 73 and the fourth image display field 74 are display fields for displaying longitudinal tomographic images of blood vessels. The third image display field 73 displays a raw longitudinal tomographic image generated from a plurality of transverse images. The fourth image display field 74 displays a longitudinal tomographic image with a marker 741 added according to the presence or absence of side branches and with the color of the blood vessel wall changed according to the amount of plaque.

[0050] Specifically, when the image diagnostic device 2 determines by the above-mentioned process that a side branch exists at each position along the axial direction of the blood vessel, it displays a bar-shaped marker 741 indicating the existence of the side branch at the corresponding position on the longitudinal tomographic image. Note that, although the markers 741 of all side branches are displayed in the same manner in Fig. 7, for example, the image diagnostic device 2 may change the display mode (e.g., display color) of the marker 741 for each same side branch.

[0051] In addition, the image diagnostic device 2 changes the display mode (e.g., display color) of the vascular wall at each position along the axial direction according to the ratio of plaque to the vascular cross section. For convenience, the image diagnostic device 2 shows the change in display color by hatching in Fig. 7. For example, the image diagnostic device 2 calculates the ratio of plaque as (area of ​​plaque) / (area of ​​plaque+area of ​​vascular lumen), and displays the portion of the vascular wall where the ratio is equal to or greater than a threshold in a display color different from the other portions.

[0052] Moreover, the image diagnostic apparatus 2 displays cursors 742, 743 on the longitudinal tomographic image. The cursors 742, 743 are objects for designating the positions of the transverse images displayed in the first image display field 71 and the second image display field 72, respectively. The cursors 742, 743 are initially positioned at the most constricted position of the blood vessel (the position where the lumen diameter of the blood vessel is the smallest).

[0053] The image diagnostic apparatus 2 receives an operation input from a user to move the cursors 742, 743 along the axial direction (lateral direction). In accordance with the movement operation of the cursors 742, 743, the first image display field 71 and the second image display field 72 display transverse slice images corresponding to the positions of the cursors 742, 743, respectively.

[0054] The image diagnostic device 2 displays the transverse cross-sectional images corresponding to the positions of the cursors 742, 743 in the first image display field 71 and the second image display field 72, and also displays the boundary line indicating the lumen of the blood vessel, the boundary line indicating the external elastic lamina of the blood vessel, etc. superimposed on the transverse cross-sectional images. The image diagnostic device 2 also calculates the lumen diameter (L) of the blood vessel, the blood vessel diameter (diameter of the external elastic lamina, V), etc., and displays them in association with the transverse cross-sectional images.

[0055] Furthermore, when a side branch is detected from the transverse slice image displayed in the first image display field 71 or the second image display field 72, the image diagnostic device 2 superimposes and displays a second marker 75 indicating a representative position of the side branch. For example, the image diagnostic device 2 specifies the center of gravity of the side branch region of the blood vessel as the representative position of the side branch, and displays the second marker 75 at the specified representative position.

[0056] In this way, by displaying the marker 741 on the longitudinal tomographic image in the fourth image display field 74, it is possible to easily grasp the positions of the side branches in the axial direction of the vascular trunk. Furthermore, by moving the cursors 742, 743 in the fourth image display field 74, the transverse image at any position can be confirmed in the first image display field 71 and the second image display field 72, and the angle at which the side branches are positioned can be easily grasped by the second marker 75.

[0057] As described above, the image diagnostic device 2 judges whether a transverse section image including a side branch (detection target region) is included in the scanning range by judging whether or not the transverse section image includes a threshold value or more, thereby judging whether or not a side branch exists at the corresponding position of the longitudinal section image, and displays the marker 741. On the other hand, since the presence or absence of a side branch is judged by combining the detection results of the side branch in a plurality of transverse section images included in the scanning range in this process, depending on the position where the cursors 742 and 743 are placed, there may be a case where the side branch is not detected from the transverse section image displayed in the first image display field 71 or the second image display field 72 and the second marker 75 is not displayed, even though the marker 741 is displayed on the longitudinal section image as if a side branch exists, depending on the position where the cursors 742 and 743 are placed.

[0058] Therefore, it is preferable that the image diagnostic apparatus 2 updates the display (second marker 75) relating to the side branch on the transverse slice image according to the determination result as to whether or not the transverse slice image including the side branch is included in a threshold amount or more.

[0059] Specifically, when a side branch is not detected from a transverse section image (first transverse section image) at a position corresponding to a scanning range determined to include a threshold or more of a transverse section image including a side branch, the image diagnostic device 2 updates the detection result of the side branch in the transverse section image based on the detection result of the side branch in the transverse section image (second transverse section image) existing before and after the transverse section image. For example, the image diagnostic device 2 estimates the position, shape, etc. of the side branch in the target transverse section image (first transverse section image) based on the position, shape, etc. of the side branch detected from the before and after transverse section images, and displays the second marker 75 superimposed on the transverse section image according to the position of the center of gravity.

[0060] By carrying out the above process, it is possible to avoid a situation in which the second marker 75 is not displayed on the transverse cross-sectional image even though the marker 741 is displayed on the longitudinal cross-sectional image.

[0061] 8 is a flowchart showing an example of a processing procedure executed by the imaging diagnostic apparatus 2. The processing contents executed by the imaging diagnostic apparatus 2 will be described with reference to FIG. The control unit 21 of the image diagnostic device 2 acquires a plurality of transverse cross-sectional images of cross sections intersecting the axial direction of a blood vessel, which are captured continuously along the axial direction (step S11). The control unit 21 inputs each acquired transverse cross-sectional image to the detection model 50, thereby detecting a detection target region (such as a side branch of the blood vessel) from each transverse cross-sectional image (step S12). The control unit 21 generates a longitudinal cross-sectional image showing a cross section along the axial direction of the blood vessel from the plurality of transverse cross-sectional images acquired in step S11 (step S13).

[0062] The control unit 21 generates distribution data indicating the presence or absence of the detection target region along the axial direction with a binary value according to whether or not the detection target region is detected from each transverse cross-sectional image (step S14). The control unit 21 determines whether or not the moving average of the distribution data is equal to or greater than a threshold value, thereby determining whether or not the transverse cross-sectional image including the detection target region is included within the scanning range along the axial direction by the threshold value or more (step S15).

[0063] The control unit 21 displays an analysis screen showing the detection result of the detection target region (step S16). Specifically, as shown in Fig. 7, the control unit 21 displays a transverse cross-sectional image corresponding to an arbitrary position on the longitudinal cross-sectional image together with the longitudinal cross-sectional image of the blood vessel on the analysis screen. Here, when the control unit 21 determines in step S15 that the transverse cross-sectional image including the detection target region is included in a number equal to or greater than the threshold value, it displays a marker 741 indicating the presence of the detection target region at the corresponding position on the longitudinal cross-sectional image. The control unit 21 ends the series of processes.

[0064] As described above, according to the first embodiment, noise that is included when a detection target region is detected from a transverse cross-sectional image of a blood vessel can be suitably removed.

[0065] (Modification) In the first embodiment, a configuration has been described in which distribution data indicating the presence or absence of side branches (detection target regions) along the axial direction of a blood vessel is generated, and a region in which the moving average of the distribution data is equal to or greater than a threshold is identified as a region in which a blood vessel exists. In this modified example, a configuration will be described in which, when it is determined that the moving average is equal to or greater than a threshold, consecutive regions in which the moving average is equal to or greater than the threshold are identified from the distribution data, including the region in which the moving average is equal to or greater than the threshold, and the region is determined as a region in which a side branch exists.

[0066] Fig. 9 is an explanatory diagram of a determination process according to a moving average according to a modified example. Fig. 9 shows a graph representing distribution data indicating the presence or absence of side branches and the moving average of the distribution data, similar to Fig. 6. An overview of this modified example will be described with reference to Fig. 9.

[0067] As in the first embodiment, the image diagnostic device 2 generates distribution data indicating the presence or absence of a side branch along the axial direction of the blood vessel with a binary value of 1 or 0 depending on whether or not a side branch is detected from each transverse slice image along the axial direction of the blood vessel. Then, the image diagnostic device 2 calculates a moving average of the distribution data, and identifies an area where the moving average is equal to or greater than a threshold value (1 in FIG. 9) as an area where a side branch exists.

[0068] In this modification, the image diagnostic device 2 scans from both ends of the identified region outward, and identifies a range in which the distribution data is continuously greater than or equal to the threshold as a region in which a side branch exists. Explaining with reference to Fig. 9, after identifying a region in which the moving average (thick line) is 1 or more, the image diagnostic device 2 further scans from the identified region to the left and right as indicated by the arrows, and identifies a region in which the distribution data (thin line) is 1 or more as a region in which a side branch exists.

[0069] In this way, when the image diagnostic device 2 determines that the moving average is equal to or greater than the threshold, it identifies, from the distribution data, a region in which the moving average is continuously equal to or greater than the threshold, including the region in which the moving average is equal to or greater than the threshold, as a region in which a side branch exists. The image diagnostic device 2 displays a marker 741 at a position on the longitudinal tomographic image corresponding to the identified region. This makes it possible to more accurately identify the region in which a side branch exists.

[0070] Since the present modification is similar to the first embodiment except for the above points, detailed description of the flowchart and other details will be omitted.

[0071] (Embodiment 2) In this embodiment, the presence or absence of a side branch is determined according to the angle of the side branch (detection target region) detected from the transverse slice image in the circumferential direction of the blood vessel. Note that the same reference numerals are used to designate the same contents as those in the first embodiment, and the description thereof will be omitted.

[0072] Fig. 10 is an explanatory diagram showing an overview of the second embodiment. The overview of the present embodiment will be described with reference to Fig. 10.

[0073] As in the first embodiment, the image diagnostic device 2 detects detection target regions such as side branches by inputting transverse slice images captured continuously along the axial direction of the blood vessel to the detection model 50. For convenience of explanation, FIG. 10 illustrates the detection results of only side branches.

[0074] In this embodiment, the image diagnostic device 2 specifies the angle of the side branch detected from each transverse slice image in the circumferential direction of the blood vessel. Specifically, as shown in Fig. 10, the image diagnostic device 2 specifies the angle of the side branch on a circle centered on the center of gravity of the blood vessel lumen.

[0075] The image diagnostic device 2 judges the presence or absence of a side branch in each transverse slice image according to the identified angle. For example, when the image diagnostic device 2 judges that the angle is equal to or less than a threshold, it judges that there is no side branch. This makes it possible to remove side branches (noise) accidentally detected by the detection model 50.

[0076] The image diagnostic device 2 generates distribution data indicating the presence or absence of a side branch according to the determination result of the presence or absence of a side branch according to the angle. The subsequent processing is the same as in the first embodiment, and the image diagnostic device 2 determines whether the moving average of the distribution data is equal to or greater than a threshold value to identify an area where a side branch exists, and displays a marker 741 at a position on the longitudinal tomographic image corresponding to the identified area.

[0077] 11 is a flowchart showing an example of a processing procedure executed by the imaging diagnostic device 2 according to embodiment 2. After detecting a detection target region (such as a side branch) from each transverse slice image captured continuously along the axial direction of a blood vessel (step S12) and generating a longitudinal slice image from the multiple transverse slice images (step S13), the imaging diagnostic device 2 executes the following processing. The control unit 21 of the image diagnostic device 2 identifies the angle of the detection target region (side branch) detected from each transverse cross-sectional image in the axial direction of the blood vessel (step S201). The control unit 21 generates distribution data indicating the presence or absence of the detection target region in binary form depending on whether the detection target region is detected from each transverse cross-sectional image (step S202). In this case, the control unit 21 determines the presence or absence of the detection target region in each transverse cross-sectional image depending on the angle identified in step S201, and generates the distribution data. The control unit 21 determines whether the moving average of the generated distribution data is equal to or greater than a threshold value, thereby determining whether the transverse cross-sectional image including the detection target region is included within the scanning range by a value equal to or greater than the threshold value (step S203), and proceeds to step S16.

[0078] As described above, according to the second embodiment, the presence or absence of a side branch can be determined more accurately.

[0079] (Embodiment 3) In this embodiment, a description will be given of a mode in which markers 741, 741, 741... that are presumed to be different side branches are displayed in different display modes (display colors) according to the distance in the axial direction or the angle in the circumferential direction.

[0080] Fig. 12 is an explanatory diagram showing an overview of the third embodiment. Fig. 12 illustrates a state in which markers 741, 741, 741 ... of different side branches are displayed in different display modes (display colors) when markers 741, 741, 741 ... are displayed on a longitudinal tomographic image. The overview of this embodiment will be described based on Fig. 12.

[0081] As in the first embodiment, the image diagnostic device 2 judges whether or not the transverse slice image including the side branch is included in the scanning range at a threshold value or more, and when it is judged that the transverse slice image including the side branch is included at a threshold value or more, it displays a marker 741 indicating the presence of the side branch at the corresponding position of the longitudinal slice image. Here, in this embodiment, the image diagnostic device 2 judges whether or not the side branches represented by the adjacent markers 741, 741 are different side branches. Then, when it is judged that they are different side branches, the image diagnostic device 2 displays each marker 741 in a different display mode.

[0082] Specifically, the image diagnostic device 2 determines whether or not the distance in the axial direction between adjacent markers 741, 741 is equal to or greater than a predetermined distance. If it is determined that the distance is equal to or greater than the predetermined distance, the image diagnostic device 2 displays each marker 741 in a different display mode, regarding the side branches represented by each marker 741 as different side branches.

[0083] Also, the image diagnostic device 2 may specify the angle of the side branches detected from each transverse slice image in the circumferential direction of the blood vessel, and determine whether or not they are different side branches depending on the angle, as in the second embodiment. Specifically, the image diagnostic device 2 determines whether or not the side branches corresponding to the markers 741, 741 adjacent to each other in the axial direction are separated by a predetermined angle or more in the circumferential direction. If it is determined that they are separated by the predetermined angle or more, the image diagnostic device 2 displays each marker 741 in a different display mode, regarding the side branches represented by each marker 741 as different side branches.

[0084] 13 is a flowchart showing an example of a processing procedure executed by the imaging diagnostic device 2 according to embodiment 3. After detecting a detection target region (such as a side branch) from each transverse slice image captured continuously along the axial direction of a blood vessel (step S12) and generating a longitudinal slice image from the multiple transverse slice images (step S13), the imaging diagnostic device 2 executes the following processing. The control unit 21 of the image diagnostic device 2 identifies the angle of the detection target region (side branch) detected from each transverse cross-sectional image in the axial direction of the blood vessel (step S301). The control unit 21 generates distribution data indicating the presence or absence of the detection target region with a binary value according to whether or not the detection target region is detected from each transverse cross-sectional image (step S302). The control unit 21 determines whether or not the moving average of the distribution data is equal to or greater than a threshold value, thereby determining whether or not the transverse cross-sectional image including the detection target region is included within the scanning range by a threshold value or more (step S303).

[0085] The control unit 21 displays an analysis screen showing the detection result of the detection target area (step S304). Specifically, as in the first embodiment, when the control unit 21 determines that the transverse section image including the detection target area is included in a threshold value or more, it displays a marker 741 indicating the presence of the detection target area at a corresponding position of the longitudinal section image. Here, when the markers 741, 741 adjacent to each other along the axial direction are separated by a predetermined distance or more, the control unit 21 displays the adjacent markers 741, 741 in different display modes. Alternatively, when the detection target areas corresponding to the markers 741, 741 adjacent to each other along the axial direction are separated by a predetermined angle or more along the circumferential direction, the control unit 21 displays the adjacent markers 741, 741 in different display modes. The control unit 21 ends the series of processes.

[0086] As described above, according to the third embodiment, it is easy to recognize that each marker 741 displayed on the longitudinal tomographic image is a different side branch. Even if multiple markers 741 are attached to one side branch, they are displayed in the same manner, so that it is easy to recognize that they are likely to be the same side branch.

[0087] (Embodiment 4) In this embodiment, a form will be described in which noise is removed by grouping transverse cross-sectional images based on feature amounts (e.g., angles) related to side branches (detection target regions) detected from the transverse cross-sectional images.

[0088] 14 to 17 are explanatory diagrams showing an overview of the embodiment 4. The overview of the present embodiment will be described with reference to Figs.

[0089] As in the first embodiment, the image diagnostic device 2 detects a detection target region such as a side branch from each transverse slice image by inputting each transverse slice image captured successively along the axial direction of the blood vessel to the detection model 50. Furthermore, the image diagnostic device 2 calculates a feature amount related to the detected detection target region. The feature amount of the detection target region is, for example, the angle of the side branch. As in the second embodiment, the image diagnostic device 2 calculates (specifies) the angle of the side branch in the circumferential direction of the blood vessel.

[0090] In this embodiment, the angle of the side branch is used as a feature of the detection target region, but this embodiment is not limited to this, and for example, the depth, brightness, area, position coordinates, etc. in the vascular wall may be used as the feature.

[0091] The calculation results for the side branch angle are shown in the upper part of Figure 14. The hatched area within the circle indicates the angle at which the side branch was detected. Note that "branch" refers to a state in which the main trunk of the blood vessel and the side branch are connected on the cross section, as in Figure 4, etc. "Separation" refers to a state in which the main trunk of the blood vessel and the side branch are separated on the cross section.

[0092] The image diagnostic device 2 groups the transverse slice images including the side branch based on the calculated feature amount (angle). Specifically, the image diagnostic device 2 groups a plurality of transverse slice images (frames) by determining whether or not the difference in the feature amount between frames is within a threshold and the frame interval is within a threshold.

[0093] "Group A" to "Group C" in Fig. 14 represent the results of grouping transverse slice images including side branches. In accordance with the example of Fig. 14, the image diagnostic device 2 first compares the second frame from the left in which a side branch is detected with the third frame. In this case, the difference in the angle of the side branch between the frames is within a threshold value and the frame interval is within a threshold value, so the image diagnostic device 2 classifies both frames into the same "Group A."

[0094] Next, the image diagnostic device 2 compares the third frame with the fourth frame. In this case, the frame interval is within the threshold, but the difference in the angle of the side branch between the frames is equal to or greater than the threshold, so the image diagnostic device 2 classifies the fourth frame into "group B" different from "group A."

[0095] Next, the image diagnostic device 2 compares the third frame with the fifth frame. In this case, the difference in the angle of the side branches between the frames is within the threshold value, and the frame interval is within the threshold value, so the image diagnostic device 2 classifies both frames into the same "Group A."

[0096] Next, the image diagnostic device 2 compares the fifth (and fourth) frame with the Nth frame. In this case, the difference in the angle of the side branches between the frames is equal to or greater than a threshold, and the frame interval is equal to or greater than a threshold, so the image diagnostic device 2 classifies the Nth frame into "Group C" which is different from "Group A" (and "Group B").

[0097] Finally, the image diagnostic device 2 determines the start point and end point of each group grouped as described above. For example, the image diagnostic device 2 determines the frame in which a branching part appears first in the same group as the start point, and determines the frame in which a branching part or separation part appears last in the same group as the end point of the group. In the example of FIG. 14, the start point of "Group A" is the second frame and the end point is the fifth frame, while the start point and end point of "Group B" are the third frame. On the other hand, since there is no frame in which a branching part appears in "Group C," it is determined that there is no start point of the group.

[0098] The image diagnostic device 2 generates distribution data that indicates the presence or absence of side branches with a binary value for each group generated above. The distribution data is illustrated in Figure 15. Here, "Group C" is determined to have no starting point for the group, and is therefore removed as noise.

[0099] As in the first embodiment, the image diagnostic device 2 determines whether or not a side branch exists by determining whether or not the moving average of the distribution data is equal to or greater than a threshold. Fig. 16 illustrates the distribution data and the moving average of the distribution data. In the example of Fig. 16, since the moving average of "group A" is equal to or greater than the threshold, it is determined that a side branch exists. On the other hand, since the moving average of "group B" is equal to or less than the threshold, it is determined that a side branch does not exist.

[0100] When it is determined that a side branch is present, the image diagnostic device 2 calculates the maximum diameter among the diameters of the side branch detected from each transverse slice image included in the group as the side branch diameter. FIG. 17 shows the calculation process. The image diagnostic device 2 specifies the side branch diameter based on the shape of the side branch detected from each transverse slice image. Then, as shown in the lower part of FIG. 17, the image diagnostic device 2 estimates the transition of the side branch diameter within the group based on the side branch diameter in each transverse slice image. The image diagnostic device 2 calculates the maximum value in the estimated transition (the value at the end of the group in FIG. 17) as the representative value of the side branch diameter.

[0101] In this manner, in the present embodiment, the image diagnostic device 2 groups the transverse slice images in which the side branches are detected, and for each group, determines whether the transverse slice images in which the side branches are detected are included within the scanning range equal to or greater than the threshold value. This makes it possible to remove noise that suddenly appears as a detection result.

[0102] For the sake of simplicity, in Figs. 14 to 17, the case where one side branch is detected from one transverse section image has been described. However, when multiple side branches are detected from one transverse section image, one transverse section image from which a side branch is detected may be classified into multiple groups at the same time. That is, when multiple side branches (detection target regions) are detected from one transverse section image, the image diagnostic device 2 calculates the angle (feature value) of each side branch, and groups the transverse section images for each side branch based on the angle. Then, the image diagnostic device 2 determines whether the transverse section images of each group are included within the scanning range by a threshold value or more. In this manner, the image diagnostic device 2 may group the transverse section images for each side branch.

[0103] 18 is a flowchart showing an example of a processing procedure executed by the imaging diagnostic device 2 according to embodiment 4. After detecting a detection target region (such as a side branch) from each transverse slice image captured continuously along the axial direction of a blood vessel (step S12) and generating a longitudinal slice image from the multiple transverse slice images (step S13), the imaging diagnostic device 2 executes the following processing. The control unit 21 of the image diagnostic apparatus 2 calculates a feature amount related to the detection target region (side branch) detected from each transverse slice image (step S401). For example, the control unit 21 calculates the angle of the detection target region in the circumferential direction of the blood vessel, as described above.

[0104] The control unit 21 groups the cross-sectional images including the detection target region based on the calculated feature amount (step S402). Specifically, the control unit 21 groups a plurality of cross-sectional images (frames) by determining whether or not the difference in the feature amount between frames is within a threshold value and the frame interval is within a threshold value.

[0105] The control unit 21 generates distribution data indicating the presence or absence of a detection target region along the axial direction with a binary value according to whether or not a detection target region is detected from each transverse slice image (step S403). Here, the control unit 21 generates distribution data for each group grouped in step S402. The control unit 21 determines whether or not the transverse slice image of each group is included within the scanning range along the axial direction by determining whether or not the moving average of the distribution data of each group is equal to or greater than a threshold value (step S404). In addition, the control unit 21 calculates the maximum diameter of the diameters of the side branches (detection target regions) detected from each transverse slice image in the group as the side branch diameter (step S405), and proceeds to step S16.

[0106] In this embodiment, the side branch of a blood vessel is described as the target, but the detection target region is not limited to the side branch. For example, the image diagnostic device 2 targets a calcified region of a blood vessel wall, groups each transverse slice image in which a calcified region is detected based on a feature value related to the calcified region (e.g., an angle range when the center of the lumen of the blood vessel is the center), and removes noise by determining whether the transverse slice images of each group are included within a scanning range along the axial direction by a threshold value or more. Furthermore, the image diagnostic device 2 calculates the maximum size (e.g., area) of the calcified region detected from each transverse slice image in the group as a representative value of the calcified region. In this way, the embodiment can be applied to detection targets other than the side branch.

[0107] As described above, according to the fourth embodiment, noise contained in the detection result can be suitably removed.

[0108] The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the scope and meaning equivalent to the claims.

[0109] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations regardless of the citation format. Furthermore, the claims use a format in which a claim cites two or more other claims (multi-claim format), but this is not limited to this. They may also be written using a format in which a multiple claim cites at least one other multiple claim (multi-multi claim). [Explanation of symbols]

[0110] 1 Server 11 Control section 12 Main memory 13. Communications Department 14 Auxiliary storage P1 Program 2. Diagnostic imaging equipment 21 Control section 22 Main memory 23 Communications Department 24 Display section 25 Input section 26 Image Processing Section 27 Auxiliary storage P2 Program 50 Detection Models

Claims

1. A plurality of transverse cross-sectional images are obtained by successively capturing images of a cross section intersecting an axial direction of the blood vessel along the axial direction; Each acquired cross-sectional image is input to a model that has been trained to detect a detection target area when a cross-sectional image is input, thereby detecting the detection target area from each cross-sectional image; generating a longitudinal image showing a cross section of the blood vessel along the axial direction from the plurality of transverse images; determining whether the transverse slice image including the detection target region is included within a scanning range along the axial direction by a threshold value or more; When it is determined that the transverse slice image including the detection target region contains a threshold value or more, a marker indicating the presence of the detection target region is displayed at a corresponding position of the longitudinal slice image. An information processing method in which processing is performed by a computer.

2. The detection target area includes a side branch of a blood vessel. The information processing method according to claim 1 .

3. Calculating a blood vessel diameter value from the transverse slice image; The scanning range is determined according to the diameter value. The information processing method according to claim 1 .

4. Displaying the transverse layer image showing the detected detection target area; According to a result of judging whether the cross-sectional image including the detection target region contains a threshold value or more, a display of the detection target region on the cross-sectional image is updated. The information processing method according to claim 1 .

5. When the detection target area is not detected from the first transverse layer image at a position corresponding to the scanning range in which it is determined that the transverse layer image including the detection target area is included in a threshold value or more, the detection result of the detection target area in the first transverse layer image is updated based on the detection result of the detection target area in the second transverse layer image existing before and after the first transverse layer image. The information processing method according to claim 4.

6. generating distribution data indicating the presence or absence of the detection target region along the axial direction as a binary value according to whether or not the detection target region is detected from each of the transverse slice images; By determining whether the moving average of the distribution data is equal to or greater than a threshold, it is determined whether the cross-sectional image including the detection target region includes a threshold or more. The information processing method according to claim 1 .

7. When it is determined that the moving average is equal to or greater than the threshold, a continuous region that is equal to or greater than the threshold, including the region where the moving average is equal to or greater than the threshold, is identified from the distribution data; The marker is displayed at a position on the longitudinal tomographic image corresponding to the specified region. The information processing method according to claim 6.

8. Identifying an angle of the detection target region detected from each of the transverse slice images in a circumferential direction of the blood vessel; The presence or absence of the detection target region in each of the cross-sectional images is determined according to the angle, and the distribution data is generated. The information processing method according to claim 6.

9. Calculating a feature amount related to the detection target region detected from each of the cross-sectional images; Grouping cross-sectional images including the detection target region based on the feature amount; It is determined whether the transverse slice images of each group are included within a scanning range along the axial direction by a threshold value or more. The information processing method according to claim 1 .

10. Identifying an angle of the detection target region detected from each of the transverse slice images in a circumferential direction of the blood vessel; When the markers adjacent to each other along the axial direction are spaced apart by a predetermined distance or more, or when the detection target regions corresponding to the markers adjacent to each other along the axial direction are spaced apart by a predetermined angle or more along the circumferential direction, the markers are displayed in different display modes. The information processing method according to claim 1 .

11. A plurality of transverse cross-sectional images are obtained by successively capturing images of a cross section intersecting an axial direction of the blood vessel along the axial direction; Each acquired cross-sectional image is input to a model that has been trained to detect a detection target area when a cross-sectional image is input, thereby detecting the detection target area from each cross-sectional image; generating a longitudinal image showing a cross section of the blood vessel along the axial direction from the plurality of transverse images; determining whether the transverse slice image including the detection target region is included within a scanning range along the axial direction by a threshold value or more; When it is determined that the transverse slice image including the detection target region contains a threshold value or more, a marker indicating the presence of the detection target region is displayed at a corresponding position of the longitudinal slice image. A program that causes a computer to carry out processing.

12. An information processing device including a control unit, The control unit: A plurality of transverse cross-sectional images are obtained by successively capturing images of a cross section intersecting an axial direction of the blood vessel along the axial direction; Each acquired cross-sectional image is input to a model that has been trained to detect a detection target area when a cross-sectional image is input, thereby detecting the detection target area from each cross-sectional image; generating a longitudinal image showing a cross section of the blood vessel along the axial direction from the plurality of transverse images; determining whether the transverse slice image including the detection target region is included within a scanning range along the axial direction by a threshold value or more; When it is determined that the transverse slice image including the detection target region contains a threshold value or more, a marker indicating the presence of the detection target region is displayed at a corresponding position of the longitudinal slice image. Information processing device.

Images