Diagnostic support device, device operation method, and diagnostic support program

Abstract

A diagnostic support device, a diagnostic support method, and a diagnostic support program are provided that can easily assess whether a subject has pulmonary embolism. [Solution] The diagnostic support device includes a determination unit that determines the shape composed of the area of ​​reduced blood flow in the subject based on a blood flow analysis image of a radiological dynamic image, or determines information regarding whether the subject has a pulmonary embolism based on a learning model trained using as input information regarding the shape, image information based on the radiological dynamic image, and information regarding whether the subject has a pulmonary embolism, and an output unit that outputs information regarding the pulmonary embolism based on the determination result of the determination unit.

Description

[Technical Field]

[0001] The present invention relates to a diagnostic support device, a diagnostic support method, and a diagnostic support program. [Background technology]

[0002] Conventionally, there is known a device that can evaluate the presence or absence of a disease (such as pulmonary embolism) by analyzing the blood flow of a subject in a radiological dynamic image of the chest region of the subject (see, for example, Patent Document 1). This configuration displays regions in the representative image where blood flow is reduced in an identifiable manner by showing the boundaries of regions in the representative image where the amount of change in signal value is equal to or less than a threshold value with dashed lines. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-121104 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the configuration described in Patent Document 1, the region where the change in signal value is below the threshold may include both a region corresponding to pulmonary embolism and a region not corresponding to pulmonary embolism. Therefore, a user must visually evaluate whether or not a subject has pulmonary embolism, which may be difficult depending on the user's level of knowledge. In particular, physicians who are not accustomed to viewing dynamic radiological images may have difficulty determining whether or not a subject has pulmonary embolism. Furthermore, such physicians may miss areas that appear to be pulmonary embolism when visually inspecting the image. In other words, the configuration described in Patent Document 1 leaves room for improvement in terms of easily assessing whether a subject has pulmonary embolism.

[0005] An object of the present invention is to provide a diagnostic support device, a diagnostic support method, and a diagnostic support program that can easily assess whether a subject has pulmonary embolism. [Means for solving the problem]

[0006] The diagnosis support device according to the present invention comprises: Based on the blood flow analysis image of the radiological dynamic image, the shape of the boundary line of the subject's blood flow decreased area Whether it is wedge-shaped or not a determination unit for determining an evaluation unit that, when the determination unit determines that the shape is the wedge-shaped shape, evaluates an angle of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the angle; Equipped with.

[0007] The present invention Equipment operation The method is: a determining unit and an evaluating unit; Diagnostic support for pulmonary embolism Operation of equipment in the device 1. A method comprising: The determination unit Based on the blood flow analysis image of the radiological dynamic image, the shape of the boundary line of the subject's blood flow decreased area Whether it is wedge-shaped or not To judge and When the determination unit determines that the shape is the wedge-shaped shape, the evaluation unit evaluates an angle of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the angle. It has.

[0008] The diagnostic assistance program according to the present invention comprises: A diagnostic support program for pulmonary embolism, comprising: On the computer, Based on the blood flow analysis image of the radiological dynamic image, the shape of the boundary line of the subject's blood flow decreased area Whether it is wedge-shaped or not A process of determining a process of evaluating an angle of the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the angle; Execute the following. [Effects of the Invention]

[0009] According to the present invention, it is possible to easily evaluate whether a subject has pulmonary embolism. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a connection diagram showing a system configuration according to an embodiment of the present invention; [Figure 2]1 is a block diagram showing the configuration of a main part of a dynamic analysis device according to an embodiment of the present invention. [Figure 3] FIG. 10 is a diagram showing an example of a portion where blood flow is reduced in a blood flow analysis image. [Figure 4] FIG. 10 is a diagram showing an example of a blood flow analysis image on which shape information is superimposed and displayed. [Figure 5] 10 is a flowchart showing an example of the operation of an evaluation process performed by the dynamic analysis device. [Figure 6] FIG. 10 is a diagram showing an example of a portion where blood flow is reduced in a blood flow analysis image. [Figure 7] FIG. 10 is a diagram showing an example of a portion where blood flow is reduced in a blood flow analysis image. DETAILED DESCRIPTION OF THE INVENTION

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will now be described in detail with reference to the accompanying drawings, in which: Figure 1 is a connection diagram showing the system configuration of this embodiment.

[0012] A radiation imaging system is configured by a radiation imaging device 20 installed in an imaging room and a radiation imaging control device (console device) 10 installed in an operation room. The radiation imaging system is installed in a predetermined facility (for example, a medical facility such as a hospital) and is capable of capturing dynamic radiation images.

[0013] Here, capturing a radiological dynamic image refers to repeatedly irradiating a subject with pulsed radiation (e.g., X-rays) at a predetermined frame rate (pulse irradiation) to obtain multiple frame images. A radiological dynamic image refers to a series of frame images obtained by capturing a radiological dynamic image. Captured radiological dynamic images can also be subjected to dynamic analysis. Dynamic analysis refers to analytical processing performed on dynamic images, and includes processing for analyzing the subject's movements based on the dynamic image, as well as processing for analyzing the dynamic image to emphasize or attenuate (remove) predetermined structures.

[0014] External systems are also connected to the radiation imaging control device 10 via a communication network. The external systems include a picture archiving and communication system (PACS) 31, a hospital information system (HIS) 32, and a radiology information system (RIS) 33. An external dynamic analysis device 34 is also connected to the radiation imaging control device 10 via the communication network. In the communication network including the radiation imaging system, PACS 31, HIS 32, RIS 33, and dynamic analysis device 34, information is transmitted and received in accordance with, for example, the Digital Image and Communications in Medicine (DICOM) standard.

[0015] The radiation imaging apparatus 20 includes a high-voltage generator 21, an X-ray tube device 22, an imaging table 23, and an FPD 24. These components are well known and may be configured in a known manner, so a description thereof will be omitted here. In addition to these components, the radiation imaging apparatus 20 also includes a display device 25 and a speaker 26. The display device 25 and the speaker 26 function as output devices for outputting guidance for guiding the subject's movements.

[0016] The radiation imaging device 20 is connected to the radiation imaging control device 10 via a communication cable. The radiation imaging control device 10 controls the imaging operation of the radiation imaging device 20 by controlling the high voltage generator 21. The radiation imaging control device 10 also performs image analysis of the radiation image obtained by the FPD 24. The radiation imaging device 20 may be installed in an imaging room, or may be configured to be mobile by being incorporated into a medical cart or the like.

[0017] The radiation imaging control device 10 inputs test order information (test order) from the HIS 32 or RIS 33 and displays this test order on the screen. The user controls the radiation imaging device 20 based on the displayed test order. The radiation imaging control device 10 may also have a function to automatically control the radiation imaging device 20 based on the test order.

[0018] The radiation imaging control device 10 basically comprises a control unit that controls radiation image capture in the radiation imaging device 20, an image processing unit that processes the radiation images (radiation dynamic images), etc. The radiation imaging control device 10 also comprises a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc. In the radiation imaging control device 10, the CPU reads out a program corresponding to the processing content from the ROM and loads it into the RAM. Then, the radiation imaging control device 10 cooperates with the loaded program to centrally control the operation of each unit.

[0019] Furthermore, the dynamic analysis device 34 performs a dynamic analysis of the radiological dynamic images captured by the radiography system. The dynamic analysis device 34 includes a CPU, a ROM, a RAM, etc. In the dynamic analysis device 34, the CPU reads out a program corresponding to the processing content from the ROM and loads it into the RAM. Then, the dynamic analysis device 34 works in cooperation with the loaded program to centrally control the operation of each unit. As shown in FIG. 2, the dynamic analysis device 34 includes a communication unit 341, a generation unit 342, a determination unit 343, an evaluation unit 344, and an output unit 345. The dynamic analysis device 34 corresponds to the "diagnosis support device" of the present invention.

[0020] The communication unit 341 is configured to be able to transmit and receive information to and from the radiation imaging system, PACS 31, HIS 32, and RIS 33. For example, the communication unit 341 acquires information on examination orders input to external systems such as the HIS 32 and RIS 33, and information on dynamic radiation images captured by the radiation imaging system. The communication unit 341 also transmits information such as dynamic radiation images that have been processed for display on a display medium and analysis results of the dynamic radiation images to the PACS 31, etc.

[0021] The generation unit 342 generates a blood flow analysis image by performing a blood flow analysis on the radiation dynamic image acquired from the FPD 24. The blood flow analysis image is included in the analysis result of the radiation dynamic image.

[0022] The determination unit 343 determines the shape of the boundary line of the region of reduced blood flow in the subject in the blood flow analysis image generated by the generation unit 342. The region of reduced blood flow is a region in the blood flow analysis image where the analysis value of blood flow is relatively low, and is a portion where the blood flow of the subject based on the blood flow analysis image is less than a predetermined amount. The region of reduced blood flow that appears due to pulmonary embolism in the blood flow analysis image is indicated by two boundary lines whose shape on the hilar side is wedge-shaped, that is, two boundary lines that extend from the hilum toward the extremities and have an angle at the center point near the hilum. In addition, the inside of the boundary line has poor blood flow and the blood flow analysis value is low, while the outside of the boundary line has high blood flow and the blood flow analysis value is high, characterized by high contrast. The "Guidelines for the Diagnosis, Treatment, and Prevention of Pulmonary Embolism and Deep Vein Thrombosis" (URL: https: / / js-phlebology.jp / wp / wp-content / uploads / 2019 / 03 / JCS2017_ito_h.pdf) states that acute pulmonary embolism shows a wedge-shaped defect on perfusion scintigraphy. Similar to perfusion scintigraphy, a wedge-shaped reduction in blood flow also occurs on perfusion analysis images. This principle is thought to be due to the disruption of blood flow at the lobe / segment / subsegment level, resulting in a convex shape at the hilum.

[0023] The determining unit 343 determines, for example, the shape of the boundary line on the side near the hilum in the blood flow analysis image.

[0024] A blood flow analysis image is a moving image in which the blood flow analysis value is the amount or rate of change of signal values ​​from a reference frame (such as end diastole) in multiple frame images included in a radiological dynamic image. This makes it possible to visualize the increase or decrease of blood flow based on the heartbeat. When the blood flow analysis image is displayed on a display medium, a color value is calculated from the amount of change based on a preset coloring table (a table in which the amount of change is associated with a color), and the display color on the display medium is determined.

[0025] Specifically, the determining unit 343 determines whether or not the shape of the boundary line of the blood flow decreased region is wedge-shaped (approximately V-shaped).

[0026] For example, if a subject has pulmonary embolism, blood flow is interrupted in the lung downstream of the pulmonary embolism site in the vascular tree structure, or in the area corresponding to the pulmonary blood vessels, and the analysis value of the blood flow rate decreases on the blood flow analysis image, appearing as an area of ​​reduced blood flow. In the blood flow analysis image, the display color of the reduced blood flow area is different from the display color of the surrounding area. By checking the display color of the reduced blood flow area, a user such as a doctor can confirm whether the subject has pulmonary embolism.

[0027] Blood vessels radiate from the origin of the pulmonary artery. It has been empirically confirmed that in blood flow analysis images of subjects with pulmonary embolism, the boundary of the region with reduced blood flow is wedge-shaped (approximately V-shaped) due to the interruption of blood flow in the blood vessels corresponding to the pulmonary embolism. In blood flow analysis images, the time change in blood volume, which is assumed to be roughly correlated with lung volume, is summed in the X-ray projection direction to obtain a two-dimensional image. The overlap of multiple lung segments, subsegments, and lobules is obtained as a projection image. Therefore, in pulmonary embolism, blood flow is interrupted in a single mass, such as a lung segment, subsegment, or lobule. Therefore, the region with reduced blood flow due to pulmonary embolism generally has two boundary lines extending from the hilum to the periphery, and the boundary line has a clear edge. In conventional configurations, users had to visually interpret the blood flow analysis image to determine whether the boundary of the region with reduced blood flow is wedge-shaped. Therefore, depending on the user's level of knowledge, it may be difficult to determine whether the patient has a pulmonary embolism.

[0028] In contrast, in this embodiment, the determination unit 343 determines whether the shape of the boundary line of the blood flow reduction area is the above-mentioned wedge shape, making it possible to easily evaluate whether or not there is pulmonary embolism.

[0029] For example, the determination unit 343 performs binarization processing on the blood flow analysis image to extract regions of reduced blood flow and regions of increased blood flow. The binarization processing may use, for example, an absolute value of the blood flow analysis value or a relative value of the blood flow analysis value in the lung field as a fixed threshold, but other methods such as Otsu's binarization may also be used. Next, the determination unit 343 determines whether the shape formed by the boundary line of the extracted region of reduced blood flow is wedge-shaped.

[0030] As another determination method, since the above-mentioned boundary line is characterized by a clear edge, the determination unit 343 performs edge detection on the blood flow analysis image and directly extracts candidates for the boundary line of the wedge-shaped blood flow reduction region. The edge detection can be performed using image processing such as a Hough transform or line detection. The edges extending radially from the origin of the pulmonary artery, with the hilum as the center point, are extracted.

[0031] Next, the determination unit 343 may determine whether a wedge-shaped inner region, which is centered around the vicinity of the hilum and is composed of two boundary line candidates or one boundary line candidate and a lung field boundary line, corresponds to a region of reduced blood flow based on the difference in blood flow analysis value between the inner region and the outer region. By this determination, the determination unit 343 determines whether the shape is a wedge-shaped region of reduced blood flow.

[0032] As described above, the determination unit 343 determines that an extracted shape (for example, the shape of the boundary between two regions of reduced blood flow, specifically, the shape of two boundary lines extending from the hilum toward the periphery) is wedge-shaped or approximately V-shaped. Specifically, the determination unit 343 determines that a shape is wedge-shaped when two radial lines, which can be considered to be lines extending toward the periphery from a point near the hilum among the boundary lines, form a shape in which a predetermined angle is formed. Furthermore, the determination unit 343 determines that a shape is not wedge-shaped when the two boundary lines do not form an angle. Empirically, the predetermined angle is, for example, inappropriate when it is less than 10 to 20 degrees because it is highly likely to cause artifacts due to pulsation of structures such as blood vessels, while an angle of approximately 30 to 60 degrees is preferable because it is considered to have a high average probability of occurrence based on the vascular tree structure. In the case of a large defect, such as at the lobe level, the angle often increases to approximately 120 degrees. In the case of total loss (where almost the entire lung field is hypoperfusion), there is no need to point out a wedge shape because it is clearly a pulmonary embolism, but it is acceptable to detect this as well. The angle between the two rays with the hilum as the center point is 180 degrees, and both rays fall on the border of the lung field.

[0033] For example, suppose that A1, A2, B1, B2, C1, C2, and D are extracted as boundary lines of blood flow reduction regions in the blood flow analysis image as shown in Fig. 3. In this case, the determination unit 343 determines that the boundary lines of two blood flow reduction regions, A1 and A2, B1 and B2, and C1 and C2, form an angle, and thus are wedge-shaped. Furthermore, the determination unit 343 determines that D, which has an arc shape, is not a wedge-shaped shape because it does not form an angle.

[0034] The size of the blood flow reduction region to be determined may be set according to the minimum size of the pulmonary embolism to be detected. For example, if the detection target is a pulmonary lobule, the size of the blood flow reduction region may be set to a diameter of approximately 1 to 2.5 cm or more. Furthermore, adjustments may be made to the blood flow analysis algorithm. For example, since the blood flow analysis algorithm uses the average value of a 1 cm square, the detection limit may be set to 1 cm square.

[0035] Note that when a region of reduced blood flow abuts a lung field boundary, the edge may not be clear, and therefore the determination unit 343 may exclude portions with unclear edges from the determination target. Furthermore, a blood flow analysis image is, more precisely, an image in which a large change in blood volume in the main blood vessel is added to the blood flow volume, which is approximately correlated with the lung volume. When a main blood vessel is interrupted, an amplified blood flow (strong signal) up to the main blood vessel appears in the blood flow image, and subsequent blood vessels and the lung (peripheral blood vessels) are missing. Therefore, the determination unit 343 may also exclude the main blood vessel portion with the strong signal from the determination target.

[0036] The evaluation unit 344 evaluates whether or not the subject has pulmonary embolism based on the determination result of the determination unit 343. Specifically, when the determination unit 343 determines that the shape is a wedge shape, the evaluation unit 344 evaluates whether or not the subject has pulmonary embolism.

[0037] More specifically, the evaluation unit 344 evaluates an index indicating the likelihood of pulmonary embolism based on the wedge shape. The index indicating the likelihood of pulmonary embolism is an index based on information about the shape of the blood flow analysis image, which is composed of multiple blood flow reduction portions. The index indicating the likelihood of pulmonary embolism may be empirically set based on, for example, blood flow analysis images of radiological dynamic images taken from multiple subjects.

[0038] The index indicating the likelihood of pulmonary embolism may be, for example, the wedge angle of the wedge shape, which is the angle between two portions of reduced blood flow where the blood flow rate of the subject is less than a predetermined amount.

[0039] The evaluation unit 344 evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the index indicating the likelihood of pulmonary embolism.

[0040] Specifically, for example, if the wedge angle is equal to or greater than a predetermined angle, the evaluation unit 344 evaluates that the subject has pulmonary embolism, and if the wedge angle is less than the predetermined angle, the evaluation unit 344 evaluates that the subject does not have pulmonary embolism.

[0041] The predetermined angle is, for example, an angle (for example, 45 degrees) at which an artifact along the blood vessel path cannot be recognized, and is an angle that can be set arbitrarily.

[0042] 3, among the three portions determined to be wedge-shaped, the wedge angles of A1 and A2 and B1 and B2 are assumed to be equal to or greater than a predetermined angle. In this case, the evaluation unit 344 evaluates that the portions related to these wedge shapes are portions corresponding to pulmonary embolism, and therefore evaluates that the subject has pulmonary embolism.

[0043] Furthermore, among the three portions determined to be wedge-shaped, the wedge angles of C1 and C2 are less than a predetermined angle. Therefore, the evaluation unit 344 evaluates that the portions related to the wedge shapes are not portions corresponding to pulmonary embolism. For example, if A1, A2 and B1, B2 are not extracted as portions with reduced blood flow, the evaluation unit 344 evaluates that the subject does not have pulmonary embolism.

[0044] This allows the dynamic analysis device 34 to easily evaluate whether or not the subject has pulmonary embolism.

[0045] When the evaluation unit 344 evaluates that the subject has pulmonary embolism, the output unit 345 outputs information about the pulmonary embolism to an external device such as the radiography control device 10 or the PACS 31. The information about the pulmonary embolism is, for example, wedge-shaped information, and is displayed on a display medium of the external device. Specifically, the output unit 345 outputs information about a blood flow analysis image on which line information for superimposing and displaying on blood vessel portions in which the blood flow rate of the subject is less than a predetermined amount is superimposed, based on the blood flow analysis image.

[0046] For example, in the example shown in Figure 3, the wedge-shaped areas A1 and A2 and the wedge-shaped areas B1 and B2 correspond to areas where pulmonary embolism exists. In this case, as shown in Figure 4, the display medium displays line information indicating the areas where blood flow is reduced at A1, A2, B1, and B2 superimposed on an image of reduced blood flow. Note that the wedge-shaped areas C1 and C2 in Figure 3 do not correspond to areas where pulmonary embolism exists, so line information is not displayed on the display medium. Furthermore, the area D in Figure 3 is not determined to be wedge-shaped, so line information is not displayed on the display medium.

[0047] This allows the user to easily confirm which location in the blood flow analysis image is the embolism location.

[0048] Furthermore, the output unit 345 selects a frame image to be a summary image from among the multiple frame images constituting the radiation dynamic image based on the blood flow analysis image. In other words, the output unit 345 determines the blood flow analysis image to be the summary image by selection or synthesis based on the blood flow analysis moving image composed of the respective blood flow analysis images of the multiple frame images. Then, the output unit 345 outputs the blood flow analysis image in which shape information (the above-mentioned line information) is superimposed on the summary image.

[0049] The summary image determination process can be performed using various methods. For example, an arbitrary frame image may be selected as the summary image from among multiple frame images. Alternatively, a synthesis process may be performed in which a representative value, such as the maximum or minimum value of the blood flow analysis value over two heartbeats in the time direction, is calculated for each pixel of the blood flow analysis moving image, and this representative value is used as the blood flow analysis value for each pixel of the summary image. Furthermore, after superimposing line information related to wedge shapes on all of the multiple frame images, the frame image that most clearly shows the wedge shapes or the frame image with the largest number of wedge shapes may be selected as the target for the summary image.

[0050] This allows the user to evaluate whether or not the subject has pulmonary embolism simply by checking the summary image, thereby improving the efficiency of user interpretation of blood flow analysis images (radiation dynamic images).

[0051] The output unit 345 may perform processing to display information in which the shape information is superimposed on a frame image such as a summary image on the display unit of the dynamic analysis device 34. In this case, the output unit 345 corresponds to the "display processing unit" of the present invention.

[0052] The user interprets the image, for example, in the following manner.

[0053] First, the display processing unit of the external device displays a summary image on a display medium. The display of shape information on the summary image may be switchable between display and non-display. Also, a summary image with superimposed shape information and a summary image without shape information may be displayed side by side.

[0054] By checking the summary image, the user can understand the outline of the blood flow analysis image.

[0055] Next, after the user checks the summary image, the user may check the details of the blood flow analysis image (for example, the presence or absence of phase abnormalities, etc.) In this case, the display processing unit of the external device displays the blood flow analysis image on the display medium as if it were being played back based on the user's operation.

[0056] The user's operation is, for example, pressing a play button for the blood flow analysis image. The blood flow analysis image may also be displayed alongside the summary image. A display switch button for switching to the blood flow analysis image may be provided within the display screen for the summary image, and the display of the summary image may be switched to the display of the blood flow analysis image by the user pressing the display switch button.

[0057] For example, if a phase abnormality (timing delay) occurs in the blood flow analysis image, there may be a portion of reduced blood flow that is not shown in the summary image. Therefore, after checking the summary image, the user can check the blood flow analysis image to see if there is a portion related to pulmonary embolism caused by the phase abnormality.

[0058] After checking the blood flow analysis image, the user may check the radiation dynamics image (original image) that has not been subjected to blood flow analysis processing. In this case, the display processing unit of the external device may display the original image on a display medium.

[0059] This allows the user to confirm the relationship between the blood flow signal and the anatomical structure (spatial position).

[0060] In addition, after completing the interpretation of a radiation dynamic image such as a summary image, the user may create an interpretation report. In this case, the user can use the summary image in creating the interpretation report. In addition, the interpretation report may include a blood flow analysis image in which shape information is superimposed on the blood flow analysis image, and an evaluation result of an index indicating the likelihood of pulmonary embolism.

[0061] That is, in this embodiment, the summary image can assist the user in interpreting the image.

[0062] Next, we will explain the flow of processing by the dynamic analysis device 34. Fig. 5 is a flowchart showing an example of the operation of evaluation processing by the dynamic analysis device 34. This control is executed appropriately when a blood flow analysis image in a radiation dynamic image is generated in the dynamic analysis device 34.

[0063] 5, the dynamic analysis device 34 extracts the boundary line of the blood flow decreased region in the blood flow analysis image (step S101). After step S101, the dynamic analysis device 34 determines whether two or more boundary lines have been extracted (step S102).

[0064] As a result of the determination, if two or more boundary lines have been extracted (YES in step S102), the dynamic analysis device 34 determines whether or not there is a wedge shape formed by the two boundary lines (step S103).

[0065] If the determination result indicates that a wedge shape is present (step S103, YES), the dynamic analysis device 34 determines whether the index of likelihood of pulmonary embolism is equal to or greater than a predetermined value (step S104). Specifically, the dynamic analysis device 34 determines whether the wedge angle is equal to or greater than a predetermined angle.

[0066] If the result of the determination is that the index of likelihood of pulmonary embolism is equal to or greater than the predetermined value (step S104, YES), the dynamics analysis device 34 evaluates that the subject has pulmonary embolism (step S105).

[0067] After step S105, the dynamic analysis device 34 outputs shape information of the wedge shape to an external device such as the radiation imaging control device 10 (step S106).

[0068] If the determinations in steps S102, S103, and S104 are NO, the dynamic analysis device 34 evaluates that the subject does not have pulmonary embolism (step S107).

[0069] After step S106 or step S107, this control ends.

[0070] According to the present embodiment configured as described above, whether or not the subject has pulmonary embolism is evaluated based on the result of determining the shape of the boundary between two blood flow reduction regions based on the blood flow analysis image.

[0071] This eliminates the need for the user to evaluate whether or not the subject has pulmonary embolism, and allows the subject to be easily evaluated as having pulmonary embolism.

[0072] Furthermore, if the shape is determined to be a wedge shape, the subject is evaluated as to whether or not they have pulmonary embolism, which allows the evaluation of pulmonary embolism to be narrowed down, thereby improving the efficiency of the evaluation work for pulmonary embolism.

[0073] Furthermore, since an index indicating the likelihood of pulmonary embolism is evaluated based on the wedge shape to evaluate pulmonary embolism, the accuracy of the evaluation of pulmonary embolism can be improved.

[0074] Furthermore, if the subject is evaluated as having pulmonary embolism, shape information is output, allowing the user to easily confirm the location of the embolism via the display medium of the external device.

[0075] Furthermore, line information for superimposing on the boundary line of the region with reduced blood flow is superimposed on the blood flow analysis image based on the blood flow analysis image, so that the user can more easily confirm the location of the embolism.

[0076] Furthermore, a frame image serving as a summary image is selected from among the multiple frame images based on the blood flow analysis image, and shape information is superimposed on the summary image. This allows the user to confirm whether or not the subject has pulmonary embolism by checking the summary image, thereby effectively assisting the user in interpreting the blood flow analysis image.

[0077] In the above embodiment, the index showing the likelihood of pulmonary embolism is the wedge angle, but the present invention is not limited to this, and may be something other than the wedge angle.

[0078] For example, the index of likelihood of pulmonary embolism may be the area of ​​a wedge region, which is, for example, an area surrounded by the boundaries of two wedge-shaped regions of reduced blood flow and the line segments connecting the ends of the boundaries.

[0079] Specifically, for example, if the area of ​​the wedge region is equal to or greater than a predetermined area value, the evaluation unit 344 evaluates that the subject has pulmonary embolism, and if the area of ​​the wedge region is less than the predetermined area value, the evaluation unit 344 evaluates that the subject does not have pulmonary embolism.

[0080] The predetermined area value is, for example, an area value that cannot be recognized as an artifact along the blood vessel path, and is an area value that can be set arbitrarily.

[0081] For example, in the example shown in Figure 3, the evaluation unit 344 evaluates whether the subject has pulmonary embolism based on the area values ​​of the area surrounded by two lines A1 and A2, the area surrounded by two lines B1 and B2, and the area surrounded by two lines C1 and C2.

[0082] For example, the evaluation unit 344 evaluates that the wedge shapes A1 and A2 and the wedge shapes B1 and B2, which have relatively large area values, correspond to embolization sites, and evaluates that the wedge shapes C1 and C2, which have relatively small area values, do not correspond to embolization sites.

[0083] Furthermore, for example, the indicator of the likelihood of pulmonary embolism may be the orientation of the wedge, which is, for example, the orientation of the tip (pointed part) of the wedge.

[0084] Specifically, for example, if the wedge is pointing toward the center of the subject, the evaluation unit 344 evaluates that the subject has pulmonary embolism, and if the wedge is pointing away from the center of the subject, the evaluation unit 344 evaluates that the subject does not have pulmonary embolism.

[0085] 6, the tip portions of the wedges A1 and A2 face toward the center, so the evaluation unit 344 evaluates that the wedge shapes of A1 and A1 correspond to an embolization site. Also, the tip portions of the wedges E1 and E2 face away from the center, so the evaluation unit 344 evaluates that the wedge shapes of E1 and E2 do not correspond to an embolization site.

[0086] Furthermore, for example, the index indicating the likelihood of pulmonary embolism may be a blood flow analysis value in the region surrounding the wedge, which may be, for example, signal values ​​in the inner and outer regions of the wedge in a blood flow analysis image.

[0087] Specifically, the evaluation unit 344 evaluates that the subject has pulmonary embolism when the blood flow analysis value of the inner region of the wedge is a value indicating decreased blood flow and the blood flow analysis value of the outer region of the wedge is a value not indicating decreased blood flow.Furthermore, the evaluation unit 344 evaluates that the subject does not have pulmonary embolism when the blood flow analysis value of the inner region of the wedge is a color not indicating decreased blood flow or the blood flow analysis value of the outer region is a value indicating decreased blood flow.

[0088] For example, as shown in FIG. 7, the wedge shapes A1 and A2 have different display colors for the inner and outer regions. Specifically, the blood flow analysis values ​​for the inner regions of the wedge shapes A1 and A2 indicate a decrease in blood flow, while the blood flow analysis values ​​for the outer regions do not indicate a decrease in blood flow. Therefore, the evaluation unit 344 evaluates that the wedge shapes A1 and A2 are embolization sites. Furthermore, the wedge shapes B1 and B2 have the same display color for the inner and outer regions. Specifically, the blood flow analysis values ​​for both the inner and outer regions of the wedge shapes B1 and B2 do not indicate a decrease in blood flow. Therefore, the evaluation unit 344 evaluates that the wedge shapes B1 and B2 are not embolization sites.

[0089] Furthermore, for example, the indices indicating the likelihood of pulmonary embolism may be two or more of the wedge angle, the area of ​​the wedge region, the wedge direction, and the blood flow analysis value of the analysis result in the region surrounding the wedge. Furthermore, the evaluation unit 344 may evaluate the subject as having pulmonary embolism if one of the indices satisfies the condition for evaluating pulmonary embolism. Furthermore, the evaluation unit 344 may evaluate the subject as having pulmonary embolism if two or more of the indices satisfies the condition for evaluating pulmonary embolism.

[0090] In the above embodiment, when the boundary line between two blood flow reduction regions forms an angle, the determining unit 343 determines that the shape is a wedge shape. However, depending on the region in the radiological dynamic image, there may be a region that is not a target of pulmonary embolism.

[0091] For example, the location of the area surrounding the arterial origin is three-dimensionally different from the area subject to reduced blood flow associated with pulmonary embolism. Also, the brachiocephalic and subclavian arteries are areas where extrapulmonary blood flow signals are mixed in, and therefore are not areas subject to reduced blood flow associated with pulmonary embolism.

[0092] Therefore, if the position of the shape of the boundary line between at least two blood flow reduction regions is a specific position, the determination unit 343 may exclude the specific position from the target of the shape determination. The specific position is a position that is not a target of blood flow reduction related to pulmonary embolism, such as the position around the arterial root, the brachiocephalic artery, or the subclavian artery, and can be set as appropriate.

[0093] This makes it possible to prevent the subject from being diagnosed as having pulmonary embolism due to a portion that is not the target of pulmonary embolism.

[0094] In the above embodiment, after determining that the shape of the boundary between the two blood flow reduction regions is wedge-shaped, the subject is evaluated as to whether or not they have pulmonary embolism. However, the present invention is not limited to this. For example, the evaluation unit 344 may evaluate that the subject has pulmonary embolism by determining that the shape is wedge-shaped.

[0095] In the above embodiment, the determination unit 343 determines the shape of the boundary lines of the at least two blood flow reduction regions, but the present invention is not limited to this. The determination unit 343 may determine information regarding whether or not the subject has pulmonary embolism using, for example, a learning model.

[0096] The learning model is a trained model that receives a blood flow analysis image (image information based on a radiological dynamic image) as input and outputs information regarding whether or not a subject has a pulmonary embolism. The learning model is trained using information regarding the shape of the boundary line, the blood flow analysis image, and information regarding whether or not the subject has a pulmonary embolism as input. Specifically, the learning model is first trained using information regarding the shape of the boundary line and information regarding whether or not the subject has a pulmonary embolism as input as correct answer information. The trained learning model is then trained by adjusting parameters according to the error between the information output when the blood flow analysis image is input and the correct answer information. More specifically, the learning model receives the blood flow analysis image as input and outputs information regarding the shape of the boundary line and information regarding whether or not the subject has a pulmonary embolism, and is trained to minimize the error between these two outputs and the correct answer information. Furthermore, when the determination unit 343 makes a determination, i.e., when making an inference using the learning model, it is not necessary to use both of the two outputs.

[0097] Using the learning model trained in this way, the determination unit 343 determines information regarding whether or not the subject has pulmonary embolism. For example, the determination unit 343 acquires the blood flow analysis image generated by the generation unit 342, inputs it to the learning model, and acquires the output information.

[0098] The information regarding whether or not the subject has pulmonary embolism output from the learning model is, for example, information indicating whether or not the subject has pulmonary embolism. When the information acquired from the learning model indicates that the subject has pulmonary embolism, the determination unit 343 determines, for example, that the subject has pulmonary embolism. Furthermore, when the information acquired from the learning model indicates that the subject does not have pulmonary embolism, the determination unit 343 determines, for example, that the subject does not have pulmonary embolism. Then, the determination result of the determination unit 343 is output by the output unit 345 as information regarding pulmonary embolism.

[0099] Even with this configuration, the user does not have to go through the trouble of assessing whether or not the subject has pulmonary embolism, and therefore it is possible to easily assess whether or not the subject has pulmonary embolism.

[0100] Furthermore, the information regarding whether or not the subject has pulmonary embolism output by the learning model may be information indicating whether or not the subject has pulmonary embolism, as well as information indicating the shape of the boundary line. The information indicating the shape of the boundary line may be, for example, information indicating whether or not the shape is a wedge, which indicates reduced blood flow. If the information acquired from the learning model indicates a wedge shape, which indicates reduced blood flow, the determination unit 343 determines, for example, that the subject has pulmonary embolism. If the information acquired from the learning model indicates that the shape is not a wedge, which indicates reduced blood flow, the determination unit 343 determines, for example, that the subject does not have pulmonary embolism. The determination result of the determination unit 343 is then output by the output unit 345 as information regarding pulmonary embolism.

[0101] Furthermore, the information regarding whether or not the subject has pulmonary embolism may include both information indicating whether or not the subject has pulmonary embolism and information indicating the shape of the boundary line, i.e., the learning model may output both information indicating whether or not the subject has pulmonary embolism and information indicating the shape of the boundary line.

[0102] This can improve the accuracy of determination by the determination unit 343. Furthermore, the output unit 345 can make it easier for the user to determine whether or not the subject has pulmonary embolism based on the information related to pulmonary embolism.

[0103] Furthermore, the information regarding whether or not the subject has pulmonary embolism may include position information of the area corresponding to pulmonary embolism. Training the learning model with the position information of the area corresponding to pulmonary embolism can enable more efficient learning. Furthermore, when the correct information of the wedge-shaped area of ​​reduced blood flow is not necessarily based on pulmonary embolism, using the position information makes it possible to learn a wedge-shaped area of ​​reduced blood flow based on a true pulmonary embolism. The position information of the area corresponding to pulmonary embolism may be, for example, graphic information such as a square or a circle that can be superimposed on the area of ​​the area in the radiological dynamic image or the blood flow analysis image. The position information of the area corresponding to pulmonary embolism may also be text information indicating the area, such as the center of the right lung. The position information of the area corresponding to pulmonary embolism is output from the learning model, for example, along with information indicating whether or not the subject has pulmonary embolism and information indicating the shape of the boundary line.

[0104] Furthermore, in the configuration in which a learning model is used to determine information regarding whether a subject has pulmonary embolism, the image information input to the learning model is a blood flow analysis image, but the present invention is not limited to this. For example, the image information input to the learning model may be a radiological dynamic image that has not undergone dynamic analysis. In this case, when training the learning model, for example, the blood flow analysis image may be input as a correct answer and simultaneously trained, thereby enabling efficient training.

[0105] Since the movement of the pulmonary artery can be confirmed in the radiological dynamic image, it is possible to determine whether or not a subject has a pulmonary embolism based on the movement of the blood vessels. Furthermore, in the radiological dynamic image, it is possible to determine whether or not a subject has a pulmonary embolism based on the low pixel values ​​of the blood vessels. Therefore, by training a learning model using the radiological dynamic image as input instead of the blood flow analysis image, the determination unit 343 can use the learning model to determine information regarding whether or not a subject has a pulmonary embolism. The advantage of inputting the radiological dynamic image is that it is possible to learn whether or not a subject has a pulmonary embolism from the radiological dynamic image itself, including image features of the pulmonary embolism, such as the movement of the blood vessels and the pixel values ​​of the blood vessels. Therefore, it is possible to determine whether or not a subject has a pulmonary embolism with higher accuracy. Furthermore, due to this advantage, it is also possible to train a learning model to determine whether or not a subject has a pulmonary embolism using both the radiological dynamic image and the blood flow analysis image as input.

[0106] Furthermore, in the configuration in which information regarding whether or not a subject has pulmonary embolism is determined using a learning model, only image information such as a blood flow analysis image is input to the learning model in the above description, but the present invention is not limited to this. For example, information regarding the shape of a boundary line may be input to the learning model in addition to image information.

[0107] For example, the determination unit 343 extracts the boundary line of the blood flow reduction region in the blood flow analysis image generated by the generation unit 342. The method of extracting the boundary line is the same as in the above embodiment. Then, information on the extracted boundary line (information on the shape of the boundary line) and the blood flow analysis image are input to the learning model, and the determination unit 343 determines information on whether or not the subject has pulmonary embolism, which is output from the learning model.

[0108] By doing so, more detailed information can be input to the learning model, allowing for more efficient training. This also makes it easier for the learning model to output more accurate information. As a result, information regarding whether or not a subject has pulmonary embolism can be determined with greater accuracy.

[0109] In addition, in the configuration in which information regarding whether or not a subject has pulmonary embolism is determined using a learning model, the determination is made according to the information output from the learning model in the above description, but the present invention is not limited to this. For example, the determination unit 343 may determine information regarding whether or not a subject has pulmonary embolism based on information regarding the confidence level output from the learning model.

[0110] Specifically, for example, when the information acquired from the learning model indicates that the subject has pulmonary embolism and the certainty of the information is equal to or greater than a predetermined value, the determination unit 343 determines that the subject has pulmonary embolism. Also, for example, when the information acquired from the learning model indicates that the subject has pulmonary embolism and the certainty of the information is less than a predetermined value, the determination unit 343 determines that the subject does not have pulmonary embolism.

[0111] Furthermore, the learning model may be provided in the dynamic analysis device 34 or in a device other than the dynamic analysis device 34 .

[0112] In the above embodiment, the evaluation unit 344 is provided, but the present invention is not limited to this, and the evaluation unit may not be provided. In this case, the determination result by the determination unit 343 is output as information regarding pulmonary embolism.

[0113] Furthermore, in the above embodiment, the display unit of the radiation imaging control device 10 was exemplified as the display medium, but the present invention is not limited to this, and a display device other than the radiation imaging control device 10 may be the display medium.

[0114] In the above embodiment, shape information is displayed by superimposing line information on the boundary of the subject's area of ​​reduced blood flow in the blood flow analysis image, but the present invention is not limited to this. For example, text information that allows the user to understand the corresponding wedge-shaped area may be displayed on the display medium.

[0115] In addition, although a summary image is generated in the above embodiment, the present invention is not limited to this, and a summary image does not have to be generated. In this case, shape information may be displayed on each frame image of the blood flow analysis image.

[0116] Furthermore, in the above embodiment, the boundary line of the blood flow reduction region has a wedge shape, but the present invention is not limited to this, and may have, for example, a shape with a pointed portion.

[0117] In the above embodiment, the dynamic analysis device 34 is exemplified as a diagnosis support device, but the present invention is not limited to this. For example, the diagnosis support device may be another device such as the radiation imaging control device 10 or the RIS 33.

[0118] Furthermore, the above-described embodiments are merely examples of specific embodiments for carrying out the present invention, and the technical scope of the present invention should not be construed as being limited by these embodiments. In other words, the present invention can be carried out in various forms without departing from the gist or main features thereof. [Explanation of symbols]

[0119] 10 Radiography control device 20 Radiography equipment 21 High voltage generator 22 X-ray tube equipment 23 Photo stand 24 FPD 25 Display device 26 speakers 31 PACS 32 HIS 33RIS 34 Dynamic analysis device 341 Communications Department 342 Generation part 343 Judgment section 344 Evaluation Department 345 Output Section

Claims

1. a determining unit that determines whether or not the shape of the boundary line of the region of reduced blood flow in the subject is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge-shaped shape, evaluates an angle of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the angle; Equipped with Diagnostic support device.

2. A determination unit that determines whether the shape of the boundary line of the subject's blood flow reduced area is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge shape, evaluates an area of ​​a wedge region in the wedge shape based on the wedge shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the area of ​​the wedge region; Equipped with Diagnostic support device.

3. A determination unit that determines whether the shape of the boundary line of the subject's blood flow reduced area is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge-shaped shape, evaluates a direction of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the direction of the wedge; Equipped with Diagnostic support device.

4. A determination unit that determines whether the shape of the boundary line of the subject's blood flow reduced area is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge-shaped shape, evaluates a signal value of the blood flow analysis image in a peripheral region of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the signal value; Equipped with Diagnostic support device.

5. A determination unit that determines whether the shape of the boundary line of the subject's blood flow reduced area is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge-shaped shape, evaluates a signal value of the blood flow analysis image in a peripheral region of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the signal value; Equipped with the determination unit determines whether the inner region of the wedge shape corresponds to a region of decreased blood flow based on a difference between blood flow analysis values ​​of the inner region and an outer region thereof. Diagnostic support device.

6. A determination unit that determines whether the shape of the boundary line of the subject's blood flow reduced area is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; an evaluation unit that, when the determination unit determines that the shape is the wedge shape, evaluates whether or not the subject has pulmonary embolism based on the wedge shape; a display processing unit that displays information about the shape on a display medium when the evaluation unit evaluates that the subject has pulmonary embolism; Equipped with the display processing unit processes and displays, on the display medium, line information to be superimposed on the boundary line based on the evaluation result of the radiation dynamic image. Diagnostic support device.

7. the determination unit determines whether the inner region of the wedge shape corresponds to a region of decreased blood flow based on a difference between blood flow analysis values ​​of the inner region and an outer region thereof. The diagnosis support device according to any one of claims 1 to 3 and 6.

8. a display processing unit that displays information about the shape on a display medium when the evaluation unit evaluates that the subject has pulmonary embolism. The diagnosis support device according to any one of claims 1 to 5.

9. the display processing unit processes and displays, on the display medium, line information to be superimposed on the boundary line based on the evaluation result of the radiation dynamic image. The diagnosis support device according to claim 8.

10. The display processing unit selecting a frame image to be a summary image from among a plurality of frame images constituting the radiological dynamic image based on the evaluation result of the radiological dynamic image; displaying the summary image on the display medium so as to superimpose the shape information on the summary image; The diagnosis support device according to claim 8.

11. the evaluation unit excludes the shape from the evaluation target for pulmonary embolism when the shape is located at a specific position. The diagnosis support device according to any one of claims 1 to 6.

12. The blood flow reduction region is a portion in the blood flow analysis image where the blood flow analysis value is less than a predetermined amount. The diagnosis support device according to any one of claims 1 to 6.

13. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determination unit determines that the shape is the wedge-shaped shape, the evaluation unit evaluates an angle of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the angle. having How the equipment operates.

14. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, comprising: determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determination unit determines that the shape is the wedge shape, the evaluation unit evaluates an area of ​​a wedge region in the wedge shape based on the wedge shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the area of ​​the wedge region. having How the equipment operates.

15. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, comprising: determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determination unit determines that the shape is the wedge-shaped shape, the evaluation unit evaluates a wedge orientation in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the wedge orientation. having How the equipment operates.

16. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, comprising: determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determination unit determines that the shape is the wedge-shaped shape, the evaluation unit evaluates a signal value of the blood flow analysis image in a peripheral region of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the signal value. having How the equipment operates.

17. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, comprising: determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determination unit determines that the shape is the wedge-shaped shape, the evaluation unit evaluates a signal value of the blood flow analysis image in a peripheral region of the wedge in the wedge-shaped shape based on the wedge-shaped shape, and evaluates whether or not the subject has pulmonary embolism based on the evaluation result of the signal value. and The determining step includes determining whether the inner region of the wedge shape corresponds to a region of decreased blood flow based on a difference between blood flow analysis values ​​of the inner region and an outer region thereof. How the equipment operates.

18. A method for operating a device in a diagnostic support device for pulmonary embolism, including a determination unit and an evaluation unit, comprising: determining, by the determining unit, whether or not a boundary line of a region of reduced blood flow in the subject has a wedge shape based on a blood flow analysis image of the radiation dynamic image; When the determining unit determines that the shape is the wedge shape, evaluating whether or not the subject has pulmonary embolism based on the wedge shape; When the evaluation unit evaluates that the subject has pulmonary embolism, displaying information about the shape on a display medium; Equipped with The display processing includes displaying, on the display medium, line information to be superimposed on the boundary line based on an evaluation result of the radiation dynamic image. How the equipment operates.

19. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; a process of evaluating an angle of the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the angle; Execute Diagnostic support program.

20. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; a process of evaluating an area of ​​a wedge region in the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the area of ​​the wedge region; Execute Diagnostic support program.

21. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; a process of evaluating a direction of the wedge in the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the direction of the wedge; Execute Diagnostic support program.

22. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; a process of evaluating a signal value of the blood flow analysis image in a peripheral region of the wedge of the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the signal value; Execute Diagnostic support program.

23. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; a process of evaluating a signal value of the blood flow analysis image in a peripheral region of the wedge of the wedge shape based on the wedge shape when the shape is determined to be the wedge shape, and evaluating whether or not the subject has pulmonary embolism based on the evaluation result of the signal value; Execute the determining process includes a process of determining whether an inner region of the wedge shape corresponds to a region of decreased blood flow based on a difference between blood flow analysis values ​​of the inner region and an outer region thereof. Diagnostic support program.

24. A diagnostic support program for pulmonary embolism, comprising: On the computer, a process of determining whether the shape of the boundary line of the subject's blood flow reduced region is wedge-shaped based on the blood flow analysis image of the radiological dynamic image; If the shape is determined to be the wedge shape, a process of evaluating whether or not the subject has pulmonary embolism based on the wedge shape; a process of displaying information about the shape on a display medium when the subject is evaluated as having pulmonary embolism; Execute The display processing includes a process of displaying line information to be superimposed on the boundary line on the display medium based on an evaluation result of the radiation dynamic image. Diagnostic support program.

Images