Medical image processing device, method, and program

Abstract

To appropriately estimate a state of a region of interest.SOLUTION: A medical image processing device includes an acquisition part, a first calculation part, a second calculation part and a specification part. The acquisition part acquires a medical image. The first calculation part calculates a first blood flow direction based on a structure of a region of interest included in the medical image. The second calculation part calculates a second blood flow direction based on a structure of a periphery of the region of interest. The specification part specifies a state of the region of interest based on the first blood flow direction and the second blood flow direction.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in the present specification and drawings relate to a medical image processing device, a method, and a program. [Background technology]

[0002] Conventionally, there are known techniques for extracting the shapes of each anatomical structure of the human body from medical images, and there are also known techniques for estimating and evaluating the diagnosis of a disease or the degree of abnormality related to the anatomical structure based on the shape characteristics of the anatomical structure extracted by the above techniques. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2018-202147 Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to appropriately estimate the state of a region of interest. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0005] A medical image processing apparatus according to an embodiment includes an acquisition unit, a first calculation unit, a second calculation unit, and an identification unit. The acquisition unit acquires a medical image. The first calculation unit calculates a first blood flow direction based on a structure of a region of interest included in the medical image. The second calculation unit calculates a second blood flow direction based on a structure surrounding the region of interest. The identification unit identifies the state of the region of interest based on the first blood flow direction and the second blood flow direction. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a medical image processing apparatus according to the first embodiment. [Figure 2] FIG. 2 is a flowchart showing the processing procedure of the processing performed by each processing function of the processing circuitry of the medical image processing apparatus according to the first embodiment. [Figure 3A] FIG. 3A is a diagram for explaining an example of processing by the first calculation function according to the first embodiment. [Figure 3B] FIG. 3B is a diagram for explaining an example of processing by the first calculation function according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining an example of processing by the second calculation function according to the first embodiment. [Figure 5A] FIG. 5A is a diagram for explaining an example of a specific process performed by a specific function according to the first embodiment. [Figure 5B] FIG. 5B is a diagram for explaining an example of a specific process performed by a specific function according to the first embodiment. [Figure 5C] FIG. 5C is a diagram illustrating an example of a specific process performed by a specific function according to the first embodiment. [Figure 5D] FIG. 5D is a diagram for explaining an example of a specific process performed by a specific function according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of correspondence information according to the first embodiment. [Figure 7A] FIG. 7A is a diagram illustrating an example of evaluation information according to the first embodiment. [Figure 7B] FIG. 7B is a diagram illustrating an example of evaluation information according to the first embodiment. [Figure 7C] FIG. 7C is a diagram illustrating an example of evaluation information according to the first embodiment. [Figure 8] FIG. 8 is a diagram for explaining the processing according to the second embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of processing according to the third embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of evaluation information according to the third embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of evaluation information according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, embodiments of a medical image processing device, method, and program will be described in detail with reference to the drawings. Note that the medical image processing device, method, and program according to the present application are not limited to the embodiments shown below. In the following description, similar components will be given common reference numerals, and duplicated descriptions will be omitted.

[0008] (First embodiment) Fig. 1 is a diagram showing an example of the configuration of a medical image processing apparatus according to the first embodiment. For example, as shown in Fig. 1, a medical image processing apparatus 3 according to this embodiment is communicably connected to a medical image diagnostic apparatus 1 and a medical image storage apparatus 2 via a network. Note that various other devices and systems may also be connected to the network shown in Fig. 1.

[0009] The medical image diagnostic device 1 captures an image of a subject to generate a medical image. The medical image diagnostic device 1 then transmits the generated medical image to various devices on a network. For example, the medical image diagnostic device 1 is an X-ray diagnostic device, an X-ray CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, an ultrasound diagnostic device, a SPECT (Single Photon Emission Computed Tomography) device, a PET (Positron Emission Computed Tomography) device, etc.

[0010] The medical image storage device 2 stores various medical images related to subjects. Specifically, the medical image storage device 2 receives medical images from the medical image diagnostic device 1 via a network, and stores the medical images in a memory circuit within the device. For example, the medical image storage device 2 is realized by a computer device such as a server or a workstation. Furthermore, for example, the medical image storage device 2 is realized by a PACS (Picture Archiving and Communication System) or the like, and stores medical images in a format compliant with DICOM (Digital Imaging and Communications in Medicine).

[0011] The medical image processing device 3 performs various information processing related to the subject. Specifically, the medical image processing device 3 receives medical images from the medical image diagnostic device 1 or the medical image storage device 2 via a network, and performs various information processing using the medical images. For example, the medical image processing device 3 is realized by computer equipment such as a server or a workstation.

[0012] For example, the medical image processing device 3 includes a communication interface 31, an input interface 32, a display 33, a memory circuit 34, and a processing circuit 35.

[0013] The communication interface 31 controls the transmission and communication of various data sent and received between the medical image processing device 3 and other devices connected via a network. Specifically, the communication interface 31 is connected to the processing circuitry 35, and transmits data received from other devices to the processing circuitry 35, or transmits data transmitted from the processing circuitry 35 to other devices. For example, the communication interface 31 is realized by a network card, a network adapter, a NIC (Network Interface Controller), or the like.

[0014] The input interface 32 accepts input operations of various instructions and information from a user. Specifically, the input interface 32 is connected to the processing circuit 35, converts the input operations received from the user into electrical signals, and transmits the electrical signals to the processing circuit 35. For example, the input interface 32 may be realized by a trackball, a switch button, a mouse, a keyboard, a touchpad that performs input operations by touching the operation surface, a touchscreen that integrates a display screen and a touchpad, a non-contact input interface using an optical sensor, a voice input interface, etc. Note that in this specification, the input interface 32 is not limited to those that have physical operation components such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives electrical signals corresponding to input operations from an external input device provided separately from the device and transmits the electrical signals to a control circuit is also included as an example of the input interface 32.

[0015] The display 33 displays various types of information and data. Specifically, the display 33 is connected to the processing circuit 35 and displays various types of information and data received from the processing circuit 35. For example, the display 33 is realized by a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, or the like.

[0016] The memory circuitry 34 stores various data and programs. Specifically, the memory circuitry 34 is connected to the processing circuitry 35 and stores data received from the processing circuitry 35, or reads out stored data and transmits it to the processing circuitry 35. For example, the memory circuitry 34 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, a hard disk, an optical disk, or the like.

[0017] The processing circuitry 35 controls the entire medical image processing device 3. For example, the processing circuitry 35 performs various processes in response to input operations received from a user via the input interface 32. For example, the processing circuitry 35 receives data transmitted from another device via the communication interface 31 and stores the received data in the memory circuitry 34. Also, for example, the processing circuitry 35 transmits the received data from the memory circuitry 34 to the communication interface 31, thereby transmitting the data to another device. Also, for example, the processing circuitry 35 displays the data received from the memory circuitry 34 on the display 33.

[0018] The above describes an example of the configuration of the medical image processing device 3 according to this embodiment. For example, the medical image processing device 3 according to this embodiment is installed in a medical facility such as a hospital or a clinic, and supports various diagnoses and the formulation of treatment plans performed by users such as doctors. For example, the medical image processing device 3 executes various processes for appropriately estimating the state of a region of interest.

[0019] As described above, there are known techniques for estimating a diagnosis or the degree of abnormality based on the shape of a region of interest extracted from a medical image. However, even for organs (e.g., valves) that have the same shape or produce the same blood flow state, the degree of abnormality or prognostic risk caused by the shape or blood flow state of the region of interest may differ depending on the relationship between the organ and the shape of surrounding organs. Therefore, current techniques that perform estimation based on the shape of a region of interest may not be able to appropriately estimate the degree of abnormality or prognostic risk caused by the shape or blood flow state of the organ of interest.

[0020] Therefore, the medical image processing device 3 according to this embodiment is configured to appropriately estimate the state of the region of interest by identifying the state of the region of interest from the structure of the region of interest and the structure of the region surrounding the region of interest. Specifically, the medical image processing device 3 calculates a first blood flow direction in the region of interest based on the structure of the region of interest, calculates a second blood flow direction in the surrounding structure based on the surrounding structure, and identifies the state of the region of interest based on the first blood flow direction and the second blood flow direction. The medical image processing device 3 having such a configuration will be described in detail below.

[0021] For example, as shown in FIG. 1, in this embodiment, the processing circuitry 35 of the medical image processing device 3 executes a control function 351, an image acquisition function 352, an extraction function 353, a first calculation function 354, a second calculation function 355, and an identification function 356. Here, the control function 351 is an example of a display control unit. The image acquisition function 352 is an example of an acquisition unit. The first calculation function 354 is an example of a first calculation unit. The second calculation function 355 is an example of a second calculation unit. The identification function 356 is an example of an identification unit.

[0022] The control function 351 generates various GUIs (Graphical User Interfaces) and various display information in response to operations via the input interface 32, and controls the display 33 to display them. For example, the control function 351 causes the display 33 to display a GUI for setting a region of interest and surrounding regions, evaluation information for evaluating the state of a region of interest identified based on the direction of blood flow, and the like. The control function 351 can also generate various display images based on medical images acquired by the image acquisition function 352.

[0023] The image acquisition function 352 acquires medical images of the subject from the medical image diagnostic apparatus 1 or the medical image storage apparatus 2 via the communication interface 31. Specifically, the image acquisition function 352 acquires medical images including morphological information of three-dimensional anatomical structures of a region of interest to be processed and surrounding regions. The image acquisition function 352 can also acquire multiple medical images obtained by capturing multiple images in three dimensions in the time direction. For example, the image acquisition function 352 acquires CT images, ultrasound images, MRI images, X-ray images, Angio images, PET images, SPECT images, etc. as the multiple medical images. By executing the image acquisition function 352, the processing circuitry 35 receives medical images of the subject from the medical image diagnostic apparatus 1 or the medical image storage apparatus 2 and stores the received medical images in the memory circuitry 34.

[0024] The extraction function 353 extracts the structure of a region of interest (hereinafter referred to as the structure of interest) and the structure of a region surrounding the region of interest (hereinafter referred to as the surrounding structure) from the medical image acquired by the image acquisition function 352. Specifically, the extraction function 353 extracts the structure of interest and the surrounding structures that are targets for evaluating the state. For example, the extraction function 353 extracts a heart valve as the structure of interest and extracts blood vessels connected to the heart valve as the surrounding structures. The processing by the extraction function 353 will be described in detail later.

[0025] The first calculation function 354 calculates a first blood flow direction in a region of interest for the medical image acquired by the image acquisition function 352. For example, the first calculation function 354 calculates the blood flow direction caused by a heart valve extracted as a structure of interest. The processing by the first calculation function 354 will be described in detail later.

[0026] The second calculation function 355 calculates a first blood flow direction in a region surrounding the region of interest for the medical image acquired by the image acquisition function 352. For example, the first calculation function 354 calculates the blood flow direction caused by blood vessels or the like extracted as surrounding structures. The processing by the second calculation function 355 will be described in detail later.

[0027] The identification function 356 identifies the state of the region of interest based on the first blood flow direction and the second blood flow direction. For example, the identification function 356 identifies the state of a heart valve based on the blood flow direction caused by the structure of the heart valve and the blood flow direction caused by the structure of the blood vessel connected to the heart valve. That is, the identification function 356 identifies the state caused by the region of interest (e.g., a heart valve) on the human body. The processing by the identification function 356 will be described in detail later.

[0028] The processing circuitry 35 described above is realized by, for example, a processor. In this case, each of the processing functions described above is stored in the storage circuitry 34 in the form of a program executable by a computer. The processing circuitry 35 then reads and executes each program stored in the storage circuitry 34 to realize the function corresponding to each program. In other words, the processing circuitry 35 has each of the processing functions shown in FIG. 1 when each program has been read.

[0029] The processing circuitry 35 may be configured by combining multiple independent processors, and each processor may execute a program to realize each processing function. Furthermore, each processing function of the processing circuitry 35 may be realized by being distributed or integrated as appropriate across a single or multiple processing circuits. Furthermore, each processing function of the processing circuitry 35 may be realized by a combination of hardware and software, such as circuits. While the example described here is one in which programs corresponding to each processing function are stored in a single storage circuitry 34, the embodiment is not limited to this. For example, the programs corresponding to each processing function may be stored in multiple storage circuits in a distributed manner, and the processing circuitry 35 may read and execute each program from each storage circuit.

[0030] Next, the processing procedure by the medical image processing apparatus 3 will be described with reference to Fig. 2, and then each process will be described in detail. Fig. 2 is a flowchart showing the processing procedure of the processing performed by each processing function of the processing circuitry 35 of the medical image processing apparatus 3 according to the first embodiment.

[0031] 2, in this embodiment, the image acquisition function 352 acquires medical images of a subject from the medical image diagnostic apparatus 1 or the medical image storage apparatus 2 (step S101). For example, the image acquisition function 352 acquires a plurality of medical images containing morphological information of the anatomical structure of the biological organ to be processed, in response to an operation for acquiring the medical images via the input interface 32, in which the biological organ is in different states. This process is realized, for example, by the processing circuitry 35 calling up a program corresponding to the image acquisition function 352 from the storage circuitry 34 and executing it.

[0032] Next, the extraction function 353 extracts a structure of interest contained in the acquired medical image (step S102) and extracts surrounding structures (step S103). This process is realized, for example, by the processing circuitry 35 calling up and executing a program corresponding to the extraction function 353 from the storage circuitry 34. Note that while Fig. 2 shows a processing procedure for extracting a structure of interest and then extracting surrounding structures, the embodiment is not limited thereto, and the structure of interest may be extracted after extracting the surrounding structures, or the structure of interest and surrounding structures may be extracted simultaneously.

[0033] Then, the first calculation function 354 and the second calculation function 355 estimate the blood flow state (step S104). Specifically, the first calculation function 354 calculates the blood flow direction caused by the structure of interest (first blood flow direction), and the second calculation function 355 calculates the blood flow direction caused by the surrounding structure (second blood flow direction). This process is realized, for example, by the processing circuitry 35 calling up and executing programs corresponding to the first calculation function 354 and the second calculation function 355 from the storage circuitry 34.

[0034] Next, the identifying function 356 identifies the state of the structure of interest based on the first blood flow state and the second blood flow state (step S105). This process is realized, for example, by the processing circuitry 35 calling up and executing a program corresponding to the identifying function 356 from the storage circuitry 34.

[0035] Then, the control function 351 displays evaluation information based on the identified state on the display 33 (step S106). This process is realized, for example, by the processing circuitry 35 calling up a program corresponding to the control function 351 from the storage circuitry 34 and executing it.

[0036] Below, details of each process executed by the medical image processing device 3 will be explained. Note that the following will explain an example of processing in which the aortic valve is the structure of interest and the ascending aorta, into which blood flows via the aortic valve, is the surrounding structure. Note that the target of the processing described in this embodiment is not limited to this, and any biological organ in the human body involving fluid or gas can be the target.

[0037] (Medical image acquisition processing) 2, the image acquisition function 352 acquires a medical image including three-dimensional morphological information of the target biological tissue (aortic valve and ascending aorta) in response to an operation for acquiring a medical image via the input interface 32. For example, the image acquisition function 352 acquires a CT image of the aortic valve and ascending aorta captured in three dimensions.

[0038] As described above, the medical image acquisition process in step S101 may be started by a user instruction via the input interface 32, or may be started automatically. In such a case, for example, the image acquisition function 352 monitors the medical image storage device 2 and automatically acquires a medical image every time a new medical image is stored.

[0039] Here, the image acquisition function 352 may determine the newly stored medical image based on preset acquisition conditions, and execute the acquisition process if the medical image satisfies the acquisition conditions. For example, acquisition conditions that can determine the state of the medical image are stored in the memory circuitry 34, and the image acquisition function 352 determines the newly stored medical image based on the acquisition conditions stored in the memory circuitry 34.

[0040] For example, the memory circuitry 34 stores, as the acquisition condition, "acquire medical images captured using an imaging protocol targeting the heart," "acquire enlarged and reconstructed medical images," or a combination thereof. The image acquisition function 352 acquires medical images that satisfy the above acquisition conditions.

[0041] (Extraction of noteworthy structures) As described in step S102 of FIG. 2, the extraction function 353 extracts a structure of interest from a medical image. Specifically, the extraction function 353 acquires coordinate information of pixels representing the aortic valve in a CT image. Here, the extraction function 353 can extract the structure of interest using various methods. For example, the extraction function 353 can extract, as the structure of interest, an area specified on the CT image via the input interface 32. That is, the extraction function 353 extracts, as the structure of interest, an area manually specified by the user.

[0042] Furthermore, for example, the extraction function 353 can extract a structure of interest based on an anatomical structure depicted in a CT image using a known region extraction technique. For example, the extraction function 353 extracts a structure of interest in a CT image using Otsu's binarization method based on CT values, a region growing method, a snake method, a graph cut method, a mean shift method, or the like.

[0043] In addition, the extraction function 353 can extract noteworthy structures in CT images using a trained model constructed based on training data prepared in advance using machine learning technology (including deep learning).

[0044] Here, if a process such as the graph cut method is performed on the entire image, the calculation cost may become excessively high. Therefore, the extraction function 353 may target an area (hereinafter referred to as an associated area) that is associated with the structure of interest and is larger than the structure of interest but smaller than the entire image for extraction processing. For example, if the structure of interest is the aortic valve, the extraction function 353 identifies the heart area, the left ventricle, and the area surrounding the left ventricle as the region of interest. Then, the extraction function 353 applies the extraction process described above only to the identified associated area to extract the region of interest. Note that the associated area may also be set manually using the input interface 32.

[0045] (Extraction of surrounding structures) As described in step S103 of FIG. 2, the extraction function 353 extracts surrounding structures around the structure of interest from the medical image. Specifically, the extraction function 353 acquires coordinate information of pixels representing the ascending aorta in the CT image. For example, the extraction function 353 extracts the surrounding structures by processing similar to the extraction of the structure of interest in step S102. Here, the surrounding structures may be preset for each structure of interest based on anatomical structures, or may be specified by the user each time processing is performed. Alternatively, the surrounding structures may be extracted by the extraction function 353 based on the continuity or distribution of pixel values ​​around the structure of interest.

[0046] Furthermore, the surrounding structures set for the structure of interest can be selected arbitrarily. For example, in this embodiment, the ascending aorta is set as the surrounding structure of the aortic valve (structure of interest). However, the left ventricular outflow tract (LVOT), the left ventricle, or the entire sinus of Valsalva may also be set as the surrounding structure. Furthermore, the surrounding structures set for the structure of interest may be set in the same anatomical structure. For example, a plane (referred to as the Nadir plane) tangent to all of the coordinates (referred to as Nadir) of the positions located closest to the LOVT in each leaflet (RCC: right coronary cusp, LCC: left coronary cusp, NCC: non-coronary cusp) of the aortic valve may be set as the structure of interest, and a plane based on the positions of the commissures may be set as the surrounding structure.

[0047] (Blood flow direction calculation process) 2, the first calculation function 354 calculates the blood flow direction in the structure of interest extracted by the extraction function 353. The second calculation function 355 calculates the blood flow direction in the surrounding structure extracted by the extraction function 353. Examples of these processes will be described in order below.

[0048] The first calculation function 354 calculates the blood flow direction (first blood flow direction) in the region of interest based on the structure of the region of interest (structure of interest). For example, the first calculation function 354 calculates the blood flow direction caused by the aortic valve based on the structure of the aortic valve extracted by the extraction function 353. FIGS. 3A and 3B are diagrams for explaining an example of processing by the first calculation function 354 according to the first embodiment. Here, FIG. 3A shows the blood flow direction caused by a normal aortic valve, and FIG. 3B shows the blood flow direction caused by an abnormal aortic valve.

[0049] For example, as shown in Figure 3A, the first calculation function 354 extracts the coordinate (Nadir) "P1" of the position closest to the LOVT in each leaflet (RCC, LCC, NCC) of the aortic valve extracted from the CT image. Note that although only two "P1"s are shown in Figure 3A, "P1"s are actually extracted for each of the three leaflets. Then, the first calculation function 354 extracts a plane (Nadir plane) "L1" that is tangent to all three extracted "P1"s.

[0050] Furthermore, the first calculation function 354 extracts the aortic valve orifice and identifies coordinates based on the shape of the extracted valve orifice. For example, as shown in FIG. 3A, the first calculation function 354 identifies the centroid position "P2" of the aortic valve orifice. Then, the first calculation function 354 calculates the direction of arrow "L2" that is perpendicular to plane "L1" and passes through the centroid position "P2" as the blood flow direction based on the structure of the aortic valve.

[0051] In the case of a normal aortic valve, the arrow "L2" shown in Fig. 3A indicates the direction of blood flow based on the structure of the aortic valve. On the other hand, in the case of an abnormal aortic valve, as shown in Fig. 3B, the direction of blood flow (arrow "L2") calculated by the first calculation function 354 reflects the structure of the aortic valve and differs significantly from the normal direction.

[0052] Note that the above method is merely an example, and any calculation method may be used based on the structure of the region of interest. For example, the first calculation function 354 extracts a plane passing through the commissures of the aortic valve, and calculates the blood flow direction based on the structure of the aortic valve from the extracted plane and the center of gravity of the valve orifice. Alternatively, for example, the first calculation function 354 identifies a plane that minimizes the sum of distances from each position of a three-dimensional closed curve representing the shape of the aortic valve annulus and valve cusps, and calculates the blood flow direction based on the structure of the aortic valve from the plane and the center of gravity of the valve orifice. Alternatively, for example, the first calculation function 354 identifies a plane based on the shape of the entire valve, and calculates the blood flow direction based on the structure of the aortic valve from the plane and the center of gravity of the valve orifice.

[0053] In the above example, the blood flow direction is calculated from the relationship between the plane and the feature point (center of gravity), but it may also be calculated from multiple feature points, or from the relationship between a line segment and the feature point. For example, the direction of a straight line passing through the center of gravity of the overall valve shape and the center of gravity of the valve orifice shape may be taken as the blood flow direction based on the structure of the aortic valve.

[0054] The second calculation function 355 calculates the blood flow direction (second blood flow direction) around the region of interest based on the structure around the region of interest (surrounding structure). For example, the second calculation function 355 calculates the blood flow direction caused by the ascending aorta based on the structure of the ascending aorta extracted by the extraction function 353. Figure 4 is a diagram for explaining an example of processing by the second calculation function 355 according to the first embodiment.

[0055] For example, as shown in Fig. 4, the second calculation function 355 extracts the position of the AS (Aortic Sinus) in the ascending aorta extracted from the CT image, and identifies the center position (or center of gravity position) "P3" of the cross-sectional structure at the extracted position. Also, for example, as shown in Fig. 4, the second calculation function 355 extracts the position of the STJ (Sinotubular Junction) in the ascending aorta extracted from the CT image, and identifies the center position (or center of gravity position) "P4" of the cross-sectional structure at the extracted position. Then, the second calculation function 355 calculates the direction of arrow "L3" passing through the identified "P3" and "P4" as the blood flow direction based on the structure of the ascending aorta.

[0056] Note that the above-described method is merely an example, and any method may be used as long as the blood flow direction is estimated based on structures surrounding the structure of interest other than the structure of interest. For example, the blood flow direction based on the structure of the ascending aorta may be calculated using the center position or center of gravity position of the LOVT region, the left ventricle region, etc., or may be calculated based on the entrance (opening) of the coronary artery. Alternatively, the blood flow direction based on the structure of the ascending aorta may be calculated based on the curvature of the center line of the ascending aorta.

[0057] (Status specific processing) As described in step S105 of FIG. 2, the identification function 356 identifies the state of the region of interest based on the blood flow direction in the structure of interest (first blood flow direction) and the blood flow direction in the surrounding structure (second blood flow direction). Specifically, the identification function 356 identifies the state of the region of interest based on the difference between the first blood flow direction and the second blood flow direction. For example, the identification function 356 determines that the greater the difference between the first blood flow direction and the second blood flow direction, the greater the adverse effect on the human body caused by the structure of the region of interest.

[0058] Here, the difference between the first blood flow direction and the second blood flow direction may be, for example, the angle between the blood flow direction based on the structure of interest and the blood flow direction based on the surrounding structures, or the minimum distance between the line indicating the blood flow direction based on the structure of interest and the line indicating the blood flow direction based on the surrounding structures. The identification function 356 determines that the greater the difference in the blood flow direction, the worse the condition. In other words, the more similar the blood flow direction estimated from the structure of interest and the blood flow direction based on the structures surrounding the structure of interest are, the smoother the blood flows. Therefore, the closer the two blood flow directions are (the smaller the angle between them, the shorter the distance), the better the condition (the lower the risk).

[0059] 5A to 5D are diagrams illustrating an example of identification processing by the identification function 356 according to the first embodiment. Here, FIGS. 5A to 5D illustrate identification processing based on a first blood flow direction (arrow "L2") calculated using the aortic valve as a structure of interest and a second blood flow direction (arrow "L3") calculated using the ascending aorta as a surrounding structure. Also, FIGS. 5A to 5D illustrate a case where determination is made based on the angle between the blood flow direction based on the structure of interest and the blood flow direction based on the surrounding structures.

[0060] For example, as shown in Fig. 5A, when the angle formed between the direction of blood flow in the aortic valve (arrow "L2") and the direction of blood flow in the ascending aorta (arrow "L3") is "0°," the specifying function 356 determines that "the aortic valve poses a small risk to the human body." On the other hand, as shown in Fig. 5B, when the angle formed between the direction of blood flow in the aortic valve (arrow "L2") and the direction of blood flow in the ascending aorta (arrow "L3") is "30°," the specifying function 356 determines that "the aortic valve poses a certain risk to the human body."

[0061] The state shown in Figure 5A and the state shown in Figure 5B have the same shape of the aortic valve and the same blood flow direction (arrow "L2"), but the shapes of the ascending aorta are different, resulting in different judgment results.

[0062] Here, when calculating the angle between a line indicating the blood flow direction based on the structure of interest and a line indicating the blood flow direction based on the surrounding structures, the identification function 356 calculates the angle by projecting each line from a predetermined direction. For example, the identification function 356 determines the projection direction of each line so that the angle between the line indicating the blood flow direction based on the structure of interest and the line indicating the blood flow direction based on the surrounding structures is maximized, projects the line, and calculates the angle. The angle may also be calculated based on the three-dimensional vector of each line.

[0063] Similarly, for example, as shown in FIG. 5C, when the angle formed between the direction of blood flow in the aortic valve (arrow "L2") and the direction of blood flow in the ascending aorta (arrow "L3") is "60°," the identification function 356 determines that "the aortic valve poses a high risk to the human body." On the other hand, as shown in FIG. 5D, when the angle formed between the direction of blood flow in the aortic valve (arrow "L2") and the direction of blood flow in the ascending aorta (arrow "L3") is "5°," the identification function 356 determines that "the aortic valve poses a low risk to the human body." Thus, the results of the determination of the states shown in FIGS. 5C and 5D differ because the shapes of the ascending aorta are different.

[0064] Here, the identification function 356 can read out correspondence information from the storage circuitry 34, which is a preset correspondence relationship between the state of blood flow direction and the magnitude of risk, and use the information for the determination. FIG. 6 is a diagram showing an example of the correspondence information according to the first embodiment. Note that FIG. 6 shows correspondence information in which the state of blood flow direction is associated with the angle formed by the blood flow direction. For example, as shown in FIG. 6, the storage circuitry 34 stores correspondence information in which the disease risk, angle, and warning message are associated with each other.

[0065] For example, the correspondence information may associate "disease risk: high," "angle: 45 to 90 degrees," and "warning message: check for aortic disease, and if no abnormalities are found, consider performing another test." Based on such correspondence information, the identification function 356 determines the disease risk to be "high" when the angle between the blood flow direction at the aortic valve and the blood flow direction at the ascending aorta is "45 to 90 degrees." The warning message in the correspondence information is also referenced when displaying the evaluation result based on the blood flow direction.

[0066] Similarly, the correspondence information associates other angle ranges, disease risks for each angle range, and warning messages for each angle range, and is used for making judgments based on the blood flow direction and displaying evaluation information.

[0067] (Display processing of evaluation information) As described in step S106 of FIG. 2, the control function 351 displays evaluation information based on the state identified by the identification function 356 on the display 33. Specifically, the control function 351 displays evaluation information indicating the determination result by the identification function 356. For example, the control function 351 displays information indicating the degree of disease risk (e.g., high, medium, low, error), warning messages, etc. on the display 33. Here, since the greater the angle or distance formed by the blood flow direction, the higher the risk, the control function 351 can also display the value itself as evaluation information.

[0068] The display of the evaluation information by the control function 351 can be provided by various methods. FIGS. 7A to 7C are diagrams showing examples of evaluation information according to the first embodiment. For example, as shown in FIG. 7A, the control function 351 can display the evaluation information as text, including the disease risk determination result of "medium" and a warning message. Here, the control function 351 can change the display format of the evaluation information based on the level of the condition of the attention area. For example, the control function 351 highlights the text by changing the color, font, size, etc. of the text corresponding to the level of disease risk (high, medium, low).

[0069] The control function 351 can also display evaluation information on medical images. For example, as shown in FIG. 7B, the control function 351 can superimpose characters indicating the degree of risk and values ​​(angles and distances) calculated in step S105 on the CT image acquired in step S101. The control function 351 can also display information indicating the blood flow direction calculated in step S104 on the CT image. For example, as shown in FIG. 7B, the control function 351 displays an arrow L2 indicating the blood flow direction of the structure of interest and an arrow L3 indicating the blood flow direction of the surrounding structure on the CT image. Here, the control function 351 can change the display form of each line (for example, by using a different color) and display it. The control function 351 can also identify a cross section that shows the angle formed by the two calculated blood flow directions, display that cross section, and then superimpose the blood flow direction on it. The control function 351 can also project and display an arrow indicating the blood flow direction on a cross section in any direction.

[0070] Furthermore, the control function 351 can also display evaluation information on a 3D displayed CT image (VR image, SR image, etc.) as shown in Fig. 7C. Since the blood flow direction is basically calculated in 3D, displaying it overlaid on a 3D image provides higher visibility.

[0071] As described above, the control function 351 can display the evaluation information in various forms. Here, in the display of the evaluation information described above, the display form, such as the size of the characters to be displayed, the thickness, color, and transparency of the arrows, can be changed as desired depending on the level of the disease risk. Note that the display of the evaluation information in step S106 may be automatically displayed after the state is identified, or may be explicitly displayed by the user selecting a button (not shown) or the like.

[0072] (Variation 1) In the above-described embodiment, in step S104, the blood flow direction is calculated (estimated) only from the structure of the region of interest and the structures surrounding the region of interest. However, the embodiment is not limited to this, and, for example, the characteristics of the valve estimated from information such as an image may also be taken into consideration. In such a case, for example, the first calculation function 354 may estimate the presence or absence and amount of calcification, or the hardness and thickness of each structure, based on the magnitude of the pixel value of the pixel corresponding to the region of interest, and calculate the blood flow direction by further taking these into consideration.

[0073] (Variation 2) In the above-described embodiment, in step S104, geometric features were calculated from the structure of the region of interest and the structure surrounding the region of interest, and the blood flow direction was calculated (estimated) based on these features. However, the embodiment is not limited to this. For example, the blood flow state may be simulated and calculated using a known fluid simulation technique. For example, an electrical circuit model simulating the circulatory dynamics of a living body may be designed in advance based on the Windkessel model or the pulse wave propagation model. The first calculation function 354 and the second calculation function 355 can acquire blood flow information for each structure by inputting the structure of the region of interest and the structure surrounding the region of interest into the electrical circuit model. Furthermore, the first calculation function 354 and the second calculation function 355 can calculate the target fluid information by numerically determining necessary equations, such as the Navies-Stokes equations, the continuity equation, Maxwell's equations, and state equations, without being limited to the electrical circuit model, and inputting various parameters into the equations.

[0074] Furthermore, when performing the above-described simulation, the following structure may be virtually constructed and the blood flow direction may be calculated. That is, the blood flow direction based on the structure of interest may be estimated from only the structure of interest (i.e., information on structures surrounding the structure of interest is not used at all), or the surrounding structures may be calculated by applying the structure of a general human body. The structure of a general human body is modeled in advance from a large amount of data, and only the size enlargement rate is modified according to the size of the structure of interest. Furthermore, the blood flow state based on the surrounding structures may be estimated from only the surrounding structures (i.e., information on the structure of interest is not used at all), or the structure of interest may be calculated by applying the structure of a general human body. Here, the structure of a general human body is modeled in advance from a large amount of data, and only the size enlargement rate is modified according to the size of the structure of interest. In this way, it is possible to calculate the blood flow state that depends on the structure of interest or the surrounding structures.

[0075] As described above, according to the first embodiment, the image acquisition function 352 acquires a medical image. The first calculation function 354 calculates a first blood flow direction based on the structure of the region of interest included in the medical image. The second calculation function 355 calculates a second blood flow direction based on the structure surrounding the region of interest. The identification function 356 identifies the state of the region of interest based on the first blood flow direction and the second blood flow direction. Therefore, the medical image processing apparatus 3 according to the first embodiment can identify the state of the region of interest taking into account the structure surrounding the region of interest, making it possible to appropriately estimate the state of the region of interest. As a result, the medical image processing apparatus 3 makes it possible to correctly estimate the degree of abnormality and prognosis risk caused by the target organ.

[0076] Furthermore, according to the first embodiment, the identification function 356 identifies the state of the region of interest based on the difference between the first blood flow direction and the second blood flow direction. Therefore, the medical image processing apparatus 3 according to the first embodiment can identify the state of the region of interest based on whether the blood flow is smooth or not, enabling more accurate estimation.

[0077] Furthermore, according to the first embodiment, the specifying function 356 determines that the greater the difference between the first blood flow direction and the second blood flow direction, the greater the adverse effect on the human body caused by the structure of the region of interest. Therefore, the medical image processing apparatus 3 according to the first embodiment makes it possible to accurately determine the risk of disease and the degree of abnormality.

[0078] Furthermore, according to the first embodiment, the control function 351 displays evaluation information based on the state of the region of interest on the display 33. Therefore, the medical image processing apparatus 3 according to the first embodiment makes it possible to provide the evaluation information to the user.

[0079] Furthermore, according to the first embodiment, the control function 351 changes the display format of the evaluation information based on the degree of the condition of the region of interest. Therefore, the medical image processing apparatus 3 according to the first embodiment can provide the user with information according to the disease risk or the degree of abnormality.

[0080] Furthermore, according to the first embodiment, the control function 351 displays the evaluation information on the medical image. Therefore, the medical image processing apparatus 3 according to the first embodiment makes it possible to provide information on the anatomical structure together with the evaluation information.

[0081] Furthermore, according to the first embodiment, the control function 351 displays information indicating the first blood flow direction and information indicating the second blood flow direction on the medical image. Therefore, the medical image processing apparatus 3 according to the first embodiment allows the user to visually confirm the information on the anatomical structure and the resulting blood flow direction.

[0082] (Second embodiment) In the first embodiment described above, a case where there is one region of interest has been described. In the second embodiment, a case where there are multiple regions of interest will be described. Note that in the second embodiment, a case where four valves, namely, the aortic valve, the mitral valve, the tricuspid valve, and the pulmonary valve, are targeted as the multiple regions of interest will be described. FIG. 8 is a diagram for explaining processing according to the second embodiment.

[0083] For example, in step S102, the extraction function 353 according to the second embodiment extracts the regions of the aortic valve, mitral valve, tricuspid valve, and pulmonary valve from a CT image including the entire heart and various blood vessels shown in Fig. 8. Furthermore, in step S103, the extraction function 353 extracts, for example, the ascending aorta as a surrounding structure for the aortic valve, and the left atrium and left ventricle as surrounding structures for the mitral valve. Furthermore, the extraction function 353 extracts the right atrium and right ventricle as surrounding structures for the tricuspid valve, and the pulmonary artery as a surrounding structure for the pulmonary valve. The extraction methods in steps S102 and S103 are the same as those in the first embodiment.

[0084] In step S104, the first calculation function 354 and the second calculation function 355 according to the second embodiment calculate the blood flow direction based on the valve structure (arrow L2 in FIG. 8) and the blood flow direction based on the surrounding structure (arrow L3 in FIG. 8) for each valve. Here, the pulmonary valve can be calculated in the same manner as in the first embodiment. Meanwhile, for the mitral valve and the tricuspid valve, for example, the first calculation function 354 calculates the blood flow direction based on the structure of interest as the first blood flow direction from a line segment that is perpendicular to the line segment connecting the left and right commissures and passes through the center of gravity of the valve orifice. The second calculation function 355 calculates the blood flow direction based on the surrounding structure as the second blood flow direction from a line segment connecting the center of gravity of the left atrium and the left ventricle or a line segment connecting the center of gravity of the right atrium and the right ventricle. Note that these calculation methods are merely examples, and other calculation methods can be used as appropriate.

[0085] Thereafter, the identification function 356 according to the second embodiment identifies the state of the corresponding structure of interest for each region of interest based on the first blood flow direction and the second blood flow direction, and identifies the state of the region consisting of the multiple regions of interest based on the state of each identified structure of interest. That is, in step S105, the identification function 356 calculates a value (angle or distance between the blood flow directions) indicating the degree of the state (risk) of each valve using the arrows L2 and L3 of each valve, calculates a predetermined statistical quantity (total, average, etc.) based on the values ​​indicating the degree of the state (risk) of all the valves, and regards the statistical quantity as the risk of the subject. This makes it possible to determine the disease risk for the entire heart.

[0086] Then, in step S106, the control function 351 according to the second embodiment displays evaluation information (e.g., a disease risk assessment result) based on the assessment result by the identification function 356. Here, the control function 351 can display the blood flow state based on all of the structures of interest and surrounding structures on the three-dimensional image, or can display it together with a schematic diagram. The control function 351 can also display the risk in each structure separately for each structure, or can display only the statistics.

[0087] As described above, according to the second embodiment, the first calculation function 354 calculates a first blood flow direction for each of multiple regions of interest included in a medical image. The second calculation function 355 calculates a second blood flow direction in each of the surrounding structures for each of the multiple regions of interest. The identification function 356 identifies the state of each region of interest based on the first blood flow direction and the second blood flow direction, and identifies the state of a region made up of multiple regions of interest based on the state of each identified region of interest. Therefore, the medical image processing apparatus 3 according to the second embodiment makes it possible to comprehensively evaluate the state (such as the degree of abnormality or prognosis risk) of a biological organ made up of multiple regions of interest from the state of each region of interest.

[0088] (Third embodiment) In the first embodiment described above, a case where a medical image at one time point is used as the target is described. In the third embodiment, a case where the state of a region of interest is identified using medical images at multiple time points is described. In such a case, the image acquisition function 352 according to the third embodiment acquires multiple medical images captured at different time points. The first calculation function 354 according to the third embodiment calculates a first blood flow direction based on the structure of the region of interest for each medical image at each time point. The second calculation function 355 according to the third embodiment calculates a second blood flow direction based on the surrounding structure for each medical image at each time point. The identification function 356 according to the third embodiment calculates the difference between the first blood flow direction and the second blood flow direction for each medical image at each time point and identifies the state of the region of interest based on the calculated difference for each time point.

[0089] 9 is a diagram for explaining an example of processing according to the third embodiment. For example, in step S101, the image acquisition function 352 acquires 4DCT images captured at times t1 to t6 shown in FIG.

[0090] Then, in step S102, the extraction function 353 extracts the same structure of interest (e.g., the aortic valve) from the CT images at each time point, and in step S103, extracts the same surrounding structure (e.g., the ascending aorta) from the CT images at each time point.

[0091] Then, in step S104, the first calculation function 354 calculates the blood flow direction (arrow L2 in FIG. 9) based on the structure of interest, and the second calculation function 355 calculates the blood flow direction (arrow L3 in FIG. 9) based on the surrounding structures.

[0092] Then, in step S105, the identification function 356 calculates a value (angle in the case of FIG. 9) indicating the degree of the condition (risk) for the CT image at each time point. Furthermore, the identification function 356 calculates a predetermined statistical quantity (total value, variance, etc.) from the value indicating the degree of the condition (risk) in each CT image, and sets the statistical quantity as the condition (risk) of the subject. For example, by using the variance, it is possible to analyze the relationship between the blood flow state caused by the valve structure and the blood flow state caused by the structure surrounding the valve based on the amount of change within one heartbeat, so that the risk may be determined to be low when the variance is small. Alternatively, the risk may be determined to be low when the total value is small.

[0093] Then, in step S106, the control function 351 displays evaluation information (e.g., a disease risk evaluation result) based on the evaluation result by the identification function 356. Here, the control function 351 can also display information on the time-dependent change in a value indicating the degree of a condition. Specifically, the control function 351 can graphically display the relationship between each piece of evaluation information based on the state of the region of interest identified in each time phase corresponding to a plurality of medical images and the respective time phases. FIG. 10 is a diagram showing an example of evaluation information according to the third embodiment. For example, as shown in FIG. 10, the control function 351 can display a graph in which the horizontal axis indicates the imaging time point (cardiac phase %) and the vertical axis indicates a value indicating the degree of a condition (angle in FIG. 10).

[0094] The third embodiment can also be implemented in combination with the second embodiment. That is, a plurality of regions of interest may be set for each of medical images taken at a plurality of time points, and a determination may be made for each region of interest. In such a case, the control function 351 can display a graph showing values ​​(angles in FIG. 11) indicating the degree of condition at each imaging time point (cardiac phase %) for the aortic valve, tricuspid valve, pulmonary valve, and mitral valve, as shown in FIG. 11. FIG. 11 is a diagram showing an example of evaluation information according to the third embodiment.

[0095] As described above, according to the third embodiment, the image acquisition function 352 acquires multiple medical images captured at different times. The first calculation function 354 calculates a first blood flow direction for each medical image based on the structure of the region of interest. The second calculation function 355 calculates a second blood flow direction for each medical image based on the surrounding structure. The identification function 356 calculates the difference between the first blood flow direction and the second blood flow direction for each medical image and identifies the state of the region of interest based on the calculated difference for each time point. Therefore, the medical image processing apparatus 3 according to the third embodiment can perform estimation taking into account changes in state over time, enabling more detailed estimation of the region of interest.

[0096] Furthermore, according to the third embodiment, the control function 351 displays a graph of the relationship between each evaluation information based on the state of the region of interest identified in each time phase corresponding to a plurality of medical images and the time phase. Therefore, the medical image processing apparatus 3 according to the third embodiment allows the user to visually confirm the change in the evaluation information over time.

[0097] (Other embodiments) In the above-described embodiment, an example has been described in which the evaluation information is displayed on the display 33 of the medical image processing device 3, but the embodiment is not limited to this. For example, the evaluation information may be displayed on the display of another device connected to the network.

[0098] In the above-described embodiment, an example has been described in which the control unit, image acquisition unit, extraction unit, first calculation unit, second calculation unit, and identification unit in this specification are realized by the control function, image acquisition function, extraction function, first calculation function, second calculation function, and identification function of a processing circuit, respectively, but the embodiment is not limited to this. For example, in addition to being realized by the control function, image acquisition function, extraction function, first calculation function, second calculation function, and identification function described in the embodiment, the control unit, image acquisition unit, extraction unit, first calculation unit, second calculation unit, and identification unit in this specification may also be realized by hardware only, software only, or a combination of hardware and software.

[0099] Furthermore, the term "processor" used in the description of the above-mentioned embodiments refers to circuits such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). Here, instead of storing a program in a memory circuit, the processor may be configured so that the program is directly embedded in the circuit. In this case, the processor realizes its function by reading and executing the program embedded in the circuit. Furthermore, each processor in the present embodiment is not limited to being configured as a single circuit for each processor, but may also be configured as a single processor by combining multiple independent circuits to realize its function.

[0100] Here, the medical image processing program executed by the processor is provided by being pre-installed in a read-only memory (ROM), a storage circuit, or the like. The medical image processing program may be provided by being recorded on a computer-readable, non-transitory storage medium such as a compact disk (CD)-ROM, a flexible disk (FD), a recordable CD-R (CD-R), or a digital versatile disk (DVD) in a format that can be installed or executed by these devices. The medical image processing program may also be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, the medical image processing program may be composed of modules including each of the processing functions described above. In terms of actual hardware, a CPU reads and executes the medical image processing program from a storage medium such as a ROM, whereby each module is loaded into a main memory device and generated on the main memory device.

[0101] In addition, in the above-described embodiments and modifications, the components of each device shown in the drawings are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution or integration of each device is not limited to that shown in the drawings, and all or part of the devices can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0102] Furthermore, among the processes described in the above-mentioned embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0103] According to at least one of the embodiments described above, the state of the region of interest can be appropriately estimated.

[0104] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0105] 3 Medical image processing equipment 35 Processing circuit 351 Control Functions 352 Image Acquisition Function 353 Extraction Function 354 First calculation function 355 Second calculation function 356 Specific Functions

Claims

1. an acquisition unit for acquiring medical images; a first calculation unit that calculates a first blood flow direction based on a structure of a region of interest included in the medical image; a second calculation unit that calculates a second blood flow direction based on a structure of a surrounding region that is connected to the structure of the region of interest and is different from the region of interest; an identification unit that identifies information related to a disease risk in the region of interest based on an angle between the first blood flow direction and the second blood flow direction; A medical image processing device having:

2. The medical image processing apparatus according to claim 1 , wherein the specifying unit determines that the greater the angle between the first blood flow direction and the second blood flow direction, the greater the adverse effect on the human body caused by the structure of the region of interest.

3. the first calculation unit calculates the first blood flow direction for each of a plurality of regions of interest included in the medical image; the second calculation unit calculates, for the plurality of regions of interest, the second blood flow direction in each of structures of surrounding regions that are connected to the structure of the region of interest and different from the region of interest; 3. The medical image processing device according to claim 1, wherein the identification unit identifies information regarding the disease risk for each region of interest based on the first blood flow direction and the second blood flow direction, and identifies information regarding the disease risk in a region composed of the multiple regions of interest based on the information regarding the disease risk for each identified region of interest.

4. the acquisition unit acquires a plurality of medical images captured at different times; the first calculation unit calculates the first blood flow direction based on the structure of the region of interest for each medical image at each time point; the second calculation unit calculates the second blood flow direction based on a structure of the surrounding region that is connected to a structure of the region of interest and different from the region of interest for the medical image at each time point; The medical image processing device according to any one of claims 1 to 3, wherein the identification unit calculates an angle between the first blood flow direction and the second blood flow direction for the medical image at each time point, and identifies information regarding the disease risk in the region of interest based on the calculated angle between the first blood flow direction and the second blood flow direction at each time point.

5. 5. The medical image processing apparatus according to claim 1, further comprising a display control unit that displays information about the disease risk in the region of interest on a display unit.

6. The medical image processing apparatus according to claim 5 , wherein the display control unit changes a display form of the information on the disease risk based on a degree of the disease risk in the region of interest.

7. The medical image processing apparatus according to claim 5 , wherein the display control unit displays information about the disease risk on the medical image.

8. The medical image processing apparatus according to claim 7 , wherein the display control unit displays the information indicating the first blood flow direction and the information indicating the second blood flow direction on the medical image.

9. The medical image processing device according to claim 4 , further comprising a display control unit that displays a graph of information regarding the disease risk in the region of interest identified in each time phase corresponding to the plurality of medical images and a relationship between the time phase and the information.

10. A medical image processing device described in any one of claims 1 to 9, wherein the structure of the surrounding area different from the area of ​​interest is the structure of an area into which blood flows from the structure of the area of ​​interest.

11. A medical image processing device described in any one of claims 1 to 10, further comprising an extraction unit that extracts the structure of a surrounding area different from the area of ​​interest based on at least one of the continuity and distribution of pixel values ​​of the structure of the area of ​​interest.

12. A medical image processing device described in any one of 1 to 11, further comprising an extraction unit that extracts a heart valve as a structure of the region of interest and extracts blood vessels connected to the heart valve as a structure of a surrounding region different from the region of interest.

13. Acquire medical images; calculating a first blood flow direction based on a structure of a region of interest included in the medical image; Calculating a second blood flow direction based on a structure of a surrounding region that is connected to the structure of the region of interest and different from the region of interest; identifying information about a disease risk in the region of interest based on an angle between the first blood flow direction and the second blood flow direction; A medical image processing method comprising:

14. an acquisition function for acquiring medical images; a first calculation function for calculating a first blood flow direction based on a structure of a region of interest included in the medical image; a second calculation function for calculating a second blood flow direction based on a structure of a surrounding region connected to the structure of the region of interest and different from the region of interest; an identifying function that identifies information about a disease risk in the region of interest based on an angle between the first blood flow direction and the second blood flow direction; A medical image processing program that causes a computer to execute the following.

Images