Medical image processing device, medical image processing method, and program

Abstract

To estimate a branching point of a blood vessel with higher accuracy.SOLUTION: A medical image processing device comprises an acquisition unit, a setting unit, a search unit, and an estimation unit. The acquisition unit acquires blood vessel shape data indicating a three-dimensional shape of a surface of a blood vessel including a branch. The setting unit sets a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point. The search unit searches for a position of the sphere that fits the surface of the blood vessel using, as search variables, the center and the radius of the sphere. The estimation unit estimates the center of the sphere searched by the search unit as a branching point of the blood vessel.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a medical image processing apparatus, a medical image processing method, and a program. [Background technology]

[0002] Known methods for estimating the shape of blood vessels from medical images include automatically segmenting tubular structures such as blood vessels in 3D tomographic images by fitting a specific cylindrical model to them, estimating the size of the branching part as the largest inscribed sphere inscribed in the boundary point group of two tubular objects, and estimating the center of the blood vessel as the center of the inscribed sphere inscribed in the cross section of the blood vessel.

[0003] In recent years, there has been research into the relationship between the diameter of a branching point in a blood vessel, such as the pulmonary artery trunk, and diseases such as pulmonary hypertension and chronic obstructive pulmonary disease, and it is believed that measuring the diameter of a branching point can be useful in predicting the risk of lung disease, etc. Therefore, there is a need for a method to accurately estimate the diameter of a branching point from the three-dimensional shape of a blood vessel, but there is still room for further study in this regard. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Special Publication No. 2005-502139 [Patent Document 2] International Publication No. 2015 / 136853 [Patent Document 3] Japanese Patent Application Laid-Open No. 2009-268741 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems that the present invention aims to solve is to be able to estimate the branching points of blood vessels with higher accuracy. However, the problems that the present invention aims to solve by the embodiments disclosed in this specification and the drawings are not limited to the above problem, and 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]

[0006] A medical image processing apparatus according to an embodiment includes an acquisition unit, a setting unit, a search unit, and an estimation unit. The acquisition unit acquires blood vessel shape data indicating the three-dimensional shape of the surface of a blood vessel, including branches. The setting unit sets a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point. The search unit searches for a position of the sphere that fits the surface of the blood vessel, using the center and the radius as search variables. The estimation unit estimates the center of the sphere found by the search unit as a branch point of the blood vessel. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a diagram showing an example of the configuration of a medical image processing system 1 including a medical image processing apparatus according to an embodiment. [Figure 2] 5A and 5B are diagrams for explaining a method for setting a reference point in the embodiment. [Figure 3] FIG. 10 is a diagram for explaining another example of a method for setting a reference point. [Figure 4] 5A and 5B are diagrams for explaining a search process executed by a search function 143 according to the embodiment. [Figure 5] FIG. 10 is a diagram showing the position of a sphere SP searched for based on an evaluation function E. [Figure 6] FIG. 10 is a diagram for explaining estimation of the diameter of a branching portion of a blood vessel. [Figure 7] FIG. 2 is a diagram showing an example of an image IM10 generated by an image generation function 145 of the embodiment. [Figure 8] 4 is a flowchart showing a series of processing steps executed by a processing circuit 140 according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, a medical image processing apparatus, a medical image processing method, and a program according to an embodiment will be described with reference to the drawings.

[0009] FIG. 1 is a diagram showing an example of the configuration of a medical image processing system 1 including a medical image processing device of an embodiment. The medical image processing system 1 includes, for example, a medical image generating device 10, a medical image DB (Database) 20, and a medical image processing device 100. The medical image generating device 10, the medical image DB 20, and the medical image processing device 100 are communicably connected, for example, via a network NW. Note that the medical image processing system 1 may be provided with at least a plurality of medical image generating devices 10 or medical image DBs 20. Furthermore, the medical image processing system 1 may be configured without including either the medical image generating device 10 or the medical image DB 20.

[0010] The network NW refers to a general information communication network that uses electrical communication technology, and includes, for example, a wireless / wired local area network (LAN), a wide area network (WAN), the Internet network, a telephone communication line network, a Wi-Fi network, Bluetooth (registered trademark), an optical fiber communication network, a cable communication network, a satellite communication network, etc.

[0011] The medical image generating apparatus 10 captures (photographs) medical images including at least branching blood vessels in a subject in accordance with imaging conditions determined based on, for example, an imaging test instruction. Medical image generating apparatuses include, for example, X-ray computed tomography apparatuses, X-ray diagnostic apparatuses, magnetic resonance imaging apparatuses, ultrasound diagnostic apparatuses, and nuclear medicine diagnostic apparatuses. The medical image generating apparatus 10 generates medical images based on operations by a user such as a doctor (radiologist) or a diagnostic radiologist. In the following description, the medical images are assumed to be CT (Computed Tomography) images captured by an X-ray computed tomography apparatus, but are not limited thereto and may be, for example, MRI (Magnetic Resonance Imaging) images captured by a magnetic resonance imaging apparatus. The medical images may also include other medical images as long as they show at least branching blood vessels.

[0012] The medical image DB 20 is, for example, a picture archiving and communication system (PACS) that acquires medical images from the medical image generating device 10 or the like, stores them in a storage device such as a database, and manages them.

[0013] The medical image processing device 100 acquires medical images generated by the medical image generating device 10 or medical images stored in the medical image DB 20, and estimates at least the branching points of blood vessels from the acquired medical images. The medical image processing device 100 also displays the processing results on its own display, or transmits them to the medical image generating device 10, the medical image DB 20, or other external devices via the network NW. The medical image processing device 100 may be, for example, a general-purpose PC (Personal Computer) or a server device, a workstation or a cloud server, a smartphone, a tablet terminal, or the like.

[0014] Next, a description will be given of the functional configuration of the medical image processing apparatus 100. The medical image processing apparatus 100 shown in Fig. 1 includes, for example, a communication interface 110, an input interface 120, a display 130, a processing circuitry 140, and a memory 150.

[0015] The communication interface 110 includes, for example, a communication interface such as a NIC (Network Interface Controller) or an antenna for wireless communication. The communication interface 110 communicates with the medical image generating apparatus 10, the medical image DB 20, other external devices, etc. via the network NW, and outputs acquired information (medical images, etc.) to the processing circuitry 140, etc. Furthermore, under the control of the processing circuitry 140, the communication interface 110 transmits information to the medical image generating apparatus 10, the medical image DB 20, other external devices, etc. via the network NW.

[0016] The input interface 120 accepts various input operations from a user of the medical image processing apparatus 100, converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing circuitry 140. For example, when an input operation is performed by the user, the input interface 120 generates information corresponding to the input operation. The input interface 120 outputs the generated information corresponding to the input operation to the processing circuitry 140.

[0017] The input interface 120 includes, for example, a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch panel, etc. The input interface 120 may be, for example, a user interface that accepts audio input from a microphone, etc. If the input interface 120 is a touch panel, the input interface 120 may also have the display function of the display 130.

[0018] In this specification, the input interface 120 is not limited to an interface having physical operation parts such as a mouse, keyboard, etc. For example, an example of the input interface 120 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs this electrical signal to a control circuit.

[0019] The display 130 displays various types of information. For example, the display 130 displays images generated by the processing circuit 140, a GUI (Graphical User Interface) for receiving various input operations from the user, etc. For example, the display 130 is an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, an organic EL (Electro Luminescence) display, etc. The display 130 is an example of a "display unit."

[0020] The processing circuitry 140 includes, for example, an acquisition function 141, a setting function 142, a search function 143, an estimation function 144, an image generation function 145, and a display control function 146. The processing circuitry 140 realizes these functions by, for example, a hardware processor (computer) executing a program stored in a memory (storage circuitry) 150.

[0021] A hardware processor refers to a circuit such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD) or a Complex Programmable Logic Device (CPLD), or a Field Programmable Gate Array (FPGA)).

[0022] Instead of storing the program in the memory 150, the program may be directly embedded in the circuit of the hardware processor. In this case, the hardware processor realizes its functions by reading and executing the program embedded in the circuit. The program may be stored in a storage device in advance, or may be stored in a non-transitory storage medium such as a DVD or CD-ROM, and installed from the non-transitory storage medium into the storage device when the non-transitory storage medium is inserted into a drive device (not shown) of the medical image processing apparatus 100.

[0023] The hardware processor is not limited to being configured as a single circuit, but may be configured as a single hardware processor by combining multiple independent circuits to realize each function, or multiple components may be integrated into a single hardware processor to realize each function.

[0024] The memory 150 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. These non-transitory storage media may be realized by other storage devices connected via a network NW, such as a NAS (Network Attached Storage) or an external storage server device. These non-transitory storage media may also be realized by storage devices such as a ROM (Read Only Memory) or a register. The memory 150 stores, for example, medical image data 151 acquired from the medical image generating device 10 or the medical image DB 20, processed data 152 indicating the results of processing by the processing circuitry 140, programs, and various other information.

[0025] The acquisition function 141 acquires medical images transmitted from the medical image generating device 10 or the medical image DB 20 via the communication interface 110. The acquisition function 141 also acquires blood vessel shape data (an example of shape data) indicating the three-dimensional shape of the surface (contour) of a blood vessel, including branches, from the medical image using a known algorithm (three-dimensional structuring algorithm). For example, the acquisition function 141 obtains each point on the blood vessel wall from a CT image, and models the surface shape of the blood vessel based on the positions of each point to acquire the blood vessel shape data. Note that the acquisition function 141 can model the three-dimensional shape of the blood vessel more efficiently and accurately by associating it with predetermined feature information related to the deformation of the blood vessel during modeling.

[0026] The acquisition function 141 may also acquire vascular shape data by, for example, performing region segmentation processing to extract vascular interior regions from medical images, and performing three-dimensional surface construction processing to construct a surface shape by three-dimensionally stacking slice images of the extracted vascular interior regions. Acquisition of vascular shape data is not limited to these, and other algorithms may be used. The acquisition function 141 may also acquire vascular shape data directly from the medical image generating device 10, the medical image DB 20, or another external device. The data acquired by the acquisition function is stored in the memory 150 as medical image data 151.

[0027] The setting function 142 sets a reference point for searching for branching points of blood vessels in the blood vessel shape data acquired by the acquisition function 141. The setting function 142 also sets the radius of a sphere centered on the set reference point.

[0028] FIG. 2 is a diagram illustrating a method for setting a reference point in an embodiment. In the example of FIG. 2, an image corresponding to vascular shape data (three-dimensional vascular surface shape data) BM near the pulmonary trunk is shown. However, vascular shape data near other organs (e.g., the brain) in the subject may also be used. For example, the setting function 142 sets a reference point P0 (e.g., three-dimensional coordinates (x0, y0, z0)) inside the vascular shape (three-dimensional vascular surface shape) corresponding to the vascular shape data BM. In this case, the setting function 142 performs, for example, a thinning process on the vascular shape data BM using a known algorithm (e.g., an open-source algorithm) and sets the reference point P0 based on the thinned blood vessel (line data). Specifically, the setting function 142 performs a binarization process on the vascular shape data BM and converts the binarized vascular region into a line image LI with a width of approximately one pixel by trimming the outside of the blood vessel. In the example of FIG. 2, a line image LI (an example of a thinned blood vessel) of a portion (near the main trunk) of the vascular shape data BM thinned by the thinning process is shown. The contents of the thinning process are not limited to the above example, and other algorithms may be used. When the line image LI is branched, the setting function 142 sets the branching position (in other words, the intersection of multiple line images LI) as the reference point P0. The branching position (intersection of line images LI) obtained by this thinning process may be shifted from the branching point of the blood vessel, but the reference point P0 can be set at a position that is somewhat close.

[0029] The setting function 142 may also set the reference point P0 based on the overall shape of the blood vessel shape data BM. Fig. 3 is a diagram for explaining another example of a reference point setting method. For example, the setting function 142 sets an outer shape OF that covers the acquired blood vessel shape data BM, and sets the center of the set outer shape OF as the reference point P0. Alternatively, the setting function 142 may set the center of the three-dimensional shape of the blood vessel shape data BM shown in Fig. 3 as the reference point P0. Alternatively, the setting function 142 may set the center of the boundary surface between two tubular objects included in the blood vessel shape data BM as the reference point P0.

[0030] Furthermore, the setting function 142 may, for example, cause the image generating function 145 to generate an image showing the blood vessel shape data BM, and cause the display control function 146 to display the image showing the blood vessel shape data BM on the display 130, and then receive an instruction for the reference point P0 from the user via the input interface 120. This allows the user to refer to the blood vessel shape data BM displayed on the display 130 and set the reference point P0 at a position desired by the user.

[0031] The setting function 142 also sets a radius r0 of a sphere centered on the set reference point P0. The radius r0 may be a fixed value, or may be set to be less than half the diameter of a typical blood vessel. The setting function 142 may also receive an instruction from the user via the input interface 120 to set the radius r0.

[0032] The search function 143 searches for the position of a sphere that fits the surface of the blood vessel corresponding to the blood vessel shape data BM while changing the center (=reference point P0) and radius r0 of the sphere set in the setting function 142 as search variables. That is, the search variables include a total of four parameters: the three-dimensional coordinates (x, y, z) of the sphere's center and the radius r. Details of the functions of the search function 143 will be described later.

[0033] The estimation function 144 estimates the center of the sphere as the branching point of the blood vessel corresponding to the blood vessel shape data BM based on the position of the sphere searched by the search function 143. The estimation function 144 also estimates the diameter of the blood vessel at the branching point based on the position of the branching point. Details of the function of the estimation function 144 will be described later.

[0034] The image generation function 145 generates images to be displayed on the display 130, an external terminal, or the like. For example, the image generation function 145 generates images showing information that the medical image processing apparatus 100 of the embodiment needs to provide to the user in order to perform image processing, and images showing information showing predetermined processing results. For example, the image generation function 145 generates an image showing at least one of the results searched by the search function 143 and the results estimated by the estimation function 144. The image generation function 145 may also generate images showing medical images and vascular shape data BM acquired by the acquisition function 141. The image generation function 145 generates images showing information such as a line image LI obtained by thinning processing, a sphere, the reference point and center of the sphere, an evaluation function E (described later), branch points, and the diameter of the branching portion. The image generation function 145 may also generate sound corresponding to the information shown by the generated image.

[0035] The display control function 146 displays the image generated by the image generation function 145 on the display 130, and transmits the image to the medical image generation device 10, the medical DB 20, etc. via the network NW. The display control function 146 may also cause the image generation function 145 to generate an image, change the display content, etc., in response to a user instruction. The display control function 146 may also cause information stored in the memory 150 to be displayed on the display 130, and output audio corresponding to the information indicated by the image generated by the image generation function 145 from a speaker (not shown), etc.

[0036] The processing circuitry 140 stores the results of processing by the above-mentioned components in the memory 150 as processed data 152. The processing circuitry 140 may also transmit the information stored in the memory 150 to the medical image generating device 10, the medical DB 20, other external devices, etc. via the communication interface 110.

[0037] [Search function 143] Next, the details of the function of the search function 143 will be described. Fig. 4 is a diagram for explaining the search processing executed by the search function 143 of the embodiment. In the example of Fig. 4, for convenience of explanation, a blood vessel portion having a branch in the blood vessel shape data BM is shown in a simplified manner. The same applies to Figs. 5 and 6 described later. For example, the search function 143 changes the center P and radius r of the sphere SP from the initial values ​​(reference point P0, radius r0) so that the surface of the sphere SP and the surface (blood vessel surface) of the blood vessel shape data BM fit together (in other words, so that the degree of deviation between the surfaces is minimized, or so that the error between the surfaces is minimized).

[0038] For example, the search function 143 uses a predetermined evaluation function E to search for the position of the sphere SP that fits the surface of the blood vessel, where the value obtained by the evaluation function E is the smallest. The evaluation function E in the embodiment includes, for example, a first index value (error term) based on the sum of errors between the distance D from the center of the sphere SP to the surface of the blood vessel in multiple directions and the radius r of the sphere SP, a second index value (radius maximization term) that decreases as the radius r of the sphere SP increases, and a third index value (search range constraint term) that constrains the search range for the center P of the sphere SP. The evaluation function E is, for example, the sum of the first to third index values, but a predetermined weighting according to priority or the like may be assigned to at least one of the preset index values ​​or the index values ​​set by the user.

[0039] The first index value (error term) is, for example, the sum of the error ΔER (=|Dr|) between the distance D from the center P of the sphere SP to the blood vessel surface and the radius r, calculated for multiple directions of the sphere SP (for example, all directions, or a predetermined number of different directions set in advance), and the calculated errors ΔER. Note that, depending on the direction, the distance D from the center P of the sphere SP to the blood vessel surface may become too large, so if the distance D is equal to or greater than a predetermined upper limit, the error ΔER in that direction may not be calculated. The predetermined number of different directions may be set randomly, or may be adjusted so that each direction is equally different.

[0040] The second index value (radius maximization term) decreases as the radius r of the sphere SP increases. However, a condition may be added to make it more difficult for a sphere SP whose radius r exceeds the vascular surface (vascular wall) to be derived as the sphere that best fits the vascular surface. For example, the condition is to change the radius r of the sphere SP, whose center is a reference point P0 inside the vascular shape data BM, from a small value (initial radius r0) to a large value during a search by the search function 143. Additional conditions may include ensuring that the difference (distance) between the radius r changed during the search and the initial radius r0 does not exceed a threshold, or to impose an additional penalty (a penalty that increases the second index value) if the radius r exceeds a predetermined upper limit. By changing the sphere from a small value to a large value during the search, it becomes easier to derive a solution that fits the vascular wall (a point at which the evaluation function is minimized). Note that the embodiment is not limited to this, and a search may be performed in which the radius r of the sphere SP is changed to a small value by setting the initial radius r0 to a large value.

[0041] The third index value (search range constraint term) is a value that increases as the distance between the center P of the sphere SP and the reference point P0 increases by a predetermined distance or more during the search. For example, since the reference point P0 is set at the branching point of the line image LI obtained using a thinning process or the like, it is assumed that the branching point of the blood vessel is located at a position relatively close to the reference point P0. Therefore, if the sphere SP moves to a position far from the reference point P0, a position different from the actual branching point may be estimated as the branching point. Therefore, by restricting the movement range of the sphere SP using the third index value, the position of the branching point can be estimated more accurately. Note that the evaluation function E may include index values ​​other than the first to third index values ​​depending on the type and shape of the blood vessel.

[0042] The search function 143 uses an algorithm such as gradient descent to change the search variables in a direction that decreases the value of the evaluation function E (for example, the sum of the first to third index values) for the evaluation function E described above, and extracts the position (for example, center P) and radius r of the sphere SP when the value of the evaluation function E is smallest. Note that the search may be performed using an algorithm other than gradient descent.

[0043] [Estimated Function 144] Next, the details of the function of the estimation function 144 will be described. Fig. 5 is a diagram showing the position of a sphere SP searched for based on the evaluation function E. In the example of Fig. 5, the sphere SP for which the value of the evaluation function E is smallest (in other words, the surface of the sphere SP fits the blood vessel surface) and its center P are shown. The estimation function 144 estimates that the center P (for example, three-dimensional coordinates (x, y, z)) of the sphere SP searched for by the search function 143 is a branching point of the blood vessel.

[0044] The estimation function 144 may determine that the position of the branch point is incorrect and cause the search function 143 to search again when predetermined conditions are met, such as when the smallest value of the evaluation function E is equal to or greater than a threshold, or when at least one of the first to third index values ​​is equal to or greater than a threshold set for each. The predetermined conditions may include when the position of the branch point of the blood vessel estimated from the search result of the search function 143 is located outside the blood vessel surface of the blood vessel shape data BM, or when the radius r of the sphere SP that fits the blood vessel surface exceeds a threshold. When performing a re-search, the search function 143 performs the re-search by changing the position of the reference point P0 and / or the radius r0 from the previous search.

[0045] Furthermore, the estimation function 144 estimates the diameter of the blood vessel at the branching point based on the estimated position of the branching point. FIG. 6 is a diagram for explaining the estimation of the diameter of the blood vessel branching point. The estimation function 144 performs a thinning process that passes through the branching point (center P), with the center P of the sphere SP as the branching point. In this case, the estimation function 144 performs the thinning process so that the estimated branching point of the blood vessel becomes a branching point (or intersection point) of the line image LI (thinned blood vessel) after the thinning process. Furthermore, the estimation function 144 estimates the line image LI obtained by the thinning process as the center line of the blood vessel shape included in the blood vessel shape data BM. This makes it possible to obtain the center line of the blood vessel with higher accuracy.

[0046] The estimation function 144 also estimates the diameter of the branching portion of the blood vessel based on the estimated center line. For example, the estimation function 144 estimates the radius r2 of a cross section passing through the center of the line image LI (center line) and perpendicular to the extension direction of the line image LI as the radius of the blood vessel at the branching portion, and estimates the diameter of the blood vessel (e.g., radius x 2) from the estimated radius. Note that the extension direction of the line image LI is, for example, the extension direction of the line image LI relative to the blood vessel with the largest diameter among multiple branching (intersecting) blood vessels, which is the upstream blood vessel in the case of an artery and the downstream blood vessel in the case of a vein. Therefore, when estimating the diameter of the branching portion of the blood vessel, the estimation function 144 estimates the diameter based on a position moved a predetermined distance toward the main trunk (upstream side of the artery) from the branching point, as shown in FIG. 6.

[0047] The method for estimating the diameter of a blood vessel is not limited to this, and the diameter of a branched portion of a blood vessel may be estimated from a cross section of the blood vessel centered on the branching point, or the diameter of a branched portion may be estimated from the radius r3 of a sphere SP that fits the surface of the blood vessel. These estimation methods may be changed depending on the type of algorithm used for the thinning process.

[0048] As described above, in the embodiment, by estimating the branching points using an evaluation function that uses a three-dimensional sphere SP for the three-dimensional blood vessel shape data BM, it is possible to estimate the appropriate positions of the branching points from any direction. Furthermore, it is possible to accurately estimate the diameter of the branching part of the blood vessel from the estimated branching points.

[0049] [Image example] Next, an example of an image generated by the image generation function 145 and displayed on the display 130 or the like by the display control function 146 in the embodiment will be described. FIG. 7 is a diagram showing an example of an image IM10 generated by the image generation function 145 in the embodiment. Note that the display aspects such as the content, layout, color, font, and design displayed in the image IM10 described below are not limited to this. The image IM10 includes, for example, a processed image display area AR10, a search information display area AR12, and a GUI switch display area A14.

[0050] The processed image display area AR10 displays, for example, an image IM11 showing vascular shape data BM corresponding to the medical image to be processed, an image IM12 showing a reference point P0, an image IM13 showing a sphere SP, and an image IM14 showing a branch point (center P of the sphere SP). The processed image display area AR10 may also include a line image LI thinned by a thinning process and an image showing the estimated radius of the blood vessel at the branch point as shown in FIG. 6. Each image is displayed in a display format that allows it to be distinguished even when superimposed, using a color or pattern different from other images. The images displayed in the processed image display area AR10 may be rotatable in three dimensions so that images viewed from different directions are displayed in response to a user instruction from the input interface 120. The rotated images viewed from different directions are also generated by the image generation function 145.

[0051] The search information display area AR12 displays information about the search results by the search function 143. The information about the search results is, for example, values ​​(numeric values) about the evaluation function E, the error term (first index value), the radius maximization term (second index value), and the search range constraint term (third index value). The information about the search results may also include information such as the three-dimensional coordinates (x0, y0, z0) of the reference point P0 on the image, the three-dimensional coordinates (x, y, z) of the branching point, the radius r of the sphere SP, and the initial value radius r0. The information about the search results may also include a numerical value indicating the diameter of the branching portion of the blood vessel.

[0052] The GUI switch display area A14 displays, for example, an icon IC10 that accepts an instruction to perform processing related to searching for a branching point of a blood vessel (or estimating the diameter of the branching point), and an icon IC12 that accepts an instruction to end processing related to searching for a branching point (or estimating the diameter of the branching point) and terminate the display of image IM10.

[0053] For example, when the user selects icon IC10, the search function 143 executes a search process based on the position of the reference point P0 and the radius r0 set by the setting function 142. Furthermore, if the user determines that the position of the branch point is incorrect based on the position of the search result (e.g., the branch point) displayed in the processed image display area AR10 or the search information display area AR12, the user selects icon IC12 again. This causes the search function 143 to execute a re-search at a position and / or a different radius r0 from the position of the reference point P0 set during the previous search. Note that, in the case of a re-search, the position of the reference point P0 and the radius r0 may be set by the user. In this way, the user can obtain a more accurate position of the branch point while viewing the results displayed in the image IM10.

[0054] Furthermore, when the user selects icon IC12, the display control function 146 ends the display of image IM10 displayed on the display 130 or the like, and stores information about the search result (or estimation result) in the memory 150. Note that the GUI switch display area A14 may include, for example, an icon for accepting an instruction to select blood vessel shape data BM, an icon for accepting an instruction to execute thinning processing, an icon for accepting an instruction to estimate the diameter of a blood vessel bifurcation, and the like.

[0055] [Processing flow] Next, the processing flow of the processing circuitry 140 in this embodiment will be described. FIG. 8 is a flowchart showing a series of processing flows executed by the processing circuitry 140 in this embodiment. In the example of FIG. 8, the acquisition function 141 acquires vascular shape data corresponding to a medical image including branching blood vessels (step S100). Next, the setting function 142 sets a reference point for estimating (searching for) branching points of blood vessels included in the vascular shape data (step S110) and sets the radius of a sphere (initial radius) (step S120). Next, the search function 143 searches for the position of a sphere that fits the vascular surface of the vascular shape data using a predetermined evaluation function E (step S130).

[0056] Next, the estimation function 144 estimates a branching point of the blood vessel based on the position of the sphere obtained as a result of the search (step S140). Next, the estimation function 144 determines whether or not to perform a re-search for the branching point using the search function 143 (step S150). In the process of step S150, for example, if the estimated position of the branching point satisfies a predetermined condition and it is determined that the position of the branching point is incorrect, it is determined to perform a re-search. Alternatively, after the process of step S140, the display control function 146 may display an image IM10 shown in FIG. 7 generated by the image generation function 145 on the display, and determine to perform a re-search when an instruction to perform a re-search (e.g., an instruction to select icon IC10) is received from the user. If it is determined to perform a re-search, the process returns to the process of step S110, and a reference point P0 and a radius r0 different from those used previously are set and the search process is executed.

[0057] Furthermore, if it is determined in the processing of step S150 that a re-search is not to be performed, the estimation function 144 estimates the diameter of the branching point of the blood vessel based on the branching point (step S160). Next, the image generation function 145 generates an image relating to each of the above-mentioned processing results (step S170). Next, the display control function 146 displays the generated image on the display 130 or the like (step S180). This ends the processing of this flowchart.

[0058] [Variations] In the embodiment, the medical image generating device 10 or the medical image DB 20 may be configured integrally with the medical image processing device 100. Also, in the embodiment, some of the components of the medical image processing device 100 may be provided in the medical image generating device 10 or the medical image DB 20.

[0059] Furthermore, in the above-described embodiment, the estimation of branching points and the diameter of branching portions of blood vessels has been described. However, for branched tubular objects other than blood vessels (e.g., tracheas, mammary ducts, etc.), similar search processing may be performed using shape data indicating the three-dimensional shape of the surface of the tubular object including branches to estimate branching points or the diameter of branching portions of the tubular object.

[0060] In the above-described embodiment, the acquisition function 141 is an example of an "acquisition unit," the setting function 142 is an example of a "setting unit," the search function 143 is an example of a "search unit," the estimation function 144 is an example of an "estimation unit," the image generation function 145 is an example of an "image generation unit," and the display control function 146 is an example of a "display control unit."

[0061] According to at least one of the embodiments described above, the medical image processing device of the embodiment has an acquisition unit that acquires blood vessel shape data indicating the three-dimensional shape of the surface of a blood vessel including branches, a setting unit that sets a reference point for the blood vessel shape data and the radius of a sphere centered on the reference point, a search unit that searches for the position of the sphere that fits the surface of the blood vessel using the center and the radius of the sphere as search variables, and an estimation unit that estimates the center of the sphere searched by the search unit as the branching point of the blood vessel, thereby making it possible to more accurately estimate the branching point of the blood vessel.

[0062] Specifically, according to the embodiment, the position and radius of a sphere are used as search variables for blood vessel shape data, and the value of an evaluation function E consisting of an error term (first index value), a radius maximization term (second index value), and a search range constraint term (third index value) is minimized to search for the position of a sphere that fits the blood vessel surface, thereby making it possible to more accurately estimate the branching points of blood vessels from the position of the sphere. Furthermore, according to the embodiment, the diameter of the branching portion and the center line of the blood vessel can also be accurately obtained based on the estimated branching points. Furthermore, according to the embodiment, robust three-dimensional measurement of blood vessel branching points can be realized, and image interpretation using branching points and risk prediction of lung disease, etc. can be performed efficiently and accurately. Furthermore, the above-mentioned estimation method can further improve the reproducibility of blood vessel branching points.

[0063] The above-described embodiment can be expressed as follows. processing circuitry; The processing circuitry acquiring blood vessel shape data indicating a three-dimensional shape of the surface of the blood vessel including branches; a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point; Using the center and the radius of the sphere as search variables, search for a position of the sphere that fits the surface of the blood vessel; The center of the searched sphere is estimated as a branch point of the blood vessel. Medical imaging equipment.

[0064] 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 reductions, 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 the inventions described in the claims and their equivalents. [Explanation of symbols]

[0065] 1... medical image processing system, 10... medical image generating device, 20... medical image DB, 100... medical image processing device, 110... communication interface, 120... input interface, 130... display, 140... processing circuit, 141... acquisition function, 142... setting function, 143... search function, 144... estimation function, 145... image generating function, 146... display control function, 150... memory

Claims

1. an acquisition unit that acquires blood vessel shape data indicating a three-dimensional shape of the surface of a blood vessel including branches; a setting unit that sets a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point; a search unit that searches for a position of the sphere that fits the surface of the blood vessel using the center and the radius of the sphere as search variables; an estimation unit that estimates the center of the sphere searched by the search unit as a branch point of the blood vessel; A medical image processing device comprising:

2. the searching unit searches for the position of the sphere that fits the surface of the blood vessel, where a value obtained by an evaluation function including a first index value based on the sum of errors between the distance from the center of the sphere to the surface of the blood vessel in multiple directions and the radius of the sphere, a second index value that decreases as the radius of the sphere increases, and a third index value that restricts a search range for the center of the sphere is smallest. The medical image processing device according to claim 1 .

3. The third index value is a value that increases as the center of the sphere becomes farther from the reference point. The medical image processing device according to claim 2 .

4. the searching unit searches for a position of the sphere that fits the surface of the blood vessel by changing the radius of the sphere, which is centered on a reference point existing inside the blood vessel shape corresponding to the blood vessel shape data, from a small value to a large value. The medical image processing device according to claim 1 .

5. the setting unit sets, as the reference points, branch points of blood vessels thinned by thinning processing of the blood vessel shape data. The medical image processing device according to claim 1 .

6. the estimation unit estimates a diameter of the branching portion of the blood vessel based on the estimated branching point of the blood vessel; The medical image processing device according to claim 1 .

7. the estimation unit performs thinning processing so that the estimated branch points of the blood vessels become branch points of the thinned blood vessels after the thinning processing. The medical image processing device according to claim 6 .

8. the estimation unit estimates a diameter of a branching portion of the blood vessel based on a position of the blood vessel thinned by the thinning process; The medical image processing device according to claim 7 .

9. a display control unit that displays an image showing at least one of the result of the search by the search unit and the result of the estimation by the estimation unit on a display unit; The medical image processing device according to claim 1 .

10. an acquisition unit that acquires shape data indicating a three-dimensional shape of a surface of a tubular object including branches; a setting unit that sets a reference point for the shape data and a radius of a sphere centered on the reference point; a search unit that searches for a position of the sphere that fits on the surface of the tubular object using the center and the radius of the sphere as search variables; an estimation unit that estimates the center of the sphere searched by the search unit as a branch point of the tubular object; A medical image processing device comprising:

11. The computer acquiring blood vessel shape data indicating a three-dimensional shape of the surface of the blood vessel including branches; a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point; Using the center and the radius of the sphere as search variables, search for a position of the sphere that fits the surface of the blood vessel; The center of the searched sphere is estimated as a branch point of the blood vessel. Medical image processing methods.

12. On the computer, acquiring blood vessel shape data indicating a three-dimensional shape of the surface of a blood vessel including branches; setting a reference point for the blood vessel shape data and a radius of a sphere centered on the reference point; Using the center and the radius of the sphere as search variables, a position of the sphere that fits the surface of the blood vessel is searched for; The center of the searched sphere is estimated as a branch point of the blood vessel. program.

Images