Image Processing Device

Abstract

To reduce a burden of confirmation on a user.SOLUTION: An image processing device includes an acquisition unit, a first detection unit, and an output unit. The acquisition unit acquires an image obtained by imaging a subject placed on a top plate of a magnetic resonance imaging device by a camera. The first detection unit detects, from the image, a loop in which an induction current is likely to be generated by a magnetic field generated by the magnetic resonance imaging device. The output unit outputs a detection result by the first detection unit.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to an image processing device.

[0002] Conventionally, a magnetic resonance imaging (MRI) apparatus generates an MR image by receiving a magnetic resonance signal from an RF (Radio Frequency) coil attached to a subject, and the MRI apparatus is connected to the RF coil via a cable.

[0003] Here, the magnetic resonance imaging apparatus generates a high-frequency magnetic field when imaging a subject. If a high-frequency magnetic field is generated in a state where a loop is formed by a cable or the like, a high-frequency induced current flows in the loop. This causes the cable forming the loop to heat up, and in severe cases, the subject may be burned. Therefore, the user must check that no loop or the like is formed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 4-71536 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems that the embodiments disclosed in this specification and the drawings aim to solve is to reduce the burden of confirmation on the user. However, the problems that the embodiments disclosed in this specification and the drawings aim to solve 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]

[0006] An image processing device according to an embodiment includes an acquisition unit, a recognition unit, a first detection unit, and an output unit. The acquisition unit acquires a three-dimensional image obtained by photographing a subject placed on a top board of a magnetic resonance imaging device with a camera. The recognition unit recognizes an object included in the three-dimensional image acquired by the acquisition unit. The first detection unit recognizes an object included in a cable of an RF (Radio Frequency) coil used in the magnetic resonance imaging device, which has a possibility of generating an induced current due to a magnetic field generated by the magnetic resonance imaging device, based on a three-dimensional spatial arrangement of the three-dimensional image acquired by the acquisition unit. To The output unit detects either a first loop formed by the sample or a second loop formed by the sample, and outputs a detection result by the first detection unit. Moreover, the first detection unit does not detect a third loop formed by a combination of the cable of the RF coil and the subject as the loop. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a confirmation support system according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of the magnetic resonance imaging apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of a subject viewed from above. [Figure 4] FIG. 4 is a diagram showing an example of the electric field region viewed from above. [Diagram 5] FIG. 5 is a diagram showing an example of the electric field region shown in FIG. 4 as viewed from the Z-axis direction. [Figure 6] FIG. 6 is a flowchart showing an example of a confirmation support process executed by the magnetic resonance imaging apparatus according to the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an image processing apparatus according to the present embodiment will be described with reference to the drawings. In the following embodiments, parts with the same reference numerals perform similar operations, and duplicated descriptions will be omitted as appropriate.

[0009] (First embodiment) FIG. 1 is a diagram showing an example of the configuration of a confirmation support system 1 according to the first embodiment. The confirmation support system 1 includes a magnetic resonance imaging (MRI) device 10 and a camera 20. The magnetic resonance imaging device 10 and the camera 20 are connected to each other via a network such as an in-hospital local area network (LAN). The confirmation support system 1 shown in FIG. 1 includes the magnetic resonance imaging device 10 and the camera 20. However, the confirmation support system 1 may include a plurality of cameras 20.

[0010] The X-axis, Y-axis, and Z-axis shown in Fig. 1 constitute an apparatus coordinate system specific to the magnetic resonance imaging apparatus 10. For example, the Z-axis direction coincides with the axial direction of the cylinder of the gradient magnetic field coil 103 (see Fig. 2) and is set along the magnetic flux of the static magnetic field generated by the static magnetic field magnet 101 (see Fig. 2). The Z-axis direction is the same as the longitudinal direction of the bed 105 and also the same as the head-to-tail direction of the subject P placed on the bed 105. The X-axis direction is set along the horizontal direction perpendicular to the Z-axis direction. The Y-axis direction is set along the vertical direction perpendicular to the Z-axis direction.

[0011] The magnetic resonance imaging apparatus 10 includes a bed 105 on which a subject P is placed, and a substantially cylindrical gantry device 11 having a cavity into which the subject P is inserted. The magnetic resonance imaging apparatus 10 generates a high-frequency magnetic field when the subject P is inserted into the cavity and the subject P is imaged. An RF (Radio Frequency) coil 12 attached to the subject P receives an MR signal generated from the subject P. The magnetic resonance imaging apparatus 10 receives the signal via a cable 13 of the RF coil 12. Then, the magnetic resonance imaging apparatus 10 generates an MR image of the subject P placed on a top board 105a of the bed 105 based on the received MR signal.

[0012] Furthermore, the cable 13 of the RF coil 12 may be colored or may have a pattern such as a geometric pattern. When detecting the cable 13 from the image captured by the camera 20, the magnetic resonance imaging apparatus 10 can easily detect it if the cable 13 is colored or has a pattern. When identifying the arrangement of the cable 13 in the Y-axis direction from the image captured by the camera 20, the magnetic resonance imaging apparatus 10 can identify the arrangement in the Y-axis direction by measuring the interval between the lines of the pattern of the cable 13.

[0013] The camera 20 is an imaging device that captures moving images or still images. The subject P placed on the tabletop 105a is included in the imaging area of ​​the camera 20. The camera 20 transmits the captured images to the magnetic resonance imaging apparatus 10. The camera 20 shown in FIG. 1 is disposed above the tabletop 105a of the bed 105. However, the camera 20 may be disposed in another position.

[0014] Here, even if the cable 13 forms a loop in the two-dimensional image, the cable 13 may not form a loop in the three-dimensional image. Therefore, the camera 20 may be disposed not only above the tabletop 105a, but also to the side of the tabletop 105a, or may be disposed at another position. Furthermore, the camera 20 may be an imaging device that captures a three-dimensional image that represents an imaging area in three dimensions, such as a ToF (Time of Flight) sensor or a LiDAR (Laser Imaging Detection and Ranging). Furthermore, the camera 20 may be an imaging device that can detect infrared rays. Thereby, the camera 20 can capture an image that makes it easy to distinguish between the subject P placed on the tabletop 105a and other objects other than the subject P.

[0015] In such a confirmation support system 1, the magnetic resonance imaging apparatus 10 acquires an image captured by the camera 20. The magnetic resonance imaging apparatus 10 also determines whether or not there is a location where the cable 13 or the like is looped from the image captured by the camera 20. Then, when the magnetic resonance imaging apparatus 10 detects a loop of the cable 13 or the like, it notifies the apparatus. The magnetic resonance imaging apparatus 10 is an example of an image processing apparatus.

[0016] Next, the magnetic resonance imaging apparatus 10 will be described.

[0017] 2 is a block diagram showing an example of the configuration of a magnetic resonance imaging apparatus 10 according to the first embodiment. The magnetic resonance imaging apparatus 100 includes a static magnetic field magnet 101, a static magnetic field power supply (not shown), a gradient magnetic field coil 103, a gradient magnetic field power supply 104, a bed 105, a bed control circuit 106, a transmission coil 107, a transmission circuit 108, a reception coil 109, a reception circuit 110, a sequence control circuit 120, and a computer system 130.

[0018] 2 is merely an example. For example, the sequence control circuit 120 and each unit in the computer system 130 may be appropriately integrated or separated. The magnetic resonance imaging apparatus 100 does not include a subject P (e.g., a human body).

[0019] The static magnetic field magnet 101 is a magnet formed in a hollow, approximately cylindrical shape, and generates a static magnetic field in the internal space. The static magnetic field magnet 101 is, for example, a superconducting magnet, and is excited by receiving a current from a static magnetic field power supply. The static magnetic field power supply supplies a current to the static magnetic field magnet 101. As another example, the static magnetic field magnet 101 may be a permanent magnet, in which case the magnetic resonance imaging apparatus 100 does not need to include a static magnetic field power supply. Also, the static magnetic field power supply may be provided separately from the magnetic resonance imaging apparatus 100.

[0020] The gradient magnetic field coil 103 is a coil formed in a hollow, approximately cylindrical shape, and is disposed inside the static magnetic field magnet 101. The gradient magnetic field coil 103 is formed by combining three coils corresponding to the mutually orthogonal X, Y, and Z axes, and these three coils are individually supplied with current from a gradient magnetic field power supply 104 to generate a gradient magnetic field whose magnetic field strength changes along each of the X, Y, and Z axes. The gradient magnetic field power supply 104 also supplies current to the gradient magnetic field coil 103 under the control of a sequence control circuit 120.

[0021] The bed 105 includes a top board 105a on which a subject P is placed, and the top board 105a is inserted into the imaging aperture with the subject P, such as a patient, placed thereon under the control of a bed control circuit 106. The bed control circuit 106 drives the bed 105 to move the top board 105a in the longitudinal direction and the vertical direction under the control of a computer system 130.

[0022] The transmitting coil 107 excites an arbitrary region of the subject P by applying a high-frequency magnetic field. The transmitting coil 107 is, for example, a whole-body type coil that surrounds the entire body of the subject P. The transmitting coil 107 receives an RF pulse from a transmitting circuit 108, generates a high-frequency magnetic field, and applies the high-frequency magnetic field to the subject P. The transmitting circuit 108 supplies an RF pulse to the transmitting coil 107 under the control of a sequence control circuit 120.

[0023] The receiving coil 109 is disposed inside the gradient magnetic field coil 103, and receives a magnetic resonance signal (hereinafter referred to as an MR (Magnetic Resonance) signal) emitted from the subject P due to the influence of a high frequency magnetic field. When the receiving coil 109 receives the MR signal, the receiving coil 109 outputs the received MR signal to the receiving circuit 110.

[0024] 2, the receiving coil 109 is provided separately from the transmitting coil 107, but this is only an example and is not limited to this configuration. For example, a configuration in which the receiving coil 109 also serves as the transmitting coil 107 may be adopted.

[0025] The receiving circuit 110 performs analog-to-digital (AD) conversion on the analog MR signal output from the receiving coil 109 to generate MR data. The receiving circuit 110 also transmits the generated MR data to the sequence control circuit 120. Note that the AD conversion may be performed within the receiving coil 109. The receiving circuit 110 is also capable of performing any signal processing other than AD conversion.

[0026] The sequence control circuit 120 drives the gradient magnetic field power supply 104, the transmission circuit 108, and the reception circuit 110 based on sequence information transmitted from the computer system 130, thereby imaging the subject P. The sequence information is information that defines a procedure for performing imaging. The sequence information includes, for example, the strength of the current supplied by the gradient magnetic field power supply 104 to the gradient magnetic field coil 103 and the timing of supplying the current, the strength of the RF pulse supplied by the transmission circuit 108 to the transmission coil 107 and the timing of applying the RF pulse, the timing of detecting the MR signal by the reception circuit 110, and the like. The sequence control circuit 120 may be realized by a processor, or may be realized by a combination of software and hardware.

[0027] When the sequence control circuit 120 receives MR data from the receiving circuit 110 as a result of driving the gradient magnetic field power supply 104, the transmitting circuit 108, and the receiving circuit 110 to image the subject P, the sequence control circuit 120 transfers the received MR data to the computer system 130.

[0028] The computer system 130 performs overall control of the magnetic resonance imaging apparatus 100, generates MR images, etc. As shown in FIG.

[0029] The NW interface 131 communicates with the sequence control circuit 120 and the bed control circuit 106. For example, the NW interface 131 transmits sequence information to the sequence control circuit 120. In addition, the NW interface 131 receives MR data from the sequence control circuit 120.

[0030] The memory circuitry 132 stores the MR data received by the NW interface 131, the k-space data arranged in the k-space by the processing circuitry 135 described later, and the image data generated by the processing circuitry 135. The memory circuitry 132 is, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, a hard disk, or an optical disk.

[0031] The input interface 133 accepts various instructions and information input from an operator. The input interface 133 is realized by, for example, a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, and a voice input circuit. The input interface 133 is connected to the processing circuit 135, and converts an input operation received from the operator into an electric signal and outputs it to the processing circuit 135. Note that in this specification, the input interface 133 is not limited to an interface having physical operation parts such as a mouse and a keyboard. For example, an electric signal processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the computer system 130 and outputs the electric signal to a control circuit is also included as an example of the input interface 133.

[0032] The display 134, under the control of the processing circuitry 135, displays a GUI (Graphical User Interface) for receiving input of imaging conditions, a magnetic resonance image generated by the processing circuitry 135, and the like. The display 134 is, for example, a display device such as a liquid crystal display.

[0033] The processing circuitry 135 controls the operation of the entire magnetic resonance imaging apparatus 10. The processing circuitry 135 has, for example, an image acquisition function 135a, a start condition detection function 135b, an object recognition function 135c, a loop detection function 135d, a cable loop detection function 135e, a subject loop detection function 135f, a contact detection function 135g, a placement detection function 135h, an electric field area detection function 135i, an entrapment detection function 135j, and an output function 135k. In the embodiment, each processing function performed by the image acquisition function 135a, the start condition detection function 135b, the object recognition function 135c, the loop detection function 135d, the cable loop detection function 135e, the subject loop detection function 135f, the contact detection function 135g, the placement detection function 135h, the electric field area detection function 135i, the entrapment detection function 135j, and the output function 135k is stored in the storage circuitry 132 in the form of a program executable by a computer. The processing circuitry 135 is a processor that realizes a function corresponding to each program by reading and executing the program from the storage circuitry 132. In other words, the processing circuitry 135 in a state in which each program has been read has each function shown in the processing circuitry 135 in FIG.

[0034] 2, the image acquisition function 135a, the start condition detection function 135b, the object recognition function 135c, the loop detection function 135d, the cable loop detection function 135e, the subject loop detection function 135f, the contact detection function 135g, the arrangement detection function 135h, the electric field area detection function 135i, the entrapment detection function 135j, and the output function 135k are realized by a single processor, but the processing circuit 135 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the function. Also, in FIG. 2, the single storage circuit such as the storage circuit 132 stores the programs corresponding to each processing function, but the processing circuit 135 may be configured by distributing a plurality of storage circuits and reading out the corresponding programs from the individual storage circuits.

[0035] The term "processor" used in the above description refers to a circuit such as a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), 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)). The processor realizes its function by reading and executing a program stored in the memory circuit 132. Note that instead of storing a program in the memory circuit 132, the processor may be configured to directly incorporate the program into its circuit. In this case, the processor realizes its function by reading and executing the program incorporated in the circuit.

[0036] The image acquiring function 135a acquires an image obtained by capturing an image of a subject P placed on a top board 105a of the magnetic resonance imaging apparatus 10 with the camera 20. The image acquiring function 135a is an example of an acquiring unit. More specifically, the image acquiring function 135a acquires an image captured by one or more cameras 20, an infrared image, or a three-dimensional image.

[0037] The start condition detection function 135b detects a start condition for starting detection of a detection target by the loop detection function 135d, the contact detection function 135g, and the arrangement detection function 135h. The start condition detection function 135b is an example of a second detection unit. More specifically, the start condition detection function 135b detects a start condition for starting a process of detecting a loop of the cable 13 by the loop detection function 135d. The start condition detection function 135b also detects a start condition for starting a process of detecting a contact point between the subject P and the cable 13 by the contact detection function 135g. The start condition detection function 135b also detects a start condition for starting a detection process of detecting a detection target from a predetermined area by the arrangement detection function 135h. The start condition detection function 135b detects, as a start condition, for example, that the cable 13 is connected to the magnetic resonance imaging apparatus 10, or that the top plate 105a is raised to insert the cable 13 into an imaging port, which is a substantially cylindrical cavity, of the gantry device 11.

[0038] The object recognition function 135c recognizes objects included in an image captured by the camera 20. The object recognition function 135c is an example of a recognition unit. For example, the object recognition function 135c recognizes that an object is the subject P, a cable 13, a wire that does not pose a risk of burns, an IV tube, an air supply tube, or the like. More specifically, the object recognition function 135c recognizes each object based on object feature information indicating the features of each object.

[0039] The object characteristic information includes a feature amount indicating the temperature, thickness, color, pattern, shape, etc. of each object. The object recognition function 135c can recognize an object by comparing the object characteristic information with an image of the object included in the image. For example, when the cable 13 is colored or patterned, the object recognition function 135c recognizes the cable 13 of the RF coil 12 that receives a signal generated from the subject P based on the color or pattern included in the image. The object recognition function 135c may recognize an object not only from one image but also from multiple images taken from different directions.

[0040] Furthermore, the object recognition function 135c may recognize an object based on an infrared image captured by the camera 20 that detects infrared rays. Furthermore, the object recognition function 135c may recognize an object based on a three-dimensional image captured by the camera 20 that generates a three-dimensional image.

[0041] In this embodiment, after the object recognition function 135c recognizes an object, the loop detection function 135d, the contact detection function 135g, and the arrangement detection function 135h each detect the detection target. However, the object recognition function 135c may recognize the object of the detection target after the loop detection function 135d, the contact detection function 135g, or the arrangement detection function 135h detects each of the detection targets.

[0042] The loop detection function 135d detects, from an image, a loop in which an induced current may occur due to a magnetic field generated by the magnetic resonance imaging apparatus 10. The loop detection function 135d is an example of a first detection unit. That is, the loop detection function 135d detects a loop formed by the cable 13 of the RF coil 12 used in the magnetic resonance imaging apparatus 10, or a loop formed by the subject P. The loop detection function 135d also includes a cable loop detection function 135e and a subject loop detection function 135f.

[0043] The cable loop detection function 135e detects the cable loop 13a formed by the cable 13. Here, FIG. 3 is a diagram showing an example of the subject P viewed from above. The cable loop detection function 135e detects the cable loop 13a formed by the cable 13. In other words, the cable loop detection function 135e detects the cable loop 13a in which an induced current may occur due to the high-frequency magnetic field generated by the magnetic resonance imaging apparatus 10. For example, the cable loop detection function 135e detects the cable loop 13a by detecting the shape of a loop from an image captured by the camera 20 by pattern matching.

[0044] The cable loop detection function 135e may detect the cable loop 13a from an infrared image captured by the camera 20 that detects infrared rays. Here, the cable loop detection function 135e can easily distinguish between the subject P and the cable 13 because of the temperature difference. In other words, the cable loop detection function 135e can reduce false detections by detecting the cable loop 13a from the infrared image.

[0045] Here, even if the cable 13 forms a loop shape in the two-dimensional image, if the cable 13 is not in contact in the Y-axis direction, it is not a loop. Therefore, the cable loop detection function 135e detects the cable loop 13a based on the three-dimensional spatial arrangement of the object such as the cable 13 included in the image. When the cable 13 has a pattern, the cable loop detection function 135e identifies the arrangement of the cable 13 in the Y-axis direction based on the interval between the lines forming the pattern. That is, the cable loop detection function 135e identifies the three-dimensional spatial arrangement of the cable 13. Then, the cable loop detection function 135e detects it as a cable loop 13a when the cables 13 forming a loop in the Y-axis direction overlap each other. Note that, when a three-dimensional image is acquired, the cable loop detection function 135e may identify the three-dimensional spatial arrangement of the cable 13 based on the three-dimensional image.

[0046] When the object recognition function 135c recognizes a specific object, the cable loop detection function 135e does not detect it as a cable loop 13a. For example, when the object recognition function 135c recognizes an object as an inspected object P or a tube, the cable loop detection function 135e does not detect a loop formed by the inspected object P or the tube. Moreover, when the object recognition function 135c recognizes an object as a tube or wiring with no risk of generating heat, the cable loop detection function 135e does not detect it as a cable loop 13a.

[0047] Furthermore, when the object recognition function 135c recognizes that they are the same object, the cable loop detection function 135e detects them as the cable loop 13a. That is, when a loop is formed by a plurality of objects, the cable loop detection function 135e does not detect it as the cable loop 13a. For example, even if a loop is formed by combining the cable 13 and the object P, the cable loop detection function 135e does not detect it as the cable loop 13a.

[0048] Note that the cable loop detection function 135e may detect the cable loop 13a by other methods than pattern matching. The cable loop detection function 135e may detect the cable loop 13a based on a trained model that detects the cable loop 13a included in an image when the image is input. For example, the trained model is generated by supervised learning in which an image and the cable loop 13a included in the image are input as teacher data.

[0049] The subject loop detection function 135f detects subject loops, which are loops formed by the subject P. The subject loop is a loop formed by contact between bare skin of the subject P. In other words, the subject loop detection function 135f does not detect it as a subject loop when it is in contact with a towel or examination gown. For example, the subject loop detection function 135f detects the loop by detecting the shape of a loop from an image captured by the camera 20 using pattern matching.

[0050] Also, the subject loop detection function 135f may detect the loop from an infrared image. Here, the subject loop detection function 135f can easily distinguish the subject P from the cable 13 because of the temperature difference. In other words, the subject loop detection function 135f can reduce false detection by detecting the subject P from an infrared image. Also, even if the subject P forms a ring shape in the two-dimensional image, if the subject P is not in contact in the Y-axis direction, it is not a loop. The subject loop detection function 135f detects the subject loop as a subject loop when the subject P that forms a ring in the Y-axis direction is in contact. Therefore, the subject loop detection function 135f detects the subject loop based on the three-dimensional spatial arrangement of an object such as the subject P included in the image. When a three-dimensional image is acquired, the subject loop detection function 135f may specify the three-dimensional spatial arrangement of the subject P based on the three-dimensional image.

[0051] The subject loop detection function 135f may detect the cable loop 13a by other methods than pattern matching. The subject loop detection function 135f may detect the subject loop based on a trained model that detects the subject loop included in an image when the image is input. For example, the trained model is generated by supervised learning in which an image and the subject loop included in the image are input as teacher data.

[0052] The contact detection function 135g detects, from the image, contact between the subject P and the cable 13 of the RF coil 12 that receives a signal generated from the subject P. The contact detection function 135g is an example of a third detection unit. More specifically, the contact detection function 135g detects a location where a part recognized by the object recognition function 135c as the subject P contacts a part recognized as the cable 13. That is, when the cable 13 or the subject P contacts a towel or examination gown, the contact detection function 135g does not detect it as a contact location.

[0053] The contact detection function 135g may detect the loop from the infrared image. Here, the contact detection function 135g can easily distinguish between the test object P and the cable 13 because of the temperature difference. In other words, the contact detection function 135g can reduce false detection by detecting the contact point from the infrared image.

[0054] Here, even if the two-dimensional image shows contact, if there is no contact in the Y-axis direction, the subject P is not in contact with the cable 13. When a three-dimensional image is acquired, the contact detection function 135g may detect the contact point between the subject P and the cable 13 based on the three-dimensional image.

[0055] The contact detection function 135g may detect the contact point between the subject P and the cable 13 based on a trained model that detects the contact point included in an image when the image is input. For example, the trained model is generated by supervised learning in which the image and the contact point between the subject P and the cable 13 are input as teacher data.

[0056] The placement detection function 135h detects a detection target from an electric field region E (see FIG. 4) identified by the magnetic field center C (see FIG. 4) of the magnetic resonance imaging apparatus 10, or a placement-prohibited region that may be involved in the movement of the bed 105 of the magnetic resonance imaging apparatus 10, based on an image acquired by the image acquisition function 135a. The placement detection function 135h is an example of a fourth detection unit. The electric field region E is an example of a first region. The placement-prohibited region is an example of a second region. The placement detection function 135h has an electric field area detection function 135i and an involvement detection function 135j.

[0057] The electric field area detection function 135i detects a detection target from an electric field region E (see FIG. 4) specified by a magnetic field center C (see FIG. 4) of the magnetic resonance imaging apparatus 10. The detection targets of the electric field area detection function 135i include the subject P and the cable 13.

[0058] Here, Fig. 4 is a diagram showing an example of the electric field region E viewed from above. Fig. 5 is a diagram showing an example of the electric field region E shown in Fig. 4 viewed from the Z-axis direction. The gantry 11 is provided with a gradient magnetic field coil 103 formed in a substantially cylindrical shape inside the gantry 11. In addition, when a subject P is inserted into the cavity of the gantry 11, the magnetic resonance imaging apparatus 10 generates a high-frequency magnetic field such that a magnetic field center C is formed at a position shown in Fig. 4, for example.

[0059] In this case, if an object such as the cable 13 or the subject P is placed in the electric field region E, an electric charge is stored between the gradient magnetic field coil 103 and the object placed in the electric field region E. In other words, the gradient magnetic field coil 103 and the object placed in the electric field region E function like a capacitor. Then, the object such as the cable 13 or the subject P may generate heat. Therefore, the subject P may be burned.

[0060] Therefore, the electric field area detection function 135i sets an electric field area E in which objects such as the cable 13 and the subject P are prohibited from being placed. More specifically, the electric field area detection function 135i sets the electric field area E to a range of a first set distance in the Z-axis direction and a second set distance from the edge of the top plate 105a, centered on the magnetic field center C on the top plate 105a. As shown in Figs. 4 and 5, the electric field area E is formed within a range of a certain distance from the inner wall of the gantry device 11. That is, the electric field area detection function 135i forms an arch-shaped electric field area E. Furthermore, since the subject P is placed on the top plate 105a, he is not placed below the top plate 105a. Therefore, the electric field area detection function 135i does not form the electric field area E below the top plate 105a. Furthermore, the first set distance and the second set distance can be arbitrarily changed. Furthermore, the magnetic field center C on the top plate 105a changes every time the subject P is imaged. For example, the part of the subject P to be imaged and the position of the subject P placed on the top plate 105a change every time the subject P is imaged. As a result, the magnetic field center C on the top plate 105a changes every time the subject P is imaged. Furthermore, the electric field region E is formed at a position on the top plate 105a in the Z direction according to the position where the magnetic field center C is set. That is, the electric field region E is formed at a position in the Z direction according to the feed amount of the top plate 105a. For example, when the feed amount of the top plate 105a is small, the electric field region E is formed at a position on the top plate 105a close to the gantry device 11. On the other hand, when the feed amount of the top plate 105a is large, the electric field region E is formed at a position on the top plate 105a far from the gantry device 11. Then, the electric field area detection function 135i detects detection objects such as the arms and legs of the subject P and the cable 13 from the electric field region E.

[0061] The entrapment detection function 135j detects a detection target from a preset entrapment attention area. The entrapment attention area is, for example, a gap area between the bed 105 and the tabletop 105a, an outer area of ​​a longitudinal side of the tabletop 105a, etc. The detection target is, for example, an IV tube, an air supply tube, a wiring, etc.

[0062] When imaging the subject P, the magnetic resonance imaging apparatus 10 inserts the tabletop 105a on which the subject P is placed into the imaging opening of the gantry device 11. When the tabletop 105a moves, if tubes or wires are placed in a region where there is a risk of the tubes or wires getting entangled in the magnetic resonance imaging apparatus 10.

[0063] For example, if a tube protrudes outward from a longitudinal side of the tabletop 105a, the tube may get caught on the gantry device 11 when the tabletop 105a is inserted into the imaging port. Alternatively, if a tube is disposed in the gap between the tabletop 105a and the bed 105, the tube may get pulled into the gap when the tabletop 105a is inserted into the imaging port. Therefore, the entrapment detection function 135j detects a detection target from the entrapment caution area.

[0064] The method of operating the magnetic resonance imaging apparatus 10 differs depending on the facility. That is, the location of the medical instruments around the magnetic resonance imaging apparatus 10 differs depending on the facility. Therefore, the location of the roll-in attention area may be arbitrarily changed.

[0065] The output function 135k outputs the detection results by the loop detection function 135d, the contact detection function 135g, and the arrangement detection function 135h. The output function 135k is an example of an output unit. More specifically, the output function 135k outputs the detection results in two stages. When the loop detection function 135d, the contact detection function 135g, or the arrangement detection function 135h detects a detection target, the output function 135k displays a detection position image indicating the position of the detection target on the display 134. The detection position image is an image that highlights the detection position of the detection target in an image showing each part of the magnetic resonance imaging apparatus 10. For example, the detection position image is an image in which an image showing the detection target is superimposed on an image of the magnetic resonance imaging apparatus 10.

[0066] In addition, when the output function 135k detects a notification condition, it notifies that the loop detection function 135d, the contact detection function 135g, or the placement detection function 135h has detected the detection target. The notification condition is, for example, an operation of inserting the top plate 105a into the imaging port of the gantry 11. For example, the operation of inserting the top plate 105a into the imaging port of the gantry 11 is an operation of clearly indicating the insertion of the top plate 105a into the imaging port of the gantry 11, or an operation involving the insertion of the top plate 105a into the imaging port of the gantry 11. The operation involving the insertion of the top plate 105a into the imaging port of the gantry 11 is, for example, an operation of identifying an organ to be imaged by the magnetic resonance imaging apparatus 10. Note that the notification condition is an example, and may be changed arbitrarily.

[0067] The output function 135k notifies by outputting an alert sound, for example. The output function 135k also displays a confirmation image requesting confirmation of the detection result of the loop detection function 135d, the contact detection function 135g, or the placement detection function 135h, in a pop-up display or the like on the display 134. The confirmation image has a confirmation button indicating that it has been confirmed that there is no problem with the detection result. Then, the output function 135k erases the confirmation image when it receives an operation indicating that it has been confirmed that there is no problem with the detection result. When the confirmation image is erased, the magnetic resonance imaging apparatus 10 continues to capture the subject P. In this way, the output function 135k can reduce the possibility of overlooking the confirmation result by restricting the magnetic resonance imaging apparatus 10 from capturing the subject P.

[0068] Next, a description will be given of a confirmation support process executed by the magnetic resonance imaging apparatus 10. Fig. 6 is a flowchart showing an example of the confirmation support process executed by the magnetic resonance imaging apparatus 10 according to the first embodiment.

[0069] The start condition detection function 135b judges whether or not a start condition for starting detection of a detection target has been detected (step S1). If the start condition has not been detected (step S1; No), the start condition detection function 135b waits.

[0070] When the start condition is detected (step S1; Yes), the image acquisition function 135a acquires an image captured by the camera 20 (step S2).

[0071] The object recognition function 135c recognizes each object included in the image acquired by the image acquisition function 135a (step S3).

[0072] The loop detection function 135d, the contact detection function 135g, or the placement detection function 135h determines whether or not the detection target is detected (step S4). If the detection target is not detected (step S4; No), the image acquisition function 135a acquires an image in step S2.

[0073] When the detection target is detected (step S4; Yes), the output function 135k notifies the detection result of the loop detection function 135d, the contact detection function 135g, or the placement detection function 135h (step S5). That is, the output function 135k causes the display 134 to display the detection position indicating the position where the detection target is detected.

[0074] The output function 135k determines whether or not the notification condition for notifying the detection result is satisfied (step S6). If the notification condition is not satisfied (step S6; No), the image acquisition function 135a acquires an image in step S2.

[0075] If the notification condition is met (step S6; Yes), the output function 135k notifies the user by displaying a confirmation screen on the display 134, which requests the user to confirm the detection result (step S7).

[0076] The output function 135k determines whether or not a confirmation operation indicating that the detection result has been confirmed has been received (step S8). If the confirmation operation has not been received (step S8; No), the output function 135k continues to display the confirmation screen in step S7.

[0077] If the confirmation operation has been accepted (step S8; Yes), the magnetic resonance imaging apparatus 10 erases the confirmation screen and ends the confirmation support process.

[0078] As described above, the magnetic resonance imaging apparatus 10 according to the first embodiment acquires an image of the subject P placed on the top plate 105a of the magnetic resonance imaging apparatus 10 by the camera 20. The magnetic resonance imaging apparatus 10 also detects the cable loop 13a, the loop of the subject P, a portion in contact with the cable 13, and a portion where the cable 13 or a tube may be entangled in the top plate 105a from the acquired image. The magnetic resonance imaging apparatus 10 then outputs the detection result to the user by displaying it, for example. Thus, the magnetic resonance imaging apparatus 10 can reduce the burden of checking on the user.

[0079] (Variation 1) In the first embodiment, it has been described that the magnetic resonance imaging apparatus 10 includes the image acquisition function 135a, the start condition detection function 135b, the object recognition function 135c, the loop detection function 135d, the cable loop detection function 135e, the subject loop detection function 135f, the contact detection function 135g, the arrangement detection function 135h, the electric field area detection function 135i, the entrapment detection function 135j, and the output function 135k. However, the image acquisition function 135a, the start condition detection function 135b, the object recognition function 135c, the loop detection function 135d, the cable loop detection function 135e, the subject loop detection function 135f, the contact detection function 135g, the arrangement detection function 135h, the electric field area detection function 135i, the entrapment detection function 135j, and the output function 135k may be included in other devices, not limited to the magnetic resonance imaging apparatus 10. For example, the image acquisition function 135a, the start condition detection function 135b, the object recognition function 135c, the loop detection function 135d, the cable loop detection function 135e, the subject loop detection function 135f, the contact detection function 135g, the placement detection function 135h, the electric field area detection function 135i, the entanglement detection function 135j, and the output function 135k may be provided in a computer device such as a personal computer, a server, or a workstation.

[0080] Although some 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, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0081] 1. Verification Support System 10. Magnetic Resonance Imaging (MRI) Equipment 11 Mounting device 12 RF (Radio Frequency) coil 13 Cable 13a Cable Loop 20 Camera 105 Bed 105a Tabletop 106 Bed control circuit 135 Processing Circuit 135a Image acquisition function 135b Start condition detection function 135c Object recognition function 135d Loop detection function 135e Cable Loop Detection Function 135f Specimen loop detection function 135g Contact detection function 135h Configuration detection function 135i Electric field area detection function 135j Entrapment detection function 135k output function C magnetic field center E Electric field region P Subject

Claims

1. an acquisition unit that acquires a three-dimensional image by photographing a subject placed on a top plate of the magnetic resonance imaging apparatus with a camera; a recognition unit that recognizes an object included in the three-dimensional image acquired by the acquisition unit; a first detection unit that detects either a first loop formed by a cable of an RF (Radio Frequency) coil used in the magnetic resonance imaging apparatus, which has a possibility of generating an induced current due to a magnetic field generated by the magnetic resonance imaging apparatus, or a second loop formed by the subject, based on a three-dimensional spatial arrangement of the three-dimensional image acquired by the acquisition unit; an output unit that outputs a detection result by the first detection unit; Equipped with the first detection unit does not detect a third loop formed by a combination of a cable of the RF coil and the subject as the loop; Image processing device.

2. the output unit outputs a confirmation image requesting confirmation of the detection result, and erases the confirmation image when an operation indicating that there is no problem with the detection result is received. The image processing device according to claim 1 .

3. When the recognition unit recognizes the object as a specific object, the first detection unit does not detect the object as the loop.

3. The image processing device according to claim 1 or 2.

4. The first detection unit detects the object as the loop when the object is recognized as the same object by the recognition unit. The image processing device according to claim 3 .

5. the recognition unit recognizes a cable of an RF coil used in the magnetic resonance imaging apparatus based on a color or a pattern included in the three-dimensional image.

5. The image processing device according to claim 3.

6. The first detection unit detects the loop from the three-dimensional image captured by the camera that detects infrared rays. The image processing device according to claim 1 .

7. the first detection unit detects the loop based on an arrangement in a three-dimensional space of an object included in the three-dimensional image; The image processing device according to claim 1 .

8. The first detection unit detects the loop based on a trained model that detects the loop included in the three-dimensional image when the three-dimensional image is input. The image processing device according to claim 1 .

9. A second detection unit that detects a start condition for starting detection of the detection target by the first detection unit, The image processing device according to claim 1 .

Images