Image recognition device and image recognition method

Abstract

To keep a magnetic substance away from a magnetic resonance imaging device.SOLUTION: An image recognition device includes an image acquisition unit, a determination unit, and a display control unit. The image acquisition unit acquires a second image including a user to be photographed when entering an imaging room in which a magnetic resonance imaging device is installed, and one or a plurality of first images including the user having been photographed in facilities equipped with the imaging room before photographing the second image. The determination unit determines whether or not the user may be carrying a magnetic substance on the basis of whether or not there is any carried item that is not included in the second image out of the carried items of the user that are included in one or the plurality of first images. The display control unit causes a display part to display a determination result regarding whether the user is carrying the magnetic substance.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in this specification and the drawings relate to an image recognition device and an image recognition method. [Background technology]

[0002] A magnetic resonance imaging (MRI) device is an imaging device that excites the nuclear spins of a subject (e.g., a patient) placed in a static magnetic field generated by a static magnetic field magnet with radio frequency (RF) signals at the Larmor frequency, and generates MR images based on magnetic resonance (MR) signals generated from the subject as a result of the excitation.

[0003] If a magnetic material is brought into the imaging room where the MRI device is installed, it may be attracted to the MRI device, leading to an accident. Furthermore, if a magnetic material is attracted to the MRI device, it may cause image quality degradation such as metal artifacts in the generated MR images.

[0004] Therefore, before entering the MRI room, patients, medical staff, hospital personnel, and other users must be sure to check that they are not carrying any magnetic materials, and the safety of each user must be confirmed. Checks for the bringing in of magnetic materials are carried out, for example, by using metal detectors, visual inspections and verbal inquiries based on warning posters, and by recognizing objects in optical images taken by an optical camera at the entrance to the MRI room.

[0005] However, metal detectors are costly to install and implement, and it is time-consuming for technicians and other users to hold the metal detector over patients and other subjects to search for metal. Furthermore, visual and verbal inquiries are prone to human error, such as oversights. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2020-081765 Summary of the Invention [Problem to be solved by the invention]

[0007] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to prevent magnetic bodies from approaching a magnetic resonance imaging apparatus. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of the configurations of the embodiments described below can also be considered as other problems. [Means for solving the problem]

[0008] An image recognition device according to one embodiment includes an image acquisition unit, a determination unit, and a display control unit. The image acquisition unit acquires a second image including a user captured when the user enters an imaging room in which a magnetic resonance imaging device is installed, and one or more first images including the user captured within a facility including the imaging room before the second image is captured. The determination unit determines whether the user is likely to be carrying a magnetic object based on whether any of the user's belongings included in the one or more first images are not included in the second image. The display control unit causes the display unit to display the determination result regarding the user's carrying a magnetic object. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing an example of the arrangement of an image recognition device according to a first embodiment. [Figure 2] FIG. 1 is an explanatory diagram illustrating an example of user movement within a facility equipped with an MRI imaging room. [Figure 3] FIG. 3 is an explanatory diagram of a first image and a second image in the first embodiment. [Figure 4] 4 is a flowchart showing an example of the operation of the image recognition device according to the first embodiment. [Figure 5]FIG. 10 is a block diagram showing an example of the configuration of an image recognition device according to a modified example of the first embodiment. [Figure 6] FIG. 10 is an explanatory diagram of a display example of an image recognition device according to a modified example of the first embodiment. [Figure 7] FIG. 10 is a block diagram showing an example of the arrangement of an image recognition device according to a second embodiment. [Figure 8] FIG. 10 is an explanatory diagram of a first image and a second image in the second embodiment. [Figure 9] 10 is a flowchart showing an example of the operation of the image recognition device according to the second embodiment. [Figure 10] FIG. 10 is a block diagram showing an example of the arrangement of an image recognition device according to a third embodiment. [Figure 11] 10 is a flowchart showing an example of the operation of the image recognition device according to the third embodiment. [Figure 12] 10 is a flowchart showing an example of the operation of an image recognition device according to a modified example of the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of an image recognition device and an image recognition method will be described in detail with reference to the drawings. In each drawing, the same elements are given the same reference numerals, and duplicated explanations will be omitted.

[0011] (First embodiment) FIG. 1 is a block diagram showing an example of the configuration of an image recognition device 1 according to a first embodiment. The image recognition device 1 is a device for confirming, based on an image captured by a camera 2, that a user (hereinafter referred to as a "user") of an imaging room (hereinafter referred to as an "MRI imaging room") in which a magnetic resonance imaging (MRI) device 3 is installed is not carrying any magnetic material, thereby enabling safe use of the MRI device 3. The users include, for example, subjects such as patients undergoing imaging using the MRI device 3, staff such as technicians who operate the MRI device 3, other medical professionals, and hospital personnel. In addition, in the event of an unforeseen incident, a person who does not normally fall under the category of user, such as a suspicious person, may also be included as a user. The confirmers who confirm that the MRI device 3 can be used safely include, for example, staff such as technicians who operate the MRI device 3, other medical professionals, and hospital personnel.

[0012] The camera 2 is composed of an optical camera, a TV camera, or the like, and captures still or moving images of the user. The camera 2 is, for example, a camera using a solid-state imaging element such as a CMOS (Complementary Metal Oxide Semiconductor) or a CCD (Charge Coupled Device). The camera 2 may be, for example, a recording type surveillance camera or a live camera installed to detect the intrusion of a suspicious person. In recent years, in a facility (hereinafter referred to as "inside the facility") equipped with an MRI imaging room R1 (see FIG. 2), multiple cameras 2 are used to capture images of the facility. Then, various data including video information such as timestamps obtained by the multiple cameras 2 and some or all of the images including the user are stored in the memory circuitry 12 of the image recognition device 1.

[0013] 1, the image recognition device 1 includes a processing circuit 11, a memory circuit 12, a network interface 13, and a display 15. The image recognition device 1 may further include an input interface 14. A portion of the image recognition device 1 is not limited to being installed within a facility, and may be installed outside the facility.

[0014] The processing circuitry 11 realizes the function of overall control of the image recognition device 1. The processing circuitry 11 is also a processor that realizes various functions by reading and executing programs stored in the memory circuitry 12. The processor of the processing circuitry 11 realizes various functions such as an image acquisition function F1, a determination function F2, a display control function F3, a management control function F4, a comparison function F5, and an information acquisition function F6. These functions are stored in the memory circuitry 12, for example, in the form of programs.

[0015] The memory circuitry 12 includes a processor-readable storage medium, such as a semiconductor memory element such as a random access memory (RAM) or a flash memory, a hard disk, or an optical disk, and stores programs used by the processing circuitry 11. The memory circuitry 12 may also include a portable storage medium, such as a universal serial bus (USB) memory or a digital video disk (DVD). The memory circuitry 12 stores various data, including video information such as timestamps captured by the multiple cameras 2 and some or all of images containing users. This data may be stored as a database. The memory circuitry 12 also stores magnetic material data, which associates one or more objects with information indicating whether the objects are magnetic. The memory circuitry 12 may also store information about users. The memory circuitry 12 is an example of a storage unit.

[0016] The network interface 13 implements various information communication protocols according to the type of network. The network interface 13 performs communication control according to various protocols and has the function of connecting to the network via wire or wirelessly. The network interface 13 is communicably connected to the camera 2 via the network. The network interface 13 may also be communicably connected to the MRI apparatus 3.

[0017] The input interface 14 is composed of an input device (e.g., a touch panel) that can be operated by the verifying person, and an input circuit that inputs signals from the input device, and outputs an operation input signal corresponding to the verifying person's operation to the processing circuit 11.

[0018] The display 15 is configured by a general display output device such as a liquid crystal display or an OLED (Organic Light Emitting Diode) display. The display 15 is a display device and may also be, for example, a GUI (Graphical User Interface) that can accept operations by the inspector. The display 15 is attached to a location where the inspector can see it, such as a wall of the antechamber of the MRI imaging room R1 or the entrance door 4. The display 15 is an example of a display unit.

[0019] An example of the movement of a user U within a facility will now be described with reference to Figure 2. In Figure 2, users U(P1), U(P2), U(P3), U(P4), U(P5), and U(P6) indicate that the same user U is at positions P1, P2, P3, P4, P5, and P6, using the symbols in parentheses. Also, the first camera 2a, second camera 2b, and third camera 2c in Figure 2 represent cameras 2 installed in different locations.

[0020] In Fig. 2, the user U moves from room R3 (i.e., position P1) through the corridor in front of room R4 (i.e., positions P2, P3, and P4), enters room R2 (i.e., position P5), and then moves to MRI imaging room R1 (i.e., position P6) within the facility. Note that the movement of the user U within the facility is not limited to the example shown in Fig. 2, and includes any movement of the user U within the facility.

[0021] In Fig. 2, user U (P1) is photographed by the third camera 2c, users U (P2), U (P3), and U (P4) are photographed by the second camera 2b, and user U (P6) is photographed by the first camera 2a. Furthermore, no camera 2 is installed in room R2, and user U (P5) is not photographed. Note that the installation locations of the cameras 2 and the types and arrangements of rooms within the facility are not limited to the example shown in Fig. 2.

[0022] Here, Fig. 3 is an explanatory diagram of the first image and the second image in the first embodiment. Fig. 3 shows an image of user U (P1), an image of user U (P3), and an image of user U (P6) and their video information when user U moves within the facility as shown in Fig. 2.

[0023] The image of user U (P6) is an image taken by the first camera 2a at 16:04. In this way, the image taken when user U enters the MRI imaging room R1 is called the second image. Also, the image of user U (P1) is an image taken by the third camera 2c at 15:15, and the image of user U (P3) is an image taken by the second camera 2b at 15:32. In this way, one or more images including user U taken within the facility before the second image is taken are called the first image. The first image is not limited to two images, but may be one image, or three or more images. Also, although a portion of user U is depicted in the image of user U in FIG. 3, the entire user U may be depicted.

[0024] In Figure 3, the images of user U at positions P1 and P3 (i.e., the first image) depict a carried item A1, whereas the image of user U at position P6 (i.e., the second image) does not depict the carried item A1. Note that the number of carried items A1 is not limited to one, and there may be multiple carried items. The carried item A1 may be any object that user U can carry with them, such as a writing implement, an accessory, a mobile phone, a bag, an oxygen cylinder, or a stretcher.

[0025] The image recognition device 1 determines whether or not the user U is likely to be carrying a magnetic object based on the difference in depiction of the carried object A1 between the one or more first images and the second image. An example of the operation of the image recognition device 1 according to the first embodiment will be described with reference to the flowchart of FIG.

[0026] In step ST10, the image acquisition function F1 acquires one or more first images including the user U taken in a facility equipped with an MRI imaging room R1. The first images are images taken before the second images including the user U are taken when the user U enters the MRI imaging room R1. The image acquisition function F1 may acquire the first images within a predetermined time range, for example, after the user U enters the facility, after changing clothes to enter the MRI imaging room R1, or after leaving a predetermined room.

[0027] The image acquisition function F1 may also acquire a first image taken at a predetermined time. For example, the first image may be an image taken on the same day as the second image, or an image taken on a different day, such as one week or one month ago. The image acquisition function F1 may also acquire a first image in a predetermined situation or a predetermined location. For example, the first image may be acquired when the user U carries an object. In this way, the image acquisition function F1 may determine the first image to acquire based on video information related to the time (e.g., the time of the timestamp), location, and situation when one or more first images were taken.

[0028] The image acquisition function F1 may acquire one or more first images from images including the user U captured by a camera 2 installed within the facility. The image acquisition function F1 acquires the images, for example, via the network interface 13. The image acquisition function F1 may acquire one or more first images from images including the user U within the facility that are stored in the memory circuitry 12.

[0029] In step ST20, the image acquisition function F1 acquires a second image including the user U captured when the user U enters the MRI imaging room R1 as the first image. The image acquisition function F1 acquires, for example, an image captured by a camera 2 (for example, the first camera 2a in FIG. 2) installed in the anteroom of the MRI imaging room R1 as the second image.

[0030] In step ST30, the determination function F2 determines whether or not there is a possibility that the user U is carrying a magnetic object based on whether or not there is an item A1 among the user U's belongings included in one or more first images that is not included in the second image. Specifically, if there is an item A1 among the user U's belongings included in one or more first images that is not included in the second image, it determines that there is a possibility that the user U is carrying a magnetic object that is not visible from the outside. Furthermore, if all of the one or more belongings of the user U included in one or more first images are included in the second image, it determines that there is no possibility that the user U is carrying a magnetic object that is not visible from the outside.

[0031] Furthermore, the determination function F2 may determine whether or not the user U is likely to be carrying a magnetic object based on video information regarding the time, place, and situation when one or more first images were captured. Even when multiple first images have been acquired, the determination function F2 may determine whether or not the user U is likely to be carrying a magnetic object using only at least one of the multiple first images that includes the user U's carried item A1. For example, if the carried item A1 is not depicted in the image of the user U at position P1, but the carried item A1 is depicted in the image of the user U at position P3, the determination may be made using the image of the user U (P3) (i.e., the first image) and the image of the user U (P6) (i.e., the second image).

[0032] If it is determined that there is no possibility that user U is carrying a magnetic material (NO in step ST30), the processing ends, and if it is determined that there is a possibility that user U is carrying a magnetic material (YES in step ST30), the processing proceeds to step ST40.

[0033] In step ST40, the determination function F2 further determines whether the carried object A1 is a magnetic material. If the carried object A1 is a magnetic material, the determination function F2 determines that the user U is carrying a magnetic material, and if the carried object A1 is not a magnetic material, the determination function F2 determines that the user U is not carrying a magnetic material.

[0034] The determination function F2 determines whether the carried object A1 is a magnetic object based on, for example, magnetic object data. The magnetic object data is data in which one or more objects that may be carried objects are associated with information indicating whether the objects are magnetic objects, and is stored, for example, in the memory circuit 12. The magnetic object data may be updated. For example, for an object that was previously confirmed to be non-magnetic, the magnetic object data may be changed so that the object is associated with a non-magnetic object. Note that if the user U is carrying an object that is not registered in the magnetic object data, the verifying person may be notified of this.

[0035] If it is determined that the user U is not carrying a magnetic material (NO in step ST40), the process ends, and if it is determined that the user U is carrying a magnetic material (YES in step ST40), the process proceeds to step ST50.

[0036] The timing of determining whether the carried item A1 is a magnetic material is not limited to the timing of step ST40. For example, after the first image is acquired in step ST10, it may be determined whether the carried item depicted in the first image is a magnetic material. After the second image is acquired in step ST20, it may be determined whether the carried item depicted in the first image or the second image is a magnetic material. In this case, after step ST20, it is determined whether the user U corresponding to step ST40 is carrying a magnetic material based on whether there is any carried item A1 of the user U included in the first image that is not included in the second image.

[0037] In step ST50, the display control function F3 displays the determination result regarding whether the user U is carrying a magnetic material on a display unit such as the display 15. The determination result regarding whether the user U is carrying a magnetic material includes at least one of the following determination results: a determination as to whether the user U is likely to be carrying a magnetic material, and a determination as to whether the user U is carrying a magnetic material. The determination result may be displayed as text, an image, or both. The display control function F3 may display an actual image of the user U taken by the camera 2 or a virtual human body model on the display 15, along with the location where the magnetic material is being carried.

[0038] The determination result may be displayed on a display (not shown) provided in the MRI apparatus 3. Furthermore, if the determination result as to whether or not the user U is likely to be carrying a magnetic material is displayed in step ST50, step ST40 may be omitted, and the process may proceed to step ST50 after step ST30.

[0039] According to the image recognition device 1 of the first embodiment, before the user U enters the MRI imaging room R1, the inspector is notified whether or not the user U is carrying a magnetic material, thereby preventing the magnetic material from coming close to the MRI device 3.

[0040] (Modification of the first embodiment) Fig. 5 is a block diagram showing an example of the configuration of an image recognition device 1 according to a modified example of the first embodiment. As shown in Fig. 5, the modified example of the first embodiment differs from the first embodiment in that the processing circuit 11 of the image recognition device 1 further implements a management control function F4.

[0041] The management control function F4 manages entry into the MRI imaging room R1. The management control function F4 permits entry into the MRI imaging room R1 when the determination function F2 determines that the user U is not carrying a magnetic object. Furthermore, after the determination function F2 determines that the user U is carrying a magnetic object, the management control function F4 may permit entry into the MRI imaging room R1 when the verification person confirms that the user U is not carrying a magnetic object.

[0042] 6 is an explanatory diagram of a display example of the image recognition device 1 according to a modified example of the first embodiment. As shown in FIG. 6, a display 15 may be installed on the door 4 of the MRI imaging room R1, and a message "You may be carrying a magnetic material" may be displayed on the display 15. The person checking the user U's carrying a magnetic material by referring to the determination result displayed on the display 15 of the image recognition device 1, and checking the user U, and inputs the confirmation result via the input interface 14.

[0043] The display 15 may further have a function as an input interface that accepts operations by a checker, and may accept a confirmation operation that the user U is not carrying a magnetic material. For example, the checker performs a confirmation operation such as selecting a display related to "agreement" on the display 15.

[0044] Furthermore, the door 4 of the MRI imaging room R1 may be provided with a locking mechanism (not shown) for opening and closing the door, and the management control function F4 may perform control so that the door 4 of the MRI imaging room R1 is unlocked when a confirmation operation is performed and entry into the MRI imaging room R1 is permitted. When the confirmation operation by the verifier that the user U is not carrying a magnetic substance is accepted, the display control function F3 may display on the display 15 that the MRI device 3 is safe to use.

[0045] The display of the determination result regarding the user U's carrying of a magnetic material and the display of the checking operation by the checker may be performed on a display (not shown) provided in the MRI apparatus 3. Furthermore, the checking operation by the checker may be acquired through an input interface (not shown) provided in the MRI apparatus 3.

[0046] According to the image recognition device 1 according to the modified example of the first embodiment, for safety reasons, a checker performs a check operation regarding the entry of the user U into the MRI imaging room R1, and the entry of the user U into the MRI imaging room R1 is managed. Therefore, it is possible to prevent magnetic objects from approaching the MRI device 3 under even stricter management than in the first embodiment.

[0047] (Second embodiment) Fig. 7 is a block diagram showing an example of the configuration of an image recognition device 1 according to the second embodiment. As shown in Fig. 7, the second embodiment differs from the first embodiment in that the processing circuitry 11 of the image recognition device 1 further implements a comparison function F5.

[0048] Here, Fig. 8 is an explanatory diagram of the first image and the second image in the second embodiment. Similar to Fig. 3, Fig. 8 shows an image of user U (P1), an image of user U (P3), and an image of user U (P6) and their video information when user U moves within the facility as shown in Fig. 2. The image of user U (P6) is an image taken by the first camera 2a at time 16:04. The image of user U (P1) is an image taken by the third camera 2c at time 15:15, and the image of user U (P3) is an image taken by the second camera 2b at time 15:32.

[0049] In Figure 8, the images of user U at positions P1 and P3 depict the carried item A1, while the image of user U at position P6 depicts an invisible area B1. The invisible area B1 is an area in which part or all of the carried item A1 may be present. In Figure 8, the invisible area B1 is a portion of the transported item that is covered by a cloth cover. Alternatively, the invisible area B1 may be a portion of clothing in which the carried item A1 may be present, such as the inside of clothing or a pocket. The invisible area B1 is not limited to one area, and may be multiple areas.

[0050] The image recognition device 1 determines whether or not the user U is likely to be carrying a magnetic object based on the difference in depiction of the carried object A1 and the invisible area B1 between the one or more first images and the second image. An example of the operation of the image recognition device 1 according to the second embodiment will be described using the flowchart of Fig. 9. As shown in Fig. 9, in the second embodiment, the process proceeds to step ST31 after step ST20.

[0051] In step ST31, the comparison function F5 determines whether there is an invisible area B1 in the second image that may contain an item A1 carried by user U that is included in one or more first images but is not included in the second image.

[0052] If it is determined that there is no invisible area B1 in which an item A1 not included in the second image among the items carried by the user U included in one or more first images may be present (NO in step ST31), the process ends. If it is determined that there is an invisible area B1 in which an item A1 not included in the second image among the items carried by the user U included in one or more first images may be present (YES in step ST31), the process proceeds to step ST32.

[0053] In step ST32, the comparison function F5 compares the area of ​​the carried item A1 with the invisible area B1. The determination function F2 determines whether or not there is a possibility that the user U is carrying a magnetic object based on the comparison result between the area of ​​the carried item A1 and the invisible area B1. If the comparison result between the area of ​​the carried item A1 and the invisible area B1 shows that the invisible area B1 is larger than the area of ​​the carried item A1 (YES in step ST32), the process proceeds to step ST40. In step ST40, the determination function F2 determines whether or not there is a possibility that the user U is carrying a magnetic object.

[0054] If the invisible area B1 is not larger than the area of ​​the carried item A1 (NO in step ST32), the process ends. For example, if the user U who was carrying the carried item A1 such as an oxygen tank in the first image is not carrying the carried item A1 in the second image and the invisible area B1 such as a clothing pocket is not larger than the area of ​​the carried item A1, it is determined that the user U is not likely to be holding the carried item A1.

[0055] In step ST40, as in the first embodiment, the determination function F2 further determines whether or not the carried item A1 is a magnetic material. If the carried item A1 is a magnetic material, the determination function F2 determines that the user U is carrying a magnetic material, and if the carried item A1 is not a magnetic material, the determination function F2 determines that the user U is not carrying a magnetic material. Note that, as in the first embodiment, the timing for determining whether or not the carried item A1 is a magnetic material is not limited to the timing of step ST40.

[0056] In step ST50, the display control function F3 displays at least one of the determination results regarding whether user U is carrying a magnetic material, namely, whether user U is possibly carrying a magnetic material, and whether user U is carrying a magnetic material, on a display unit such as display 15.

[0057] An invisible area B1 in which the user U may be carrying a magnetic object may be displayed on the display 15 together with the determination result regarding whether the user U is carrying a magnetic object. For example, if there is an invisible area B1, it may be determined that the carried item A1 is possibly inside, and the display control function F3 may cause the display 15 to clearly show the invisible area B1.

[0058] In addition, if the determination result as to whether or not the user U is possibly carrying a magnetic material is displayed in step ST50, step ST40 may be omitted and the process may proceed to step ST50 after step ST32.

[0059] According to the image recognition device 1 of the second embodiment, even if there is a possibility that user U's belongings A1 are present in the invisible area B1 where belongings A1 may be present, the inspector is informed of whether or not user U is carrying a magnetic object before user U enters the MRI imaging room R1, and the magnetic object can be prevented from approaching the MRI device 3.

[0060] (Third embodiment) Fig. 10 is a block diagram showing an example of the configuration of an image recognition device 1 according to a third embodiment. As shown in Fig. 10, the third embodiment differs from the first embodiment in that the processing circuit 11 of the image recognition device 1 further implements an information acquisition function F6. In the third embodiment, the behavioral history of the user U is used to determine whether the user U is carrying a magnetic object.

[0061] An example of the operation of the image recognition device 1 according to the third embodiment will be described using the flowchart of Fig. 11. In the third embodiment, step ST1 is performed before step ST20.

[0062] In step ST1, the information acquisition function F6 acquires information about the behavior history of the user U in the facility including the MRI imaging room R1 before the second image is taken. The information acquisition function F6 may also acquire information about the behavior history of the user U outside the facility including the MRI imaging room R1 before the second image is taken.

[0063] The information about the behavioral history of user U is at least one of the following: (a) information contained in an image of user U taken by a camera in the facility, (b) information contained in a stored image of user U, (c) location information of user U at the time of user U's behavior, and (d) information about the behavioral schedule of user U. The information about user U's behavioral history may be updated or added. For example, in FIG. 2, if user U previously often traveled in the order of position P1, position P3, position P5, and position P6, but recently often travels in the order of position P5, position P3, position P1, and position P6, information about both behavioral histories may be acquired.

[0064] 11, in the third embodiment, after step ST1, the process proceeds to step ST20, where the image acquisition function F1 acquires a second image including the user U, which is captured when the user U enters the MRI imaging room R1. Then, after step ST20, the process proceeds to step ST41.

[0065] In step ST41, the determination function F2 determines whether or not there is a possibility that the user U is carrying a magnetic material, based on the second image and the information related to the behavior history.

[0066] If it is determined that the user U is not carrying a magnetic material (NO in step ST41), the processing ends, and if it is determined that the user U is carrying a magnetic material (YES in step ST41), the processing proceeds to step ST50. In step ST50, the display control function F3 displays the determination result regarding whether the user U is carrying a magnetic material on a display unit such as the display 15. Note that if it is determined that the user U is not carrying a magnetic material (NO in step ST41), the determination result regarding whether the user U is possibly carrying a magnetic material may be displayed on the display 15.

[0067] Based on information about the user U's behavioral history, the display 15 may display that the user U is likely to be carrying a magnetic object. For example, if the user U visits the MRI imaging room R1 after undergoing surgery every Monday, there is a possibility that the user U is carrying surgical tools. If the user U has the habit of putting his / her mobile phone in his / her right pocket after using it, there is a possibility that the mobile phone is in his / her right pocket. Furthermore, since the user U was carrying the item A1 when he / she visited the MRI imaging room R1 in the past via a predetermined flow path within the facility, there is a possibility that the user U is carrying the same item A1 as last time when he / she visits the MRI imaging room R1 via the same predetermined flow path this time.

[0068] Based on information on the user U's behavioral history, the display 15 may display that there is no possibility that the user U is carrying a magnetic object. Also, if there is no possibility that the user U is carrying a magnetic object, the magnetic object may not be displayed on the display 15. For example, if the user U had a surgery scheduled on his / her activity schedule but the surgery was canceled and he / she did not stop by the operating room, there is a high possibility that he / she does not have any surgical tools. Furthermore, if the user U has the habit of putting his / her mobile phone in his / her right pocket after using it, but is wearing clothing that does not have an invisible area B1 such as a pocket, there is a high possibility that he / she does not have his / her mobile phone.

[0069] According to the image recognition device 1 of the third embodiment, based on information regarding behavioral history, the inspector is informed whether or not the user U is carrying a magnetic material before entering the MRI imaging room R1, thereby preventing magnetic materials from approaching the MRI device 3.

[0070] (Modification of the third embodiment) 12 is a flowchart showing an example of the operation of the image recognition device 1 according to a modification of the third embodiment. As shown in FIG. 12, the modification of the third embodiment differs from the third embodiment in that step ST10 is further performed. In the modification of the third embodiment, the process proceeds to step ST10 after step ST1.

[0071] In step ST10, the image acquisition function F1 acquires one or more first images including the user U taken within the facility before the second image was captured. The number of the one or more first images to be acquired may be adjusted based on information related to the behavioral history. For example, if the user U is in the facility every day and is behaving in the same way as in his / her normal behavioral history, the number of images to be acquired may be reduced, and if the user U is behaving differently from his / her normal behavioral history, the number of images to be acquired may be increased. Furthermore, the number of the one or more first images to be acquired may be adjusted depending on how frequently the user U is in the facility. For example, the number of the one or more first images to be acquired may be increased as the frequency with which the user U is in the facility decreases.

[0072] In a modification of the third embodiment, the process proceeds to step ST42 after step ST20. In step ST42, the determination function F2 determines whether or not there is a possibility that the user U is carrying a magnetic object, based on information indicating whether or not there is any item A1 carried by the user U that is included in one or more first images and that is not included in the second image, and information related to the behavioral history.

[0073] If it is determined that the user U is not carrying a magnetic material (NO in step ST42), the process ends, and if it is determined that the user U is carrying a magnetic material (YES in step ST42), the process proceeds to step ST50.

[0074] According to the image recognition device 1 according to the modified example of the third embodiment, it is possible to efficiently acquire one or more appropriate first images based on information related to the behavioral history. Furthermore, similar to the third embodiment, it is possible to prevent magnetic objects from approaching the MRI device 3. Note that information related to the behavioral history can also be used in the image recognition device 1 according to the second embodiment.

[0075] (others) When a predetermined object is brought into the MRI room R1, one or more first images may be images of the predetermined object taken within the facility before the second image is taken. In this case, the second image is an image of the predetermined object taken when the object is brought in. The determination function F2 further determines whether the predetermined object is likely to be a magnetic object based on whether there is a carried object A1 other than the predetermined object that is included in one or more first images and is not included in the second image. In addition, the display control function F3 displays the determination results of whether the predetermined object and the other objects are magnetic objects on a display unit such as the display 15.

[0076] For example, a first user may carry a predetermined item such as a stretcher to a first position, place another magnetic item on the predetermined item, and then a second user may carry the predetermined item and the other items from the first position to the MRI imaging room R1. The user U included in one or more first images and the second image may not be the same, and the user U may not be the same between the multiple first images. In this case, the user U may be a user who does not enter the MRI imaging room R1. It is sufficient that the predetermined item included in one or more first images and the second image is the same.

[0077] According to at least one of the embodiments described above, it is possible to keep magnetic materials away from the magnetic resonance imaging apparatus.

[0078] In the above embodiments, the term "processor" refers to a circuit such as a dedicated or general-purpose CPU (Central Processing Unit), GPU (Graphics Processing Unit), or 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 an FPGA). The processor realizes various functions by reading and executing programs stored in a storage medium.

[0079] In addition, although the above embodiment shows an example in which a single processor of a processing circuit realizes each function, a processing circuit may be configured by combining multiple independent processors, and each processor may realize each function. Furthermore, when multiple processors are provided, a storage medium for storing the program may be provided separately for each processor, or a single storage medium may store all of the programs corresponding to the functions of all the processors.

[0080] In addition, the image acquisition function F1, judgment function F2, display control function F3, management control function F4, comparison function F5, and information acquisition function F6 in the description of the embodiment are examples of the image acquisition unit, judgment unit, display control unit, management control unit, comparison unit, and information acquisition unit, respectively, as described in the claims.

[0081] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0082] REFERENCE SIGNS LIST 1...image recognition device 2...camera 3...magnetic resonance imaging device 11...processing circuit 12...memory circuit 12 13...network interface 14...input interface 15...display F1...image acquisition function F2...determination function F3...display control function F4...management control function F5...comparison function F6...information acquisition function

Claims

1. an image acquisition unit that acquires a second image including a user that is captured when the user enters an imaging room in which a magnetic resonance imaging device is installed, and one or more first images including the user that are captured in a facility that includes the imaging room before capturing the second image; a determination unit that determines whether or not there is a possibility that the user is carrying a magnetic object based on whether or not there is any carried item of the user that is included in the one or more first images and that is not included in the second image; a display control unit that displays a determination result regarding the user's carrying of a magnetic substance on a display unit; An image recognition device comprising:

2. The determination unit further determines whether the carried object is a magnetic body, If the carried object is a magnetic object, it is determined that the user is carrying a magnetic object; If the carried object is not a magnetic object, it is determined that the user is not carrying a magnetic object. The image recognition device according to claim 1 .

3. a storage unit that stores magnetic body data in which one or more objects that may be the carried item are associated with information indicating whether the object is a magnetic body; The determination unit determines whether the carried item is a magnetic body based on the magnetic body data. The image recognition device according to claim 2 .

4. the image acquisition unit acquires the one or more first images from images including the user taken by a camera installed in the facility; The image recognition device according to claim 1 .

5. a storage unit that stores an image including the user in the facility; the image acquisition unit acquires the one or more first images from images including the user in the facility stored in the storage unit; The image recognition device according to claim 1 .

6. the determination unit determines whether or not there is a possibility that the user is carrying a magnetic object based on video information relating to the time, place, and situation when the one or more first images were taken. The image recognition device according to claim 1 .

7. A management control unit that manages entry into the imaging room, The management control unit permits entry into the imaging room when (a) the determination unit determines that the user is not carrying a magnetic object, or (b) after the determination unit determines that the user is carrying a magnetic object, a verification person confirms that the user is not carrying a magnetic object. The image recognition device according to claim 2 .

8. a comparison unit that, when there is an invisible area in the second image that may contain an item carried by the user that is included in the one or more first images but is not included in the second image, compares the area of ​​the item with the invisible area; The determination unit determines whether or not there is a possibility that the user is carrying a magnetic object based on a comparison result between the area of ​​the carried object and the invisible area. The image recognition device according to claim 1 .

9. the determination unit determines whether or not there is a possibility that the user is carrying a magnetic object when the invisible area is larger than the area of ​​the carried object. The image recognition device according to claim 8.

10. The determination unit further determines whether the carried object is a magnetic body, If the carried object is a magnetic object, it is determined that the user is carrying a magnetic object; If the carried object is not a magnetic object, it is determined that the user is not carrying a magnetic object. The image recognition device according to claim 8.

11. an image acquisition unit that acquires a second image including the user, which is captured when the user enters an imaging room in which a magnetic resonance imaging apparatus is installed; an information acquisition unit that acquires information about the user's behavior history inside and outside the facility that includes the imaging room before capturing the second image; a determination unit that determines whether or not the user is likely to be carrying a magnetic object based on the second image and information related to the behavior history; a display control unit that displays a determination result regarding the user's carrying of a magnetic substance on a display unit; An image recognition device comprising:

12. an information acquisition unit that acquires information about a behavior history of the user inside and outside the facility that includes the imaging room before capturing the second image; the determination unit determines whether or not there is a possibility that the user is carrying a magnetic object based on information indicating whether or not there is any carried item of the user included in the one or more first images that is not included in the second image, and information related to the behavior history. The image recognition device according to claim 1 .

13. The information regarding the behavioral history is at least one of: (a) information contained in an image including the user taken by a surveillance camera within the facility; (b) information contained in a stored image including the user; (c) location information of the user at the time of the user's behavior; and (d) information regarding the user's behavior schedule. The image recognition device according to claim 11.

14. Acquire a second image including the user that is captured when the user enters an imaging room in which a magnetic resonance imaging device is installed, and one or more first images including the user that are captured in a facility that includes the imaging room before capturing the second image, determining whether or not there is a possibility that the user is carrying a magnetic object based on whether or not there is any carried item of the user included in the one or more first images that is not included in the second image; displaying the determination result regarding the user's carrying of a magnetic object on a display unit; Image recognition methods.

15. acquiring a second image including the user, the second image being captured when the user enters an imaging room in which a magnetic resonance imaging apparatus is installed; acquiring information about the user's behavior history in the facility that includes the imaging room before capturing the second image; determining whether or not the user is likely to be carrying a magnetic object based on the second image and the information related to the behavior history; displaying the determination result regarding the user's carrying of a magnetic object on a display unit; Image recognition methods.

Images