Camera-assisted object support configuration

Abstract

The present invention provides a medical instrument (100, 300) comprising: an object support (110) including a support surface (112); a camera system (118); and a signal system (148). The execution of machine-executable instructions (152) causes a processor (142) controlling the medical instrument to: receive (400) a list of selected targets (160), each selected target having selected coordinates (162); and signal (402) indicate the list of selected targets. The execution of the machine-executable instructions also causes the processor to repeatedly: use the camera system to acquire (404) camera data; input the camera data (406) into a neural network to generate a list of placed targets (166); determine (408) a list of missing targets (168) by comparing the list of selected targets with the list of placed targets; indicate (410) the list of missing targets using a signal system; determine (412) a list of incorrectly placed targets (170) by comparing the selected coordinates of the list of each target with the coordinates of the targets placed on the support surface; and indicate (414) the list of incorrectly placed targets using a signal system.

Description

Technical Field

[0001] This invention relates to medical imaging and radiotherapy, and more particularly to the configuration of an object support. Background Technology

[0002] In both medical imaging and radiotherapy, the physical configuration of the object being measured, along with the various instruments and supports, is a crucial part of configuring the imaging or radiotherapy protocol. For example, in various medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), or positron emission tomography (PET), the physical configuration of the object being measured, along with the various instruments and supports, is configured differently depending on the type of examination to be performed. For instance, in MRI, which depends on the part of the object being imaged, different types of receiving coils, as well as specialized pads and supports, may be positioned around the object. Correctly and consistently configuring MRI systems or other medical imaging systems can be challenging for operators.

[0003] US Patent Application Publication US2009 / 0182221 discloses a magnetic resonance imaging (MRI) apparatus that receives magnetic resonance signals emitted from a subject using a receiving coil, and reconstructs an image of the test subject based on the received magnetic resonance signals, the object, and the image positions of first and second cameras at the receiving coil. During the setting of the receiving coil, an audio recorder records the same information for storage in a PACS server. Furthermore, during subsequent setting of the receiving coil, the position of the test subject and the information of the receiving coil are read from the PACS server and confirmed using a monitor and a speaker.

[0004] US Patent Application US2018 / 0116613 mentions determining the relative position of the object to be imaged to the imaging system (i.e., the X-ray source and the X-ray detector). Summary of the Invention

[0005] The present invention provides a medical instrument, a computer program product, and a method in the independent claims. Embodiments are given in the dependent claims.

[0006] Embodiments of the present invention can reduce the burden of correctly configuring medical instruments. This is achieved by using a camera system to image the support surface of an object support. When a target or object is placed on the support surface, it is imaged by the camera system. These targets are added to the configuration of the medical instrument. Camera data from the camera system is fed into a neural network that has been trained or configured to output a list of placed targets and the coordinates of the placed targets. The list of selected targets (each target having selected coordinates) can then be compared with the list of placed targets. The list of selected targets can be used to create a list of targets that should be placed on the object support, while the list of placed targets can be used to update which objects have been placed on the object support and which objects are in the correct position. The comparison of the list of placed targets and their coordinates with the prescribed positioning of the selected targets generates feedback on correct positioning. This feedback may include instructions on how to move an incorrectly placed target from its current position to its correct position. This correction can be performed manually by an operator guided by the medical instrument, or it can be automatic, i.e., the medical instrument drives the incorrectly positioned target to its correct position based on the position information from the feedback.

[0007] This invention provides a medical device comprising an object support including a support surface configured to receive an object. The medical device also includes a camera system configured to acquire image data describing the support surface. The camera system can be, for example, a two-dimensional camera, a three-dimensional camera, an infrared camera, a thermal camera, or all combinations thereof. Because the camera system is configured to acquire image data describing the support surface, a target (e.g., an object placed on the support surface or other target) can be imaged and present in the image data. The medical device also includes a signal system. The signal system can be any device that provides signals or information to an operator. For example, the signal system can be a display. Examples of displays include projectors, monitors, televisions, tablets, touchscreens, or other equipment suitable for displaying images. The signal system can also provide other visual or auditory signals, such as warning sounds or even recorded or synthesized speech.

[0008] The medical instrument also includes memory for storing machine-executable instructions and a neural network. The neural network is trained or configured to generate a list of placed targets in response to input camera data. The camera data may be images or image data acquired using one or more cameras. The list of placed targets identifies targets placed on a support surface and their coordinates. In different examples, the coordinates of the placed targets can be constructed or provided in different ways. For example, the neural network can use bounding boxes to identify the placed targets. The neural network can also identify the location of all or part of the support surface. This can also be identified using bounding boxes. There may be relationships trained into the neural network, or there may be external programs or algorithms for deriving coordinates associated with various bounding boxes. For many radiotherapy applications, coordinates on the object support are given in an indexed or discrete manner. Typically, the surface of the object support will be divided into multiple discrete regions. The bounding boxes output by the neural network can usually be easily used to derive or compute these discrete coordinates.

[0009] The medical instrument also includes a processor for controlling the medical instrument. The execution of the machine-executable instructions causes the processor to receive a list of selected targets. The list of selected targets is chosen from predetermined targets. That is, the list of selected targets is chosen from predetermined targets used to train the neural network. The list of selected targets includes selected coordinates for each target in the list. In other words, the list of selected targets includes targets that can be recognized by the neural network and have coordinates provided for each of them, indicating where they should be placed on the object support. The execution of the machine-executable instructions also causes the processor to use a signaling system to signal the list of selected targets and the selected coordinates for each target in the list. This can be useful for medical professionals setting up object supports to perform imaging or radiotherapy protocols. The signaling system provides healthcare professionals with information about the objects that need to be properly prepared and where these objects should be placed on the object support. Thus, healthcare professionals are guided by instructions on where to place the appropriate targets to correctly position them on the object support.

[0010] Signaling systems can provide information using audible tones or voice. They can also be conventional displays that output or display information to objects. In some cases, signaling systems can provide information by projecting data or position onto a supporting surface using a projector or laser.

[0011] The execution of the machine-executable instructions also causes the processor to repeatedly acquire camera data using the camera system. In this step, images of the supporting surface are repeatedly acquired. A subsequent execution of the machine-executable instructions further causes the processor to repeatedly feed the camera data into a neural network to generate a list of placed targets. The list of placed targets indicates which objects were found in the camera data and their coordinates.

[0012] The execution of the machine-executable instructions also causes the processor to repeatedly determine the list of missing targets by comparing the list of selected targets with the list of placed targets. Objects not placed on the object support can then be indicated on the list of missing targets. The execution of the machine-executable instructions also causes the processor to repeatedly indicate the list of missing targets using the signaling system. This can be performed, for example, in different ways. As mentioned earlier, the list of selected targets and their coordinates are issued using a signaling system. For example, the list of missing targets can be a separate list of targets, or it can be indicated by marking a status or highlighting the list of selected targets in some way. The list of missing targets and / or the list of misplaced targets can also be signaled using audible voice or tone. In other examples, the list of missing targets and / or the list of misplaced targets is signaled by projecting a graphic image or position onto the object surface using a projector or laser. This will guide the operator to add the missing targets in the appropriate location.

[0013] The execution of the machine-executable instructions also enables the processor to determine the list of misplaced targets by comparing the selected coordinates of each target in the list of targets with the coordinates of the targets placed on the support surface. The execution of the machine-executable instructions also enables the processor to indicate the list of misplaced targets using a signal system. Similarly, the indication of the list of misplaced targets can be performed in different ways. For example, there might be a separate list of targets located in the wrong position, or the display of the list of selected targets might be modified so that the coordinates of a particular target's location are not specified in the list of selected targets, and the selected coordinates for each of these are obvious.

[0014] This embodiment can be beneficial because it can provide an automated way to provide a list of what targets should be placed on the object support and in what positions. Not only is the list of selected targets at selected coordinates indicated by a signal, but a neural network is also used to check to ensure that the correct object or target is placed on the support surface and in the correct position. This increases the automation of guiding the user to place the appropriate object in its correct position.

[0015] The neural network can be trained using images of different objects placed on an object support. Deep training can be used to train both the coordinates and identity of a specific object. This adds 3D guidance to the user when configuring the target.

[0016] One object of the present invention is to provide guidance on the proper technical configuration of medical instruments to perform a specific imaging protocol. To this end, a neural network is provided that generates a list of placed targets from camera data (configured images) and identifies targets placed on a support surface (e.g., using bounding boxes). These targets enhance the configuration of the medical instrument, for example, to support an object to be subjected to the action of the medical instrument. This action can be a diagnostic imaging or therapeutic action. Thus, objects are added to the configuration that supports or even enables the medical instrument to perform actions on the object. The neural network identifies placed targets from images from the camera. The neural network is trained to identify predetermined targets. Furthermore, a list of selected targets associated with the imaging protocol to be performed is received. These selected targets and their coordinates are then sent to the user so that they can be placed in their respective appropriate positions. That is, the present invention indicates which targets need to be prepared and where they will be placed on the object support. This can be done sequentially to allow monitoring of objects that may be placed on top of each other, or objects that may be partially occluded from the camera's view during configuration. In this way, healthcare professionals are guided to properly configure medical instruments for the relevant medical (e.g., imaging or therapeutic) protocol. A record of how the targets actually used are configured to perform the protocol can also be made. This invention can automatically record missing or misplaced targets. A list of missing and / or misplaced targets can be provided to the user interface of a medical system. Notably, this invention increases the reproducibility of configurations, such as for imaging for treatment planning and for actual delivery of treatment, particularly in radiotherapy.

[0017] The medical instrument of the present invention provides information about the actual configuration of objects on an object support, including the presence or absence of objects and whether they are in the correct position. This feedback also provides information about which objects should be added or replaced, in what position, and how the actual position of a misplaced target relates to its correct position. That is, the medical instrument of the present invention provides technical guidance to the user to establish an appropriate configuration of the medical instrument for application to an object (i.e., a patient to be examined or treated). In one embodiment of the medical instrument, the object support can automatically move from its initial position to its operating position. In its initial position, the configuration of the target can be established under the guidance of a camera system, and the object can be accurately positioned. In the operating position of the object support, the configuration of the target and objects is in place to enable the object to operate the medical instrument according to the protocol.

[0018] The neural network determines which objects are present and their correct locations. Furthermore, the neural network can be operated to generate feedback in the form of a list of placed targets, missing targets, and misplaced targets. The use of the neural network provides technical guidance to the user in accurately setting up the correct configuration for the protocol to be performed. Feedback is repeatedly provided as the configuration is established, indicating whether and how it deviates from the correct configuration and how to correct it. The neural network provides technical guidance in setting up the technical configuration accurately and effectively for the relevant protocol. Information about correctly placed, missing, or misplaced targets during configuration construction, and the information generated regarding achieving the correct configuration, constitutes practical information about the internal technical state of the medical instrument. The neural network also provides information about which targets still need to be located and how to reposition misplaced targets to their correct positions.

[0019] In another embodiment, the execution of machine-executable instructions also causes the processor to use a signaling system to signal the list of selected targets in a defined order within the list of selected targets. This can be advantageous because, when configuring objects on an object support, placing them in a specific order on the object support can be beneficial. For example, this can be useful when one target needs to be placed on top of or on top of another target, or when one target may be partially occluded by another target. This embodiment can also be beneficial because it can help healthcare professionals correctly configure medical instruments.

[0020] In another embodiment, the execution of the machine-executable instructions also causes the processor to determine a list of correctly positioned targets using a list of placed targets, a list of missing targets, and a list of misplaced targets. If a member of a correctly positioned target is identified among the misplaced and / or missing targets, the execution of the machine-executable instructions also causes the processor to generate a signal. In this embodiment, the signal is provided if a previously correctly positioned target is subsequently moved to an incorrect location or removed. In different examples, the signal can take different forms. For example, the signal can be a visual or auditory signal that alerts healthcare professionals to an unauthorized deviation from standard protocols. The signal can also indicate notifications or signals from a signaling system. In other examples, the signal can be used to record objects identified as being on an object support and their coordinates. This can be useful when recording objects actually used to perform medical imaging protocols.

[0021] In another embodiment, the medical instrument includes a medical imaging system configured to acquire medical images from an imaging region. A support surface is configured to support at least a portion of an object within the imaging region.

[0022] In another embodiment, the memory also includes an imaging protocol database. The imaging protocol database includes a list of selected targets, each selected target associated with an imaging protocol. The execution of machine-executable instructions further causes the processor to receive a selection of a medical imaging protocol. The execution of the machine-executable instructions also causes the processor to use the selection of the medical imaging protocol to receive the list of selected targets from the medical imaging protocol database. In this embodiment, the selection of a medical imaging protocol is an instruction to select a specific imaging technique and / or a region of the object. Based on this selection, the correct list of selected targets is retrieved from the medical imaging protocol. For example, this can be useful in helping medical professionals set up medical instruments for a large or varying number of different medical imaging protocols. That is, the medical instrument provides guidance to the user to locate objects according to the selected imaging protocol.

[0023] In another embodiment, selected coordinates for each target in the list of targets are specified in discrete coordinates. The coordinates of the targets placed on the object support are specified in discrete coordinates. The discrete coordinates used here are a coordinate system that divides the object support into discrete regions. When an object is placed on the object support, the use of discrete coordinates specifies which region(s) the object should be placed in. Within these specific regions, healthcare professionals are then free to place it anywhere within the volume or region specified by the discrete coordinates. This can be advantageous because such coordinate systems are commonly used to set targets and structures for use in radiotherapy.

[0024] In another embodiment, the execution of machine-executable instructions also causes the processor to append the status of a list of misplaced targets and a list of missing targets to the medical image data. This can be beneficial because it provides a means of automatically recording which objects are missing or not placed in standard locations during medical imaging. For example, a DICOM file can automatically record information about the setup. The status lists of misplaced targets and missing targets can detail what is missing or not missing, or may simply be metadata describing whether these lists are empty.

[0025] In another embodiment, the execution of machine-executable instructions also causes the processor to append a list of placed targets and their coordinates to the medical image data. This can also be done in, for example, a DICOM file format, and these lists are appended automatically.

[0026] In another embodiment, the object support is configured to move from an initial position to an operational position. In the initial position, the camera system is configured to acquire camera data describing the object support. In the operational position, the object support is configured to support at least a portion of the object within the imaging region. This can describe, for example, many different medical imaging systems, such as magnetic resonance imaging or computed tomography, where the object and any support or target are first positioned on the object support before the object is injected into the medical imaging system and / or radiotherapy system.

[0027] The execution of the machine-executable instructions also causes the processor to repeatedly provide user interface controls using the signal system after repeatedly signaling the list of missing targets and the list of misplaced targets. The execution of the machine-executable instructions also causes the processor to generate an accept command upon receiving a signal from the user interface controls. The execution of the machine-executable instructions further causes the processor to move the object support from its initial position to its operating position upon generating the accept command. The execution of the machine-executable instructions further causes the processor to control the medical imaging system to acquire medical image data when the object support is in the operating position. This embodiment may be advantageous because the user interface controls enable the operator of the medical instrument to begin medical imaging even if not all targets in the selected target list are present and / or not located in the positions specified in the selected target list.

[0028] In another embodiment, the execution of machine-executable instructions also causes the processor to append a list of placed targets and their coordinates to the medical image data in response to signals received from the user interface controls. This can be beneficial, as it may be useful for automatically recording targets actually used on an object support during medical imaging protocols.

[0029] In another embodiment, the execution of machine-executable instructions also causes the processor to store the camera data and the medical image data. For example, this could be appending the camera data to a DICOM file or an equivalent file. This can be useful for automatically archiving the conditions used when acquiring medical image data.

[0030] In another embodiment, the predetermined target includes an object. The neural network is also configured to recognize the object's orientation or location. For example, this can be useful because it can provide instructions on how the object should be positioned on an object support. These instructions can guide the user to position the object relative to an established target configuration.

[0031] In another embodiment, the predetermined target includes any of the following: a cushion, a head mirror, a headrest, a knee rest, an armrest, a magnetic resonance imaging coil, a footrest, an ankle support, and combinations thereof.

[0032] In another embodiment, the medical instrument also includes a radiotherapy system configured to irradiate a target area, which is located within the imaging area.

[0033] In another embodiment, the medical imaging system is configured to guide the radiotherapy system during irradiation of the target area. This embodiment may be advantageous because the use of a system for placing the target on a support structure allows for more repeatable radiotherapy to the subject. Thus, the configuration of the target, guided by medical instruments, allows for a more accurate reproduction of the positioning between imaging / planning and the actual delivery of treatment.

[0034] In another embodiment, the medical imaging system is a magnetic resonance imaging system.

[0035] In another embodiment, the medical imaging system is a computed tomography (CT) system.

[0036] In another embodiment, the medical imaging system is a positron emission tomography (PET) system.

[0037] In another embodiment, the medical imaging system is a single-photon emission computed tomography (SPECT) system.

[0038] In another embodiment, the imaging system includes a video camera.

[0039] In another embodiment, the imaging system includes a camera.

[0040] In another embodiment, the imaging system includes a color camera.

[0041] In another embodiment, the imaging system includes a monochrome camera.

[0042] In another embodiment, the imaging system includes an infrared camera.

[0043] In another embodiment, the imaging system includes a thermal camera.

[0044] In another embodiment, the imaging system includes multiple cameras.

[0045] In another embodiment, the imaging system includes a three-dimensional camera.

[0046] In another aspect, the present invention provides a computer program product including machine-executable instructions for execution by a processor controlling a medical instrument. The medical instrument further includes an object support comprising a support surface configured to receive an object. The medical instrument also includes a camera system configured to acquire camera data describing the support surface. The medical instrument further includes a signal system.

[0047] The execution of the machine-executable instructions also causes the processor to receive a list of selected targets. The list of selected targets is chosen from predetermined targets. The list of selected targets includes selected coordinates for each of the listed targets. The execution of the machine-executable instructions also causes the processor to use a signaling system to indicate the list of selected targets and the selected coordinates for each target in the list.

[0048] The execution of the machine-executable instructions also causes the processor to repeatedly acquire the image data using the camera system. The execution of the machine-executable instructions also causes the processor to repeatedly input the camera data into a neural network to generate a list of placed targets. The neural network is trained or configured to generate the list of placed targets in response to the input camera data. The list of placed targets identifies predetermined targets placed on a support surface and the coordinates of the placed targets on the support surface.

[0049] The execution of the machine-executable instructions further causes the processor to repeatedly determine the list of missing targets by comparing the list of selected targets with the list of placed targets. The execution of the machine-executable instructions further causes the processor to use the signal system to indicate the list of missing targets. The execution of the machine-executable instructions further causes the processor to determine the list of incorrectly placed targets by comparing the selected coordinates of each target in the list of targets with the coordinates of the targets placed on the support surface. The execution of the machine-executable instructions further causes the processor to repeatedly indicate the list of incorrectly placed targets using the signal system.

[0050] In another aspect, the present invention provides a method for operating a medical instrument. The medical instrument further includes an object support comprising a support surface configured to receive an object. The medical instrument also includes a camera system configured to acquire image data describing the support surface. The medical instrument further includes a signal system.

[0051] The method includes receiving a list of selected targets. The method also includes using a signaling system to signal selected coordinates for each target in the list of selected targets. The method includes using a camera system to repeatedly acquire camera data. The method includes repeatedly feeding the camera data into a neural network to generate a list of placed targets. The neural network is trained to generate the list of placed targets in response to input image data. The list of placed targets identifies predetermined targets placed on a support surface and the coordinates of the placed targets on the support surface. The list of selected targets is selected from the predetermined targets.

[0052] The selected target list includes selected coordinates for each of the listed targets. The method also includes determining a list of missing targets by comparing the list of selected targets with a list of placed targets. The method further includes using a signaling system to indicate the list of missing targets. The method also includes determining a list of misplaced targets by comparing the selected coordinates of each target in the target list with the coordinates of targets placed on a support surface. The method further includes using a signaling system to repeatedly indicate the list of misplaced targets.

[0053] It should be understood that one or more of the foregoing embodiments of the present invention may be combined, as long as the combined embodiments are not mutually exclusive.

[0054] As those skilled in the art will recognize, several aspects of the invention can be implemented as apparatus, method, or computer program product. Therefore, aspects of the invention can take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware aspects, which can be collectively referred to herein as “circuit,” “module,” or “system.” Furthermore, aspects of the invention can take the form of computer program products implemented in one or more computer-readable media having computer-executable code implemented thereon.

[0055] Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" includes any tangible storage medium that can store instructions executable by a processor of a computing device. The computer-readable storage medium may be referred to as a "computer-readable non-transient storage medium." The computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, the computer-readable storage medium may also be able to store data accessible by the processor of the computing device. Examples of computer-readable storage media include, but are not limited to: floppy disks, magnetic hard disk drives, solid-state drives, flash memory, USB thumb drives, random access memory (RAM), read-only memory (ROM), optical disks, magneto-optical disks, and processor register files. Examples of optical disks include compact optical disks (CDs) and digital multi-purpose optical disks (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R discs. The term computer-readable storage medium also refers to various types of recording media accessible by the computer device via a network or communication link. For example, data may be retrieved via a modem, via the Internet, or via a local area network. Computer-executable code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, or any suitable combination of the foregoing.

[0056] Computer-readable signal media may include propagated data signals having computer-executable code implemented therein, for example, in baseband or as part of a carrier wave. Such propagated signals may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and is capable of transmitting, propagating, or conveying a program for use by or in connection with an instruction execution system, apparatus, or device.

[0057] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that a processor can directly access. "Computer storage device" or "storage device" is another example of a computer-readable storage medium. A computer storage device is any non-volatile computer-readable storage medium. In some embodiments, a computer storage device may also be computer memory, or vice versa.

[0058] As used herein, the term "processor" encompasses any electronic component capable of executing programs or machine-executable instructions or computer-executable code. References to computing devices including "processor" should be interpreted as including more than one processor or processing core. A processor may, for example, be a multi-core processor. A processor can also refer to a collection of processors within a single computer system or distributed across multiple computer systems. The term computing device should also be interpreted as potentially referring to a collection or network of computing devices, each including one or more processors. The computer-executable code can be run by multiple processors, which may reside within the same computing device or even be distributed across multiple computing devices.

[0059] Computer executable code may include machine-executable instructions or programs that instruct a processor to perform aspects of the present invention. Computer executable code for performing operations relating to aspects of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages, and compiled into machine-executable instructions. In some cases, the computer executable code may be used in the form of a high-level language or in a pre-compiled form in conjunction with an interpreter that generates machine-executable instructions in flight.

[0060] The computer-executable code can run as a standalone software package entirely on the user's computer, partially on the user's computer, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or via a connection to an external computer (e.g., via the Internet using an Internet service provider).

[0061] Various aspects of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block or portion of a block in a flowchart, illustration, and / or block diagram can be implemented, where applicable, by computer program instructions in the form of computer-executable code. It should also be understood that combinations of blocks in different flowcharts, illustrations, and / or block diagrams can be combined, where they are not mutually exclusive. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create units for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0062] These computer program instructions may also be stored in a computer-readable medium that can direct a computer, other programmable data processing apparatus or other device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing comprising instructions that implement the functions / actions specified in flowcharts and / or one or more block diagrams.

[0063] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer-implemented process, such that the instructions running on the computer or other programmable apparatus provide for implementing the functions / actions specified in the flowchart and / or one or more block diagram boxes.

[0064] As used herein, a "user interface" is an interface that allows a user or operator to interact with a computer or computer system. A "user interface" can also be referred to as a "human-machine interface device." A user interface can provide information or data to an operator and / or receive information or data from an operator. A user interface enables input from an operator to be received by the computer and can provide output from the computer to the user. In other words, a user interface allows an operator to control or manipulate a computer, and the interface allows the computer to indicate the effects of the operator's control or manipulation. The display of data or information on a monitor or graphical user interface is an example of providing information to an operator. Receiving data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, gamepad, webcam, helmet, pedal, wired gloves, remote control, and accelerometer are all examples of user interface components that implement the receiving of information or data from an operator.

[0065] As used herein, "hardware interface" encompasses any interface that enables a computer system's processor to interact with or control external computing devices and / or apparatuses. A hardware interface allows the processor to send control signals or instructions to external computing devices and / or apparatuses. A hardware interface also enables the processor to exchange data with external computing devices and / or apparatuses. Examples of hardware interfaces include, but are not limited to: Universal Serial Bus (USB), IEEE 1394 port, parallel port, IEEE 1284 port, serial port, RS-232 port, IEEE-488 port, Bluetooth connectivity, wireless LAN connectivity, TCP / IP connectivity, Ethernet connectivity, control voltage interface, MIDI interface, analog input interface, and digital input interface.

[0066] As used herein, the terms "display" or "display device" encompass output devices or user interfaces suitable for displaying images or data. Displays can output visual, audio, and tactile data. Examples of displays include, but are not limited to: computer monitors, television screens, touchscreens, haptic electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bistable displays, electronic paper, vector displays, flat panel displays, vacuum fluorescent displays (VFs), light-emitting diode (LED) displays, electroluminescent displays (ELDs), plasma display panels (PDPs), liquid crystal displays (LCDs), organic light-emitting diode (OLED) displays, projectors, and head-mounted displays.

[0067] Medical image data is defined in this text as two-dimensional or three-dimensional data acquired using a medical imaging scanner. A medical imaging system is defined herein as an apparatus suitable for acquiring information relating to the physical structure of an object and constructing a collection of two-dimensional or three-dimensional medical image data. Medical image data can be used to construct visualizations useful for physician diagnosis. Such visualizations can be performed using a computer.

[0068] Magnetic resonance imaging data, or MRI data in this paper, is defined as the recorded measurement of radio frequency signals emitted by atomic spins through the antenna of a magnetic resonance device during a magnetic resonance imaging scan. MRI data is an example of medical imaging data. MRI images, or MR images, are defined herein as reconstructed two-dimensional or three-dimensional visualizations of anatomical data contained within MRI data. Such visualizations can be performed using a computer. Attached Figure Description

[0069] In the following description, preferred embodiments of the invention will be illustrated by way of example only and with reference to the accompanying drawings, in which:

[0070] Figure 1 Examples of medical instruments are illustrated;

[0071] Figure 2 It shows Figure 1 Another view of medical instruments;

[0072] Figure 3 This illustration shows another example of a medical instrument;

[0073] Figure 4 It is a graphical operation Figure 1 or Figure 3 A flowchart of a method for using medical instruments;

[0074] Figure 5 The contents of the DICOM file are graphically displayed;

[0075] Figure 6 The diagram illustrates the functionality of the example system;

[0076] Figure 7 Further illustrations Figure 6 The functionality of the example system; and

[0077] Figure 8 The diagram illustrates and illustrates examples of graphical user interfaces.

[0078] List of reference numerals

[0079] 100 Medical Instruments

[0080] 102 Medical Imaging System

[0081] 102 Magnetic Resonance Imaging System

[0082] 104 Imaging Area

[0083] 106 Radiofrequency Therapy System

[0084] 108 Target Area

[0085] 110 Object Support

[0086] 111 Initial position

[0087] 112 Supporting surface

[0088] 114 Actuator

[0089] 116 Imaging System Borehole

[0090] 118 Camera System

[0091] 120 headrest

[0092] 140 Computers

[0093] 142 processor

[0094] 144 Hardware Interfaces

[0095] 146 User Interface

[0096] 148 Display (Signal System)

[0097] 150 memory

[0098] 152 Machine-Executable Instructions

[0099] 154 Neural Networks

[0100] 156 Imaging Protocol Database

[0101] 158 Selection of Medical Imaging Protocols

[0102] 160. List of selected targets

[0103] 162 Select coordinates

[0104] 164 camera data

[0105] 166 List of targets to be placed

[0106] 168 List of missing targets

[0107] 170 List of misplaced targets

[0108] 172 Indicator

[0109] 174 archived images

[0110] 176 User Interface Controls

[0111] 200 Operating Positions

[0112] 202 Object

[0113] 204 Medical Image Data

[0114] 300 medical images

[0115] 300 Medical Instruments

[0116] 304 magnet

[0117] 309 Areas of Interest

[0118] 310 Magnetic Gradient Coil

[0119] 312 Magnetic Gradient Coil Power Supply

[0120] 314 RF coil

[0121] 316 transceiver

[0122] 320 Pulse Sequence Command

[0123] 322 Magnetic Resonance Imaging Data

[0124] 324 MRI images

[0125] 400 Receive a list of selected targets

[0126] 402. Use a signaling system to signal a list of selected targets and the selected coordinates for each target in the list of selected targets.

[0127] 404 Using a camera system to collect camera data

[0128] 406. Camera data is fed into a neural network to generate a list of placed targets.

[0129] 408. Determine the list of missing targets by comparing the list of selected targets with the list of placed targets.

[0130] 410 Use a signaling system to indicate a list of missing targets

[0131] 412 The list of misplaced targets is determined by comparing the selected coordinates of each target in the list of objects with the coordinates of the target placed on the support surface.

[0132] 414 List of misplaced images using a signaling system

[0133] 500 medical imaging files

[0134] 600 images

[0135] 700 images

[0136] 800 Object Information

[0137] 802 Headgear

[0138] 804 should be placed correctly.

[0139] 806 Not placed correctly Detailed Implementation

[0140] In these figures, similarly numbered elements are equivalent elements or perform the same function. If the functions are equivalent, elements that have been discussed previously will not necessarily be discussed in later figures.

[0141] Figure 1 An example of a medical instrument 100 is illustrated. The medical instrument 100 is shown optionally including a medical imaging system 102 configured to acquire medical image data from an imaging region 104. The medical instrument 100 is also shown to include an optional radiotherapy system 106. In this example, the optional radiotherapy system 106 is configured to irradiate a target region 108 within the imaging region 104. If present, the medical imaging system 102 can therefore be used to guide the radiotherapy system 106. In some examples, the medical instrument 100 does not include a medical imaging system 102. or Excluding radiotherapy systems 106.

[0142] An object support 110 is present, configured to receive an object. The object support 110 is shown in an initial position 111. In the initial position 111, the support surface 112 is imageable by a camera system 118. The camera system 118 may be configured, for example, to capture still and / or video feeds of a target 120 shown on the support surface 112. In this example, a headrest 120 is present, placed on the support surface 112. The medical instrument 100 is also shown to include an actuator 114 configured to move the object support 110 from the initial position 112 to... Figure 2 The operating position is shown in the diagram. The medical imaging system 102 is cylindrical and has a bore 116 into which an object support 110 can be inserted or injected. Any target on the surface 112, such as an object or other target 120, will also be moved into the bore 116.

[0143] The medical instrument 100 is also shown to include a computer 140. The computer 140 includes a processor 142, and a processor 106 is connected to a hardware interface 144. The hardware interface 144 enables the processor 142 to control the operation of other components. A camera system 118, a medical imaging system 102, and a radiotherapy system 106 are all shown connected to the hardware interface 144. The processor 142 is also connected to a user interface 146 and a memory 150. The user interface 146 also includes a signaling system 148. In this example, the signaling system is a display 148.

[0144] However, the display 148 can be replaced with different types of signal systems. Information on the display can be audibly indicated using a computer voice system. Information displayed on the display 148 can also be graphically projected onto the support surface 112 using a laser or projector.

[0145] Memory 150 can be any combination of memory accessible to processor 142. This can include main memory, cache memory, and non-volatile memory such as flash RAM, hard disk drives, or other storage devices. In some examples, memory 150 can be considered as a non-transitory computer-readable medium.

[0146] Memory 150 is shown to contain machine-executable instructions 152. The execution of machine-executable instructions 152 enables processor 142 to perform tasks such as controlling other components and performing basic image and mathematical processes. Memory 150 is also shown to contain a neural network 154. Neural network 154 receives camera data 164 from camera 118 and outputs a list 166 of placed targets. Memory 150 is shown to contain an optional imaging protocol database 156 containing details of various imaging protocols that can be executed by medical instrument 100. Processor 142 may, for example, receive a selection of medical imaging protocol 158. This can be used to retrieve a list 160 of selected targets from the optional imaging protocol database 156. The list 160 of selected targets also contains selected coordinates 162, indicating the position of the target 120 to be placed on surface 112. User interface 148 is shown to display a list of selected targets 160 and their coordinates 162.

[0147] Memory 150 is shown storing copies of both a list 160 of selected targets and selected coordinates 162. Memory 150 is also shown containing camera data 164. The camera data 164 is then fed into neural network 154 and used to generate a list of placed targets 166. The list of placed targets 166 is then compared with the list of selected targets 160 and the selected coordinates 162 to generate a list of missing targets 168 and a list of misplaced targets 170, both of which are shown stored in memory 150. An indicator 172 may be present on display 148 to indicate whether any misplaced targets 170 or missing targets 168 exist.

[0148] User interface 148 is also shown to include a presentation of camera data 164. This could be useful, for example, to a medical professional configuring medical instrument 100. Optionally, there may be archived images 174 showing partially or fully configured surfaces 112. This could, for example, be an additional guide to assist healthcare professionals. User interface 148 is also shown to have optional user interface controls 176 that can be used to trigger the object support 110 into the insertion chamber 116. For example, in some cases, the operator may not necessarily want to precisely follow the list 160 of selected targets and the selected coordinates 162. The use of optional user interface controls 176 gives the operator the option to execute the imaging protocol regardless of the circumstances.

[0149] Figure 2Another view of the medical instrument 100 is shown. In this view, actuator 114 is used to move object support 110 into chamber 116. Object support 110 is now in operating position 200. Object 202 is shown repositioned on object support 110. A portion of object 202 can be imaged in imaging area 104 and the radiotherapy system 106 can be used to irradiate a location within target area 108. Memory 150 is shown to contain medical image data 204 acquired by controlling medical imaging system 102. Memory 150 is also shown to include a medical image 206 reconstructed from medical imaging data 204. Medical image 206 can be used, for example, to guide radiotherapy system 106 to irradiate object 202.

[0150] Figure 3 Another example of a medical instrument 300 is shown. In this example, the medical imaging system is a magnetic resonance imaging system 102. The magnetic resonance imaging system 102 includes a magnet 304. The magnet 304 is a superconducting cylindrical magnet with a bore 116 passing through it. It is also possible to use different types of magnets; for example, split cylindrical magnets and so-called open magnets can also be used. A split cylindrical magnet is similar to a standard cylindrical magnet, except that the cryostat has been split into two parts to allow access to the isoplanarity of the magnet, thereby allowing the magnet to be used, for example, in conjunction with charged particle beam therapy. An open magnet has two magnet sections, one on top of the other, with a space in between large enough to accommodate the object: the arrangement of the two sections is similar to the arrangement of Helmholtz coils. Open magnets are popular because the object is less restricted. Inside the cryostat of the cylindrical magnet is an assembly of superconducting coils. Within the bore 116 of the cylindrical magnet 304, there is an imaging region 108, in which the magnetic field is strong and homogeneous enough to perform magnetic resonance imaging. Region of interest 309 within imaging region 104 is shown. Acquired magnetic resonance data is typically acquired for the region of interest. Object 202 is shown supported by object support 110, such that at least a portion of object 118 is within imaging region 104 and region of interest 309. The object support is in operating position 200.

[0151] The magnet chamber 116 also contains an assembly of magnetic field gradient coils 310, which are used to acquire primary magnetic resonance data for spatial encoding of magnetic spins within the imaging region 104 of the magnet 304. The magnetic field gradient coils 310 are connected to a magnetic field gradient coil power supply 312. The magnetic field gradient coils 310 are intended to be representative. Typically, the magnetic field gradient coils 310 comprise an assembly of three discrete coils for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply provides current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 310 is time-controlled and can be either slanted or pulsed.

[0152] Adjacent to the imaging region 104 is an RF coil 314, which is used to manipulate the orientation of the magnetic spins within the imaging region 104 and to receive RF transmissions from spins also located within the imaging region 104. The RF antenna may comprise multiple coil elements. The RF antenna may also be referred to as a channel or antenna. The RF coil 314 is connected to an RF transceiver 316. The RF coil 314 and the RF transceiver 316 may be replaced by separate transmit and receive coils, and separate transmitters and receivers. It is to be understood that the RF coil 314 and the RF transceiver 316 are representative. The RF coil 314 is intended to also represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 316 may also represent separate transmitters and receivers. The RF coil 314 may also have multiple receive / transmit elements, and the RF transceiver 316 may have multiple receive / transmit channels. For example, if performing a parallel imaging technique such as SENSE, the RF coil 314 may have multiple coil elements.

[0153] Transceiver 316, gradient controller 312, and camera system are shown as a hardware interface 144 connected to computer system 140. Memory 134 is shown as containing machine-executable instructions 140. The machine-executable instructions 140 enable processor 130 to control the operation and functions of magnetic resonance imaging system 100. The machine-executable instructions 140 also enable processor 130 to perform various data analysis and calculation functions.

[0154] Memory 150 is shown as containing pulse sequence commands 320. Pulse sequence commands are commands or data that can be translated into commands for controlling the magnetic resonance imaging system 102' to acquire magnetic resonance imaging data 322. Memory 150 is shown as containing magnetic resonance imaging data 322 acquired by controlling the magnetic resonance imaging system using pulse sequence commands 320. Magnetic resonance imaging data 332 is an example of medical image data. Memory 150 is also shown as including a magnetic resonance image 324 reconstructed from the imaging magnetic resonance imaging data 322.

[0155] Figure 4 A flowchart is shown, illustrating the operations. Figure 1 and 2 The medical instruments shown or Figure 3The method of the medical instrument 300 shown is as follows: First, in step 400, a list 160 of selected targets is received. The list of selected targets is selected from predetermined targets used to train the neural network. The list of selected targets includes selected coordinates for each of the listed targets 162. Next, in step 402, the list 160 of selected targets and the selected coordinates 162 for each selected target are displayed on a display 148. The method then proceeds to steps 404-414. Method steps 404-414 are performed in a loop. The operator may voluntarily stop this loop, or it may be stopped, for example, when it is selected or decided to initiate imaging of an object. In step 404, camera data 164 is acquired using a camera system 118. Then, in step 406, the camera data 164 is input into a neural network 154 to generate a list 166 of placed targets. Then, in step 408, a list 168 of missing targets is determined by comparing the list 160 of selected targets with the list 166 of placed targets. In step 410, the list 168 of missing targets is indicated 172 on display 148. After step 410, the method proceeds to step 412, where a list 170 of misplaced targets is determined by comparing selected coordinates for each of the listed targets with the coordinates of targets placed on support surface 112. Then, in step 414, the list 168 of misplaced targets is indicated 172 on display 148. Steps 408 and 412 can be interchanged. The method then loops back from step 414 to step 404.

[0156] Figure 5 An example of a medical imaging file 500 is illustrated. The medical imaging file 500 can be used, for example, for archiving or storage. Figure 1 and 2 The medical instrument 100 shown Figure 3 The medical image file 500 is a container or file for medical images acquired by the medical instrument 300 shown. The medical image file 500 may be, for example, a DICOM file. The medical imaging file 500 may include, for example, medical image 206 or magnetic resonance image 324. The medical image file 500 may also contain camera data 164 acquired by camera system 118. This can be used as an archive record for configuring medical device 100 or 300. The medical imaging file 500 may also contain a list 166 of placed targets. This can be useful as an automatically generated list used and as coordinates for placing them on object support 110. The medical imaging file 500 may also optionally contain a list 168 of missing targets and / or a list 170 of incorrectly placed targets. The medical imaging file 500 may be automatically generated, for example, when medical image 206 or magnetic resonance image 324 is reconstructed.

[0157] As mentioned above, preparing subject 202 for examination is a time-consuming task and requires trained operator skills. The operator may place positioning devices (e.g., knee supports, headrests) to ensure the subject remains in a stable resting position throughout the examination, or must adequately position coil 314 (MRI) and accessories 120, 802 (i.e., sensors) to obtain repeatable image quality. In repeated or subsequent scans, and in scans used for treatment planning, monitoring, and corresponding treatment phases, it may be beneficial to reproduce previous subject setups and corresponding images with the same quality to make them comparable. For example, in radiotherapy, accurate subject setups are typically reproduced as closely as possible over up to 40 radiotherapy sessions. To accurately but still quickly reposition all equipment, subject support in treatment planning is often equipped with mechanical devices to allow only a limited set of positions. The following... Figure 6 An example is provided where the knee support can only be positioned at discrete locations H4 to F7. Quality assurance requires accurate reporting of all relevant setup information during each session to enable comparison and reproduction of the settings. This is a time-consuming and error-prone task.

[0158] Figure 6 and 7 The proof of concept for the example is illustrated. Figure 6 In the image 600, an automatically detected knee positioning device is shown at platform index position 4 in the foot direction or F4. This is performed using a trained classification neural network or neural network. Figure 7 In more complex scenarios with partial obstruction, table movement, and misleading gestures, the small index bar at location F3 still correctly classifies the data.

[0159] For radiotherapy planning, RFID-based systems exist to check for the presence of the correct type of positioning equipment and its corresponding location. These systems can utilize multiple RFID sensors integrated into a set of positioning and indexing / holding devices. The system can be used with a group of registered devices equipped with such a system. While RFID helps automate, reproduce, and protect setup reporting and reproducibility workflows, the system has limitations in reporting the full complexity of typical object setups. Custom or third-party devices, often unknown to the system, are frequently used and cannot be easily equipped with RFID. Some devices are not suitable for installation along fixed, predefined grating indices (e.g., support wedges, pads, or mats, or custom object-specific devices). All of these devices will not be included in setup reports and will limit reproducibility. Furthermore, RFID can malfunction individually, so the likelihood of errors increases with the number of devices. More complex object setups cannot be reproduced using such systems due to the lack of step-by-step guidance to achieve correct results. RFID also presents RF security concerns, leading to increased integration workload and cost. Similarly, RFID is a short-range communication technology and will fail over long distances. RFID technology can also be severely affected by radio frequency interference, especially when used with other large electronic devices such as medical imaging equipment.

[0160] The example uses a camera-based object 202 setup classification and reproduction system to detect the type and location of the positioning device used. A neural network can be trained to classify the image into one of several categories: each category corresponds to a given target device (e.g., a knee positioning device) at a given location (e.g., index position F4). Ideally, a category corresponds to a target device that does not exist. The system can handle more complex categories consisting of multiple devices or combinations of categories. During object setup, the trained neural network determines a list of installed devices and their location categories, as well as a confidence level for the determined devices and locations (see [link to documentation]). Figure 6 and Figure 7 The location classification, determined with low confidence, indicates improper installation and high sensitivity. This can be used to trigger alarms (or signals) to remind staff to correctly locate the location. Automatic storage of raw camera images for scene classification and quality control is proposed. Figure 5As shown in the diagram. The camera system operates remotely and does not interfere with the workflow. It can classify the type and location category of set components (e.g., indexing) while being sensitive to all spatial orientations, thus covering a greater set diversity than could be achieved using an RFID system. The proposed method also has several advantages: no markers or modifications to the device are required. This avoids the sterility and safety issues associated with such devices. Since it operates optically, it is not susceptible to RF interference as long as standard methods are provided to shield the camera electronics from spurious RF interference. The term camera or camera system 118 can include cameras that generate images (camera data): for example, RGB, monochrome, infrared, thermal imaging, and 3D (stereo, time-of-flight, structured light, LADAR, RADAR) cameras.

[0161] The use of camera system 118 allows for the use of a wider variety of devices from any vendor at a lower cost. Device type and location can be detected from images provided by the camera system using neural networks. The system is scalable, meaning it can be extended to more device types or more device locations or pose categories. Such a system will allow for the classification of setups at a higher level of abstraction. The camera system will also provide clearer failure paths; for example, if the camera may be damaged, it can be easily detected. Alternatively, if a classification error occurs, the recorded camera image will indicate a single error, and the setup can still be reproduced with high accuracy. This system can be applied to general tomographic imaging and allows for extremely high repeatability in subsequent examinations, eliminating the need for complex changes to scanning protocols while providing a consistent level of image quality.

[0162] Figure 8 An example of a user interface 148 that can be displayed is illustrated. Camera data 164 is displayed along with object information 800, a list of selected targets 160, and selected coordinates 162. Lists of placed targets, missing targets, and incorrectly placed targets can be used to modify or highlight the list of selected targets 160 and selected coordinates 162. In this example, the headpiece 802 has been correctly placed and can be marked on the display 148 using highlights or different colors. Since the numbers are black and white, this is indicated by labeling the headpiece with label 804. Other items that have not yet been placed are displayed as 806 on display 148.

[0163] The user interface (UI) or display 148 is used for initial and subsequent inspection setup. The user is presented with a list to configure specific settings for the inspection. The camera evaluates the configuration items, checking completed items and highlighting the remaining tasks. The algorithm pays particular attention to the correct and locked positions of relevant setup components. The UI is presented to the user via a side screen or directly onto the tabletop via a projector. Both methods of displaying this guidance, as well as other methods and combinations thereof, are applicable.

[0164] Although the invention has been illustrated and described in detail in the accompanying drawings and the foregoing description, such illustrations and descriptions should be considered illustrative or exemplary, and not restrictive. The invention is not limited to the disclosed embodiments.

[0165] Those skilled in the art, through studying the accompanying drawings, disclosure, and claims, will understand and implement other variations of the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality. A single processor or other unit can perform the functions of several items recited in the claims. Although specific measures are recited in dissimilar dependent claims, this does not imply that combinations of these measures cannot be advantageously used. Computer programs can be stored / distributed on suitable media such as optical storage media or solid-state media provided with or as part of other hardware, but can also be distributed in other forms such as via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A medical instrument (100, 300), comprising: a subject support (110) comprising a support surface (112) configured to receive a subject (202); a camera system (118) configured to acquire camera data (164) descriptive of the support surface; a signaling system (148); a memory (150) to store machine executable instructions (152) and a neural network (154), wherein the neural network is trained to generate a list of placed targets (166) in response to inputting the camera data, wherein the list of placed targets identifies predetermined targets placed on the support surface and coordinates of the placed targets on the support surface; a processor (142) to control the medical instrument, wherein execution of the machine executable instructions further causes the processor to: receive (400) a list of selected targets (160), wherein the list of selected targets is selected from the predetermined targets, wherein the list of selected targets includes a selected coordinate (162) for each target in the list of targets; and signal (402) the list of selected targets and the selected coordinate for each target in the list of selected targets using the signaling system; wherein execution of the machine executable instructions further causes the processor to repeatedly: acquire (404) the camera data using the camera system; input (406) the camera data into the neural network to generate the list of placed targets; determine (408) a list of missing targets (168) by comparing the list of selected targets to the list of placed targets; indicate (410) the list of missing targets using the signaling system; determine (412) a list of misplaced targets (170) by comparing the selected coordinate for each target in the list of targets to the coordinates of the placed targets on the support surface; and indicate (414) the list of misplaced targets using the signaling system; wherein execution of the machine executable instructions further causes the processor to signal the list of selected targets using the signaling system in an order defined in the list of selected targets.

2. The medical instrument of claim 1, wherein, execution of the machine executable instructions further causes the processor to determine a list of correctly positioned targets using the list of placed targets, the list of missing targets, and the list of misplaced targets, wherein execution of the machine executable instructions further causes the processor to generate a signal in the event the correctly positioned targets are identified as members of the misplaced targets and / or the missing targets.

3. The medical instrument of any one of the preceding claims, wherein, the selected coordinate for each target in the list of targets is specified in discrete coordinates, and wherein the coordinates of the placed targets on the support surface are specified in the discrete coordinates.

4. The medical instrument of claim 1 or 2, wherein, the predetermined targets include the subject, wherein the neural network is further configured to identify a subject orientation.

5. The medical instrument of claim 1 or 2, wherein, The predetermined targets include any of the following: a cushion, a head mirror (802), a headrest (120), a knee rest, an arm rest, a magnetic resonance imaging coil, a foot rest, an ankle rest, and combinations thereof.

6. The medical instrument of claim 1 or 2, wherein, The medical instrument further includes a medical imaging system (102, 102') configured to acquire medical image data (204, 322) from an imaging zone (104), wherein the support surface is configured to support at least part of the subject within the imaging zone.

7. The medical instrument of claim 6, wherein, The medical imaging system is any of the following: a magnetic resonance imaging system (102'), a computed tomography system, a positron emission tomography system, and a single photon emission tomography system.

8. The medical instrument of claim 6, wherein, The memory further includes an imaging protocol database (156), wherein the imaging protocol database includes a list of selected targets, each selected target being associated with an imaging protocol, wherein execution of the machine executable instructions further causes the processor to: receive a selection of a medical imaging protocol (158); and use the selection of the medical imaging protocol to retrieve the list of selected targets from the imaging protocol database.

9. The medical instrument of claim 1 or 2, wherein, The subject support is configured to move from an initial position (111) to an operational position (200), wherein in the initial position the camera system is configured to perform the acquisition of the camera data descriptive of the support surface.

10. The medical instrument of claim 9, wherein, Execution of the machine executable instructions further causes the processor to: after repeatedly using the signaling system to indicate the list of missing targets and the list of misplaced targets, repeatedly provide a user interface control (176) using the signaling system; if a signal is received from the user interface control, generate an accept command; if the accept command is generated, move the subject support from the initial position to the operational position; when the subject support is in the operational position, control the medical imaging system to acquire the medical image data.

11. The medical instrument of claim 1 or 2, wherein, The medical instrument further includes a radiotherapy system (106) configured for irradiating a target zone, wherein the support surface is configured to support at least part of the subject within the imaging zone.

12. The medical instrument of claim 1 or 2, wherein, The camera system includes any of the following: a video camera, a camera, a color camera, a black and white camera, an infrared camera, a thermal camera, a plurality of cameras, a three-dimensional camera, and combinations thereof.

13. A computer program product comprising machine executable instructions (152) for execution by a processor (142) controlling a medical instrument (100, 300), wherein, The medical instrument includes a subject support (110) including a support surface (112) configured for receiving a subject (202), a camera system (118) configured for acquiring camera data (164) descriptive of the support surface, and a signaling system (148); wherein execution of the machine executable instructions further causes the processor to: receive (400) a list of selected targets (160); and signal (402) the list of selected targets and a selected coordinate for each target in the list of selected targets using the signaling system; wherein execution of the machine executable instructions further causes the processor to repeatedly: acquiring (404) the camera data using the camera system; inputting (406) the camera data into a neural network (154) to generate a list of placed objects (166), wherein the neural network is trained to generate the list of placed objects in response to inputting the camera data, wherein the list of placed objects identifies predetermined objects placed on the support surface and coordinates of the placed objects on the support surface, wherein the list of selected objects is selected from the predetermined objects, wherein the list of selected objects includes a selected coordinate for each object in the list of objects; determining (408) a list of missing objects (168) by comparing the list of selected objects to the list of placed objects; indicating (410) the list of missing objects using the signaling system; determining (412) a list of misplaced objects (170) by comparing the selected coordinate for each object in the list of objects to the coordinates of the placed objects on the support surface; and indicating (414) the list of misplaced objects using the signaling system, wherein execution of the machine executable instructions further causes the processor to signal the list of selected objects using the signaling system in an order defined in the list of selected objects.

14. A method of operating a medical instrument (100, 300), wherein The medical instrument comprises an object support (110) comprising a support surface (112) configured to receive an object (202), a camera system (118) configured to acquire camera data describing the support surface, and a signaling system (148); wherein the method comprises: receiving (400) a list of selected objects (160); and signaling (402) the list of selected objects and a selected coordinate for each selected object in the list of selected objects using the signaling system; wherein the method comprises repeatedly: acquiring (404) the camera data using the camera system; inputting (406) the camera data into a neural network (154) to generate a list of placed objects (166), wherein the neural network is trained to generate the list of placed objects in response to inputting the camera data, wherein the list of placed objects identifies predetermined objects placed on the support surface and coordinates of the placed objects on the support surface, wherein the list of selected objects is selected from the predetermined objects, wherein the list of selected objects includes a selected coordinate for each object in the list of objects; determining (408) a list of missing objects (168) by comparing the list of selected objects to the list of placed objects; indicating (410) the list of missing objects using the signaling system; determining (412) a list of misplaced objects (170) by comparing the selected coordinates for each object of the list of objects to the coordinates of the placed objects on the support surface; and indicating (414) the list of misplaced objects using the signaling system, wherein signaling the list of selected objects is performed using the signaling system in the order defined in the list of selected objects.

Images