Camera-based detection of subject position

Abstract

Disclosed herein is a medical system comprising a memory storing machine executable instructions and an anatomical keypoint locator module. The anatomical keypoint locator module is configured to output a set of anatomical keypoint coordinates of the subject in response to receiving a camera image showing the subject. The medical system further comprises a computing system. Execution of the machine executable instructions causes the computing system to receive the camera image, receive a set of anatomical keypoint coordinates in response to inputting the camera image into the anatomical keypoint locator module, receive a list of coordinates, search the list of coordinates, search the list of coordinates to determine a match with the set of anatomical keypoint coordinates, and provide an alert signal if a match is determined.

Description

[Technical field]

[0001] The present invention relates to medical imaging, and in particular to automatic detection of a subject's position or orientation prior to imaging. [Background technology]

[0002] Various medical imaging techniques, such as magnetic resonance imaging (MRI), computed tomography, positron emission tomography, and single photon emission computed tomography, allow for detailed visualization of a subject's anatomy. Summary of the Invention [Problem to be solved by the invention]

[0003] In medical imaging modalities such as these, it is important that the subject is properly positioned prior to the procedure, otherwise the subject may be imaged improperly.

[0004] "Collision prediction software for radiotherapy treatments" (The journal publication Padilla et al., "Med. PhD, 42(11), November 2015, pp. 6448-6456, http: / / dx.doi.org / 10.1118 / 1.4932628) describes the use of a three-dimensional camera to scan the patient and immobilize the device in treatment position in a simulator. The surface of the subject was reconstructed. The treatment isocenter was marked using a simulated orthogonal laser projected onto the surface scan. The point cloud of this surface was then shifted to the isocenter and transformed from Cartesian to cylindrical coordinates. A slab was used to model the treatment couch. The collimation was performed from the isocenter. Collisions were estimated using a cylinder with radius equal to the normal distance to the tap plate and height defined by the collimator diameter. Points inside the cylinder would be impacted with the treatment table at 0° and points outside would be impacted with the gantry fully rotated. The collision angles were reported. This methodology was experimentally validated using a mannequin placed in an alpha cradle with both arms up. Collision calculations were performed for two treatment isocenters and the results were compared to collisions detected in the room. The accuracy of the 3D surface was assessed by comparing it to the external surface of the planning CT scan. [Means for solving the problem]

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

[0006] Accurate detection of body position can be useful when performing a medical imaging scan of a subject. Currently, systems exist that use three-dimensional cameras to image the surface of a subject. A drawback of these systems is that they can do a poor job of predicting the subject's pose. Embodiments can provide an improved means of recognizing when a subject is improperly positioned, or possibly placed in a dangerous pose, before a medical imaging scan is performed. Embodiments can achieve this by using an anatomical keypoint locator module that provides a set of anatomical keypoint coordinates in response to receiving a camera image of the subject. The set of anatomical keypoint coordinates can be compared to a list of coordinates, for example, to determine whether the absolute or relative positions of individual anatomical keypoints are inaccurate.

[0007] In one aspect, the present invention provides a medical system comprising a memory storing machine executable instructions and an anatomical keypoint locator module. In some examples, the anatomical keypoint locator module may be embodied in the machine executable instructions. The anatomical keypoint locator module is configured to output a set of anatomical keypoint coordinates of the subject in response to receiving a camera image indicative of the subject.

[0008] Anatomical key points as used herein encompass anatomical landmarks or locations located within an object. Anatomical key points can incorporate the location of various joints or surface landmarks (eyes, ears, nose) of an object. The camera image shows the object and provides a description of the object's exterior or surface (texture and / or description). For example, the camera image may be an optical image, an infrared image, a thermal image, or a color image. In another example, the camera image is a three-dimensional surface image. In another example, the camera image is a composite image formed from multiple camera images. For example, two two-dimensional images can be used to provide a stereo image that provides three-dimensional or spatial information. In another example, the camera image is a composite image formed from multiple types of images. Infrared or thermal images can be combined with the three-dimensional image.

[0009] In both single or composite images, landmarks can be detected in each image. This can be used to provide additional information and options when matching anatomical keypoint coordinates to a list of coordinates. Identification of landmarks in multiple images can also enable 3D location of the landmarks.

[0010] The medical system further comprises a computing system. As used herein, a computing system may encompass a computing system or a processor possibly located in one or more locations. Execution of the machine executable instructions causes the computing system to receive the camera images. Execution of the machine executable instructions further causes the computer system to receive a set of anatomical key point coordinates in response to inputting the camera images into the anatomical key point locator module. Execution of the machine executable instructions further causes the computing system to receive a list of coordinates.

[0011] The list of coordinates can take different forms in different examples. The list of coordinates can include, for example, absolute or relative positions of various anatomical key points of the subject. The list of coordinates can also define relationships between anatomical key points. For example, if it is an absolute position, an anatomical key point in the list of coordinates can specify a position that can provide data regarding potential damage to the subject. For example, if the subject places an appendage, such as a hand, elbow, or foot, in an incorrect position, it may be bumped or pinched and wrapped around when the subject moves into the medical imaging system. As used herein, appendage refers to the hand or foot of the subject.

[0012] In some examples, the list of coordinates includes two-dimensional coordinates. This may be used, for example, when the camera images are two-dimensional images (e.g., when color or infrared images are used). In other examples, the list of coordinates includes three-dimensional coordinates. This may be the case when multiple two-dimensional camera images are used and / or when the camera images include three-dimensional images.

[0013] In yet another example, the list of coordinates includes n-dimensional coordinates, where n is greater than 3. This may be the case when coordinates are given in three dimensions and an additional coordinate is used to measure change over time, for example three spatial dimensions and a time coordinate.

[0014] In another example, in the case of magnetic resonance imaging, the touch of a finger or a finger to a certain body part, or even crossing an arm or leg, may create a conductive loop in the body, which may result in RF heating of the subject. The position and posture of the subject can then be determined by defining the relationship between the positions of the anatomical key points. For example, when a subject crosses his / her legs, there is a certain relationship in the coordinates. For example, the hip joints are placed next to each other, and then there is an intersection of the coordinates of the legs. Thus, a list of coordinates can define various positions and orientations of the subject.

[0015] Execution of the machine executable instructions further causes the computing system to search the list of coordinates to determine a match with a set of anatomical keypoint coordinates. The determination of a match can take different forms in different examples. In an example, the determination is detection of a match. For example, the list of coordinates may be searched to see if there are appendages that are in the wrong position. In other cases, it may be searched to see if appendages (such as hands or feet) overlap or other body parts overlap to form conductive loops. Execution of the machine executable instructions further causes the computing system to provide a warning signal if a match is detected.

[0016] The determination of a match may also include an accuracy measure of how accurately the match fits the set of anatomical keypoint coordinates. A match may be detected if the set of anatomical keypoint coordinates is within a certain distance or neighborhood of a coordinate in the list of coordinates. However, within this neighborhood there may be better or worse matches. The measured accuracy may, for example, be a measure that describes the distance between the set of anatomical keypoint coordinates and the list of coordinates. This measure may, for example, be the RMS value of the difference between each coordinate.

[0017] In another embodiment, the one or more conductive body loops are conductive loops within the subject's body that can result in RF heating of the subject. During use of a magnetic resonance imaging system, a large, changing electromagnetic field is present. From Faraday's law, it is known that the changing electromagnetic field induces currents in the conductive loops. When a subject places a finger on the hip joint or other body part, this contact can form an electrical connection between these two body regions, thereby forming a conductive loop, which is referred to herein as a conductive body loop. The current induced in this conductive loop can cause resistive heating in the subject's body, resulting in burns.

[0018] In another embodiment, the list of coordinates defines relative coordinates between two or more of the sets of anatomical keypoint coordinates. The list of coordinates may include sets of coordinates to which anatomical keypoints are compared. For example, the list of coordinates may include a relative change between different anatomical keypoint coordinates. The list of coordinates may also include a ratio of the relative change.

[0019] The list of coordinates can have different sources: they can be received from a user interface, i.e. entered by a user, in another example they can be predefined, received via a network interface or retrieved from a computer memory or storage device.

[0020] In another embodiment, the list of coordinates includes body postures defined as relative changes between the set of anatomical keypoint coordinates. Searching the list of coordinates to determine a match within the set of anatomical keypoint coordinates then includes using the set of anatomical keypoint coordinates to detect a selected body posture from the body postures in the list of coordinates. In this embodiment, the relative positions of the anatomical keypoints are used to define the particular body posture. Execution of the machine executable instructions further causes the computing system to provide a warning signal if an irregular body posture is detected. This may be particularly useful in situations where a particular positioning of the subject may lead to a poor medical imaging procedure or may put the subject at risk.

[0021] In another embodiment, the list of coordinates includes body poses defined as relative changes between members of a set of anatomical keypoint coordinates.

[0022] In another embodiment, detecting the selected body pose from the body poses in the list of coordinates using the set of anatomical keypoint coordinates includes determining a relative change between members of the set of anatomical keypoint coordinates and comparing the relative change for the body pose between members of the set of anatomical keypoint coordinates.

[0023] In another embodiment, the camera image includes a three-dimensional surface image. For example, the camera image may be acquired by a so-called three-dimensional camera. The body posture detection is performed at least in part using the three-dimensional surface image to detect the position of the limbs. For example, a set of anatomical key point coordinates may be useful to define the posture of the subject as well as the position of certain body parts. However, this information does not always provide detailed information that can be used to increase the safety of the subject. For example, when the subject is inserted into a medical imaging system, the position of the joints may not be sufficient to detect whether a collision with the medical imaging system will occur when the subject is inserted. The three-dimensional surface image may also provide additional information regarding the body posture and external dimensions of the subject.

[0024] In another embodiment, body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions by matching the three-dimensional surface image to a set of predefined surface images, each depicting a different body posture.

[0025] In another embodiment, the set of anatomical keypoint coordinates includes one or more accessory keypoint coordinates. For example, anatomical keypoints defining an appendage may be provided at different levels. In some models, the position of the wrist alone may be provided. In other examples, details about the positions of various joints for various fingers may be provided. Execution of the machine executable instructions further causes the computing system to calculate a range of accessory coordinates for one or more accessory keypoint coordinates. The set of anatomical keypoint coordinates may not only provide details about the positions of various parts or the position of the wrist joint, but may also provide information about other joints such as the elbow and shoulder of the subject. This can be used to provide an estimate of the range of motion that the subject's appendage may have during a medical procedure. This can then be used to predict whether it is possible or likely that the subject will place the appendage in a dangerous position. The detection of the body posture can be determined by defining the body posture on a list of coordinates. This may be beneficial as it not only allows the detection of a particular body posture that occurs when the image is taken, but can also be used to predict whether the subject will move to this body posture at a future time. This may be useful not only to improve the quality of the medical images, but also to improve patient safety.

[0026] In another embodiment, the one or more appendage keypoint coordinates are keypoint coordinates that define a location on an appendage of the subject.

[0027] In another embodiment, the range of appendage coordinates is determined using a predefined range of acceptable motion for appendage keypoint coordinates. For example, the motions allowed by various joints in the body are known. These known possible or acceptable motions can be used as the range of acceptable motion for appendage keypoint coordinates.

[0028] In another embodiment, the medical system further comprises a medical imaging system configured to acquire medical imaging data from a subject at least partially within the imaging zone. The medical imaging in some examples can be tomographic medical imaging, such as an MRI, CT, or PET system. In other examples, the medical imaging system can include an X-ray or fluoroscopy system or the like. The medical imaging system further comprises a subject support configured to support the subject at least partially within the imaging zone. The medical imaging system further comprises a camera system configured to acquire camera images showing the subject on the subject support. That is, the camera images can image the subject while the subject is supported by the subject support. For example, the subject support can be a bed or treatment table on which the subject lies. Execution of the machine-executable instructions further causes the computing system to control the camera system to acquire the camera images.

[0029] In another embodiment, the camera system may have coordinates that are aligned to the medical imaging system and / or the subject support. Alternatively, the anatomical keypoint locator module may be configured to determine coordinates relative to a position on the subject support. For example, there may be an artificial intelligence module that is able to recognize the position of the subject relative to the position of the subject support or medical imaging system and provide alignment between the coordinate systems of the medical imaging system, the subject support and / or the camera system.

[0030] In another embodiment, execution of the machine-executable instructions further causes the computing system to control a medical imaging system to obtain medical imaging data.

[0031] In another embodiment, execution of the machine-executable instructions further causes the computing system to reconstruct a medical image from the medical imaging data.

[0032] In another embodiment, the camera system includes an infrared camera.

[0033] In another embodiment, the camera system further comprises an optical camera.

[0034] In another embodiment, the optical camera is a color camera.

[0035] In another embodiment, the medical imaging system is a thermal camera.

[0036] In another embodiment, the medical imaging system comprises a computed tomography system.

[0037] In another embodiment, the medical imaging system comprises a positron emission tomography system.

[0038] In another embodiment, the medical imaging system comprises a single photon emission computed tomography system.

[0039] In another embodiment, the medical imaging system comprises an image guided therapy system such as a Gamma Knife or LINAC guided by MRI or CT.

[0040] In another embodiment, the medical imaging system comprises a digital x-ray system.

[0041] In another embodiment, the medical imaging system comprises a digital fluoroscope.

[0042] In another embodiment, the medical imaging system comprises a magnetic resonance imaging system, for which identification of various postures may be beneficial as it may be difficult or difficult for an operator to determine if a subject is in an improper or unsafe position.

[0043] In another embodiment, the list of coordinates is configured to define one or more conductive body loops. This embodiment may be beneficial because positioning of the body may cause conductive loops to be defined by the body. When the magnetic resonance imaging system is performed, a current may be induced in one of these conductive body loops, which may cause heating or RF burns in the subject. Thus, defining the conductive body loops in the list of coordinates may improve the safety of the magnetic resonance imaging system.

[0044] In another embodiment, execution of the machine executable instructions further causes the computing system to provide, if a warning signal is provided, a rendering of the camera image of an overlay indicating a match between the list of coordinates and the set of anatomical keypoint coordinates, which may be beneficial as it provides a visual guide to an operator of the medical imaging system, making it easier to properly position the subject.

[0045] In another embodiment, execution of the machine-executable instructions further causes the computer system to provide an audible warning system when a warning signal is provided, which can be an effective means of alerting an operator of the medical device if there is a problem.

[0046] In another embodiment, execution of the machine-executable instructions further causes the computing system to render a warning message on a display if a warning signal is provided.

[0047] In another embodiment, execution of the machine executable instructions further causes the computing system to disable acquisition of medical imaging data if a warning signal is provided. This may be particularly useful, for example, to prevent a dangerous situation for the subject. In some examples, if the position of the object changes, the system may then enable acquisition of medical imaging data when the object is in an appropriate or safe position.

[0048] In another embodiment, the list of coordinates is configured to define an insertion collision, for example, when a subject is placed on a subject support and the subject support is inserted into a medical imaging system, such as a magnet or a CT ring, it may be possible that the subject will collide with parts of the medical imaging system when the subject is inserted.

[0049] In another embodiment, the list of coordinates is configured to define prohibited hand positions, for example when the subject places their hand in a location where it may be pinched. This may also be a position where the hand is touching an apparatus or device that the subject should not touch.

[0050] In another embodiment, a list of coordinates is configured to define prohibited foot positions. Similar to the hands, the feet may be placed in positions that could result in them being pinched or otherwise improperly positioned (e.g., forming a conductive body loop).

[0051] In another embodiment, a list of coordinates is configured to define the location of the medical device. For example, there may be various coils or other fixtures or devices in the vicinity of the subject. The system can then be used to prevent the subject from possibly touching or modifying the medical device.

[0052] In another embodiment, the list of coordinates is configured to define subject support pinch points, which may be locations where, for example, a portion of the subject can be pinched if in contact.

[0053] In another embodiment, the list of coordinates is configured to define locations of high electric or magnetic fields that may be responsible for producing high local SAR exposure for magnetic resonance imaging.

[0054] In another embodiment, the medical system is used with an X-ray system, a digital fluoroscopy system, or a computed tomography system. The list of coordinates is configured to define locations that receive unwanted X-rays. For example, when the eyes are in the X-ray plane for a head CT scan. Or the hands are placed on the abdomen for an abdominal scan. The list of coordinates can then be used to avoid or minimize the amount of radiation received by these body regions.

[0055] In another embodiment, the anatomical keypoint locator module comprises a neural network configured to output a separate anatomical keypoint coordinate probability map for each of at least one anatomical keypoint coordinate in response to receiving an image of the subject on the subject support. For example, various joints and locations within the subject may be included in the anatomical keypoint coordinates. For each set, there may be a separate image or map output, on which the probability of the joint or anatomical location being at a particular location is output. The most likely location may be obtained, for example, by taking the maximum probability. The system is particularly good at identifying joints or other anatomical locations when they are obscured or partially obscured, for example when the subject has clothing or a blanket placed on the subject.

[0056] Execution of the machine executable instructions further causes the computing system to receive distinct anatomical keypoint coordinate probability maps in response to inputting the images to the neural network. Execution of the machine executable instructions further causes the computing system to calculate a set of anatomical keypoint coordinates from the distinct joint coordinate probability maps for each of the set of joint coordinates.

[0057] Training the neural network can be accomplished by having images of the subject and then training a keypoint coordinate probability map for each of at least one anatomical keypoint coordinate labeled. For example, one can have a series of images of different subjects in slightly different positions wearing different clothes or covered with a blanket or with the body partially obscured. An operator can then move and mark up various points so that the location of the anatomical keypoint coordinate is indicated. This can then be used, for example, in a deep learning algorithm to train the neural network.

[0058] In another embodiment, the list of coordinates comprises a predefined list of coordinates stored in memory.

[0059] In another aspect, the present invention provides a method of medical imaging. The method includes receiving a camera image. As discussed above, the camera image may be a composite image including multiple images and possibly multiple types of images. The method further includes receiving a set of anatomical keypoint coordinates in response to input of the camera image to an anatomical keypoint locator module. The anatomical keypoint locator module is configured to output a set of anatomical keypoint coordinates of the subject in response to receiving a camera image showing the subject. The method further includes receiving a list of coordinates. The method further includes searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates. The method further includes providing an alert signal if a match is determined.

[0060] In another aspect, the present invention provides a computer program including machine executable instructions for execution by a computing system. For example, the computer program may be stored on a non-transitory storage medium. Execution of the machine executable instructions causes the computing system to receive a camera image. Execution of the machine executable instructions further causes the computing system to receive a set of anatomical keypoint coordinates in response to inputting the camera image into an anatomical keypoint locator module. Execution of the machine executable instructions further causes the computing system to receive a list of coordinates. Execution of the machine executable instructions further causes the computing system to search the list of coordinates to determine a match with the set of anatomical keypoint coordinates. Execution of the machine executable instructions further causes the computing system to provide an alert signal if a match is determined.

[0061] In another embodiment, the memory further stores an object detection module. The object detection module may be a software module capable of identifying objects and / or significant object locations within the image. For example, the object detection module may be a convolutional neural network used to identify objects such as instruments, trolleys, injectors, docking points, or other pinch point locations. In some examples, a subject may, for example, pinch a finger, as the case may be. The object detection module may provide a list of object coordinates that may be added to the list of coordinates.

[0062] The object determination module may be a standard convolutional neural network used to classify images and place bounding boxes within the images. The object determination module may be trained using deep learning with training images labeled with either objects and / or pinch point locations.

[0063] It will be understood that one or more of the above-described embodiments of the present invention may be combined, unless the combined embodiments are mutually exclusive.

[0064] As will be appreciated by one of ordinary skill in the art, aspects of the present invention may be embodied as an apparatus, a method, or a computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be referred to generally herein as a "circuit," "module," or "system," and further, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer executable code embodied thereon.

[0065] Any combination of one or more computer readable media may be utilized. A computer readable medium may be a computer readable signal medium or a computer readable storage medium. As used herein, a "computer readable storage medium" encompasses any tangible storage medium capable of storing instructions executable by a processor or a computing system of a computing device. A computer readable storage medium may be referred to as a computer readable non-transitory storage medium. A computer readable storage medium may also be referred to as a tangible computer readable medium. In some embodiments, a computer readable storage medium may also be capable of storing data that can be accessed by a computing system of a computing device. Examples of computer readable storage media include, but are not limited to, floppy disks, magnetic hard disk drives, solid state hard disks, flash memory, USB thumb drives, random access memory (RAM), read only memory (ROM), optical disks, magneto-optical disks, and register files of a computing system. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), such as CDROM, CDRW, CDR, DVDROM, DVDRW, or DVDR disks. The term computer-readable storage medium also refers to various types of recording media that can be accessed by a computer device over a network or communication link. For example, data can be retrieved over a modem, over the Internet, or over a local area network. Computer executable code embodied on a computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wireline, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0066] A computer-readable signal medium may include a propagated data signal having computer-executable code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal 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 is not a computer-readable storage medium but may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0067] "Computer memory" or "memory" is one example of a computer-readable storage medium. Computer memory is any memory directly accessible to a computing system. "Computer storage" or "storage" is a further example of a computer-readable storage medium. Computer storage is any non-volatile memory computer-readable storage medium. In some embodiments, computer storage may be computer memory, and vice versa.

[0068] As used herein, a "computing system" encompasses electronic components capable of executing programs, machine-executable instructions, or computer-executable code. References to a computing system, including examples of "computing system," should be interpreted as including more than one computing system or processing core, as the case may be. A computing system may be, for example, a multi-core processor. A computing system may also refer to a collection of computing systems within a single computer system or distributed among multiple computer systems. The term computing system should also be interpreted as referring to a collection or network of computing devices, each possibly comprising a processor or computing system. Machine-executable code or instructions may be executed by multiple computing systems or processors, which may be within the same computing device or may be distributed across multiple computing devices.

[0069] Machine-executable instructions or computer-executable code may comprise instructions or programs that cause a processor or other computing system to perform aspects of the present invention. Computer-executable code for performing operations for 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, Python, Smalltalk, C++, and traditional procedural programming languages ​​such as the "C" programming language or similar programming languages, and compiled into machine-executable instructions. In some cases, the computer-executable code may be in the form of a high-level language or in a pre-compiled form and may be used in conjunction with an interpreter that generates machine-executable instructions on the fly. In other cases, the machine-executable instructions or computer-executable code may form a program for a programmable logic gate array.

[0070] The computer executable code may run entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may 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 the connection may be to an external computer (e.g., via the Internet using an Internet Service Provider).

[0071] 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 present invention. It should be understood that each block or portion of a block in the flowcharts, diagrams, and / or block diagrams may be implemented by computer program instructions in the form of computer executable code, where applicable. Furthermore, it should be noted that combinations of blocks in different flowcharts, diagrams, and / or block diagrams may be combined, if not mutually exclusive. These computer program instructions may be provided to a general purpose computer, special purpose computer, or other programmable data processing device computing system to generate a machine such that the instructions, executed via the computer or other programmable data processing device computing system, create means for performing the functions / operations specified in the flowchart and / or block diagram blocks or blocks.

[0072] These machine-executable instructions or computer program instructions may be stored on a computer-readable medium that can instruct a computer, other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored on the computer-readable medium produce an article of manufacture that includes instructions that implement the function / act specified in a block or blocks of the flowcharts and / or block diagrams.

[0073] The machine-executable instructions or 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 executed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions executing on the computer or other programmable apparatus provide a process for implementing the function / operation specified in the flowchart and / or block diagram block or blocks.

[0074] A "user interface" as used herein is an interface that allows a user or operator to interact with a computer or computer system. A "user interface" may also be referred to as a "human interface device," and a user interface may provide information or data to an operator and / or receive information or data from an operator. A user interface may allow input from an operator to be received by a computer and may provide output from the computer to a user. In other words, a user interface may allow an operator to control or manipulate a computer, and an interface may allow a computer to show the effect of the operator's control or manipulation. The display of data or information on a display 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, headset, pedals, wired gloves, remote control, and accelerometer are all examples of user interface components that allow for the reception of information or data from an operator.

[0075] As used herein, a "hardware interface" encompasses an interface that allows a computing system of a computer system to interact with and / or control external computing devices and / or devices. A hardware interface may allow a computing system to send control signals or instructions to external computing devices and / or devices. A hardware interface may also allow a computing system to exchange data with external computing devices and / or devices. Examples of hardware interfaces include, but are not limited to, a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS232 port, an IEEE 488 port, a Bluetooth connection, a wireless local area network connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0076] As used herein, a "display" or "display device" encompasses an output device or user interface adapted to display images or data. A display can output visual, audio, and / or tactile data.

[0077] Examples of displays include, but are not limited to, computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (liquid), memory tubes, bi-stable displays, electronic paper, vector displays, flat panel displays, vacuum fluorescent displays (VF), light emitting diode (LED) displays, electroluminescent displays (ELD), plasma display panels (PDP), liquid crystal displays (LCD), organic light emitting diode displays (OLED), projectors, and head mounted displays.

[0078] Medical imaging data is defined herein as recorded measurements made by a tomographic medical imaging system that are indicative of a subject. Medical imaging data may be reconstructed into a medical image. Medical imaging data is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained within the medical imaging data. This visualization may be performed using a computer.

[0079] Medical imaging data is defined herein as measurements made by a medical imaging system that can be reconstructed into a medical image that depicts the subject.

[0080] K-space data is defined herein as the recorded measurements of radio frequency signals emitted by atomic spins using the antenna of a magnetic resonance machine during a magnetic resonance imaging scan. Magnetic resonance data is an example of medical imaging data.

[0081] A magnetic resonance imaging (MRI) image or MR image, defined herein as a reconstructed two- or three-dimensional visualization of anatomical data contained within magnetic resonance imaging data, is an example of a medical image. This visualization can be performed using a computer.

[0082] In the following, preferred embodiments of the invention will be described, by way of example only, with reference to the drawings in which: [Brief description of the drawings]

[0083] [Figure 1] 1 shows an example of a medical system. [Diagram 2] 2 shows a flow chart illustrating a method of using the medical system of FIG. [Diagram 3] 1 illustrates a further example of a medical system. [Figure 4] 4 shows a flow chart illustrating a method of using the medical system of FIG. [Diagram 5] Illustrates examples of arm postures that have a high probability of allowing hand contact. [Figure 6] Compared to Figure 5, the hands are closer together and the fingers are less likely to touch. [Figure 7] A similar situation is shown in FIG. 6, where the blanket obscures the arms and hands. [Figure 8] 1 shows examples of postures that may be preferred from an RF point of view for a magnetic resonance imaging procedure. [Figure 9] 1 shows a subject lying on a subject support with a zoomed view of the arm and hand. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0084] Like numbered elements in these figures are equivalent elements or perform the same function. An element described above is not necessarily discussed in a subsequent figure if there is functional equivalence.

[0085] FIG. 1 illustrates an example of a medical system 100. The medical system 100 is shown as comprising a computer 102. The computer 102 is intended to represent one or more computers or computing devices at one or more locations. For example, the computer 102 may be integrated into a medical imaging system, such as a magnetic resonance imaging system. In another example, the medical system 100 may be a workstation, for example, in a radiology department. In yet another example, the medical system 100 may be a server configured to perform image processing tasks for a radiology department. In yet another example, the medical system 100 may be implemented as a web-based service provided. For example, the computer 102 may be a virtual computing system.

[0086] The computer 102 is shown as including a computing system 104, which may represent one or more computing systems or processors located in one or more locations. The computing system 104 is connected to an optional hardware interface 106. If other components of the medical system 100, such as a medical imaging system, are present, the hardware interface 106 may enable the computing system 104 to communicate with these other components. The computing system 104 is further shown as being connected to an optional user interface 108. The user interface 108 may provide, for example, a display or human interface device that allows an operator to control the operation and functionality of the medical system 100.

[0087] The computing system 104 is further shown as being connected to a memory 110. The memory 110 represents various types of memory, such as a hard drive, RAM, or non-transitory storage media, that may be in communication with the computing system 104. The memory 110 is shown as including machine-executable instructions 120. The machine-executable instructions 120 enable the computing system 104 to perform various computational and data processing tasks. The machine-executable instructions 120 may also enable the computing system 104 to control other components of the medical system 100.

[0088] The memory 110 is further shown as including an anatomical keypoint locator module 122. The anatomical keypoint locator module 122 may be implemented, for example, as a neural network that takes the camera image 124 as an input and outputs a set of anatomical keypoint coordinates. The memory 110 is further shown as storing the camera image 124 and a set of anatomical keypoint coordinates 126. The memory 110 is further shown as including a list of coordinates 128. The list of coordinates 128 may be, for example, a list of absolute coordinates or may be pairs or definitions of relative coordinate positions. This may be used, for example, to identify undesirable and dangerous postures or positions of the subject. The memory 110 is further shown as including a warning signal that may be provided if the set of anatomical keypoint coordinates 126 matches the list of coordinates 128.

[0089] 2 shows a flow chart illustrating a method of operating the medical system 100 of FIG. 1. First, in step 200, a camera image 124 is received. Next, in step 202, a set of anatomical keypoint coordinates 126 is received from an anatomical keypoint locator module 122 in response to receiving the camera image 124 as an input. Next, in step 204, a list of coordinates 128 is received. In some examples, the list of coordinates 128 may be received from a user interface 108. In other examples, it may be retrieved from the memory 110. Next, in step 206, the list of coordinates 128 is searched to determine a match with the set of anatomical keypoint coordinates 126. Finally, in step 208, if a match is determined, an alert signal 130 is provided.

[0090] 3 shows a further example of a medical system 300. The medical system 300 is similar to the medical system 100 shown in FIG.

[0091] The magnetic resonance imaging system 302 comprises a magnet 304. The magnet 304 is a superconducting cylindrical magnet with a bore 306. Different types of magnets can be used, for example both split cylindrical magnets and so-called open magnets. Split cylindrical magnets are similar to standard cylindrical magnets, except that the cryostat is split into two sections to allow access to the magnet's isoplane, and such magnets can be used, for example, in conjunction with charged particle beam therapy. Open magnets have two magnet sections, one above the other, with a space between them large enough to accommodate the subject, i.e. an arrangement of the two section areas similar to the area of ​​a Helmholtz coil. Open magnets are popular because they are less confining to the subject. Inside the cryostat of the cylindrical magnet is a collection of superconducting coils.

[0092] Within the bore 306 of the cylindrical magnet 304 is an imaging zone 308 where the magnetic field is strong and sufficiently uniform to perform magnetic resonance imaging. The magnetic resonance data acquired is typically acquired over a field of view. A subject 318 is shown supported by a subject support 320 with a view to a camera 322.

[0093] The camera 322 is shown positioned such that the subject 318 may be imaged as it lies on the subject support 320. The subject support 320 is shown connected to an actuator 322 that is configured to insert the subject support 320 and the subject 318 into the bore 306 of the magnet 304.

[0094] Also within the magnet bore 306 are a set of magnetic field gradient coils 310 used for preliminary magnetic resonance data acquisition for spatially encoding magnetic spins within the imaging zone 308 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 include three separate coil sets for spatially encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils 310. The current supplied to the magnetic field gradient coils 310 is controlled as a function of time and may be ramped or pulsed.

[0095] Adjacent to the imaging zone 308 is a radio frequency coil 314 for manipulating the orientation of magnetic spins in the imaging zone 308 and for receiving radio transmissions from the spins in the imaging zone 308. A radio frequency antenna may include multiple coil elements. A radio frequency antenna may also be referred to as a channel or antenna. The radio frequency coil 314 is connected to a radio frequency transceiver 316. The radio frequency coil 314 and the radio frequency transceiver 316 may be replaced by separate transmit and receive coils, as well as separate transmitters and receivers. It is understood that the radio frequency coil 314 and the radio frequency transceiver 316 are representative. The radio frequency coil 314 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 316 may represent a separate transmitter and receiver. The radio frequency coil 314 may also have multiple receive / transmit elements, and the radio frequency transceiver 316 may have multiple receive / transmit channels. For example, if a parallel imaging technique such as sensing is performed, the radio frequency 314 may have multiple coil elements.

[0096] The subject 318 and subject support 320 are shown in this view as being outside the bore 306 of the magnet 304. While the subject is in this position, a camera system 324 is positioned to image the exterior surface of the subject 318. This can be used to provide the camera image 124. The camera system 324 can be comprised of, for example, an optical camera, a color camera, an infrared camera, and / or a 3D camera. The camera system 324 can also be located within the bore of the magnet 306.

[0097] The hardware interface 106 is shown as being connected to a camera system 324, an actuator 322, a gradient coil power supply 312, and a transceiver 316. The computing system 104 can control these and other components via the hardware interface 106.

[0098] The memory 110 is further shown as including pulse sequence commands 330. The pulse sequence commands are commands or data that can be converted into such commands that can be used to control a magnetic resonance imaging system to acquire magnetic resonance data. The magnetic resonance data can be reconstructed into a magnetic resonance image. The magnetic resonance data is an example of medical imaging data, and the magnetic resonance image is an example of a medical image.

[0099] FIG. 4 shows a flow chart illustrating a method of operating the medical system 300 of FIG. 3. The method illustrated in FIG. 4 is similar to the method illustrated in FIG. 2. In FIG. 4, the method starts with step 400. In step 400, the computing system 104 controls the camera system 324 to acquire the camera image 124. After step 400 is performed, steps 200, 202, and 204 as shown in FIG. 2 are performed. After step 204 is performed, step 402 is performed. In step 402, a range of appendage coordinates is calculated from one or more appendage keypoint coordinates. As used herein, an appendage is a hand or a foot. Thus, a range of hand or foot coordinates is calculated by determining one or more keypoint coordinates indicative of the coordinates of the hand or foot. This allows prediction of possible positions where the subject may place his or her hand during the examination.

[0100] After step 402 is performed, step 206 is performed. In this case, the list of coordinates is searched to determine if a particular body pose is detected. A particular body pose is defined by the relative positions of various key point coordinates. In this case, for example, fingertips may indicate touching or legs may indicate crossing. These are two particular examples. After step 206 is performed, step 208 is performed, as shown in FIG. 2.

[0101] Preparing a patient for a magnetic resonance (MR) or other imaging modality can be a time-consuming task and require trained skills of the operator. The operator may place a surface coil on or adjacent to the anatomy to be imaged. Patient setup tends to be complex and may include blankets, cushions, hearing protection, and nurse call. While completing all these tasks, proper patient positioning needs to be ensured for a safe magnetic resonance imaging (MRI) scan. One of the most important things to avoid are body loops that may represent a current path for induced radio frequency (RF) currents, which in turn can result in increased local electric fields and specific absorption rates (SAR), potentially resulting in harm to the patient with the formation of RF burns.

[0102] Against this background, a patient setup monitoring workflow analysis camera (camera system 324) is proposed, which analyzes the position and orientation of the patient's limbs, even when partially covered by a blanket or coil. Such a camera can estimate the risk of looping or touching body parts that are most likely to lead to safety-related body postures, e.g. touching hands or looping arms or legs. The camera runs algorithms to detect the position and orientation of the patient's body joints and limbs. From this, the patient's size is known and also the orientation and (potentially touching) endpoints of partially hidden limbs can be estimated.

[0103] FIG. 5 shows an example of a camera image 502 with a set of anatomical keypoint coordinates 126 superimposed. In the image, a subject 318 is seen lying on a subject support 320. Several anatomical keypoints 502 of the set of anatomical keypoints are seen. The set of anatomical keypoints also includes list keypoint coordinates 504. List keypoint coordinates are an example of adjunct keypoint coordinates or hand keypoint coordinates. The list keypoint coordinates 504 define the position of the subject's hand. From this, a range of hand coordinates 506 is calculated and displayed. This shows the possible positions where the subject 318 can place his fingers. In this example, the range of hand coordinates 506 overlap and can be seen to touch fingers 508. In case of magnetic resonance imaging, this provides a ground loop between the two arms and the chest of the subject. This can lead to RF heating at the subject's fingertips touching 508. FIG. 5 shows an example of arm postures that have a high probability of allowing hand touching for a given subject. In this setting, a body loop can occur and there is a high risk of RF burns. In such a situation, the technician should be alerted and should correct the arm posture so that physical contact between the hands is no longer possible.

[0104] FIG. 6 shows an image of the same subject 318 lying on the same subject support 320. In this example, the subject's hand is in a different position and it is visible that the ranges of hand coordinates 506 no longer overlap. Thus, the subject's 318 fingers are not touching. In this example, the possibility of a conductive body loop is eliminated. FIG. 6 shows a threshold situation where the hand is approaching but the fingers may or may not be touching. This situation can alert the technician as there may be a high risk of RF burns.

[0105] FIG. 7 shows a further example of a camera image with a set of anatomical keypoints 502, 504 superimposed on the image 700. The subject is partially covered with a blanket. The wrist keypoint coordinates 504 are again identified as the range of the hand coordinates 506. In this example, the ranges of hand coordinates do not overlap. FIG. 7 shows a similar situation with a blanket obscuring the arm. In all three images, the color overlay represents the calculated probability map for the joints and limbs, and the yellow semicircles indicate the estimated possible range of movement. The camera detects such situations with a residual risk of a dangerous situation.

[0106] Fig. 8 shows a further example of a camera image 800. In this example, the anatomical key points 502, 504 are still shown. The hands are far enough apart so that there is no need to display or show the range of hand coordinates. The image 800 shows an example of a safe posture of the subject 318 during magnetic resonance imaging. Fig. 8 shows an example of a posture that may be preferred from an RF point of view.

[0107] 9 shows an image of a subject 318 lying on a subject support 320. The image zooms in to show the subject's arm 900 and hand 902 in more detail. The wrist anatomical key point 504 is visible. Additionally, a number of finger anatomical key points 906 are visible, indicating the location of the knuckles and the tips of the fingers. The subject support 320 has a sliding mechanism that moves it, and the sides of the subject support 904 are potential pinch points or locations where the subject 318 can potentially pinch the fingers. The entire side area 904 can be identified as a potential pinch point.

[0108] Identification of finger anatomical key points 906 allows for the determination of whether the fingers can potentially be damaged by the sliding mechanism. This allows for the detection of safety risks posed by the hand 902 gripping around the table edge or side area 904. This risk is immediately visible and detected by comparison with a list of coordinates. It may also be possible to predict the location of the finger anatomical key points even in the event of partial occlusion of the hand 902.

[0109] Here is a possible example: The camera system 324 is streaming images to the processing unit (computing system 104) during patient setup. The positions of the body joints are automatically detected by a detection algorithm, which calculates a spatial probability map of joint presence. Alternatively, the segments connecting the two joints can be detected directly (then the limbs). Based on the size and orientation of the body segments, regions are calculated that represent the likelihood of presence. If the camera also provides 3D data (e.g., in the formation of a depth map), these additional data can be used to refine the calculation of the body part presence regions. If the calculated regions overlap or are very close to each other, the pose setup is flagged as potentially dangerous, including localization information to guide the operator to resolve the conflict.

[0110] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium provided together with or as part of other hardware, but also in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be interpreted as limiting the scope. [Explanation of symbols]

[0111] 100 Medical Systems 102 Computer 104 Computing Systems 106 Hardware Interface 108 Optional User Interface 110 Memory 120 Machine Executable Instructions 122 Anatomical Keypoint Locator Module 124 camera images A set of 126 anatomical keypoint coordinates List of 128 coordinates 130 Warning Signal 200 Receive camera images 202 receiving a set of anatomical keypoint coordinates in response to inputting the camera image to the anatomical keypoint locator module. 204 Received coordinate list Search a list of coordinates to find a match with a set of 206 anatomical keypoint coordinates 208 Provides a warning signal if a match is found 300 Medical Systems 302 Magnetic Resonance Imaging Equipment 304 Magnet 306 Magnet Bore 308 Imaging Zone 310 Magnetic Gradient Coil 312 Gradient coil power supply 314 High Frequency Coil 316 Transceiver 318 Subject 320 Subject support part 322 Actuator 324 Camera System 330 Pulse Sequence Commands Controls the 400 camera system and acquires camera images 402 Calculate the range of accessory coordinates from one or more accessory keypoint coordinates 500 camera images 502 Anatomical Key Points 504 Wrist (appendage or hand) keypoint coordinates 506 Hand (appendage) coordinate range 508 Finger Touch 600 camera images 700 camera images 800 camera images 900 Arm 902 Hands 904 Pinch position or pinch point 906 Finger Keypoint Coordinates

Claims

1. 1. A medical system comprising: a memory storing machine-executable instructions and an anatomical keypoint locator module configured to, in response to receiving a camera image showing a subject, output a set of anatomical keypoint coordinates for the subject; a medical imaging system configured to acquire medical imaging data from a subject at least partially within an imaging zone, the medical imaging system comprising a magnetic resonance imaging system; a subject support configured to at least partially support a subject within the imaging zone; a camera system configured to acquire camera images showing a subject on the subject support; a computing system, wherein execution of the machine-executable instructions causes the computing system to: controlling the camera system to acquire the camera images; receiving the camera image, the camera image comprising a three-dimensional surface image; receiving the set of anatomical keypoint coordinates in response to inputting the camera image into the anatomical keypoint locator module; receiving a list of coordinates configured to define one or more conductive body loops, the list of coordinates having body postures defined as relative changes between the set of anatomical keypoint coordinates; searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates, wherein searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates comprises using the set of anatomical keypoint coordinates to detect a body posture selected from a plurality of body postures in the list of coordinates, and if the body posture is detected, execution of the machine-executable instructions further causes the computing system to provide the warning signal, and wherein the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions, and the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions by matching the three-dimensional surface image to a set of predetermined surface images each depicting a different body posture; providing a warning signal if said match is determined; A computing system that executes A medical system having:

2. the list of coordinates having body postures defined as relative changes between members of the set of anatomical keypoint coordinates, and detecting a body posture selected from a plurality of body postures in the list of coordinates using the set of anatomical keypoint coordinates comprises: determining relative changes between members of said set of anatomical keypoint coordinates; comparing relative changes between members of the set of anatomical keypoint coordinates for the body posture; The medical system of claim 1 , comprising:

3. 3. The medical system of claim 1, wherein the set of anatomical keypoint coordinates includes one or more appendage keypoint coordinates, and execution of the machine-executable instructions further causes the computing system to calculate a range of appendage coordinates from the one or more appendage keypoint coordinates, and wherein detecting the body posture selected from the body postures in the list of coordinates is performed using the range of appendage coordinates.

4. The medical system of claim 3 , wherein the one or more appendage keypoint coordinates are keypoint coordinates located on an appendage of the subject, and / or the range of the appendage coordinates is determined using a predetermined range of allowable movement for the appendage keypoint coordinates.

5. The medical system of claim 1 or 2, wherein the medical imaging system further comprises any one of a computed tomography system, a positron emission tomography system, a single photon emission tomography system, and an image-guided radiation therapy system.

6. When the warning signal is provided, execution of the machine-executable instructions causes the computing system to: providing a rendering of the camera image with an overlay indicating matches between the list of coordinates and the set of anatomical keypoint coordinates; providing an audible warning signal; rendering a warning message on a display; disabling acquisition of said medical imaging data; performing the combination; The medical system according to claim 1 or 2, further comprising:

7. 3. The medical system of claim 1, wherein the list of coordinates is configured to define any one of an insertion collision, a prohibited hand position, a prohibited foot position, a medical device position, a pinch point of a subject support, and combinations thereof.

8. the anatomical keypoint locator module comprises a neural network configured to output a separate anatomical keypoint coordinate probability map for each of the at least one anatomical keypoint coordinate in response to receiving an image of the subject on the subject support, and execution of the machine-executable instructions causes the computing system to: receiving the distinct anatomical keypoint coordinate probability maps in response to inputting the images into the neural network; calculating the set of anatomical keypoint coordinates from the distinct anatomical keypoint coordinate probability maps for each of the set of anatomical keypoint coordinates; The medical system according to claim 1 or 2, further comprising:

9. The medical system of claim 1 or 2, wherein the list of coordinates comprises a predetermined list of coordinates stored in the memory.

10. 3. The medical system of claim 1 or 2, wherein the one or more conductive body loops are conductive loops within the body of the subject that can result in RF heating of the subject, and / or the list of coordinates defines relative coordinates between two or more of the sets of anatomical keypoint coordinates.

11. 1. A method of medical imaging, said method comprising: controlling a camera system to acquire a camera image, the camera image showing a subject on a subject support, the subject support configured to support the subject at least in part within an imaging zone of a medical imaging system, the medical imaging system configured to acquire medical imaging data from the subject at least in part within the imaging zone, the medical imaging system comprising a magnetic resonance imaging system; receiving the camera image; receiving a set of anatomical keypoint coordinates in response to inputting the camera image into an anatomical keypoint locator module, the anatomical keypoint locator module being configured to output a set of anatomical keypoint coordinates of the subject in response to receiving a camera image showing the subject; receiving a list of coordinates configured to define one or more conductive body loops, the list of coordinates having body postures defined as relative changes between the set of anatomical keypoint coordinates; searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates, wherein searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates comprises using the set of anatomical keypoint coordinates to detect a body posture selected from a plurality of body postures in the list of coordinates, and if the body posture is detected, execution of the machine-executable instructions further causes the computing system to provide the warning signal, and wherein the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions, and the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions by matching the three-dimensional surface image to a set of predetermined surface images each depicting a different body posture; providing a warning signal if said match is determined; A method comprising:

12. A computer program having machine-executable instructions and an anatomical keypoint locator module for execution by a computing system, the anatomical keypoint locator module being configured to output a set of anatomical keypoint coordinates of a subject in response to receiving a camera image showing the subject, the computing system being configured to control a medical system, the medical system being configured to: a medical imaging system configured to acquire medical imaging data from the subject at least partially within an imaging zone, the medical imaging system comprising a magnetic resonance imaging system; a subject support configured to support the subject at least partially within the imaging zone; a camera system configured to acquire camera images showing the subject on the subject support; and executing the machine-executable instructions causes the computing system to: controlling the camera system to acquire the camera images; receiving the camera image, the camera image comprising a three-dimensional surface image; receiving the set of anatomical keypoint coordinates in response to inputting the camera image into the anatomical keypoint locator module; receiving a list of coordinates configured to define one or more conductive body loops, the list of coordinates having body postures defined as relative changes between the set of anatomical keypoint coordinates; searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates, wherein searching the list of coordinates to determine a match with the set of anatomical keypoint coordinates comprises using the set of anatomical keypoint coordinates to detect a body posture selected from a plurality of body postures in the list of coordinates, and if the body posture is detected, execution of the machine-executable instructions further causes the computing system to provide the warning signal, and wherein the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions, and the body posture detection is performed at least in part using the three-dimensional surface image to detect limb positions by matching the three-dimensional surface image to a set of predetermined surface images each depicting a different body posture; providing a warning signal if said match is determined; Execute Computer program.

Images