Automated object monitoring for medical imaging

Abstract

The present invention provides a medical instrument (100, 600), the medical instrument comprising a medical imaging system (102, 102'), an object support (110) and a camera system (104), the camera system being configured to image the object support in an initial position. Execution of the machine executable instructions causes a processor (108) to: place (500) the object support in the initial position (116); control (502) the camera system to acquire a series of repeated images (142); detect (506) the placement of one or more background objects (200); detect (508) one or more foreground objects (704); construct (510) a background object surface image (202) at least in part by stitching the series of repeated images together to replace image regions containing background objects occluded by the one or more foreground objects; and use the background a three-dimensional object surface (208) from an object surface image; detecting (514) the object in one of the series of repeated images (312); calculating (516) an object segmentation (304) of the object in the one of the series of repeated images; determining (518) a visible object surface (308) using the object segmentation and the one of the series of repeated images; and calculating (520) a three-dimensional object model (310) by estimating a volume (314) defined by the three-dimensional object surface and the visible object surface.

Description

Technical Field

[0001] The present invention relates to medical imaging, in particular to magnetic resonance imaging or computer tomography. Background Art

[0002] In medical imaging systems using imaging modalities such as magnetic resonance imaging (MRI) or computed tomography (CT), proper placement of the subject being imaged and other objects such as mats, antennas, or other objects can be time consuming.

[0003] US Patent Application Publication US 2016 / 0050368 A1 discloses a video processing device. The video processing device includes: a storage device configured to store a video captured by a camera; and a controller configured to separate a target object from a background image in each of a plurality of key frames contained in the video, splice the separate background images to generate a panoramic background image, synthesize the target object and the panoramic background image to acquire a plurality of panoramic images corresponding to a plurality of key frames, and combine the panoramic images on a time axis to generate a panoramic video. Summary of the invention

[0004] The invention provides a medical apparatus, a computer program product and a method in the independent claims. Embodiments are given in the dependent claims.

[0005] Embodiments can provide means for providing detailed information about the position of an object in the form of a three-dimensional object model to help prepare for imaging the object in a medical imaging system. When preparing to use a medical imaging system to perform a medical imaging protocol, various background objects can be placed on the support surface of an object support before the object is positioned. A camera system can be used to directly measure or infer the position of a surface defined by an object support and background objects placed on the object support. These surfaces can be represented as a three-dimensional object support model and a three-dimensional object surface, respectively. When an object is placed on an object support, a camera system can be used to image the object and directly measure or infer an object model representing the three-dimensional volume of the object. The three-dimensional object support model and the three-dimensional object surface can be used to define the back side of an object away from the camera system. When background objects are placed on an object support, foreground objects (such as an operator of a medical instrument) can block the view of the background objects. By stitching together images from a series of repeated images (such as a video feed), a more complete view of the background objects can be constructed.

[0006] In one aspect, the present invention provides a medical instrument comprising a medical imaging system for acquiring medical imaging data from an object in an imaging region. The medical instrument further comprises an object support having a support surface. The support surface is configured to receive the object. The object support is configured to support the object in an initial position, wherein in the initial position, the object is outside the imaging region.

[0007] The medical instrument further comprises a camera system configured to image the support surface when the object support is in the initial position. The medical instrument further comprises a memory containing or including machine executable instructions. The medical instrument further comprises a processor for controlling the medical instrument. Execution of the machine executable instructions causes the processor to place the object support in the initial position. Execution of the machine executable instructions also causes the processor to control the camera system to repeatedly acquire a series of repeated images.

[0008] Execution of the machine executable instructions further causes the processor to detect placement of one or more background objects that at least partially obstruct a surface of an object support within or using the series of repeated images. Execution of the machine executable instructions further causes the processor to detect one or more foreground objects that obstruct at least a portion of the one or more background objects in the series of repeated images. Execution of the machine executable instructions further causes the processor to construct a background object surface image at least in part by stitching the series of repeated images together to replace image regions containing background objects obstructed by the one or more foreground objects. Execution of the machine executable instructions further causes the processor to determine a three-dimensional object surface using the background object surface image. Execution of the machine executable instructions further causes the processor to detect the object in one of the repeated images in the series of repeated images.

[0009] Execution of the machine executable instructions further causes the processor to calculate an object segmentation of the object in the one of the series of repeated images. Execution of the machine executable instructions further causes the processor to determine a visible object surface using the object segmentation and the one of the series of repeated images. Execution of the machine executable instructions further causes the processor to calculate a three-dimensional object model by estimating a volume defined by the three-dimensional object surface and the visible object surface. This embodiment may be beneficial because it may provide a means of estimating the volume of an object and the position of an object.

[0010] The present invention relates to the (repeated) acquisition of successive images showing one or more background objects being placed or (re)moved from an object support (a patient table). In addition, (parts of) the successive images show foreground objects (e.g. the object to be imaged). Background objects may occlude the support surface (from the camera's perspective), and foreground objects may occlude background objects. Foreground objects may be eliminated by stitching the images, e.g. by replacing an image in which the background is occluded by another image in which the occluding foreground object is not present or is present at a different position. This allows the generation of a 3D object surface of a scene with (only) the background objects in the appropriate position. The objects may be headrests, knee supports and other forms of cushions on a patient table on which the patient to be examined is positioned.

[0011] In addition, when the view is blocked onto a background object on an object support, the object is detected from the camera's perspective. Based on the detection of the object, the visible object segmentation (from the camera's perspective) is segmented to form a set of objects, backgrounds, and object supports. This provides a surface rendering of the object within the range directly visible from the camera's perspective. Finally, based on the visible object surface and the 3D object surface, a volume representation of the object is derived in the form of a calculated 3D object model. The insight of the present invention is that the 3D object surface corresponds to the back surface of the object that is away from the camera's field of view because it is blocked by the object itself. In addition, based on the calculated 3D object model, any part of the background object that may still be visible from the camera's perspective when the object is placed on the object support can be eliminated. Therefore, an accurate segmentation of the object from the background objects and the object support is achieved, which accurately represents the volume of the object.

[0012] In some examples, the camera system may be a camera system that acquires a series of repeated still images. In other examples, the camera system may be a video system that provides a continuous video feed.

[0013] In various examples, the identification of objects in an image (such as an object or background or foreground object) can be detected in various ways. For example, this can be done using deformable models, landmark detection, or even artificial intelligence modules. For example, a convolutional neural network can be trained to easily identify specific objects within an image.

[0014] Various specific foreground objects can be identified and excluded from the background. Such objects may include magnetic resonance coils, magnetic resonance antennas, people, subjects, electrodes, hearing protectors or other medical instruments.

[0015] In different examples, repeatedly acquired images may take different forms. In some examples, this may mean images acquired sequentially or successively, it may mean images acquired continuously or on a repeated basis (i.e., one discrete frame after another), or it may even mean a video feed.

[0016] In another embodiment, execution of the machine executable instructions further causes the processor to receive a registration of a three-dimensional object support model to a series of repeated images. In some examples, the relationship between the three-dimensional object support and the image may be known a priori. In other examples, the registration may be determined based on the series of images themselves. The three-dimensional object support model describes the three-dimensional structure of the support surface. The three-dimensional object support model can be used to at least partially construct the three-dimensional object surface.

[0017] In another embodiment, in the second position, the object support is configured to support at least a portion of the object within the imaging zone.

[0018] In another embodiment, the object support is configured to transport the object from an initial position to a second position. Execution of the machine executable instructions further causes the processor to move the object support from the initial position to the second position. The second position is determined at least in part using the three-dimensional object model. For example, the three-dimensional object model can be used to approximately determine the position of the object relative to a model or anatomical landmark that is fitted or registered to the three-dimensional object model. This embodiment can be beneficial because it can eliminate the need for a light shield or other device for identifying the position of the object before moving the object into the imaging area.

[0019] In another embodiment, execution of the machine executable instructions further causes the processor to control the medical imaging system to acquire the medical imaging data.

[0020] In another embodiment, the medical imaging system is a magnetic resonance imaging system. The memory further comprises pulse sequence commands configured to control the magnetic resonance imaging system to acquire the medical imaging data from a region of interest in the imaging zone. This embodiment may be beneficial because the use of a three-dimensional object model may provide benefits in moving the object to the correct position or even for adjusting various parameters during a magnetic resonance imaging scan.

[0021] In another embodiment, the execution of the machine executable instructions further causes the processor to fit a region of interest to the three-dimensional object model. The execution of the machine executable instructions further causes the processor to modify the pulse sequence commands to image the fitted region of interest. This embodiment can be beneficial because it can eliminate the need for a survey scan, or can allow a survey scan to be acquired with a smaller FOV or higher resolution or with a shorter duration, or a combination thereof. A survey scan is typically a lower resolution image acquired before the data used to make clinical data is executed. Modifications to the pulse sequence commands can include modifying various parameters or characteristics of a subsequent pulse sequence or magnetic resonance imaging protocol.

[0022] In another embodiment, execution of the machine executable instructions further causes the processor to identify at least a portion of the one or more foreground objects that are fixed in at least a predetermined number of sequential frames in the series of repeated images. Execution of the machine executable instructions further causes the processor to determine whether at least a portion of the one or more foreground objects are correctly placed relative to the three-dimensional object model using predetermined criteria, which may be referred to as predetermined model criteria. For example, various foreground objects (such as coils, hearing protectors, or other objects) can be identified and then compared to the three-dimensional object model to see if they are correctly placed on the object for a given examination target anatomy. This can be beneficial because it can help ensure that the magnetic resonance imaging protocol is properly executed.

[0023] If something is stationary, this may mean that a subject or object determined to be stationary within a certain number of frames is stationary or moves less than a predetermined amount within those images.

[0024] In another embodiment, a trained image recognizer can be used to automatically recognize objects and mark them as foreground objects. Specific geometric models or machine learning can be used to check placement.

[0025] In another embodiment, the foreground object comprises any of: a magnetic resonance imaging coil, a magnetic resonance imaging antenna, an ECG electrode or other physiological sensor, a hearing protector, a nurse call, a pillow and / or a blanket and / or a pad, and / or similar objects, and combinations thereof.

[0026] In another embodiment, execution of the machine executable instructions further causes the processor to select a specific absorption rate (SAR) model using the three-dimensional object model. Execution of the machine executable instructions further causes the processor to modify the pulse sequence commands using, at least in part, the specific absorption model. This may also include contrast affecting sequence parameters such as subject height and also weight may be associated with a contrast enhanced magnetic resonance imaging protocol.

[0027] In another embodiment, execution of the machine executable instructions further causes the processor to select a peripheral nerve stimulation model using the three-dimensional object model. Execution of the machine executable instructions further causes the processor to modify the pulse sequence command at least in part using the peripheral nerve stimulation model. This can reduce subject discomfort during a magnetic resonance imaging examination.

[0028] In another embodiment, execution of the machine executable instructions further causes the processor to select an acoustic pressure model using the three-dimensional object model. Execution of the machine executable instructions further causes the processor to modify the pulse sequence commands using, at least in part, the acoustic pressure model. Knowledge of the volume of the object enables modeling of sound within the bore of a magnetic resonance imaging magnet.

[0029] In another embodiment, the medical imaging system is a CT system.

[0030] In another embodiment, execution of the machine executable instructions further causes the processor to use the three-dimensional object model to adjust CT protocols and / or CT system parameters. This may be beneficial because it may provide a more efficient means of identifying scan areas and / or may eliminate the need for a sunshade or CT survey and thus may reduce X-ray dose.

[0031] In another embodiment, execution of the machine executable instructions further causes the processor to automate definition of a starting position of a Z coordinate of an object support corresponding to a starting position of a CT scan or a localizer;

[0032] In another embodiment, execution of the machine executable instructions further causes the processor to automate definition of an end or length of the object support corresponding to an end of a CT scan or a localizer.

[0033] In another embodiment, execution of the machine executable instructions further causes the processor to determine a horizontal centering of the object: that is, a vertical diameter of the gantry should pass through a head-foot centerline of the patient.

[0034] In another embodiment, execution of the machine executable instructions further causes the processor to determine vertical centering of the object: that is, the horizontal diameter of the gantry should pass through the patient's anterior-posterior centerline (at least approximately at the target body part).

[0035] In another embodiment, execution of the machine executable instructions further causes the processor to use the three-dimensional object model to select an X-ray absorption model. For example, knowledge of the thickness of the object can help select an appropriate X-ray absorption model and can improve imaging quality. Knowledge of the three-dimensional object model can also help predict the location or position of an organ at risk (e.g., thyroid gland) where dose should be kept minimal.

[0036] In another embodiment, execution of the machine executable instructions further causes the processor to select a subject support height.This embodiment may be beneficial because it may help to properly place the subject within the imaging area.

[0037] In another embodiment, the camera system is a three-dimensional camera system. This can be beneficial because it can allow direct measurement of the position of the support surface and / or background objects. The measurements themselves can be used to provide registration of the support surface or even the three-dimensional object support model. The use of a three-dimensional camera can also help to directly measure the three-dimensional object surface. Similarly, the use of a three-dimensional camera can help to directly measure the visible object surface. These various measured quantities can then be used to directly calculate the three-dimensional object model.

[0038] In another embodiment, execution of the machine executable instructions further causes the processor to control the camera system to acquire an initial image. Execution of the machine executable instructions further causes the processor to determine a three-dimensional object support model using, at least in part, the initial image.

[0039] In another embodiment, the camera system is a two-dimensional camera system. In this embodiment, the camera system is not a three-dimensional camera. The execution of the machine executable instructions also causes the processor to assign a three-dimensional object model to the one or more background objects in the background object surface image. The execution of the machine executable instructions also causes the processor to use the assigned three-dimensional object model to construct the three-dimensional object surface. The term "assignment" as used herein means fitting or inferring a model. There may be specific models for specific pillows, blankets, pads, coils and other objects that can be used in a specific examination room or with a medical imaging system. These can be identified in a series of repeated images, and the model can be correctly placed so that it corresponds to the two-dimensional image. In this way, a two-dimensional camera can be used to infer or determine a three-dimensional surface.

[0040] In another embodiment, execution of the machine executable instructions can assign a three-dimensional foreground object model to a foreground object in a repeated image in a series of repeated images containing an object. This can be useful, for example, for locating objects placed on or near the object, such as coils, antennas or other objects. The visible object surface can also be determined in this way. In another embodiment, execution of the machine executable instructions also causes the processor to control the camera system to capture an initial image. Execution of the machine executable instructions also causes the processor to align the initial image to a three-dimensional object support model. The three-dimensional object support model describes the three-dimensional structure of the support surface.

[0041] In another embodiment, execution of the machine executable instructions further causes the processor to approximate gaps in the surface of the three-dimensional object. For example, if not all portions of the surface of the three-dimensional object are imaged because there are foreground objects and / or people or objects that occlude it during all images, then what the entire three-dimensional object surface is may be unknown. In this case, neighboring measurements on either side of the unknown area can be extrapolated or interpolated to fill in the missing surface data.

[0042] In another embodiment, when the object support is in the initial position, any of the following is continuously updated: detection of placement of the one or more background objects that at least partially occlude the object support using repeated images; detection of the one or more foreground objects that occlude at least a portion of the one or more background objects in the series of repeated images; construction of the background object surface at least in part by stitching the series of repeated images together to replace image regions containing background objects occluded by the one or more foreground objects; determination of the three-dimensional object surface using the object surface images; detection of the object in the one or more series of repeated images; calculation of the object segmentation of the object in the one or more series of repeated images; determination of the visible object surface using the object segmentation and one or more series of repeated images; calculation of a three-dimensional object model by estimating a volume defined by the three-dimensional object surface and the visible object surface; and combinations thereof. This embodiment can be beneficial because the steps performed are continuously updated as the position of the object or objects changes.

[0043] In another aspect, the object segmentation is calculated after the object is detected as being stationary in at least a selected number of sequential images in the series of repeated images.

[0044] Stationary may mean that the object is in the same position for a certain number of frames or that the object moves less than a predetermined amount.

[0045] In another embodiment, the one or more background objects are selected from a predetermined list of background objects. This may be beneficial because if the list of background objects is limited, it may improve the ability to identify the object or even provide a suitable model for the two-dimensional image.

[0046] In another embodiment, the one or more foreground objects are selected from a predetermined list of foreground objects. Again, this can facilitate the identification of foreground objects by limiting the possibilities. This can be reasonable in the case of both background objects and foreground objects, since typically for medical imaging systems, the objects that are allowed to be placed into the imaging system are limited.

[0047] In another aspect, the present invention provides a computer program product, comprising machine executable instructions for being executed by a processor controlling a medical imaging system, the medical imaging system being used to acquire medical imaging data from an object within an imaging region. The medical imaging system also includes an object support having a support surface. The support surface is configured to receive the object. The object support is configured to support the object in an initial position. In the initial position, the object is outside the imaging region. In the second position, the object support is configured to support at least a portion of the object within the imaging region. The medical imaging system also includes a camera system configured to image the support surface when the object support is in the initial position. Execution of the machine executable instructions also causes the processor to place the object support in the initial position. Execution of the machine executable instructions also causes the processor to control the camera system to repeatedly acquire a series of repeated images.

[0048] Execution of the machine executable instructions further causes the processor to use the series of repeated images to detect placement of one or more background objects that at least partially occlude the support surface. Execution of the machine executable instructions further causes the processor to detect one or more foreground objects that occlude at least a portion of the one or more background objects in the series of repeated images.

[0049] Execution of the machine executable instructions further causes the processor to construct a background object surface image at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects. Execution of the machine executable instructions further causes the processor to determine a three-dimensional object surface using the background object surface image. Execution of the machine executable instructions further causes the processor to detect the object in one of the series of repeated images. Execution of the machine executable instructions further causes the processor to calculate an object segmentation of the object in the one of the series of repeated images.

[0050] Execution of the machine executable instructions further causes the processor to determine a visible object surface using the object segmentation and the one of the series of repeated images. Execution of the machine executable instructions further causes the processor to calculate a three-dimensional object model by estimating a volume defined by the three-dimensional object surface and the visible object surface. The benefits of this embodiment have been discussed previously.

[0051] In another aspect, the present invention provides a method for operating a medical instrument. The medical instrument includes a medical imaging system for acquiring medical imaging data from an object in an imaging region. The medical instrument also includes an object support having a support surface. The support surface is configured to receive the object. The object support is configured to support the object in an initial position. In the initial position, the object is outside the imaging region. In the second position, the object support is configured to support at least a portion of the object in the imaging region. The medical instrument also includes a camera system configured to image the support surface when the object support is in the initial position.

[0052] The method includes placing the object support in the initial position. The method also includes controlling the camera system to repeatedly capture a series of repeated images. The method also includes using the series of repeated images to detect the placement of one or more background objects that at least partially occlude the support surface. The method also includes detecting one or more foreground objects that occlude at least a portion of the one or more background objects and / or the object support in the series of repeated images.

[0053] The method also includes constructing a background object surface image at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects. The method also includes determining a three-dimensional object surface using the background object surface image. The method also includes detecting an object in one of the series of repeated images. The method also includes calculating an object segmentation of the object in the one of the series of repeated images. The method also includes determining a visible object surface using the object segmentation and the one of the series of repeated images. The method also includes calculating a three-dimensional object model by estimating a volume defined by the three-dimensional object surface and the visible object surface.

[0054] 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.

[0055] As will be appreciated by those skilled in the art, aspects of the present invention may be implemented as an apparatus, method, or computer program product. Thus, aspects of the present invention may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software aspects and hardware aspects, all of which are generally referred to herein as "circuits," "modules," or "systems." In addition, aspects of the present invention may take the form of a computer program product embodied in one or more computer-readable media having a computer executable code embodied thereon.

[0056] 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, "computer-readable storage medium" includes any tangible storage medium that can store instructions that can be executed by a processor of a computing device. A computer-readable storage medium may be referred to as a computer-readable non-transient 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 store data that can be accessed by a processor 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 memories, USB thumb drives, random access memories (RAM), read-only memories (ROM), optical disks, magneto-optical disks, and register files of processors. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R disks. The term "computer-readable storage medium" also refers to various types of recording media that can be accessed by a computer device via a network or communication link. For example, data may be retrieved on a modem, on the Internet, or on a local area network. Computer executable code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0057] A computer readable signal medium may include a propagated data signal embodying computer executable code 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 may be any computer readable medium that is not a computer readable storage medium and that is capable of conveying, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0058] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a processor. "Computer storage" or "storage device" is another example of a computer-readable storage medium. A computer storage device can be any non-volatile computer-readable storage medium. In some embodiments, a computer storage device can also be computer memory or vice versa.

[0059] As used herein, "processor" includes an electronic component capable of executing a program or machine executable instructions or computer executable code. References to computing devices including "processors" should be interpreted as possibly including more than one processor or processing core. The processor may be, for example, a multi-core processor. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems. The term computing device should also be interpreted as possibly referring to a collection or network of multiple computing devices, each of which includes one or more processors. Computer executable code may be executed by multiple processors, which may be within the same computing device, or may even be distributed across multiple computing devices.

[0060] Computer executable code may include machine executable instructions or programs that cause a processor to perform an aspect of the present invention. Computer executable code for performing operations for various aspects of the present invention may be written in any combination of one or more programming languages ​​and compiled into machine executable instructions, including object-oriented programming languages ​​(e.g., Java, Smalltalk, C++, etc.) and conventional procedural programming languages ​​(e.g., "C" programming language or similar programming languages). In some instances, the computer executable code may be in the form of a high-level language or in a precompiled form, and may be used in conjunction with an interpreter that generates machine executable instructions on the fly.

[0061] The computer executable code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on a remote computer or server. In the last case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or a connection to an external computer (e.g., through the Internet using an Internet service provider).

[0062] Various aspects of the present invention are described with reference to the flowchart illustration and / or block diagram of the method, device (system) and computer program product according to an embodiment of the present invention. It should be understood that each frame or part of the frame of the flowchart, diagram and / or block diagram can be implemented by the computer program instruction in the form of computer executable code when appropriate. It should also be understood that when mutually non-exclusive, the frames in different flowcharts, diagrams and / or block diagrams can be combined. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a unit for implementing the function / action specified in one or more frames of the flowchart and / or block diagram.

[0063] 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 function in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0064] 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, thereby producing a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0065] "User interface" used herein is an interface that allows a user or operator to interact with a computer or computer system. "User interface" can also be referred to as "human-machine interface device". The user interface can provide information or data to the operator and / or receive information or data from the operator. The user interface can enable the input from the operator to be received by the computer, and output can be provided to the user from the computer. In other words, the user interface can allow the operator to control or manipulate the computer, and the interface can allow the computer to indicate the effect of the control or manipulation of the operator. The display of data or information on a display or graphical user interface is an example of providing information to the operator. Receiving data by keyboard, mouse, tracking ball, touch pad, pointing stick, graphic input board, joystick, game handle, game pad, webcam, head mounted device, foot pedal, wired gloves, remote controller and accelerometer is all examples of user interface components that enable receiving information or data from the operator.

[0066] As used herein, "hardware interface" encompasses interfaces that enable a processor of a computer system to interact with and / or control an external computing device and / or apparatus. A hardware interface may allow a processor to send control signals or instructions to an external computing device and / or apparatus. A hardware interface may also enable a processor to exchange data with an external computing device and / or apparatus. Examples of hardware interfaces include, but are not limited to, universal serial bus, IEEE 1394 port, parallel port, IEEE 1284 port, serial port, RS-232 port, IEEE-488 port, Bluetooth connection, wireless LAN connection, TCP / IP connection, Ethernet connection, control voltage interface, MIDI interface, analog input interface, and digital input interface.

[0067] As used herein, a "display" or "display device" encompasses an output device or user interface suitable for displaying images or data. A display may output visual, auditory, and / or tactile data. Examples of displays include, but are not limited to: computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bi-stable 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 displays (OLEDs), projectors, and head mounted displays.

[0068] Medical image data is defined herein as two-dimensional data or three-dimensional data that has been acquired using a medical imaging system or scanner. A medical imaging system is defined herein as a device suitable for acquiring information about a patient's body structure and constructing a collection of two-dimensional medical image data or three-dimensional medical imaging data. The medical imaging data can be used to construct a visualization useful for a doctor's diagnosis. The visualization can be performed using a computer.

[0069] Magnetic resonance (MR) data is defined herein as the measurement of radio frequency signals emitted by atomic spins recorded using the antenna of a magnetic resonance device during a magnetic resonance imaging scan. Magnetic resonance data is an example of medical imaging data. A magnetic resonance imaging (MRI) image or MR image is defined herein as a two-dimensional or three-dimensional visualization reconstructed from anatomical data contained within the magnetic resonance imaging data. This visualization can be performed using a computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In the following, preferred embodiments of the present invention will be described by way of example only and with reference to the accompanying drawings, in which:

[0071] Figure 1 Examples of medical instruments are illustrated;

[0072] Figure 2 Shows Figure 1 Additional views of medical instruments;

[0073] Figure 3 Shows Figure 1 Additional views of medical instruments;

[0074] Figure 4 Shows Figure 1 Additional views of medical instruments;

[0075] Figure 5 The diagram shows the use of Figure 1 A flowchart of a method of a medical instrument;

[0076] Figure 6 Another example of a medical instrument is illustrated; and

[0077] Figure 7 Several images of an object support are shown.

[0078] Reference numerals list

[0079] 100 Medical instruments

[0080] 102 Medical Imaging Systems

[0081] 102' Magnetic Resonance Imaging System

[0082] 104 Camera System

[0083] 106 Computer Systems

[0084] 108 Processors

[0085] 110 Object Support

[0086] 112 Chamber

[0087] 114 Imaging Area

[0088] 116 Initial Position

[0089] 118 Support surface

[0090] 120 Support actuator

[0091] 130 Hardware Interface

[0092] 132 User Interface

[0093] 134 Memory

[0094] 140 machine executable instructions

[0095] 142 A series of repeated images

[0096] 144 3D Object Support Model

[0097] 146 Registration of a 3D Object Support Model to a Series of Repeated Images

[0098] 200 Background Objects

[0099] 202 Background object surface image

[0100] 204 Surface of background object

[0101] 208 3D object surface

[0102] 300 objects

[0103] 302 A repeated image showing an object in a series of repeated images

[0104] 304 Object Segmentation

[0105] 306 Object Surface

[0106] 308 Visible object surface

[0107] 310 3D object model

[0108] 314 The volume defined between the surface of the object and the surface of the background objects

[0109] 316 Second Position

[0110] 400 Medical Image Data

[0111] 400 MRI data

[0112] 402 Medical Images

[0113] 402 Magnetic Resonance Images

[0114] 500 Place the object support in the initial position

[0115] 502 Control the camera system to repeatedly capture a series of repeated images

[0116] 504 receiving a registration of a three-dimensional object support model to a series of repeated images

[0117] 506 Detecting placement of one or more background objects that at least partially occlude the surface of the support within a series of repeated images

[0118] 508 Detecting one or more foreground objects that occlude at least a portion of one or more background objects in a series of repeated images

[0119] 510 constructing a background object surface image at least in part by stitching together a series of repeated images to replace image regions containing background objects occluded by one or more foreground objects

[0120] 512 Using background object surface images to determine the surface of a three-dimensional object

[0121] 514 Detecting an object in a repeated image in a series of repeated images

[0122] 516 Compute object segmentation of an object in one of a series of repeated images

[0123] 518 Determining Visible Object Surfaces Using Object Segmentation and One of a Series of Repeated Images

[0124] 520 Computing a three-dimensional object model by estimating a volume defined by a three-dimensional object support model

[0125] 522 Move the object support from the initial position to the second position

[0126] 524 Acquiring Medical Imaging Data

[0127] 604 Magnet

[0128] 612 Magnet bore

[0129] 608 Area of ​​Interest

[0130] 610 Magnetic Field Gradient Coil

[0131] 612 Magnetic Field Gradient Coil Power Supply

[0132] 614 RF Coil

[0133] 616 Transceiver

[0134] 620 Pulse sequence command

[0135] 600 Medical instruments

[0136] 700 First Image

[0137] 702 Second Image

[0138] 704 Foreground Objects

[0139] 706 Occluded Area

[0140] 706' Blocked Area

[0141] 708 Splicing Area DETAILED DESCRIPTION

[0142] In these drawings, elements with the same number are equivalent elements or perform the same function. Elements that have been discussed previously need not be discussed in subsequent drawings if the function is the same.

[0143] Figure 1 An example of a medical instrument 100 is illustrated. The medical instrument 100 comprises a medical imaging system 102. The medical instrument 100 also comprises a camera system 104. 104 is intended to represent both a three-dimensional camera and a two-dimensional camera.

[0144] The medical instrument 100 is further shown to include a computer system providing a processor 108. The processor 108 is configured for controlling the medical instrument 100. The medical instrument is further shown to include a subject support 110.

[0145] The medical imaging system 102 is intended to be representative. In this example, it is of a cylindrical type with a bore 112 for receiving an object. There is an imaging region 114 where medical imaging data can be acquired from the object. The medical imaging system 102 can be used to represent both CT and MRI systems, for example.

[0146] The subject support 110 is shown in an initial position 116. The subject support 110 has a support surface 118 configured to receive a subject. A support actuator 120 is also shown that can move the support surface 118 into the bore 112 of the medical imaging system 102. In the initial position 116, the camera system 104 can image the support surface 118.

[0147] The computer system 106 is shown as including a hardware interface 130 that enables the processor 108 to communicate with and control other components of the medical instrument 100. The hardware interface is shown connected to the camera system 104, the medical imaging system 102, and the support actuator 120. The support actuator 120 can be used, for example, to move the position of the support surface 118 into the bore, and in some embodiments, in the vertical direction to control the height position of the object.

[0148] The computer system 106 is also shown to include a user interface 132 and computer memory 134. The memory 134 can be any combination of memory accessible to the processor 108. This can include, for example, main memory, cache memory, and non-volatile memory such as flash RAM, hard drives, or other storage devices. In some examples, the memory 134 can be considered a non-transitory computer readable medium.

[0149] The computer memory 134 is shown as containing machine executable instructions 140 that enable the processor 108 to control the medical instrument 100 and perform various tasks, such as performing calculations, performing image processing, and reconstructing various images. The computer memory 134 is also shown as containing a series of repeated images 142. Figure 1 In the example in FIG. 1 , no object or subject is present on the support surface 118. So far, the image is just the support surface itself. The memory 134 is also shown as containing a three-dimensional object support model 144 that models the three-dimensional surface of the support surface 118. The determination of the three-dimensional object support model 144 is optional. In some examples, portions of the support surface are located in an image that contains other background objects.

[0150] The memory is also shown as containing a registration of the object support model 144 to the series of repeated images 146. This registration is optional. For example, if the camera system 104 is a two-dimensional camera, the object support model 144 can be an a priori model that is then registered to the series of repeated images 142. If the camera system 104 is a three-dimensional camera system, the registration 146 and the object support model 144 can be measured by the camera system 104 itself.

[0151] Figure 2 Yet another view of the medical instrument 100 is shown. Again, the subject support 110 is in the initial position 118. Several background objects 200 are shown that have been placed onto the support surface 118. The camera system 104 has acquired background object surface images 202. The background object surface images 202 show the support surface 118 partially obscured by the surfaces 204 of the background objects 200. The images of the surfaces of the background objects 204 can be used to determine a three-dimensional object surface 208, which is stored in the memory 134. If the operator is placing background objects 200 onto the support surface 118, the camera system 104 will not be able to image the background objects 200 if they are obscured. A series of repeated images 142 can be used to stitch together the entire background object surface images 202, which are then used to reconstruct the three-dimensional object surface 208. In the event that some portions of the surfaces of the background objects 204 remain obscured, portions of the three-dimensional object surface 208 can be interpolated or extrapolated.

[0152] Figure 3Yet another view of the medical instrument 100 is shown. In this example, an object 300 is seen lying on an object support and background objects 200. The camera system 104 is capable of imaging the object 300, and the object 300 has been identified in one of the series of repeated images 302. The processor 108 then segments the one of the series of repeated images 302 to determine an object segmentation 304. The object segmentation 304 is used to determine a visible object surface 308 in one of the series of repeated images 302. This corresponds to the physical surface of the object 306. The position of the camera 104 is illustrative, and the camera can be placed in any position where it can image the object surface 308.

[0153] A three-dimensional object model 310 is formed using the visible object surface 308. In the case of a three-dimensional camera, the three-dimensional object model 310 can be measured directly. In the case of a two-dimensional camera system, the model can be fitted to the visible object surface 308. The three-dimensional object model 310 defines a volume 314 defined by the physical surface of the object 306 and the surfaces of the background objects 204. The surfaces of the background objects may include the support surface 118. The three-dimensional object support model 310 can be used, for example, to calculate a second position 316 to move the object support 110 to.

[0154] Figure 4 A further view of the medical instrument 100 is shown. Figure 4 , the processor has controlled the support actuator 120 to move the object support 110 into the second position 316. A portion of the object 300 is now within the imaging zone 114. The processor 108 then controls the medical imaging system 102 to acquire medical image data 400. The memory 134 is also shown as containing a medical image 402 that has been reconstructed from the medical image data 400.

[0155] Figure 5 The diagram shows the operation Figure 1-4 1. A flowchart of a method of a medical instrument 100 illustrated in FIG. 1. First, in step 500, an object support 110 is placed into an initial position 116. Next, in step 502, the camera system 104 is controlled to repeatedly acquire a series of repeated images 142. Next, in optional step 504, a registration 146 of an object support model 144 to the series of repeated images 142 is received. Next, in step 506, the placement of one or more background objects 200 that at least partially occlude the object support surface 118 is detected in the series of repeated images 142. The optional registration 146 may also be performed when background objects 200 are present on the object support. Then, in step 508, one or more foreground objects that occlude at least a portion of one or more background objects 200 are detected in the series of repeated images 142.

[0156] Then, in step 510, a background object surface image 202 is constructed by stitching together a series of repeated images to replace image regions containing background objects that are occluded by one or more foreground objects. Then, in step 512, a three-dimensional object surface is determined using the background object surface image 202. Next, in step 514, an object 300 is detected in one of the repeated images 302 in the series of repeated images 142. Next, in step 516, an object segmentation 304 is calculated using one of the repeated images 302 in the series of repeated images 142. Next, in step 518, a visible object surface 308 is determined using the object segmentation 304 and one of the repeated images in the series of repeated images 302. Then, in step 520, a three-dimensional object model 310 is determined by estimating the volume 314 defined by the three-dimensional object support model 144, the three-dimensional object surface 208.

[0157] In step 522, the object support 110 is moved from the initial position 116 to the second position 316. The second position 316 is determined at least in part using the three-dimensional object model 310. Finally, in step 524, medical imaging data 400 is acquired from the object 300. In some examples, the method may also be performed by reconstructing a medical image 402 based on the medical image data 400.

[0158] Figure 6 Yet another example of a medical instrument 600 is illustrated. Figure 6 The medical instrument 600 is similar to Figure 1-4 The medical apparatus 100 is illustrated in FIG. 1 , except that in this particular case the medical imaging system is a magnetic resonance imaging system 102 ′.

[0159] The magnetic resonance imaging system 102' comprises a magnet 104. The magnet 104 is a superconducting cylindrical magnet having a bore 112 passing through it. Different types of magnets may also be used; for example, split cylindrical magnets and so-called open magnets may also be used. A split cylindrical magnet is similar to a standard cylindrical magnet, but the cryostat has been split into two parts to allow access to the isoplane of the magnet, which magnet may be used, for example, in conjunction with charged particle beam therapy. An open magnet has two magnet parts, one above the other, with a space large enough in between to accommodate a subject: the arrangement of the zones of the two parts is similar to the arrangement of Helmholtz coils. Open magnets are popular because the subject is less confined. Inside the cryostat of the cylindrical magnet there is a set of superconducting coils. Within the bore 112 of the cylindrical magnet 604 there is an imaging zone 114, where the magnetic field is strong enough and uniform enough to perform magnetic resonance imaging. A region of interest 608 within the imaging zone 114 is shown. Magnetic resonance data is typically acquired for a region of interest. The object 300 is shown supported by the object support 110 such that at least a portion of the object 300 is within the imaging zone 114 and the region of interest 608 .

[0160] Also within the bore 112 of the magnet is a set of magnetic field gradient coils 610 for collecting preliminary magnetic resonance data to spatially encode magnetic spins within the imaging zone 114 of the magnet 604. The magnetic field gradient coils 610 are connected to a magnetic field gradient coil power supply 612. The magnetic field gradient coils 610 are intended to be representative. Typically, the magnetic field gradient coils 610 include three independent sets of coils, which are used to perform spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply provides current to the magnetic field gradient coils. The current provided to the magnetic field gradient coils 610 is controlled as a function of time and can be ramp-varied or pulse-varied.

[0161] Adjacent to the imaging zone 608 is a radio frequency coil 614, which is used to manipulate the orientation of magnetic spins within the imaging zone 608 and to receive radio frequency transmissions also from spins within the imaging zone 608. The radio frequency antenna may contain multiple coil elements. The radio frequency antenna may also be referred to as a channel or antenna. The radio frequency coil 614 is connected to a radio frequency transceiver 616. The radio frequency coil 614 and the radio frequency transceiver 616 may be replaced by separate transmitting coils and receiving coils and separate transmitters and receivers. It should be understood that the radio frequency coil 614 and the radio frequency transceiver 616 are representative. The radio frequency coil 614 is also intended to represent a dedicated transmitting antenna and a dedicated receiving antenna. Similarly, the transceiver 616 may also represent a separate transmitter and receiver. The radio frequency coil 614 may also have multiple receiving / transmitting elements, and the radio frequency transceiver 616 may have multiple receiving / transmitting channels. For example, if a parallel imaging technique such as SENSE is performed, the radio frequency coil 614 will have multiple coil elements. The transceiver 616 and gradient controller 612 are also shown as being connected to the hardware interface 130 of the computer system 106 .

[0162] In this example, the medical imaging data is magnetic resonance imaging data 400', and the magnetic resonance imaging data 400' has been reconstructed into a magnetic resonance image 402'. The memory 134 is also shown as containing pulse sequence commands 620 that enable the processor 108 to control the magnetic resonance imaging system 102' to acquire the magnetic resonance imaging data 400'. The pulse sequence commands 620 are configured to control the magnetic resonance imaging system 102' to acquire a series of magnetic resonance data from the object 300 according to a quantitative magnetic resonance imaging protocol.

[0163] Improvements in examination workflow in radiology are of high commercial interest due to the potential associated healthcare cost reductions. Camera sensors (camera systems) including depth sensors (3D cameras) are ideal sensor candidates for providing information about the patient, movable medical devices and accessories, and additional imaging modality devices. In order to accurately extract relevant information about the patient and the device, these can be segmented from the rest of the background environment. However, while the scanning room is typically a controlled environment, the determination of background elements (such as patient supports, pillows, blankets, and coils placed under the patient) is challenging for at least two reasons:

[0164] - Clinical workflow is very dynamic and variable between staff and hospitals, so that non-standard / unexpected equipment may be present on the patient support and background objects may all undergo changes until the patient is in a final and comfortable recumbent position for scanning.

[0165] - Background objects may be partially and temporarily occluded by the operator and / or the patient.

[0166] This makes standard techniques based on overall motion analysis of the entire scene or object recognition inapplicable.

[0167] The example may provide the following solutions:

[0168] Since the background is static over a much longer period of time than the examination object, staff and accessories, the paradigm can apply temporal-spatial stitching techniques to assemble the latest background image (background surface image) and further dynamically update it until the patient is in the final and comfortable lying position for scanning.

[0169] The system (medical instrument) which may consist of a depth camera (camera system) continuously acquires images and detects image patches that are static over time. These image patches are then stitched together into an overall reference background image. See below Figure 7 Preparing an inspection table for inspection The support will often partially but only temporarily obscure the background scene of interest.

[0170] The starting point is the image without the patient present. Whenever motion is detected within the patch (e.g. due to the technology moving or some pillows shifting back and forth), the image patch is updated with the content corresponding to the point in time when the scene in the image patch becomes static again. This is done until the system detects the presence of a patient (object) on the examination table. Patient detection can be done by several means (image processing techniques, data from another sensor, or manually). At this point in time, an accurate background calculation is available and a precise patient outline can be segmented. Patches that never become visible between the last patient until the current patient lies still on the patient support will be filled in by interpolation / extrapolation.

[0171] In some examples, the background image can still be updated to take into account the displacement of objects placed under the patient. (For example pillows can be added under him, for example under his legs to get a more comfortable position, or he can adapt the head pillow to his needs). The system can also detect the patient and his body parts, for example using tracking methods and initial patient segmentation, and estimate the changes of the background scene using visible patches that do not belong to the patient as much as possible. Typically, there are a limited number of devices, because object recognition techniques can be applied, and previously detected objects that have not left the scene can be fitted to the most current data.

[0172] Using this technique, the system is able to assign confidence levels to measured parameters, which may be, for example, the patient's weight, height, position and orientation, and it can apply background corrections to obtain the best possible estimate.

[0173] Figure 7A first image 700 and a second image 702 are shown. Two consecutive frames (images) 700, 702 show the residual patch for patient support background estimation over time. The two images 700, 702 show the segmentation. In the first image 700, the support surface 118 is visible together with several surfaces of background objects 204. The foreground object 704, which is a person, is shown as an occluded area 706. Parts of the support surface 118 and the surfaces of the background objects 204 cannot be imaged in the area marked 706.

[0174] The second image 702 shows the same view of the surface of the support surface 118 and the surface of the background object 204. However, in this case, the foreground object 704, which is also a person, has moved to a different position. There are two areas marked as 706', which are areas that are blocked in both the first image 700 and the second image 702. In the area 706', there is no image of the surface of the support surface 118 or the background object 204. However, the area 708 has been spliced ​​from the first image 700. It can be seen that if a large number of images are collected, then other areas can be spliced ​​and the area 706' can also be filled. In some examples, if the area 706' cannot be filled, then the data in these areas can be interpolated or extrapolated.

[0175] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0176] Those skilled in the art can understand and implement other variations of the disclosed embodiments when practicing the claimed invention by studying the drawings, the specification and the claims. In the claims, the word "comprising" does not exclude other elements or steps, and the words "one" or "an" do not exclude multiple. A single processor or other unit can implement the functions of several items recorded in the claims. Although certain measures are recorded in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used to advantage. The computer program may be stored / distributed on a suitable medium, for example, an optical storage medium or solid-state medium supplied together with other hardware or as part of other hardware, but may also be distributed in other forms, for example, via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be interpreted as limiting the scope.

Claims

1. A medical instrument (100, 600), comprising: A medical imaging system (102, 102') for acquiring medical imaging data (400, 400') from a subject (300) within an imaging region (114); an object support (110) having a support surface (118), wherein the support surface is configured to receive the object, wherein the object support is configured to support the object in an initial position (116), wherein in the initial position the object is outside the imaging region; a camera system (104) configured to image a surface of the support when the object support is in the initial position; a memory (134) comprising machine-executable instructions (140); and A processor (108) for controlling the medical instrument, wherein execution of the machine executable instructions causes the processor to: placing (500) the object support in the initial position; controlling (502) the camera system to repeatedly capture a series of repeated images (142); detecting (506) within the series of repeated images the placement of one or more background objects (200) that at least partially occlude the support surface; detecting (508) in the series of repeated images one or more foreground objects (704) that occlude at least a portion of the one or more background objects; constructing (510) a background object surface image (202) at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects; determining (512) a three-dimensional object surface (208) using the background object surface image; detecting (514) the object in a repeated image in the series of repeated images (312); calculating (516) an object segmentation (304) of the object in the one of the series of repeated images; determining (518) a visible object surface (308) using the object segmentation and the one of the series of repeated images; and A three-dimensional object model (310) is calculated (520) by estimating a volume (314) defined by the three-dimensional object surface and the visible object surface.

2. The medical instrument according to claim 1, wherein: The object support is configured to transport the object from an initial position to a second position (316), wherein, in the second position, the object support is configured to support at least a portion of the object within the imaging area, wherein execution of the machine-executable instructions further causes the processor to move (522) the object support from the initial position to the second position, wherein the second position is determined at least in part using the three-dimensional object model.

3. The medical instrument according to claim 1 or 2, wherein: The medical imaging system is a magnetic resonance imaging system (102'), wherein the memory further comprises pulse sequence commands (620) configured to control the magnetic resonance imaging system to acquire the medical imaging data from a region of interest (608) in the imaging zone.

4. The medical instrument according to claim 3, wherein: Execution of the machine executable instructions further causes the processor to: fitting the region of interest to the three-dimensional object model; and The pulse sequence commands are modified to image the fitted region of interest.

5. The medical instrument according to claim 3, wherein: Execution of the machine executable instructions further causes the processor to: identifying at least a portion of the one or more foreground objects that are stationary in at least a predetermined number of sequential images in the series of repeated images; A predetermined criterion is used to determine whether the at least a portion of the one or more foreground objects is correctly positioned relative to the three-dimensional object model.

6. The medical instrument according to claim 3, wherein: Execution of the machine executable instructions further causes the processor to: using the three-dimensional subject model to select a specific absorption model, a peripheral nerve stimulation model, an acoustic pressure model, a subject height, and / or a subject weight; and The pulse sequence commands are modified using, at least in part, the specific absorption model, the peripheral nerve stimulation model, the acoustic pressure model, the subject height, and / or the subject weight.

7. The medical instrument according to claim 1 or 2, wherein: The medical imaging system is a CT system, wherein execution of the machine executable instructions further causes the processor to perform any of the following: Automates the definition of the start of the locator; automating the definition of the end or length of said locator; determining horizontal centering of the object; determining the vertical centering of the object; selecting an X-ray absorption model using the three-dimensional object model; Select the object support height; and Its combination.

8. The medical instrument according to claim 1 or 2, wherein: The camera system is a three-dimensional camera system.

9. The medical instrument according to claim 1 or 2, wherein: The camera system is a two-dimensional camera system, wherein execution of the machine-executable instructions further causes the processor to: assigning a three-dimensional object model to the one or more background objects in the background object surface image; The three-dimensional object surface is constructed using the assigned three-dimensional object model.

10. The medical instrument according to claim 1 or 2, wherein: Execution of the machine executable instructions further causes the processor to approximate gaps in a surface of the three-dimensional object.

11. The medical instrument according to claim 1 or 2, wherein: When the object support is in the initial position, any of the following is continuously updated: detection of placement of one or more background objects at least partially occluding the support surface within the series of repeated images; detecting, in the series of repeated images, the one or more foreground objects that occlude at least a portion of the one or more background objects; constructing an image of a surface of the background object at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects; Determine the three-dimensional object surface using the object surface image; detecting the object in a repeated image in the series of repeated images; computing the object segmentation of the object in the one of the series of repeated images; determining the visible object surface using the object segmentation and the one of the series of repeated images; as well as calculating a three-dimensional object model by estimating a volume defined by the three-dimensional object surface and the visible object surface; and Its combination.

12. The medical instrument according to claim 1 or 2, wherein: The object segmentation is calculated after the object is detected as stationary in at least a selected number of sequential images in the series of repeated images.

13. The medical instrument according to claim 1 or 2, wherein any one of the following is present: The one or more background objects are selected from a predetermined list of background objects; The one or more foreground objects are selected from a predetermined list of foreground objects; and Its combination.

14. A computer program product comprising machine executable instructions (140) for execution by a processor (108) for controlling a medical instrument (100, 600), wherein: The medical instrument comprises a medical imaging system (102, 102') for acquiring medical imaging data (400, 400') from an object (300) within an imaging zone (114), wherein the medical imaging system further comprises a subject support (110) having a support surface (118), wherein the support surface is configured to receive the subject, wherein the subject support is configured to support the subject in an initial position (116), wherein in the initial position the subject is outside the imaging zone, wherein the medical imaging system further comprises a camera system (104) configured to image the support surface when the subject support is in the initial position; wherein execution of the machine executable instructions causes the processor to: placing (500) the object support in the initial position; controlling (502) the camera system to repeatedly capture a series of repeated images (142); using the series of repeated images to detect (506) placement of one or more background objects (200) that at least partially occlude the support surface; detecting (508) in the series of repeated images one or more foreground objects (704) that occlude at least a portion of the one or more background objects; constructing (510) a background object surface image (202) at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects; determining (512) a three-dimensional object surface (208) using the background object surface image; detecting (514) the object in a repeated image in the series of repeated images (302); calculating (516) an object segmentation (304) of the object in the one of the series of repeated images; determining (518) a visible object surface (308) using the object segmentation and the one of the series of repeated images; and A three-dimensional object model (310) is calculated (520) by estimating a volume defined by the three-dimensional object surface and the visible object surface.

15. A method of operating a medical instrument (100, 600), wherein: The medical instrument comprises a medical imaging system (102, 102') for acquiring medical imaging data (400, 400') from an object within an imaging zone (114), wherein the medical instrument further comprises a subject support (110) having a support surface (118), wherein the support surface is configured to receive the object, wherein the subject support is configured to support the object in an initial position (116), wherein in the initial position the object is outside the imaging zone, wherein the medical instrument further comprises a camera system (104) configured to image the support surface when the subject support is in the initial position, Wherein, the method comprises: placing (500) the object support in the initial position; controlling (502) the camera system to repeatedly capture a series of repeated images (142); using the series of repeated images to detect (506) placement of one or more background objects (200) that at least partially occlude the support surface; detecting (508) in the series of repeated images one or more foreground objects (704) that occlude at least a portion of the one or more background objects; constructing (510) a background object surface image (202) at least in part by stitching together the series of repeated images to replace image regions containing background objects occluded by the one or more foreground objects; determining (512) a three-dimensional object surface (208) using the background object surface image; detecting (514) the object in a repeated image in the series of repeated images (312); calculating (516) an object segmentation (304) of the object in the one of the series of repeated images; determining (518) a visible object surface (308) using the object segmentation and the one of the series of repeated images; and A three-dimensional object model (310) is calculated (520) by estimating a volume (314) defined by the three-dimensional object surface and the visible object surface.

Images