3D imaging of an object on a target support

Abstract

Disclosed herein are medical systems 200, 300, 500, 600 having a subject support 206, a first camera 214 configured to image a first portion of a support surface of the subject support, and a second camera 216 configured to image a second portion of the support surface, the first and second portions including an overlapping region, and the subject support being movable relative to the first and second cameras along a predetermined path 218 between a first position 324, at least one intermediate position 326, and a second position 328, each of the one or more intermediate positions being located between the first and second positions. A composite three-dimensional image is constructed from camera image data acquired by the first and second cameras for at least two positions of the subject support along the predetermined path.

Description

[Technical Field]

[0001] The present invention relates to medical imaging, and more particularly to the configuration of medical imaging systems. [Background technology]

[0002] Various tomographic medical imaging techniques, such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), and single photon emission tomography (SET), allow for detailed visualization of a subject's anatomy. It is often beneficial to determine the position of a subject before the subject is inserted into a medical imaging system.

[0003] US Patent Application Publication US2022287669A1 discloses an automatic lighting arrangement for medical visualization, which includes the steps of providing a medical 3D image, providing spatial information about a region of interest in the 3D image and spatial information about a virtual camera, determining a plurality of possible arrangements of light sources using depth information based on the 3D image, the spatial information about the region of interest in the image, and the spatial information about the virtual camera, where a valid arrangement is one where shadows on the region of interest are below a predetermined threshold, and / or the determination or arrangements are based on a plurality of predetermined perceptual metrics specifically applied to the region of interest, prioritizing the determined arrangements, and selecting the arrangement with the highest priority.

[0004] US Patent Application Publication US2009 / 285357A1 discloses a 3D optical system that obtains optical and depth images of a patient while the patient is moved into a bore in order to obtain a whole body 3D mesh that is used to identify various body parts of the patient.

[0005] US Patent Application Publication US2019 / 394449A1 discloses a plastic surgery planning system that uses dual optics to obtain 3D images and distance information of a stationary patient.

[0006] US Patent Application Publication US2021 / 104055A1 discloses a system that uses 3D images obtained from a capture device to confirm the position of a patient on a table in preparation for a medical scanning procedure. Summary of the Invention [Problem to be solved by the invention]

[0007] The present invention provides a medical system, a method and a computer program according to the independent claims. Embodiments are given in the dependent claims.

[0008] The difficulty with using stereo cameras to image an object on an object support is that a pair of stereo cameras generally cannot image the entire object, so there may be unclear areas in the 3D image. [Means for solving the problem]

[0009]

[0006] Embodiments may provide an improved means for providing a composite three-dimensional image. A first camera and a second camera are used to image an object on an object support that can move along a predetermined path between a first position, at least one intermediate position, and a second position. At the first position, the first camera acquires initial first camera image data, and the second camera acquires initial second camera image data. At one of the intermediate positions, the first camera acquires additional first camera image data, and the second camera acquires additional second camera image data. The initial three-dimensional image is reconstructed from the initial first camera data and the initial second camera data.

[0010] Since the displacement along the predetermined path between the first position and the intermediate position is known, this information is used to reconstruct a first camera 3D image from the initial first camera image data and the additional first camera image data. This information is further used to reconstruct a second camera 3D image from the initial second camera image data and the additional second camera image data. A composite 3D image is constructed by combining the initial 3D image, the first camera 3D image, and the second camera 3D image.

[0011] In one aspect, the present invention provides a medical system having a subject support. The subject support has a support surface for receiving a subject. The medical system further includes a first camera configured to image a first portion of the support surface. The medical system further includes a second camera configured to image a second portion of the support surface. The first portion and the second portion have an overlapping region. The subject support is movable relative to the first camera and the second camera along a predetermined path between a first position, at least one intermediate position, and a second position. Each of the one or more intermediate positions is located between the first position and the second position.

[0012] The medical system further includes a memory including machine-executable instructions. The medical system further includes a computing system configured to control the medical system. For example, the computing system can be used to control the first camera, the second camera, and the object support. Execution of the machine-executable instructions causes the computing system to control the first camera to acquire initial first camera image data depicting an object on the object support when the object support is in a first position. Execution of the machine-executable instructions further causes the computing system to control the second camera to acquire initial second camera image data depicting the object on the object support when the object support is in the first position. Execution of the machine-executable instructions further causes the computing system to construct an initial three-dimensional image of the object using at least a portion of an overlapping area between the initial first camera image data and the initial second camera image data.

[0013] Execution of the machine-executable instructions further causes the computing system to identify regions of the object that were imaged by the initial first camera image data but were obstructed in the initial second camera image data as first obstructed regions, and identify regions of the object that were imaged by the initial second camera image data but were obstructed in the initial first camera image data as second obstructed regions. That is, in the previous step, images were acquired with the first camera and the second camera, which were then used to construct the initial three-dimensional image.

[0014] Execution of the machine-executable instructions further causes the computing system to at least once control the object support to move to one of the one or more intermediate positions. Execution of the machine-executable instructions further causes the computing system to at least once control the first camera to acquire additional first camera image data depicting the object on the object support when the object support is in one of the one or more intermediate positions.

[0015] Execution of the machine-executable instructions further causes the computing system to perform the following at least once: control the second camera to acquire additional second camera image data depicting the object on the object support when the object support is in one of one or more intermediate positions. Execution of the machine-executable instructions further causes the computing system to construct a first camera three-dimensional image of the object using the initial first camera image data and the additional first camera image data. Images of the object are taken at at least two positions using the first camera. Only images from this first camera are used to construct the first camera three-dimensional image. A potential advantage is that for a given (unknown) object, reconstruction may be able to select one other intermediate position with minimally obstructed regions, or only regions of low interest, or minimal obstructions in the regions of interest. This may be because obstructed regions often differ rather than occurring in both cameras at a single position.

[0016] Execution of the machine-executable instructions further causes the computing system to construct a second camera 3D image of the object using the initial second camera image data and the additional second camera image data. Similarly, a potential advantage is that multiple images acquired by the second camera are less likely to result in obstructed areas in the second camera 3D image.

[0017] Execution of the machine-executable instructions further causes the computing system to construct a composite 3D image, a first camera 3D image, and a second camera 3D image. The first obstructed region is at least partially replaced by the first camera 3D image. The second obstructed region is at least partially replaced by the second camera 3D image. When the object was in a first position, images from the first camera and the second camera were used to construct an initial 3D image. By moving to intermediate positions and taking additional images, a first camera 3D image and a second camera 3D image could be constructed.

[0018] The medical system may have a calibration in memory in some instances. For example, graph paper or other object with a discernible pattern can be placed on the support surface to perform the calibration. The support can then be moved from a first position to one or more intermediate positions, and images can be acquired. This can be used to create a mapping of how the surface moves from the initial image to the intermediate images as a function of the target support. If there is a target or other object on the support surface, portions of the object or object will be closer to the camera than the support surface. This may have the effect of shifting the distance between images somewhat more than if it were placed directly on the support surface and had no height.

[0019] Instead of storing the calibration in memory, the extrinsic parameters of the camera relative to the medical device are known: a 3x3 rotation matrix and a 1x3 translation vector represent the angle and position of the camera relative to the reference coordinate system of the medical device.

[0020] This can allow the coordinates of a pixel in the camera image to be transformed into the 3D coordinates of the corresponding point in the coordinate system of the medical device.

[0021] Alternatively, if the camera is not calibrated to the medical device, the height profile of the object can be obtained simply by processing the camera images. However, in this case, the absolute position is unknown. However, if the imaging system or a rigid part thereof is partially within the FOV of the first or second camera, automatic registration can be used to obtain the registration.

[0022] In another embodiment, the predetermined path is a straight path.

[0023] In another embodiment, the predetermined path is a linear path and the target support can be raised or lowered a predetermined amount while traversing the linear path.

[0024] In another embodiment, the first and second cameras may have portions of the object occluded in their respective images, which has the advantage of providing a complete three-dimensional image of the object when the object support is moved to at least one of the intermediate positions.

[0025] In another embodiment, the images used to construct the composite 3D image are stitched together to provide a more complete 3D image of the object. In some cases, portions of the images can be connected. If the regions of the object in these various images overlap, one option is to calculate the average value of the images, which reduces the amount of noise in the composite 3D image.

[0026] In another embodiment, execution of the machine-executable instructions further causes the computing system to additionally perform at least one construction of an additional three-dimensional image of the object using the additional first camera image data and the additional second camera image data. Execution of the machine-executable instructions further causes the computing system to additionally use the additional three-dimensional image when constructing the composite three-dimensional image. This may be useful, for example, for averaging with other three-dimensional images when constructing the composite three-dimensional image. This may have the effect of reducing the amount of noise in the composite three-dimensional image, which may, for example, provide a means for more accurately constructing a composite three-dimensional image of the object.

[0027] In another embodiment, the composite 3D image has an average region constructed by averaging overlapping regions of two or more of the initial 3D image, the first camera 3D image, the second camera 3D image, the additional 3D image, and previous iterations of the composite 3D image. For example, as the object is moved to multiple intermediate positions, there will be additional images available that can be averaged into the existing composite 3D image. This can provide a means of generating a much higher resolution or more accurate composite 3D image of the object.

[0028] In another embodiment, the memory further comprises an anatomical keypoint module configured to output a set of anatomical keypoints of the object based on receiving any one of the initial first camera image data, the initial second camera image data, the additional first camera image data, and the additional second camera image data. Execution of the machine-executable instructions further causes the computing system to receive initial first camera keypoint data based on inputting the initial first camera image data to the anatomical keypoint module, and receive initial camera keypoint data based on inputting the initial second camera image data to the anatomical keypoint module.

[0029] This embodiment is considered advantageous because excellent algorithms are available for identifying anatomical keypoints of a subject. By identifying them in both the first and second cameras, the stereo or three-dimensional location of the anatomical keypoints can be determined. This is particularly advantageous because it provides an improved means for aligning various three-dimensional images to generate a composite three-dimensional image, and can provide a means for detecting subject motion or other problems during the process of acquiring the various images and constructing the composite three-dimensional image.

[0030] Anatomical keypoints, as used herein, encompass anatomical landmarks or locations located within an object. Anatomical keypoints can incorporate the locations of various joints or surface landmarks (eyes, ears, nose) of an object. A camera image depicts an object and provides a depiction of the object's appearance or surface (texture and / or shape). For example, the camera image is 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. An infrared or thermal image can be combined with a three-dimensional image.

[0031] In another embodiment, the anatomical keypoint module includes a neural network configured to output a separate anatomical keypoint coordinate probability map for each of at least one anatomical keypoint coordinate based on receiving an image of the object on the object support. For example, various joints and locations within the object can be included in the anatomical keypoint coordinates. For each set, a separate image or map is output, and the probability that the joint or anatomical location is at a particular location is output on this map. The most likely location can be obtained, for example, by taking the maximum probability. This system can be particularly good at locating joints or other anatomical locations when they are unclear or partially obscured, such as when there is clothing or a blanket placed on the object.

[0032] Execution of the machine-executable instructions further causes the computing system to receive distinct anatomical keypoint coordinate probability maps based on the input of 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.

[0033] Training a neural network can be accomplished by having images of a subject and then having a training keypoint coordinate probability map for each of at least one labeled anatomical keypoint coordinate. For example, a series of images of different subjects in slightly different poses, wearing different clothes, covered with a blanket, or with their body partially obscured, can be used. An operator can go and mark various points to indicate the location of the anatomical keypoint coordinates. This can be used, for example, in a deep learning algorithm to train a neural network.

[0034] In another embodiment, execution of the machine-executable instructions further results in the computing system calculating one of one or more intermediate positions using the positions of anatomical keypoints in the first camera keypoint data and / or the positions of anatomical keypoints in the initial second camera keypoint data. For example, the position of a first obstructed region can be referenced using the initial first camera keypoint data, and the position of a second obstructed region can be located using the initial second camera keypoint data. These keypoints are located in separate images, so that the positions of the obstructed regions in the images can be inferred. Knowing the positions of these obstructed regions, intermediate positions can be determined to obtain appropriate positions for acquiring additional first camera image data and additional second camera image data.

[0035] In another embodiment, execution of the machine-executable instructions further causes the computing system to receive image-guided treatment position data representing predetermined anatomical keypoints of the subject relative to the subject support, and execution of the machine-executable instructions further causes the computing system to detect subject positioning errors by comparing the predetermined anatomical keypoints with the initial first camera keypoint data and / or the initial second camera keypoint data.

[0036] Execution of the machine-executable instructions further causes the computing system to provide a warning signal if a subject positioning error is detected. For example, the warning signal may cause a user interface, audio system, or other human interface device to provide the warning signal. In other cases, it may be used to disable a radiation therapy device if the subject moves too much. In this embodiment, the position of the subject on the subject support is compared to data or keypoints acquired when the subject is positioned on the subject support. This helps prevent errors in positioning the subject's position during radiation therapy. Without the use of anatomical keypoints, it may be difficult to detect subject movement with a camera system because of other moving parts or objects in the image and shadows that may obscure the subject's position.

[0037] In another embodiment, execution of the machine-executable instructions further causes the computing system to receive additional first camera keypoint data based on inputting the additional first camera image data to the anatomical keypoint module. Execution of the machine-executable instructions further causes the computing system to receive additional second camera keypoint data based on inputting the additional second camera image data to the anatomical keypoint module. Execution of the machine-executable instructions further causes the computing system to detect a subject motion state between the first position of the subject support and one of the one or more intermediate positions by detecting a difference between the initial first camera keypoint data and the additional first camera keypoint data and / or a difference between the initial second camera keypoint data and the additional second camera keypoint data.

[0038] Because the position of the object support is known, simple translation can be used to compare the coordinates between the initial first camera keypoint data and the additional first camera keypoint data, or the difference between the initial second camera keypoint data and the additional second camera keypoint data. Execution of the machine-executable instructions further causes the computing system to exclude at least a portion of the first camera 3D image and / or the second camera 3D image from the composite 3D image if a motion state of the object is detected. In some examples, if the object moves, certain 3D images or image data may be discarded or excluded. In other cases, not all images need to be discarded, for example, if the object simply moves its hands or feet. For example, if a certain keypoint moves, the vicinity of this keypoint can be identified, and image data in the vicinity of this keypoint can be excluded from constructing the composite 3D image of the object.

[0039] In another embodiment, the target support has a maximum width perpendicular to the predetermined path, and the stereo baseline is between 10% and 200% of the maximum width of the target support. This embodiment is advantageous because it can provide an effective means of positioning the first and second cameras to obtain high-quality three-dimensional images.

[0040] In another embodiment, the stereo baseline is preferably between 50% and 150% of the maximum width of the target support. Selecting a stereo baseline width between 50% and 150% can provide an effective means of eliminating obstructed areas.

[0041] In another embodiment, execution of the machine-executable instructions further causes the computing system to identify at least one stationary object region by detecting stationary voxels between the initial first camera image data and the additional first camera image data, and thereby detecting stationary voxels between the initial second camera image data and the additional second camera image data. The at least one stationary object region is excluded from the composite three-dimensional image of the object. The object support is moved between the first position and an intermediate position. If the object appears stationary in images acquired when the object support is in a different position, this means that the object is actually stationary. Such objects can be excluded because, for example, they are not part of the object or are not objects moved by the object support.

[0042] In another embodiment, the medical system further comprises a medical imaging system for acquiring measurement data from the imaging volume. The medical imaging system is, for example, a tomographic medical imaging system. When the subject support is in the second position, at least a portion of the support surface is within the imaging volume. Execution of the machine-executable instructions further causes the computing system to control the subject support to move to the second position. Execution of the machine-executable instructions further causes the computing system to control the medical imaging system to acquire the measurement data.

[0043] In another embodiment, execution of the machine-executable instructions further causes the computing system to reconstruct a medical image from the measurement data.

[0044] In another embodiment, execution of the machine-executable instructions further causes the computing system to calculate a scanning isocenter using the composite three-dimensional image of the object.

[0045] In another embodiment, execution of the machine-executable instructions further causes the computing system to use the synthetic three-dimensional image for positioning and orienting an object.

[0046] In another embodiment, execution of the machine-executable instructions further causes the computing system to perform collision risk prediction in a medical imaging system using the synthetic three-dimensional image.

[0047] In another embodiment, when the medical system is a magnetic resonance imaging system, the computing system uses the synthetic three-dimensional images to compute the SAR estimates using the object model.

[0048] In another embodiment, execution of the machine-executable instructions further causes the computing system to calculate a weight of the subject using the composite three-dimensional image of the subject.

[0049] In another embodiment, execution of the machine-executable instructions further causes the computing system to calculate a height of the subject using the composite three-dimensional image of the subject.

[0050] In another embodiment, the medical imaging system is a magnetic resonance imaging system.

[0051] In another embodiment, the medical imaging system is a positron emission tomography system.

[0052] In another embodiment, the medical imaging system is a single photon emission computed tomography system.

[0053] In another embodiment, the medical imaging system is a computed tomography system.

[0054] In another embodiment, the medical imaging system is a combination positron emission tomography system and magnetic resonance imaging system.

[0055] In another embodiment, the medical imaging system is a combination positron emission tomography system and a computed tomography system.

[0056] In another embodiment, the medical imaging system is a combined computed tomography system and a radiation therapy system.

[0057] In another embodiment, the medical imaging system is a combination computed tomography system and a positron emission tomography system.

[0058] In another embodiment, the medical imaging system is a combined magnetic resonance imaging system and a radiation therapy system.

[0059] In another embodiment, the medical imaging system is part of an image-guided radiation therapy system.

[0060] In another aspect, the present invention provides a method for controlling a medical system. The medical system includes a subject support. The subject support has a support surface for receiving a subject. The medical system further includes a first camera configured to image a first portion of the support surface. The medical system further includes a second camera configured to image a second portion of the support surface. The first and second portions have an overlapping region. The subject support is movable relative to the first and second cameras along a predetermined path between a first position, at least one intermediate position, and a second position. Each of the one or more intermediate positions is located between the first and second positions.

[0061] The method includes controlling a first camera to acquire initial first camera image data depicting an object on the object support when the object support is in a first position, controlling a second camera to acquire initial second camera image data depicting the object on the object support when the object support is in the first position, and constructing an initial three-dimensional image of the object using at least a portion of an overlapping area of ​​the initial first camera image data and the initial second camera image data.

[0062] The method further includes identifying a first occluded region of the object imaged by the initial first camera image data but occluded in the initial second camera image data. The method further includes identifying a region of the object imaged by the initial second camera image data but occluded in the initial first camera image data as a second occluded region. Execution of the machine-executable instructions further causes the computing system to perform at least one of the following: controlling the object support to move to one or more intermediate positions; controlling the first camera to acquire additional first camera image data depicting the object on the object support when the object support is in one of the one or more intermediate positions; controlling the second camera to acquire additional second camera image data depicting the object on the object support when the object support is in one of the one or more intermediate positions; constructing a first camera three-dimensional image of the object using the initial first camera image data and the additional first camera image data. This also includes constructing a second camera 3D image of the object using the initial second camera image data and the additional second camera image data. And finally, this also includes constructing a composite 3D image of the object using the initial 3D image, the first camera 3D image, and the second camera 3D image. The first obstructed region is at least partially replaced by the first camera 3D image. The second obstructed region is at least partially replaced by the second camera 3D image.

[0063] In another aspect, the present invention provides a computer program product including machine-executable instructions for execution by a computing system that controls a medical system. The computer program product can be stored, for example, on a non-transitory storage medium. The medical system includes a subject support. The subject support has a support surface for receiving a subject. The medical system further includes a first camera configured to image a first portion of the support surface. The medical system further includes a second camera configured to image a second portion of the support surface. The first and second portions have an overlapping region. The subject support is movable relative to the first and second cameras along a predetermined path between a first position, at least one intermediate position, and a second position. Each of the one or more intermediate positions is located between the first and second positions.

[0064] Execution of the machine-executable instructions causes the computing system to control a first camera to acquire initial first camera image data depicting an object on the object support when the object support is in a first position. Execution of the machine-executable instructions further causes the computing system to control a second camera to acquire initial second camera image data depicting the object on the object support when the object support is in the first position. Execution of the machine-executable instructions further causes the computing system to construct an initial three-dimensional image of the object using at least a portion of an overlapping region between the initial first camera image data and the initial second camera image data. Execution of the machine-executable instructions further causes the computing system to identify a region of the object that was captured by the initial first camera image data but was occluded in the initial second camera image data as a first occluded region.

[0065] Execution of the machine-executable instructions further causes the computing system to identify a region of the object imaged by the initial second camera image data but obscured in the initial first camera image data as a second obstructed region. Execution of the machine-executable instructions further causes the computing system to perform the following at least one time, including controlling the object support to move to one or more intermediate positions. This further includes controlling the first camera to acquire additional first camera image data depicting the object on the object support when the object support is in one of the one or more intermediate positions. This also includes controlling the second camera to acquire additional second camera image data depicting the object on the object support when the object support is in one of the one or more intermediate positions. This includes constructing a first camera three-dimensional image of the object using the initial first camera image data and the additional first camera image data. This further includes constructing a second camera three-dimensional image of the object using the initial second camera image data and the additional second camera image data. This further includes constructing a composite 3D image of the object using the initial 3D image, the first camera 3D image, and the second camera 3D image, where at least a first obstructed region is at least partially replaced by the first camera 3D image, and where a second obstructed region is at least partially replaced by the second camera 3D image.

[0066] It should be understood that one or more of the above-described embodiments of the present invention may be combined, provided that the combined embodiments are not mutually exclusive.

[0067] As will be appreciated by one skilled 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 circuits, modules, or systems. Furthermore, 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.

[0068] Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium capable of storing instructions executable by a processor or computing system of a computing device. The computer-readable storage medium may also be referred to as a computer-readable non-transitory storage medium. The computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, the computer-readable storage medium may also store data accessible by the 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 computer system register files. 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, and DVD-R disks. The term computer-readable storage medium refers to various types of storage media that can be accessed by a computer device over a network or communications link. For example, data may be obtained via a modem, the Internet, or a local area network. The computer-executable code embodied in the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0069] A computer-readable signal medium may include a propagated data signal having computer-executable code embodied therein, for example, as part of a baseband or 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.

[0070] "Computer memory" or "memory" is an 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 computer-readable storage medium. In some embodiments, computer storage can be computer memory, or vice versa.

[0071] As used herein, a "computing system" encompasses an electronic element capable of executing a program or machine-executable instructions or computer-executable code. References to a computing system with the example of a "computing system" should be interpreted as potentially including multiple computing systems or processing cores. A computing system is, for example, a multi-core processor. A computing system can refer to a collection of computing systems within one 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 having a processor or computing system. Machine-executable code or instructions can be executed by multiple computing systems or processors, which may be within the same computing device or even distributed across multiple computing devices.

[0072] 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, Smalltalk, C++, and conventional 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 is in the form of a high-level language or in a pre-compiled form, used in conjunction with an interpreter that generates the machine-executable instructions on the fly. In other examples, the machine-executable instructions or computer-executable code may be in the form of programming for a programmable logic gate array.

[0073] 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 and 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).

[0074] Aspects of the present invention will be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block, or a portion of a block, of the flowcharts, illustrations, and / or block diagrams, where applicable, can be implemented by computer program instructions in the form of computer-executable code. It will also be understood that combinations of blocks in different flowcharts, illustrations, and / or block diagrams are possible, if not mutually exclusive. These computer program instructions can be provided to a general-purpose computer, special-purpose computer, or other programmable data processing device computing system to generate a machine, wherein the instructions, when executed by the computer or other programmable data processing device computing system, create means for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0075] 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 including instructions that implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0076] The machine-executable instructions or computer program instructions are loaded into a computer, other programmable data processing device, or other device to produce a computer-implemented process, causing a series of operational steps to be performed on the computer, other programmable device, or other device. The instructions, which execute on the computer or other programmable device, provide a process for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0077] As used herein, a "user interface" is an interface that allows a user or operator to interact with a computer or computer system. A "user interface" is also referred to as a "human interface device." A user interface can provide information or data to an operator and / or receive information or data from an operator. A user interface can allow input from an operator to be received by a computer and can provide output from the computer to a user. In other words, a user interface allows an operator to control or manipulate a computer, and the interface allows the computer to show the effects of the operator's control or manipulation. Displaying 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 elements that allow information or data to be received from an operator.

[0078] 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 equipment. A hardware interface may allow a computing system to send control signals or commands to external computing devices and / or equipment. A hardware interface may also allow a computing system to exchange data with external computing devices and / or equipment. 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 RS-232 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.

[0079] As used herein, "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. Examples of displays include, but are not limited to, computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), storage 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.

[0080] Measurement data is defined herein as recorded measurements made by a tomographic medical imaging system that describe an object. Medical imaging data can be reconstructed into a medical image. A medical image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained in the medical imaging data. This visualization can be performed using a computer.

[0081] 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 measurement data.

[0082] A magnetic resonance imaging (MRI) image or MR image is defined herein as a reconstructed two-dimensional, three-dimensional, or four-dimensional visualization of anatomical data contained in magnetic resonance imaging data, which visualization can be performed using a computer. [Brief explanation of the drawings]

[0083] [Figure 1] FIG. 1 illustrates a two-dimensional rendering of a three-dimensional image. [Figure 2] FIG. 1 illustrates an example of a medical system. [Figure 3] FIG. 1 illustrates a further example of a medical system. [Figure 4] FIG. 4 is a flowchart illustrating a method of using the medical system of FIG. 3. [Figure 5] FIG. 1 illustrates a further example of a medical system. [Figure 6] FIG. 1 illustrates a further example of a medical system. [Figure 7] FIG. 7 is a flowchart illustrating a method of using the medical system of FIG. 6. DETAILED DESCRIPTION OF THE INVENTION

[0084] Preferred embodiments of the present invention will now be described, by way of example only, with reference to the following drawings, in which:

[0085] Like numbered elements in the figures are equivalent elements or perform the same function. An element previously described is not necessarily described in a later figure if the function is equivalent.

[0086] Stereo-based depth sensing, including structured light enhancement techniques, suffers from shadows in areas where both cameras do not have line-of-sight. Typically, these problem areas occur at the edges of objects. This effect is illustrated in Figure 1.

[0087] FIG. 1 shows an exemplary 2D rendering of a 3D image. This image is a 3D image of a cat. There are two black bands 102 on either side of the cat. These black bands are obstructed regions 102. The reason for these obstructed regions 102 is that in these regions it is not visible to both cameras. Therefore, a 3D image 100 cannot be constructed within the obstructed regions 102. These are essentially holes in the 3D image.

[0088] To overcome this, AI-based algorithms have recently been proposed that fill the resulting data gaps with reasonable values. The drawback of this method is that these values ​​are not actually measured and may therefore be subject to error. A similar problem occurs in the outer regions where the FOVs of the two cameras do not overlap. In this case, there is no stereo data that can be matched from one camera to the other. This results in a reduced FOV relative to the native FOV of each camera in the stereo pair.

[0089] While these commonly known stereoscopic drawbacks are generally difficult to overcome for robotic navigation purposes, they can be overcome in the context of medical imaging examinations involving a patient support that can be automatically moved in a controlled manner along defined axes. Therefore, no additional sensors are required to fill data gaps with real data. Instead, the table motion axes are used to acquire additional images from each of the two cameras. These additional images, combined with the known table displacement between image acquisitions, allow for data gaps to be filled and a dense depth map to be created with the same resolution as the native resolution of the cameras. One of the key insights and tricks here is the selection of any two appropriate time points from [tStart, tEnd] for any table movement event. Such a table movement event is a phase in which the patient is immobilized or stabilized and the examination setup is not changed. Therefore, depth errors due to movement are minimized. There may be multiple such events during examination preparation, at least one of which is the table insertion from the out-down position to the up-in position.

[0090] FIG. 2 shows a simplified diagram of a medical system 200. Not all elements of the medical system 200 are shown in FIG. 2. A top view 202 and a side view 204 are shown adjacent to each other. The medical system 200 is shown as having a subject support 206 with a support surface 208. A subject 210 resides on the support surface 208. The subject support 206 is shown in a first position and can be moved along a predetermined path 218 to position the subject 210 within a medical imaging system 212. A first camera 214 and a second camera 216 are positioned above the support surface 208 and can image the top of the subject 210 and exposed portions of the support surface 208. A baseline 220 perpendicular to the predetermined path is between the two cameras 214, 216. Object 210 has a first obstructed region 222, which is an area that can be viewed by camera 1 but not camera 2 216, and a second obstructed region 224, which is an area that can be viewed by camera 2 216 but not camera 1 214. Object support 206 has a width 226. The width of baseline 220 can be defined relative to the width of object support 226. In side view 204, the fields of view of camera 1 214 and camera 2 216 overlap.

[0091] It can be seen that when subject support 206 is in the first position, obstructed regions 222 and 224 cannot be three-dimensionally imaged. However, if subject support 206 is moved along predetermined path 218 and multiple images are acquired, these multiple images from either camera 1, 214 or camera 2, 216 can be used to construct additional three-dimensional images that can be used to fill in obstructed regions 222, 224.

[0092] The two cameras 214, 216 are connected to a computing system that may be connected to MR scanning (or other imaging modality) hardware and software. The computing system receives the table position and camera images. The cameras 214, 216 also receive the table motion state or position, and any number of camera images can be selected for a given table movement event within the time interval [tStart, tEnd]. The disparity between pairs of images during this event is calculated. The image frames may be adjacent or at any time during the table movement. A neural network can optionally be used to determine suitable frame candidates, where the optical flow in the images is limited to coherent table movements. For example, software for determining the location of anatomical keypoints can be used for this determination.

[0093] The distance traveled between any two acquired images can be used to convert the calculated disparity into a depth map. Stationary parts of the scene have the most robust stereo matching performance, resulting in infinite distance. These regions are filtered out. Additionally, the table region can be calibrated, and disparity calculations can be limited to the table region. Multiple image frames during table movement can be used to identify incoherent motion or static obstacles. Disparity information from multiple image pairs can be used to construct a dense disparity map by removing spurious incoherent motion regions or static obstacles and filling in information with reliable values ​​from other image pairs as needed. Connecting this technique to a patient keypoint detection AI network can focus this gap filling on specific parts of the examination area or examination setup. Furthermore, the patient keypoint detection network can be used to detect patient motion events during table movement, for example, by comparing relative keypoint positions between selected camera images. This is useful to ensure that patient motion does not impair the results of the proposed algorithm.

[0094] One of its fundamental advantages over stereo matching with a static baseline is the availability of multiple baseline measurements for each image patch. This makes it possible to cross-validate the confidence values ​​of the stereo matches, reduce noise by averaging, or select the most reliable measurements from a set of images. Any number of matching computations can be elegantly parallelized using current GPU architectures.

[0095] FIG. 3 illustrates an example of a medical device 300. The medical device is shown as having a subject support 206. The subject support 206 has an actuator 304 configured to move the subject support 206 a controlled distance or displacement along a predetermined path 218. A subject 210 lies on a support surface 208. The support surface 208 faces two cameras 214, 216. A side view 204 is shown, with the fields of view of the two cameras 214, 216 overlapping. The cameras 214, 216 can capture images of the support surface 208 and / or the subject 210 when the subject support 206 is in various positions. The medical device 300 is further shown as including a computer 312. The computer 312 has a hardware interface 314 that allows the computing system 316 to communicate with and control other elements of the medical device 300.

[0096] Specifically, in this figure, the hardware interface 314 is shown interfacing with two cameras 314, 316 to acquire images, and with an actuator 304 to control the position of the subject support 206. In other examples or embodiments, the hardware interface 314 may be used to control additional elements, such as the medical imaging system 212 (or scanner).

[0097] Computing system 316 is in communication with hardware interface 314, memory 320, and optional user interface 318. Memory 320 can be any combination of memory accessible to computing system 316. This includes main memory, cache memory, and non-volatile memory such as flash RAM, a hard drive, or other storage device. In some examples, memory 320 is considered a non-transitory computer-readable medium.

[0098] Arrow 322 indicates the height or distance above the support surface 208. Dashed line 324 indicates the position of the end of the subject support 206 when the subject support is in a first position 324. Dashed line 330 indicates the position of the end of the subject support 206 when the subject support is in a second position 330. Dashed line 328 indicates the current position of the end of the subject support 206. The subject support 206 is currently in an intermediate position 328. As the subject support 206 is moved to different displacements 332, 334 relative to the first position 324, images are acquired by the cameras 214, 216. Portions of the subject 210 closer to the cameras 214, 216 than the support surface 208 may move more than the support surface 208 between images.

[0099] For example, a graph or other pattern can be placed on the support surface 208 and the support surface imaged at multiple positions. This can provide information about how the displacements 332, 334 relate to pixel displacements in the image of the support surface 208. When the object 210 is placed on the support surface 208, pixels representing the same portion of the object 210 will move by a larger amount than they would if only the support surface 208 were moved. This larger movement of individual pixels or groups of pixels can be used to develop a three-dimensional measurement of the distance of the surface of the object 210 above 322 the support surface 208.

[0100] Memory 320 is shown as including machine-executable instructions 340. The machine-executable instructions enable computing system 316 to perform various computational tasks, such as calculating a three-dimensional image from multiple two-dimensional images. Memory 320 is further shown as including initial first camera image data 342 and initial second camera image data 344. Memory 320 is further shown as including initial three-dimensional image 346 calculated from initial first camera image data 342 and initial second camera image data 344. After subject support 102 was moved to intermediate position 128, multiple other images were acquired. Memory 320 is further shown as including additional first camera image data 348 and additional second camera image data 350. Memory 320 is further shown as including first camera three-dimensional image 352 calculated from initial first camera image data 342 and additional first camera image data 348.

[0101] Memory 320 is further shown to include a second camera 3D image 354 calculated from initial second camera image data 344 and additional second camera image data 350. Memory 320 is further shown to include an optional additional 3D image calculated from first camera 3D image 352 and second camera 3D image 354. Memory 320 is further shown to include a composite 3D image 358 calculated from initial 3D image 346, first camera 3D image 352, second camera 3D image 354, and optionally additional 3D image 356. Composite 3D image 358 can be constructed in a patchwork manner, taking various portions from the various 3D images 346, 352, 354, 356. In some cases where the images overlap, they are averaged. Memory 320 is further shown to include an optional control signal 360 generated using composite 3D image 358. The composite three-dimensional image 358 is useful, for example, for determining object positioning, object mass to determine whether SAR issues will occur in magnetic resonance imaging, or even to detect the probability of the object 210 colliding with a medical imaging system.

[0102] Figure 4 shows a flowchart illustrating a method of operation of the medical system 300 of Figure 3. This method is also applicable to the medical system 200 of Figure 2. First, in step 400, when the subject support 206 is in the first position 324, the first camera 214 is controlled to acquire initial first camera image data 342. Next, in step 402, when the subject support 206 is in the first position 324, the second camera 216 is controlled to acquire initial second camera image data 344. Next, in step 406, an initial three-dimensional image 346 is constructed using overlapping regions of the initial first camera image data 342 and the initial second camera image data 344.

[0103] Next, in step 406, a first obstructed region 222 is identified in the initial second camera image data 344. Next, in step 208, a second obstructed region 224 is identified in the initial first camera image data 342. The following steps 410, 412, 414, 416, 418, 420, 422 are repeated for at least one intermediate position. In step 410, the target support is controlled to move to one of the one or more intermediate positions 328. Next, in step 412, the first camera 414 is controlled to acquire additional first camera image data 348. Next, in step 414, the second camera 216 is controlled to acquire additional second camera image data 350. Next, in step 416, a first camera three-dimensional image 352 is constructed from the initial first camera image data 342 and the additional first camera image data 348. Next, in step 418, a second camera 3D image 354 is constructed from the initial second camera image data 344 and the additional second camera image data 350. Step 420 is an optional step. In step 420, an additional 3D image 356 is constructed from the additional first camera image data 348 and the additional second camera image data 350. Finally, in step 422, a composite 3D image 358 of the object is constructed using the initial 3D image 346, the first camera 3D image 352, and the second camera 3D image 354. In some examples, the composite 3D image 358 can also be constructed using the additional 3D image 356. The first obstructed region 222 is at least partially replaced by the first camera 3D image 352. The second obstructed region 224 is at least partially replaced by the second camera 3D image 354. Steps 410 , 412 , 414 , 416 , 418 , 420 , 422 can be repeated to reduce the size of the obstructed regions 222 , 224 and / or to reduce noise in the composite three-dimensional image 358 .

[0104] FIG. 5 illustrates a further example of a medical device 500. The illustrated medical device 500 is similar to the medical device 200 of FIG. 2, except for the addition of a medical imaging system 212. The medical imaging system has a medical imaging volume 504 from which measurements can be taken. The subject support 206 is configured to move at least a portion of the subject 210 into the medical imaging volume 504. In this example, the medical imaging system 212 is cylindrical and has a bore 506 through which the subject 210 can be moved using the subject support 206. However, this is not necessary, and not all medical imaging systems 212 need to be cylindrically symmetric as shown in this figure. Additionally, note that the camera 110 is currently attached to the medical imaging system 302 and oriented at an oblique angle relative to the support surface 108. The memory 320 is further shown as containing measurement data 540 acquired when the subject 210 was at least partially within the imaging volume 504. The memory 320 is further shown as containing a medical image 542 reconstructed from the measurement data 540.

[0105] FIG. 6 illustrates a further example of a medical device 600. The medical device 600 of FIG. 6 is similar to the medical device 500 of FIG. 5. However, in this example, the medical imaging system 212 is a magnetic resonance imaging system 212′. The magnetic resonance imaging system 212′ has a main magnet 604, which may be referred to as a magnet. The magnet 404 is a superconducting cylindrical magnet 604 with a bore 506 therethrough. Different types of magnets may be used. Within the cryostat of the cylindrical magnet is a collection of superconducting coils. Within the bore 506 of the cylindrical magnet 604 is an imaging volume 504, where the magnetic field is strong and uniform enough to perform magnetic resonance imaging.

[0106] Also within the magnet bore 506 are a set of magnetic field gradient coils 610 used to acquire magnetic resonance data that spatially encodes magnetic spins within the imaging volume 504 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 separate coil sets for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils 610. The current supplied to the magnetic field gradient coils 610 is controlled as a function of time and can be ramped or pulsed.

[0107] A magnetic resonance coil or antenna 614 adjacent to the imaging volume 504 manipulates the orientation of magnetic spins within the imaging volume 504 and functions as a radio frequency antenna for receiving radio transmissions from the spins within the imaging volume 504. The radio frequency coil may have multiple coil elements. The radio frequency antenna is sometimes referred to as a channel. The coil 614 is connected to a radio frequency transceiver 616. The coil 614 and the radio frequency transceiver 616 may have separate transmitters and receivers. The coil 614 and the transceiver 616 form a radio frequency system.

[0108] If the coil 614 is composed of multiple coil elements, they can be used individually to acquire magnetic resonance data. Thus, the coil elements can be used in parallel imaging magnetic resonance techniques. An optional body coil 615 is also shown. The body coil 615 is useful in parallel imaging techniques because it can acquire data simultaneously with each individual coil element and be used to calculate a set of coil sensitivities. Magnetic resonance data can be acquired from within the imaging volume 504. The magnetic resonance data is an example of medical image data.

[0109] Within the bore 506 of the magnet 604, the subject support 206 is shown supporting a portion of the subject 210 within the imaging volume 504. The subject support 206 is in a second position 330.

[0110] The transceiver 616, the actuator of the subject support 604, the two cameras 214, 216, the actuator 304, and the gradient controller 612 are shown connected to a hardware interface 314 of the computer system 312. Within the memory 320 are machine-executable instructions 140.

[0111] The computer memory 320 is further shown as including pulse sequence commands 640. The pulse sequence commands 640 are either instructions or data that can be converted into instructions that can be used to control the magnetic resonance imaging system 212' to acquire measurement data 540. In this case, the measurement data 540 is k-space data 540'. In this example, the medical image 542 is a magnetic resonance image 542'.

[0112] Within imaging volume 504 is field of view 608. Field of view 608 can be identified, for example, using synthetic three-dimensional image 358 before the object is moved to second position 330.

[0113] FIG. 7 shows a flowchart illustrating a method similar to the method shown in FIG. 4. In the method shown in FIG. 7, first, method steps 400 to 422 are performed. After step 422, step 600 is performed. In step 600, the subject support 206 is moved to a second position 330. Next, in step 602, the medical imaging system 212 is controlled to acquire measurement data 642. In this example, the measurement data 642 is k-space data. Finally, in step 604, the measurement data 642 is reconstructed into a medical image 644. In this example, the medical image is a magnetic resonance image 644.

[0114] While the invention has been illustrated and described in detail in the drawings and description, such illustration and description are exemplary or explanatory only and are not restrictive. The invention is not limited to the disclosed embodiments.

[0115] 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 figures, the description, 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 a claim. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means 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, supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless communication systems. Any reference signs in the claims should not be interpreted as limiting the scope of the invention.

Claims

1. 1. A healthcare system comprising: an object support portion, the object support portion including a support surface for receiving an object; a first camera configured to image a first portion of the support surface; a second camera that images a second portion of the support surface, the first portion and the second portion including an overlapping region, the subject support being movable relative to the first camera and the second camera along a predetermined path between a first position, at least one intermediate position, and a second position, each of the one or more intermediate positions being located between the first position and the second position; a memory containing machine-executable instructions; and a computing system configured to control the medical system, wherein execution of the machine-executable instructions causes the computing system to: controlling the first camera to acquire initial first camera image data depicting an object on the object support when the object support is in the first position; controlling the second camera to acquire initial second camera image data depicting an object on the object support when the object support is in the first position; constructing an initial three-dimensional image of the object using at least a portion of an overlap region of the initial first camera image data and the initial second camera image data; identifying a region of the object that is captured by the initial first camera image data but is occluded in the initial second camera image data as a first obstructed region; and identifying a region of the object captured by the initial second camera image data but obstructed in the initial first camera image data as a second obstructed region; Execution of the machine-executable instructions further comprises at least one time causing the computing system to: controlling the subject support to move to one of the one or more intermediate positions; controlling the first camera to acquire additional first camera image data depicting an object on the object support when the object support is in one of the one or more intermediate positions; controlling the second camera to acquire additional second camera image data depicting an object on the object support when the object support is in one of the one or more intermediate positions; constructing a first-camera three-dimensional image of the object using the initial first-camera image data and the additional first-camera image data; constructing a second-camera three-dimensional image of the object using the initial second-camera image data and the additional second-camera image data; A medical system that performs constructing a composite 3D image of the object using the initial 3D image, the first camera 3D image, and the second camera 3D image, wherein the first obstructed region is at least partially replaced by the first camera 3D image and the second obstructed region is at least partially replaced by the second camera 3D image.

2. 2. The medical system of claim 1, wherein execution of the machine-executable instructions further causes the computing system to additionally perform, at least once, constructing an additional three-dimensional image of the object using additional first camera image data and additional second camera image data, and wherein the composite three-dimensional image is additionally constructed using the additional three-dimensional images of the object.

3. 3. The medical system of claim 2, wherein the composite three-dimensional image has an average region constructed by averaging two or more overlapping regions of the initial three-dimensional image, the first camera three-dimensional image, the second camera three-dimensional image, the added three-dimensional image, and a previous iteration of the composite three-dimensional image.

4. The memory further comprises an anatomical key point module that outputs a set of anatomical key points of the object based on receiving any one of the initial first camera image data, the initial second camera image data, the additional first camera image data, and the additional second camera image data, and execution of the machine-executable instructions further causes the computing system to: receiving initial first camera keypoint data based on inputting the initial first camera image data into the anatomical keypoint module; and 4. The medical system of claim 1, further comprising: receiving initial second camera keypoint data based on inputting the initial second camera image data into the anatomical keypoint module.

5. 5. The medical system of claim 4, wherein execution of the machine-executable instructions further causes the computing system to calculate one of the one or more intermediate positions using positions of anatomical keypoints in the initial first camera keypoint data and / or using positions of anatomical keypoints in the initial second camera keypoint data.

6. Execution of the machine-executable instructions further causes the computing system to: receiving image-guided treatment position data representative of predetermined anatomical key points of the subject relative to the subject support; detecting object positioning errors by comparing the predetermined anatomical keypoints with the initial first camera keypoint data and / or the initial second camera keypoint data; and 6. The medical system of claim 4 or 5, which provides for providing a warning signal if a positioning error of the object is detected.

7. Execution of the machine-executable instructions further causes the computing system to: receiving additional first camera keypoint data based on inputting the additional first camera image data into the anatomical keypoint module; receiving additional second camera keypoint data based on inputting the additional second camera image data into the anatomical keypoint module; detecting a difference between the initial first camera key point data and the additional first camera key point data and / or a difference between the initial second camera key point data and the additional second camera key point data, thereby detecting an object motion state between the first position of the object support and one of the one or more intermediate positions; The medical system of claim 4 , 5 or 6 , wherein when the target motion state is detected, at least a portion of the first camera 3D image and / or the second camera 3D image is excluded from the composite 3D image.

8. The medical system according to claim 1 , wherein the first camera and the second camera form a stereo baseline perpendicular to a predetermined path.

9. the target support has a maximum width perpendicular to the predetermined path; the stereo baseline is between 10% and 200% of the maximum width of the target support; The medical system of claim 8 , wherein the stereo baseline is preferably between 50% and 150% of the maximum width of the subject support.

10. 10. The medical system of claim 1, wherein execution of the machine-executable instructions further causes the computing system to identify at least one stationary object region by detecting stationary voxels between the initial first camera image data and the additional first camera image data and / or by detecting stationary voxels between the initial second camera image data and the additional second camera image data, and wherein the at least one stationary object region is excluded from the composite three-dimensional image of the subject.

11. The medical system further comprises a medical imaging system for acquiring measurement data from an imaging volume, and when the subject support is in the second position, at least a portion of the support surface is within the imaging volume, and execution of the machine-executable instructions further comprises the computing system: controlling the subject support to move to the second position; controlling the medical imaging system to obtain the measurement data; and A medical system according to any one of claims 1 to 10, preferably providing for the reconstruction of a medical image from said measurement data.

12. 12. The medical system of claim 10 or 11, wherein execution of the machine-executable instructions further causes the computing system to perform any one of: calculating an isocenter of the object; determining a position and / or orientation of the object; performing a collision risk prediction of the object with the medical imaging system; calculating a SAR estimate of the object; calculating a weight of the object; calculating a height of the object; and combinations thereof.

13. 13. The medical system of claim 10, 11 or 12, wherein the medical imaging system is one of a magnetic resonance imaging system, a positron emission tomography system, a single photon emission computed tomography system, a computed tomography system, a combined positron emission tomography and magnetic resonance imaging system, a combined positron emission tomography and computed tomography system, a combined computed tomography and radiation therapy system, a combined computed tomography and positron emission tomography system, a combined magnetic resonance imaging and radiation therapy system, and an image-guided radiation therapy system.

14. a first camera configured to capture an image of a first portion of the support surface; and a second camera configured to capture an image of a second portion of the support surface, the first and second portions including an overlapping region, the subject support being movable relative to the first and second cameras along a predetermined path between a first position, at least one intermediate position, and a second position, the one or more intermediate positions each being located between the first position and the second position; The method comprises: controlling the first camera to acquire initial first camera image data depicting an object on the object support when the object support is in a first position; controlling the second camera to acquire initial second camera image data depicting an object on the object support when the object support is in a first position; constructing an initial three-dimensional image of the object using at least a portion of an overlap region of the initial first camera image data and the initial second camera image data; identifying a region of the object that is captured by the initial first camera image data but is occluded in the initial second camera image data as a first obstructed region; identifying a region of the object captured by the initial second camera image data but obstructed in the initial first camera image data as a second obstructed region; Execution of the machine-executable instructions causes the computing system to: controlling the subject support to move to one of the one or more intermediate positions; controlling the first camera to acquire additional first camera image data depicting an object on the object support when the object support is in one of one or more intermediate positions; controlling the second camera to acquire additional second camera image data depicting an object on the object support when the object support is in one of one or more intermediate positions; constructing a first-camera three-dimensional image of the object using the initial first-camera image data and the additional first-camera image data; constructing a second-camera three-dimensional image of the object using the initial second-camera image data and the additional second-camera image data; and constructing a composite three-dimensional image of the object using the initial three-dimensional image, the first camera three-dimensional image, and the second camera three-dimensional image, wherein the first obstructed region is at least partially replaced by the first camera three-dimensional image and the second obstructed region is at least partially replaced by the second camera three-dimensional image.

15. 1. A computer program comprising machine-executable instructions executed by a computing system for controlling a medical system, the medical system comprising: a subject support, the subject support including a support surface for receiving a subject; a first camera configured to image a first portion of the support surface; and a second camera configured to image a second portion of the support surface, the first portion and the second portion including an overlapping region, the subject support being movable relative to the first camera and the second camera along a predetermined path between a first position, at least one intermediate position, and a second position, each of the one or more intermediate positions being located between the first position and the second position; Execution of the machine-executable instructions causes the computing system to: controlling the first camera to acquire initial first camera image data depicting an object on the object support when the object support is in the first position; controlling the second camera to acquire initial second camera image data depicting an object on the object support when the object support is in the first position; constructing an initial three-dimensional image of the object using at least a portion of an overlap region of the initial first camera image data and the initial second camera image data; identifying a region of the object that is captured by the initial first camera image data but is occluded in the initial second camera image data as a first obstructed region; and identifying a region of the object captured by the initial second camera image data but obstructed in the initial first camera image data as a second obstructed region; Execution of the machine-executable instructions further comprises at least one time causing the computing system to: controlling the subject support to move to one of the one or more intermediate positions; controlling the first camera to acquire additional first camera image data depicting an object on the object support when the object support is in one of the one or more intermediate positions; controlling the second camera to acquire additional second camera image data depicting an object on the object support when the object support is in one of the one or more intermediate positions; constructing a first-camera three-dimensional image of the object using the initial first-camera image data and the additional first-camera image data; constructing a second-camera three-dimensional image of the object using the initial second-camera image data and the additional second-camera image data; a computer program causing execution of constructing a composite 3D image of the object using the initial 3D image, the first camera 3D image, and the second camera 3D image, wherein the first obstructed region is at least partially replaced by the first camera 3D image and the second obstructed region is at least partially replaced by the second camera 3D image.

Images