Patient motion detection in diagnostic imaging

Abstract

The apparatus includes a camera / 3D surface scanning system and an input for receiving a trigger indicating that the current spatial configuration of the subject should be maintained for inspection. The apparatus includes a processor and an output, the processor being adapted, upon receipt of the trigger, to acquire reference data of the subject using the camera / 3D system and, after acquiring the reference data, to acquire further data of the subject using the camera / 3D system. The processor is adapted to compare the reference data, representing a reference state of the subject substantially at the time the trigger was received, with the further data, representing a more recent state of the subject. The processor is adapted to provide output data via the output, the output data representing a comparison of the further data with the reference data, to indicate movement of the subject relative to the reference state.

Description

[Technical Field] 【0001】 The present invention relates to the field of diagnostic imaging, and more particularly to devices, systems, workstations, methods and computer program products for monitoring the positioning (spatial configuration) of a subject (e.g., one or more body parts of a patient) in a diagnostic imaging environment, for example, to check for unwanted patient movement before starting a medical imaging procedure, for example, especially after initial preparation of the patient to ensure that correct positioning for the examination has been completed. [Background technology] 【0002】 Preparing a patient for a diagnostic imaging examination, for example, to diagnose a medical condition and / or plan treatment, is a complex task that typically relies heavily on manual intervention by trained and experienced personnel. Typically, a skilled operator (e.g., a medical technical assistant, MTA) must carefully prepare and set up for the session according to established protocols and / or specific guidelines regarding correct patient positioning and image acquisition configuration, e.g., configuration of the diagnostic imaging system. 【0003】 For example, for acquisition of an X-ray image, the patient needs to be properly positioned relative to the X-ray imaging system (and / or vice versa). This typically means that the patient needs to assume a specific posture with respect to the image detector and X-ray tube. For example, limbs and joints may need to be precisely positioned and / or oriented relative to the detector and tube as dictated by the diagnostic objectives of the examination. After this positioning, the patient is typically instructed to avoid any further movement, but X-ray images are generally not acquired immediately after positioning. For example, the operator may need to configure system parameters for acquisition and / or to retreat to a safe distance and / or behind radiation shielding (or a different room) to avoid exposing the operator to potentially harmful radiation (which can accumulate over time, even for typically very small doses, e.g., routinely, without appropriate protective measures). 【0004】 However, if the patient moves after the correct position has been assumed, e.g., assisted and confirmed by the operator, but before image acquisition is performed, the x-ray image may be inappropriate or suboptimal for the intended diagnostic purpose. Therefore, in such cases, reacquisition of the image may be necessary. Unfortunately, even digital radiography technology does not allow for rapid detection of whether the diagnostic quality of the acquired image is sufficient, e.g., within just a few seconds. It will be appreciated that repeating image acquisition has several undesirable consequences, such as exposing the patient to additional radiation doses that could be avoided, and unnecessary waste of time and other resources, such as power drawn by use and / or wear of the system (e.g., of the x-ray tube). 【0005】 Various approaches to improving patient positioning processes that rely on optical (digital) camera images are known in the art, for example, displaying to the patient the target position of a limb or body part, or more generally the target spatial configuration, in combination with live camera imaging feedback in order to guide the patient to the correct position (see, for example, US 2015 / 003674 A1 and US 2017 / 020469 A1). 【0006】 Thus, visual feedback may be provided to position the patient in a desired position for a diagnostic imaging examination. However, such techniques typically rely on specific processing to determine the correct (desired) position for the examination, e.g., to detect the current spatial configuration of the patient's relevant body parts in a reference frame tied to the diagnostic imaging system and / or optical camera (where the correspondence between these coordinate systems is typically precisely established), and / or to compare the current position with a desired state. This may involve specific, possibly complex processing techniques that can increase the cost of developing, manufacturing, and / or maintaining the system, limit the flexibility of the system (e.g., supporting only common examinations, typical body shapes, and / or standard use cases), create a risk of erroneous inference of information from the observed images, e.g., considering the detection of a body part or parts, and / or erroneously determine a recommended spatial configuration for atypical patients (e.g., considering injuries, congenital disorders, and / or other medical conditions). 【0007】 While various methods, including the examples described above, are known in the art to assist in the process of guiding a patient to a particular position required (or desired) for a particular imaging examination, there remains a need in the art to provide a simple and robust approach to monitoring patient positioning, preferably without using (or at least minimally relying on) complex image recognition and / or processing techniques, and preferably without relying on predetermined definitions and / or assumptions of the desired geometric state (i.e., "position" in the broadest sense), e.g., in an examination-non-diagnostic and patient-non-diagnostic manner, i.e., regardless of the particular (type) of examination and / or patient. 【0008】 Once the operator has finished positioning the patient, other actions may be required before the acquisition process can begin. For example, the X-ray equipment may be configured and / or fine-tuned for the examination; for example, the collimation and / or other settings of the X-ray beam may need to be adjusted. After the patient setup and any configuration steps that need to be performed locally at the imaging site (e.g., where the X-ray tube and / or detector are located; note that remotely controllable settings may vary from system to system), the operator typically leaves the immediate vicinity of the patient (e.g., leaving the imaging site, e.g., in the acquisition room) to control the image acquisition process from a console (e.g., a control room). Thus, the actual X-ray image acquisition may occur a significant amount of time after positioning setup. Furthermore, the operator may not be able to observe the patient directly or in sufficient detail during the final steps before the acquisition is performed. Embodiments of the present invention can address the need for a simple technique to ensure that the patient remains motionless after the preparation step (patient positioning), i.e., the patient is essentially frozen until the (e.g., X-ray) diagnostic image is acquired. 【0009】 U.S. Patent Application Publication No. 2020 / 029919(A1) discloses that proper positioning of a patient in an X-ray imaging system can present challenges for medical professionals due to the small size of important anatomical features that need to be captured in an X-ray image by hand and the significant movement in the field of view exhibited by a typical patient. U.S. Patent Application Publication No. 2020 / 029919 proposes acquiring an image of the patient's position within the field of view approximately simultaneously as the initial X-ray image is acquired. If it is determined that a subsequent X-ray image with updated field of view settings (e.g., collimation parameters) needs to be acquired, the patient's movement at the time the second image is taken is taken into account in providing the updated field of view settings. 【0010】 Another document, US 2015 / 208981 A1, discloses a method for providing information for magnetic resonance computed tomography (MRI), the method comprising: performing imaging of a patient by executing a sequence including a plurality of protocols; and providing the patient with threshold-related information regarding the patient's movement corresponding to a currently executed protocol among the plurality of protocols. 【0011】 Another document, WO 2021 / 136250 A1, relates to a method for automated image acquisition and image processing. The method may include acquiring imaging information of an object. The method may include determining at least target device position information of an imaging device based on the image information. The method may include positioning the imaging device to perform image acquisition based on the target device position information of the imaging device. The method may include providing guidance information based on the examination information, where the guidance information is configured to guide the positioning of the object. The method may also include acquiring a target image from an imaging operation by the imaging device. Furthermore, the method may include determining a target image processing algorithm for the medical image. Summary of the Invention [Problem to be solved by the invention] 【0012】 It is an object of embodiments of the present invention to provide simple, convenient, and / or efficient means and methods for monitoring the spatial configuration ("position") of a subject (e.g., in a general sense) in a diagnostic imaging environment (e.g., of at least one body part or at least one portion of the subject that is of particular interest for the imaging examination) in order to check for undesired movement of the subject, for example, before starting a medical imaging procedure such as an X-ray image acquisition. In particular, embodiments may be used to ensure that correct positioning of the subject for an imaging examination is maintained after initial preparations have been made to set up the patient, for example, before the actual diagnostic image acquisition is performed. [Means for solving the problem] 【0013】 An advantage of embodiments of the present invention is that poor diagnostic image quality (e.g., insufficient for diagnostic purposes) and / or reacquisition of diagnostic images due to patient movement after positioning and before acquisition can be avoided or reduced. Another advantage is that additional radiation dose exposure of the patient due to reconstruction of diagnostic images can be avoided or reduced (e.g., at least statistically). Similarly, it is advantageous to reduce or avoid radiation exposure of sensitive organs or tissues that are located outside the collimated radiation field (e.g., not of interest for the intended examination), but are nevertheless positioned to be exposed due to undesired patient movement. Wasted resources, e.g., time, electricity, system wear, etc., due to unnecessary retakes of diagnostic images can also be reduced or avoided. 【0014】 Furthermore, if suboptimal positioning of the patient during diagnostic image acquisition is not detected in time by the operator, the risk of an erroneous or indeterminate diagnosis may arise, which may also be reduced by embodiments of the present invention. It will be appreciated that the costs associated with returning the patient to a facility for a repeat examination at a later time (e.g., date) in light of poor diagnostic image quality that went unnoticed during earlier acquisition may be even higher than when immediate re-acquisition of images is performed. 【0015】 An advantage of embodiments of the present invention is that they allow the use of a camera system (e.g., one or more cameras) that does not need to be specifically and / or precisely aligned with a diagnostic imaging system, such as by a calibration procedure or the like, including precise determination of the correspondence between the camera coordinate system and the diagnostic imaging coordinate system. For example, in systems that automatically determine a patient's desired spatial configuration and / or guide the patient (possibly through operator interaction) to this desired configuration, precise mapping is typically required to relate the camera observations to the coordinate frame of the diagnostic image intended to be taken. However, embodiments of the present invention can monitor the patient for signs of (any substantial) movement after a trigger is received to indicate that the desired position has been achieved, such that knowledge of the coordinate system of the diagnostic imaging system (and therefore of the diagnostic image to be acquired) is not required. This results in a very robust approach (e.g., coordinate mapping errors are avoided and / or temporal camera alignment changes are not necessarily an issue) and is simple to install and use (e.g., detailed calibration procedures are not required). Furthermore, the camera does not need to be integrated into the diagnostic imaging system, and may, for example, be installed as a simple add-on without requiring complex integration into the diagnostic imaging system, or even any substantial co-integration (e.g., data connections, precise mechanical linkages, etc.). 【0016】 An advantage of embodiments of the present invention is that simple and robust techniques are applied to detect the movement of a patient (or its body parts and / or its associated body parts) and / or compare the current state with a desired state, without relying on specific, e.g., complex, processing techniques, to determine the accurate (or at least desired) spatial configuration of a patient's body for a particular examination, to detect the current spatial configuration of the patient's body or its associated body parts (e.g., by fitting a model of the body or its parts to live camera images), and / or to compare the current state with a desired state. By avoiding such complex processing techniques, the development, manufacturing, and / or maintenance costs of systems according to embodiments can be kept low and a high degree of flexibility can be provided, e.g., the system does not (broadly) rely on assumptions regarding a particular examination (e.g., embodiments can be applied to essentially any examination without requiring prior knowledge) or a particular patient's body shape, condition, and / or other characteristics. It will be appreciated that a simple approach that minimizes the use of assumptions and / or prior knowledge (machine learning and / or codified) may avoid or at least reduce the risks resulting from erroneous estimation and / or inference of information (e.g., physical feature detection, model fitting, etc.) Thus, the flexibility provided advantageously allows the operator to use their own experience and best judgment to position the patient without being constrained by a reference condition (patient position / spatial configuration) defined and / or determined by the system. 【0017】 However, it should be noted that some (e.g., limited and / or simple) image processing is not necessarily excluded. For example, landmark features, which may (preferably) be easily and robustly computable, may be detected in the camera images. The use of landmark features may enable more reproducible quantification and / or characterization of patient motion, e.g., checking quantified motion against a predetermined threshold of "acceptable" motion without requiring detailed knowledge of the imaging procedure to perform specific patient features; approaches according to embodiments may still advantageously be considered procedure- and patient-independent. 【0018】 An advantage of embodiments of the present invention is that any position (i.e., spatial configuration) of a patient (or relevant body part of the patient) can be used as a reference for detecting movement, e.g., substantial deviation of the patient's position from this reference, in a simple manner, without requiring e.g. programming, (machine) training, and / or explicit definition of the reference. 【0019】 An advantage of embodiments of the present invention is that position information of a patient and / or position information and / or movement information (e.g., changes in this position information) of particular body parts can be conveniently monitored by an operator, for example, using overlay(s) shown to the operator on a display. Additionally or alternatively, such information can be displayed to the subject, for example, to enable the subject to recognize changes in his or her position and correct such movement. 【0020】 An advantage of embodiments of the present invention is that even though depth and / or 3D camera images are used to enable changes in the patient's spatial configuration to be detected in substantially three dimensions, changes in position occurring in a direction, e.g., perpendicular to the camera image plane (or at least having a substantial component in this depth direction), may be detected in addition to in-plane changes that are also detectable using a conventional 2D camera. 【0021】 Depth (e.g., 3D) imaging can also advantageously enable better detection of motion by increasing the separability and detectability of the patient (or, in general, their body parts) in the camera (depth / 3D) image(s), so that changes in spatial configuration can be more easily detected. Even if a body part has poor image contrast relative to the background, it can be typically positioned at a distance from the camera's perspective, so that it can be easily detected and dynamically compared to a reference image (e.g., captured earlier upon receiving a trigger to register the patient's position as the desired state for diagnostic image acquisition). Note that this does not require any assumptions about the shape or other properties of the body part, merely that it be sufficiently physically removed from surrounding objects. It will be appreciated that even if a body part is placed in contact with a surface, e.g., the plane of a detector or detector enclosure (and the camera observes generally from the opposite direction, e.g., from a more or less favorable point of view of the X-ray tube, but without being limited thereto), the thickness of the (and generally any) body part will cause it to stand out proportionally, literally, in the acquired depth or 3D image. This also reduces false detections of motion, e.g., moving shadows, changes due to lighting and / or other such observable changes in a purely 2D (e.g., color or grayscale) image that are not related to actual changes in the position of the actual object (body part or parts). 【0022】 A further advantage of embodiments of the present invention is that an objective assessment value can be determined to indicate whether it is necessary or desirable to reposition the subject (e.g., return to the patient positioning preparation stage) in order to obtain good diagnostic image quality, e.g., X-ray images of sufficiently high quality for diagnostic purposes. Such an assessment can be made by an operator (e.g., an MTA), but can also be determined automatically in accordance with embodiments of the present invention (e.g., as automatically generated advice to the operator). When the assessment determined by a system or method according to embodiments is negative, execution of the prepared imaging examination may be interrupted, e.g., by disabling a button or other signal source to activate the acquisition process, so that the operator is not only warned but also forced to take corrective action before the acquisition can occur (it will be understood that in such cases, an override option may be provided to allow the operator to continue anyway, relying on their experience and professional judgment). 【0023】 While the automated generation of the assessment (i.e., a value indicating whether an observed change in patient positioning is likely to substantially degrade diagnostic image quality) may (e.g., optionally) explicitly or implicitly take into account some (e.g., limited) prior knowledge of the imaging procedure to be performed, it will be understood that this is distinct from automatically guiding the patient to a position prescribed for the procedure (e.g., using a geometric 3D model of the patient and / or an otherwise codified definition of preferred patient positioning for a particular procedure) and comparing the patient's position to a reference, e.g., based on the model, based on a predetermined procedure. Embodiments of the present invention allow an operator to position the patient in any way they deem appropriate for the intended purpose, without any constraints imposed by an automated patient positioning guidance system. After the operator indicates that the patient is correctly positioned, changes in position can be detected in an automated manner, e.g., alerting the operator (and / or the patient) when detected movement exceeds a predetermined threshold. The assessment value can be determined by processing a reference position, e.g., a snapshot image of the patient taken at the time the operator indicated that positioning preparations were complete, and the currently observed position (e.g., a live camera image), or information derived therefrom. For example, a machine learning algorithm (e.g., a trained artificial intelligence model) can use this information to estimate whether the diagnostic image taken at that time, i.e., the patient positioned as observed relative to what was originally intended by the operator (e.g., the reference image), is of sufficient quality (likely). However, this does not limit the flexibility or usefulness of systems and / or methods according to embodiments; an operator is free to position the patient in any way that, in their best judgment, is deemed appropriate when defining a reference state (e.g., a reference snapshot). 【0024】 An advantage of embodiments of the present invention is that a partially automated, e.g., machine-assisted, procedure is provided to routinely improve the workflow and / or efficiency of patient positioning tasks in diagnostic imaging examinations, e.g., X-ray examinations, e.g., projection X-ray radiography examinations. 【0025】 An advantage of embodiments of the present invention is that they can provide real-time, e.g., substantially continuously updated (or at least reasonably frequently updated) monitoring of a patient's spatial configuration (e.g., position) to detect movement away from (e.g., above a predetermined threshold) a previous spatial configuration of the patient selected as a reference. 【0026】 An advantage of embodiments of the present invention is that a motion detection approach (i.e., change detection for the spatial configuration of an object) as provided by the embodiments can be applied in combination with any diagnostic imaging system, for example, any general-purpose, non-standard, third-party, custom-made, and / or generally any imaging system, without (or with little to no) modification, alignment, mathematical modeling, and / or initialization. In other words, the approach does not rely on knowledge of the characteristics, parameters, configuration, features, and / or type of diagnostic imaging system, nor does it rely on knowledge of the diagnostic imaging procedure being performed, nor on knowledge of the characteristics of the subject. However, it will be understood that some (e.g., limited) prior knowledge about the system, examination, and / or subject can be used in accordance with some embodiments of the present invention (i.e., such embodiments are not necessarily excluded), if deemed useful. 【0027】 A method, computer program product, apparatus, system and / or workstation according to an embodiment of the present invention achieves the above objectives. 【0028】 In a first aspect, the present invention relates to a method, e.g., a computer-implemented method, for detecting movement of at least one body part of a subject in a diagnostic imaging examination, e.g., an X-ray imaging examination, e.g., X-ray projection radiography. The method includes receiving a trigger signal indicating that a current spatial configuration of the subject should be maintained for the diagnostic imaging examination. The method includes, upon receipt of the trigger signal, acquiring spatial data and / or a reference image of the subject using a camera and / or a 3D surface scanning system. The method further includes acquiring further images and / or spatial data of the subject using the camera and / or the 3D surface scanning system after the reference image and / or spatial data of the subject has been acquired using the camera and / or the 3D surface scanning system. The method also includes comparing the spatial data and / or reference image of the subject, which represents a state of the subject substantially at the time the trigger was received, with the further image and / or spatial data of the subject, which represents a more recent state of the subject (or vice versa, representing the further data relative to the reference data). The method includes providing an output to an operator and / or subject representing said comparison of the further image and / or spatial data with the reference image and / or spatial data to indicate movement of the subject relative to the subject's reference state. 【0029】 In methods according to embodiments of the present invention, output may be provided via at least one display monitor and / or human interface device. 【0030】 In methods according to embodiments of the present invention, output may be provided as an image overlay, displaying the comparison in the form of a difference image as an overlay on the further image and / or spatial data. 【0031】 In methods according to embodiments of the present invention, further images and / or spatial data of the object may be repeatedly, periodically, and / or substantially continuously acquired to obtain a live stream of further images and / or spatial data, wherein the reference images and / or spatial data are repeatedly compared with recently acquired further images and / or spatial data of the live stream, and the output is repeatedly provided to present a dynamic view of current changes in the spatial configuration of the object relative to an earlier state of the object. 【0032】 In a method according to an embodiment of the present invention, a trigger signal may be received from an operator via a human interaction interface, for example, a button, a voice control interface, and / or a gesture detection system, to detect a gesture made by the operator. 【0033】 A method according to an embodiment of the present invention may include detecting proximity of an operator to a subject using radio frequency identification tag detection, an indoor positioning system, a light beam gate, a sonar, radar, and / or lidar system, and / or another sensor system for presence, proximity, and / or location detection, wherein the trigger signal is generated when the proximity detection indicates that the operator has left the vicinity of the subject. 【0034】 In a method according to an embodiment of the present invention, a trigger signal may be received from an automated system for detecting a predetermined reference spatial configuration of a subject in a live imaging stream from a camera and / or 3D surface scanning system, during a diagnostic imaging examination. 【0035】 A method according to an embodiment of the present invention may comprise the steps of acquiring a live image stream from a camera and / or 3D surface scanning system, performing scene analysis of the live image stream to detect a predetermined condition, and in response generating said trigger, wherein the predetermined condition corresponds to an operator leaving the immediate vicinity of the object. 【0036】 In methods according to embodiments of the present invention, the reference image and / or spatial data may be acquired at the moment the trigger is received or a predetermined short time thereafter, and / or the reference image and / or spatial data may be selected from a buffer storing a stream of image and / or spatial data acquired from the camera and / or 3D surface scanning system, the selection corresponding to a recent point in time before the trigger is received. 【0037】 In methods according to embodiments of the present invention, acquiring spatial data and / or reference images of the subject using a camera and / or 3D surface scanning system may include acquiring conventional monochrome and / or color digital photographic images in the visible and / or infrared spectrum. 【0038】 In methods according to embodiments of the present invention, acquiring spatial data and / or reference images of the subject using a camera and / or 3D surface scanning system may include acquiring the reference images and / or spatial data using multiple cameras included in the camera system simultaneously to acquire images and / or spatial information of the subject from different viewpoints. 【0039】 In methods according to embodiments of the present invention, acquiring reference images and / or spatial data of the object using a camera and / or 3D surface scanning system may include acquiring 3D and / or depth information. 【0040】 In methods according to embodiments of the present invention, comparing the reference image and / or spatial data of the object may include detecting at least one image feature and / or landmark in the reference image and / or spatial data and the further image and / or spatial data, and comparing the position of the at least one image feature and / or landmark between the reference image and / or the further image and / or spatial data for use in determining the output. 【0041】 In methods according to embodiments of the present invention, the image features and / or landmarks may include at least one anatomical landmark on a joint, bone, muscle, and / or other externally identifiable anatomical feature of the subject's body. 【0042】 In a method according to an embodiment of the present invention, providing an output may include determining a difference measure indicative of movement of the object relative to a reference state based on the comparison, and alerting an operator that the object is no longer in the intended reference position when the difference measure exceeds a predetermined threshold. 【0043】 In a second aspect, the present invention relates to an apparatus for detecting movement of at least one body part of a subject in a diagnostic imaging examination, such as an X-ray diagnostic imaging examination, e.g., a projection radiography examination. The apparatus comprises a camera and / or a 3D surface scanning system for acquiring images and / or spatial data of the subject and an input for receiving a trigger signal indicating that the current spatial configuration of the subject should be maintained for the diagnostic imaging examination. The apparatus comprises a processor and an output, the processor being adapted to acquire reference images and / or spatial data of the subject using the camera and / or 3D surface scanning system when the trigger signal is received, and to acquire further images and / or spatial data of the subject using the camera and / or 3D surface scanning system after the reference images and / or spatial data of the subject have been acquired. The processor is further adapted to compare the spatial data and / or reference images of the subject representing a reference state of the subject substantially at the time the trigger signal was received with the further images and / or spatial data of the subject representing a more recent state of the subject (or, equivalently, to compare the further data with the reference data, i.e., vice versa). The processor is adapted to provide output data to an operator and / or subject via the output, the output data representing a comparison of the further image and / or spatial data to the reference image and / or spatial data so as to indicate movement of the subject relative to a reference state of the subject. 【0044】 In an apparatus according to an embodiment of the present invention, a processor may be adapted to repeat the steps of acquiring further image and / or spatial data via a camera and / or 3D surface scanning system, comparing the reference image and / or spatial data with the further image and / or spatial data, and providing updated output data to present a dynamic view of current changes in the spatial configuration of the subject relative to a previous reference state of the subject. 【0045】 In an apparatus according to an embodiment of the present invention, the output may include a display monitor, and the processor may be adapted to present a visual representation of the comparison via the display monitor. 【0046】 In an apparatus according to an embodiment of the invention, the processor may be adapted to present in the output data the shape, area and / or volume of the two-dimensional and / or three-dimensional differences determined by the comparison as an overlay and / or contour on a visualization of further image and / or spatial data and / or as markers and / or annotations accompanying such visualization. 【0047】 In an apparatus according to an embodiment of the present invention, the processor may be adapted to determine a difference measure indicative of the object's movement relative to a reference state based on said comparison, and to output via said output a warning to an operator and / or the object and / or a signal to a diagnostic imaging system when said difference measure exceeds a predetermined threshold, indicating that the object is no longer in the intended reference state. 【0048】 In an apparatus according to an embodiment of the present invention, the camera and / or 3D surface scanning system may include at least one camera and / or 3D surface scanning device arranged to obtain two-dimensional and / or three-dimensional views of at least one body part and / or subject, said at least one camera and / or 3D surface scanning device including an optical camera for acquiring monochrome, color and / or multi-spectral two-dimensional images in the infrared and / or visible spectrum, and / or a plurality of such cameras arranged to observe the subject from different angles, and / or a depth camera and / or 3D surface imaging system. 【0049】 In a device according to an embodiment of the present invention, the input may include a human interaction interface. 【0050】 In a device according to an embodiment of the present invention, the input, eg, human interaction interface, may include buttons, a voice control interface, and / or a gesture detection system for detecting gestures made by an operator. 【0051】 In an apparatus according to an embodiment of the invention, an input may comprise a proximity and / or position detection system for detecting the proximity of an operator to the subject, such that the trigger signal is generated when the operator leaves the vicinity of the subject. 【0052】 In devices according to embodiments of the present invention, inputs, for example, a proximity and / or position detection system may comprise a radio frequency identification tag in combination with at least one radio frequency identification tag detection sensor, and / or may comprise at least one light gate, and / or may comprise a sonar, radar and / or lidar system, and / or may be implemented using a processor to detect the position of an operator in a live stream of images and / or spatial data of objects acquired by a camera and / or 3D surface scanning system. 【0053】 Apparatus according to embodiments of the present invention may comprise connections for receiving trigger signals from an automated system for detecting predetermined reference spatial configurations of a subject, diagnostic imaging examinations, in a live imaging stream where the input is provided by a camera and / or a 3D surface scanning system. 【0054】 An apparatus according to an embodiment of the present invention may include said automated system for detecting a predetermined reference spatial configuration of a subject. 【0055】 An apparatus according to an embodiment may comprise an artificial intelligence module for evaluating a trained machine learning model and generating said trigger signal (provided as an input) by taking into account the output of the evaluated model. The trained machine learning model uses as input said image and / or spatial data, and / or data from and / or derived from a diagnostic imaging system. The data from the diagnostic imaging system (received as input in operation of the apparatus) may include device status information of the diagnostic imaging system and / or control input information received from user interaction by the diagnostic imaging system. 【0056】 In an apparatus according to an embodiment of the present invention, the processor may be adapted to compare the further image and / or spatial data with the reference image and / or spatial data by detecting at least one image feature and / or landmark in the reference image and / or spatial data and a corresponding at least one image feature and / or landmark in the further image and / or spatial data, and to compare the position of the at least one image feature and / or landmark between the reference image and / or spatial data and the further image and / or spatial data. 【0057】 In a third aspect, the present invention relates to a diagnostic imaging system, wherein the system is adapted to perform a method according to an embodiment of the first aspect of the invention and / or comprises an apparatus according to an embodiment of the second aspect of the invention. 【0058】 Dagnostic imaging systems according to embodiments of the present invention may include X-ray imaging systems, for example projection X-ray imaging systems. 【0059】 In a fourth aspect, the present invention relates to a workstation for a diagnostic imaging system, such as a diagnostic X-ray imaging system, adapted to perform a method according to an embodiment of the first aspect of the invention and / or comprising an apparatus according to an embodiment of the second aspect of the invention. 【0060】 In a fifth embodiment, the invention relates to a computer program product for performing a method according to the first embodiment of the invention when the computer program product is executed on a computer (e.g., an apparatus according to the second embodiment of the invention). 【0061】 The independent and dependent claims set out particular and preferred features of the invention. Features from the dependent claims may be combined with features of the independent claims and with features of other dependent claims as appropriate and not necessarily as explicitly set out in the claims. [Brief explanation of the drawings] 【0062】 [Figure 1] 1 illustrates a method according to an embodiment of the present invention. [Figure 2] To illustrate embodiments of the present invention, an exemplary visualization of patient motion relative to a frozen reference image (eg, included in the output of a method and / or apparatus according to an embodiment) is shown. [Figure 3] 1 illustrates schematically an apparatus according to an embodiment of the present invention; [Figure 4] 1 illustrates a diagnostic imaging system according to an embodiment of the present invention, and a workstation for a diagnostic imaging system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION 【0063】 The drawings are schematic and non-limiting. Elements in the drawings are not necessarily drawn to scale. The present invention is not necessarily limited to the particular embodiment(s) of the invention shown in the drawings. 【0064】 Notwithstanding the exemplary embodiments described below, the present invention is limited only by the appended claims, which are expressly incorporated into this detailed description, with each claim, and each combination of claims permitted by the substructure defined by the claims, forming a separate embodiment of the present invention. 【0065】 The term "comprising," when used in the claims, is not limited to the features, elements, or steps as set forth below, and does not exclude additional features, elements, or steps. Thus, it specifies the presence of a stated feature without excluding the further presence or addition of one or more features. 【0066】 In this detailed description, various specific details are presented. Embodiments of the present invention may be practiced without these specific details. Furthermore, well-known features, elements, and / or steps are not necessarily described in detail for the sake of clarity and conciseness of this disclosure. 【0067】 In a first aspect, the present invention relates to a method for checking the motion of a subject (e.g., at least one body part of a subject) in a diagnostic imaging environment, e.g., for checking for undesired patient motion before starting a medical imaging procedure, e.g., after initial preparations to bring the subject into the correct position (posture, or generally, desired spatial configuration) for examination. Thus, motion can be detected with respect to an earlier position and spatial configuration of the subject before performing a diagnostic image acquisition. The position, orientation, deformation, and / or other spatial (geometric) properties of the subject can be monitored to detect changes in the spatial relationship between the subject and the diagnostic imaging system (e.g., detector and X-ray tube) so that it remains substantially constant. 【0068】 It will be understood that the principles of the present invention are equally applicable to various types of diagnostic imaging examinations and are not necessarily limited to X-ray imaging in general or X-ray projection radiography in particular, and therefore, references to X-ray images made throughout this disclosure are for illustrative purposes only and are not necessarily limiting. 【0069】 However, it will also be appreciated that embodiments of the present invention may be particularly advantageous and / or useful in light of certain circumstances of X-ray and / or X-ray projection images. For example, the configuration process for an X-ray examination, e.g., beam collimation, tube voltage (kVp), tube current, filtration parameters and / or other settings, and the need for radiation protection precautions for operator safety, may typically result in a substantial time span between the moment the patient assumes a desired position for the examination and the moment of actual acquisition, during which the operator may not be able to (easily) verify that the patient maintained the desired position. 【0070】 Furthermore, conventional (e.g., relatively simple) projection radiography systems may lack many automated features and / or support systems that allow for advanced remote control of the system from a control room (e.g., remote collimation, automatic insertion / configuration of beam filter plates, automatic patient treatment table, etc.) and / or means for high-quality remote patient observation (e.g., by high-resolution cameras and / or cameras for simultaneous observation of the patient from various viewing angles), and as a result, the length of time that the patient is expected to remain in the intended position while the operator is distracted by other (often manual) tasks and / or the length of time that it is not possible to easily visually confirm that the patient's position has not changed can be particularly problematic in conventional projection radiography examinations using such systems. 【0071】 Methods according to embodiments of the invention may be computer-implemented methods, i.e., automated or semi-automated methods that may be performed by dedicated processing hardware (e.g., using application-specific integrated circuits) and / or configured / programmed processing hardware, such as a computer or other general-purpose processor that is programmed for the specific task of performing the method (e.g., by executing specific software designed for that purpose), and / or a configurable hardware platform (e.g., a field-programmable gate array) configured for the specific task of performing the method. Combinations of application-specific hardware (e.g., ASICs) and / or configured hardware (e.g., FPGAs) and / or one or more programmed processing devices (e.g., using a CPU, GPU, or other suitable processor, typically in combination with supporting hardware such as is commonly found in a computer, e.g., a computer). The methods may also be performed by multiple processors, computers, and / or other processing devices operating in cooperation, e.g., using host-client architectures, web-based architectures, cluster processing, and / or other forms of distributed processing, data collection, data presentation, and / or data storage. 【0072】 "Automated" and "semi-automated" may refer to a computer-implemented method implemented by a (e.g., digital) processor, controller, and / or other such hardware, where the method is performed in an autonomous or supervised-autonomous mode requiring only limited input from and / or interaction with an operator, e.g., to oversee the procedure and / or other such limited interaction, to start, stop, and / or interrupt the procedure, e.g., to select or enter relevant parameters and / or configuration options. 【0073】 When reference is made to a "camera," "depth camera," "3D camera," or similar component, it will be understood that the referenced device is not to be confused with such a diagnostic imaging system (or diagnostic imaging component thereof). While a "camera" may be implemented as part of an imaging system, either by default or with appropriate modifications, it will be understood that the primary purpose of a diagnostic imaging system typically relates to the image acquisition process by different means, e.g., ionizing radiation, radio frequency signals, and is not, as such, based essentially (or at least not solely) on "camera" observations. For example, the radiation detection component (i.e., image detector) of a PET or SPECT system may be referred to as a PET or SPECT "camera," but it will be understood that this is different from a "camera" within the meaning of this disclosure. 【0074】 A camera in the sense of the present disclosure can include, for example, a conventional optical imaging camera and / or a depth imaging camera. The former (conventional camera) generally relates to an imaging camera that detects light within the (human) visible and / or infrared spectrum (i.e., particularly for determining images from images). Conventional cameras can be adapted for, for example, monochrome, color, and / or multispectral imaging. The latter (depth camera) generally relates to techniques that detect depth information in addition to in-plane information (e.g., the two-dimensional projection plane of an image detector), e.g., using stereoscopic imaging (or more generally, camera imaging from multiple different viewpoints simultaneously), range cameras, LIDAR, RADAR, and / or other such techniques, to determine points and / or surfaces in three-dimensional space, e.g., such that the surface contours (e.g., facing the camera) of object(s) are, at least to some extent, three-dimensionally conformal. In this context, a depth camera is generally understood to refer to any suitable means for collecting spatial data characterizing an observed scene in three spatial dimensions, for example determining the (3D) position in space of a point on the surface of an object in the observed scene (at least when unobscured from the camera's viewpoint). Note that when referring to a camera system below, this equally refers to a 2D image camera, a depth or 3D camera, or a 3D surface scanning system (or any combination thereof). 【0075】 Some examples of optical and / or other distance sensing technologies that may be suitable for use in a camera and / or 3D surface scanning system according to embodiments include, but are not limited to, structured light systems, stereo vision systems, and / or active stereo systems. Active stereo systems additionally refer to stereo vision systems that use structured light to improve detection of surface details, for example, using structured light patterns (e.g., using infrared light) to actively provide optically detectable details in homogeneous surface areas. Range measurements may be acquired at a single point, across a scan plane, and / or across an entire volume in space, for example, a complete image with depth measurements at every point within the sensor's field of view. 【0076】 Methods according to embodiments of the present invention may be used to assist in patient positioning during an imaging session, for example, in a projection X-ray imaging examination preparation step, particularly after positioning the patient (e.g., assisted by an operator) and before performing diagnostic image acquisition. It will be understood that when referring to a diagnostic (or medical) imaging session or environment, this may refer to a procedure (or an environment therefor, e.g., an examination room) in which a (e.g., human) subject is positioned in a desired posture or generally in a desired spatial configuration relative to an imaging system (e.g., with respect to an X-ray tube and X-ray detector) to perform the imaging procedure, after which one or more diagnostic images may be acquired. Embodiments of the present invention may be particularly useful when the patient is expected to remain in the desired posture until acquisition is complete. This may be particularly problematic when the patient is not supported by a support or specific positioning means, for example, in routine examinations where the patient is standing (e.g., upright) or sitting (e.g., on a stool) without much mechanical support of the body but must still remain in a desired orientation and / or position relative to the detector plane. This is often the case, for example, in projection radiography to diagnose, but not limited to, fractures, etc. 【0077】 1, an exemplary method 100 according to an embodiment of the present invention is shown. The method, e.g., computer-implemented method 100, may be used, for example, to assist in positioning a subject during and / or after preparation steps for a diagnostic imaging session, e.g., to avoid movement from a desired position / pose (i.e., spatial configuration). 【0078】 The method 100 includes receiving 101 a trigger signal indicating that the current spatial configuration of the subject should be maintained. 【0079】 This trigger may be provided manually by an operator. For example, an operator (e.g., a medical technical assistant, MTA) may place the patient in a position (generally, spatial configuration) that is deemed suitable or desirable, e.g., optimal, for the intended diagnostic imaging examination. The operator, for example, may preferably exercise his or her best judgment, relying on his or her experience and knowledge, without being constrained by any substantial limitations imposed by a method or system according to embodiments. Once the subject is in the desired position, the operator provides a trigger indicating that this position (i.e., spatial configuration) of the subject should be maintained. 【0080】 However, alternatively or additionally (e.g., using an “or” logical connection), the method (e.g., a system integrating the method) may also be combined with a different method for automatically determining and matching the correct positioning of the patient, for example, a machine vision algorithm for detecting when the patient is in a predetermined position (spatial configuration) suitable for the examination. Such algorithms are known and generally outside the scope of this application, but the trigger may be generated by an additional system to assist in patient positioning. As illustrated by the examples in the Background section above, various approaches for guiding the patient into a position suitable for the examination are known in the art and therefore will not be described in detail. The method according to the embodiments may also include, for example, such prior art methods for assisting in the positioning of the subject, performed before step 101 of receiving the trigger. The trigger may be generated by this (automatic or semi-automatic) positioning assistance step as an intermediate output, or the positioning assistance step may be performed before the operator performs manual confirmation of the patient's position and manually generates the trigger. In other words, method 100 may include a positioning assistance step for bringing the patient into a predetermined or automatically determined spatial configuration. Thus, the trigger may be generated by the system implementing the positioning assistance step (e.g., automatically) or may be received as an external input (e.g., due to an action performed by a user, i.e., operator). 【0081】 The trigger may be generated by a human interaction interface, such as pressing a button or switch (or more generally using a button or switch), a voice interface, gesture detection (e.g., detecting an operator's gestures), keyboard and / or mouse interaction with a (e.g., graphical) user interface, and / or any other suitable means for interacting with a user, i.e., receiving a signal from an operator (e.g., an at least one-bit signal in any suitable form). Thus, a hardware button (possibly included in a general-purpose interface such as a keyboard and / or mouse), gesture detection, or voice control system may be used to indicate the moment of good positioning of the object for inspection. 【0082】 For example, a camera system (described in more detail below) may be used to detect gestures from an operator. While the operator is preferably not visible in the reference image and / or further spatial data (discussed below), the operator may temporarily provide (machine-) detectable gestures, such as a swiping motion on the camera view (e.g., moving a hand over the camera lens from a short distance), or more complex gestures, such as a thumbs-up gesture. For example, moving a hand over the camera, or in general, e.g., a swipe, grasp, or other gesture, short-distance movement, or hand posture that obscures a substantial portion of the camera's field of view by the hand (or equivalently, by an alternative body part or object), may be particularly easy to detect with good sensitivity, accuracy, and robustness. Thus, a trigger signal may be readily generated in accordance with embodiments of the present invention by detecting a significant change in a camera image, such as a substantial drop in the average image intensity of a conventional optical camera image (e.g., obtained by a 2D monochrome, color, or similar conventional camera), a large increase in image intensity (e.g., when using a passive or active infrared camera), a substantial change in average color value, a substantial decrease in the average distance from the camera to points in the scene (e.g., of the average depth value per pixel across the depth image), and / or another similar simple detection strategy. Optionally, such change detection may be configured to detect a temporary change (e.g., a drop) associated with a return of a tested parameter (e.g., average image intensity) to approximately its previous value (e.g., approximately the same value as before the drop). Appropriate thresholds, fractions, or other suitable test parameters for generating a trigger signal based on such a "substantial" change may be readily determined by one skilled in the art, for example, by direct experimentation and / or trial and error. 【0083】 It will be appreciated that for some gestures, a (short) delay timer may be activated (or the short delay may be accommodated in other ways) to allow the operator to retract the camera's view before a trigger is generated in response to the detected gesture. Gestures may also be detected, for example, via a separate camera distinct from the camera system. Gestures may also be detected in other ways, such as by an accelerometer or machine-detectable tag attached to the operator's clothing, for example in / on a wristband or clothing clip. 【0084】 The method can include generating a trigger by acquiring an image from a camera system, e.g., a live image stream, and performing scene analysis 110. Thus, it is possible to automatically determine the appropriate point in time when the patient is considered to be in a suitable position for the diagnostic imaging procedure, i.e., when the preparatory steps for positioning the subject are considered to be complete. However, this does not require detailed knowledge of the procedure to be performed. In particular, the scene analysis can detect when the operator leaves the immediate vicinity of the patient. Such smart automatic triggering has the advantage of facilitating the detection of patient movement provided by embodiments of the present invention without requiring changes to the diagnostic imaging workflow (e.g., unless substantial movement is later detected by the method and the operator is implicitly or explicitly alerted to take action accordingly). The scene analysis can include detecting the shape of the operator and / or the operator's limbs (e.g., one or both arms) in images acquired by the camera system (e.g., a live stream), and generating a trigger when this shape moves outside the image frame, e.g., after a short predetermined delay to avoid false detections. For example, it will be understood that the operator's arm or arms can generally move from a central position in the image frame toward and outside the edges of the frame. For example, the body parts of the subject and operator may be spatially separated from one another at some point, and one (or more) spatially isolated segments may join the edge of the image frame (if not already) and decrease in size to zero over time (moving outside the frame). 【0085】 This detection can be as simple as detecting a dramatic decrease in image content (e.g., pixels, surface area, or voxels) that can be attributed to biological material. For the latter, it can be advantageous (but not strictly necessary) to use depth imaging (for clear separation of patient and operator from background due to depth differences) and / or infrared imaging (using body / body thermal emissions to provide good contrast for algorithmic separation from background). 【0086】 Additionally or alternatively, the camera system may comprise one or more additional cameras to cover a larger volume of the scene, e.g., a wider field of view of the examination room, e.g., configured to provide a long (longer) image shot, with the primary camera being able to track the subject's position in detail, while the secondary camera can detect when the operator leaves the vicinity of the subject (e.g., and thus be observed from a wider overall field of view). In other words, the trigger may be generated by recognition of a "gesture" of the operator (see above), where the "gesture" may include or consist of the volume of space monitored by (at least one camera of) the camera system. 【0087】 Additionally or alternatively, the trigger may be generated by proximity or spatial location detection of the operator using one or more sensors, for example, a radio frequency identification tag (on the operator's body) in combination with an RFID reader positioned in or near the region of space where the patient will be positioned for testing. This may be used, for example, relying on generally short-range RFID communications, to detect when the operator is no longer near the subject (or when the state changes from present, i.e., RFID detected, to absent, i.e., RFID no longer detected). Other suitable sensors may include, for example, a light beam gate (detecting when the operator crosses one or more light beams while leaving the testing area), an indoor positioning system (e.g., using operator position triangulation, which, although not entirely accurate, is referred to as "GPS for indoor tracking"), sonar, lidar, and / or radar technology, and / or another such suitable sensor system. 【0088】 It is advantageous that operator interaction, e.g., actions to be performed by a diagnostic imaging technician, can be reduced and / or their workflow can be simplified. Ideally, interaction steps are reduced to a minimum. Any type of trigger explicitly given by the technician, even if only in a minimal way, increases workflow complexity. Voice or gesture interaction may be preferable to, for example, pressing a button, since it can be given without constraining the operator's position to the button's location. Similarly, automatically detecting triggers without requiring conscious operator action, for example, using detection of the operator's position (particularly detection of the moment the operator leaves the area where the subject is set up for examination), may be even more preferable. 【0089】 The method may also include evaluating a trained machine learning and / or artificial intelligence model, e.g., an artificial neural network, to generate the trigger (or taking into account the output of the ML / AI model to generate the trigger). For example, an image or image sequence (e.g., a live stream) acquired via a camera system may be provided as input (directly or indirectly, e.g., via intermediate processing such as a feature extraction step) to the trained ML / AI model. Thus, performing scene analysis 110 may include evaluating the trained machine learning and / or artificial intelligence model. However, other input(s) may also be used (additionally or alternatively, directly or indirectly), such as motion sensor (e.g., X-ray) device control input and / or output, audio input (e.g., microphone), etc. 【0090】 The ML / AI model may be trained (or may be trained) on a dataset including multiple, e.g., generally numerous, user-operated interactions with a diagnostic imaging modality, for example, using an X-ray system (e.g., a system of the same or similar type as that to which the intended application of the method according to the embodiments relates). For example, patient positioning may be monitored, e.g., via a camera system, for numerous test cases, and the time at which the patient is positioned to be maintained during the diagnostic imaging session may be added as an annotation (e.g., determined via a manually generated explicit trigger signal provided by an operator or added after the fact when preparing the training dataset). The ML / AI model may thus receive this training input (e.g., camera images and / or other sensor data and / or information derived therefrom, e.g., extracted features) and corresponding training output (trigger annotations) and be trained to generate a trigger at the appropriate time or sufficiently close to the appropriate time. The specific choice of input to the ML / AI model may be flexible; e.g., many input sources would be obvious, as long as sufficient information can be at least implicitly inferred therefrom. 【0091】 For example, user interactions with a diagnostic imaging (e.g., X-ray) system may be used as input (possibly in combination with other data, e.g., the camera data mentioned above) to predict when the system (and user) is in a steady state, i.e., when the subject is prepared for a diagnostic imaging session. For example, an ML / AI model may be trained to use implicit information, embedded in actions for repositioning the X-ray tube, adjusting beam parameters, moving an activated support aid (e.g., the patient platform), adjusting collimation, activating / deactivating an indicator light field (a visual representation of the X-ray beam), etc., to detect when the operator has finished the patient preparation procedure and moved on to another task, i.e., when a trigger is generated. 【0092】 It will further be appreciated that the trigger effectively used in performing the present methods may be determined by combining trigger signals from multiple sources and / or generation methods. For example, different inputs, such as a general human interaction interface, buttons, voice control interfaces, gesture detection systems, proximity / position detection systems (e.g., to detect whether an operator and subject are near each other), and / or other trigger signals, may be combined, for example, in logical "OR" combinations, logical "and" combinations, combinations thereof (e.g., combining different logical operations in non-trivial expressions), weighted combinations, majority voting, and / or in any other suitable manner. 【0093】 The method further includes, upon receiving the trigger (101), acquiring reference images and / or spatial data of the subject using a camera system (102). The camera system is typically aligned with the subject's anatomical structure of interest, e.g., such that relevant body parts of the subject can be adequately observed by the data provided by the camera system. However, as described in more detail below, precise positioning and / or alignment of the camera is not required, e.g., it is not necessary to recreate or determine an exact mapping between the coordinate system of the camera system and the coordinate system of the diagnostic imaging system. 【0094】 For example, the reference image / spatial data may be acquired at the moment the trigger is received, or at a predetermined time thereafter (e.g., delayed by the time required to process the trigger and control the camera system accordingly to acquire the data, and / or by other such insubstantial delays, taking technical and practical limitations into account), e.g., preferably substantially simultaneously or shortly thereafter. It will be appreciated that the camera system may also be configured to continuously capture image and / or spatial data (e.g., update the image and / or spatial data buffer) such that upon receiving a trigger, image and / or spatial data may be selected from the buffer as the reference image and / or spatial data, even if the selected data represents the subject's state before the trigger was received (immediately prior). It will be appreciated that this approach allows the subject's reference state to be captured (i.e., represented by the reference image / spatial data) and the subject to indicate the reference to be recorded substantially simultaneously upon receiving a trigger (e.g., provided by an operator); for example, the buffer can compensate for any short technical delays and may even compensate for any non-technical delays, e.g., the operator's biological decisions and / or muscle response time. However, it will also be appreciated that such technical and / or biological delays are typically of such magnitude that they do not require any compensation at all, and that, for example, in most applications, a delay of one or even a few seconds (negative or positive, e.g., before or after the trigger time) may generally be acceptable. 【0095】 Therefore, "when the trigger is received" should be interpreted in the sense that the acquired reference image / spatial data represents the state of the object (e.g., has a certain spatial position, orientation, and / or other geometric state in time) at the substantial time when the trigger is received (and therefore the substantial time when the trigger is generated), for example, less than 5 seconds before or after the time of receiving the trigger, for example, preferably less than 1 second before or after the trigger time, preferably within the range of 0.5 seconds before receiving the trigger to 0.5 seconds after receiving the trigger. 【0096】 After positioning the patient, where the operator has confirmed that the patient's spatial configuration (e.g., relative to the diagnostic imaging system) is correct (or has actively guided the patient), a trigger is generated (either implicitly by the operator's movements or automatically by a dedicated algorithm) and reference image / spatial data is determined in response thereto, e.g., a camera image of the subject, or at least the anatomical region of interest, is acquired at a time sufficiently close to the time instant indicated by the trigger, and the trigger assumes that the subject is positioned in the correct (i.e., desired) posture. 【0097】 Acquiring spatial data and / or reference images of the subject using a camera system 102 can include conventional (digital) photographic acquisition, e.g., capturing color or monochrome camera images. For example, using infrared imaging may also be advantageous, such that the camera system comprises an infrared camera, e.g., a camera configured to acquire infrared image data (possibly in combination with one or more visible spectral components). Thus, the camera system may comprise, for example, one or more optical cameras, e.g., monochrome and / or color cameras, sensitive to one or more spectral bands in the visible (and / or infrared) range. It will be understood that color camera refers to (a) a color camera and does not necessarily limit the selection of a particular selection of color components (e.g., RGB) or a particular combination thereof. It will also be understood that a “color” camera may be sensitive (intentionally or unintentionally) to one or more infrared bands, possibly exclusively, and possibly in combination with visible light bands. The camera system is also not necessarily limited to a "color" camera having a relatively small number of color bands (e.g., red, green, blue), but may comprise a multispectral camera(s) adapted to more fully quantify, for example, the light spectrum received at each pixel location, for example, by decomposition into a relatively large number of spectral bins (e.g., so that a substantial spectral image dimension is formed in addition to the 2D image coordinates). 【0098】 The reference image and / or spatial data, e.g., one or more images and / or spatial information relating to the observed scene (including the subject or relevant body part or portions thereof) in any suitable form, can optionally include 3D and / or depth information. Accordingly, acquiring 102 the reference image and / or spatial data may include acquiring 3D and / or depth information. For example, acquiring the reference image / spatial data may (alternatively or additionally) include acquiring depth images and / or acquiring three-dimensional (3D) data (e.g., a 3D point cloud and / or a surface model constructed from such a 3D point cloud) in another manner by a camera system. For example, the camera system may comprise a depth camera and / or another suitable device for capturing 3D surface information, e.g., another suitable device for capturing a 3D (external) surface map of the patient's body (or at least the relevant body part / portions). Accordingly, the image and / or spatial data may include monochrome images, color images, infrared images, multispectral images, depth images, 3D images, and / or combinations thereof. Depth information may be collected in addition to in-plane image information, or at least three-dimensional (3D) information may be acquired that is not trivially reducible to 2D data, e.g., not expressed solely in coplanar coordinates. For example, a 2D map (e.g., image) of depth and / or a set of 3D points (e.g., a 3D point cloud) may be acquired. Depth images may be acquired, for example, by a distance camera that can generate 2D images showing the distance of points in a scene from a predetermined reference point or plane (e.g., a focal point or other reference point). Depth information may also be acquired by stereo imaging, in which images are acquired (e.g., substantially simultaneously) by two (conventional, e.g., monochrome or RGB) cameras from different viewpoints. Processing techniques known in the art may be applied to such stereo images (to pairs of simultaneously acquired images) to derive depth information from such stereo images, e.g., by disparity analysis. This principle can be easily extended to three or more cameras, which are sometimes commonly referred to as stereo images (i.e., "stereo" should not be interpreted in the narrowest sense of using only two cameras).An advantage of stereo (or multi-camera) depth imaging is that the required equipment components can be readily available and relatively inexpensive. For example, such a system may be built using conventional (2D) cameras, or existing (2D) cameras may be easily upgraded by adding one or more additional cameras. 【0099】 The processing that may be required to compute a corresponding depth pixel map (i.e., a depth image) is relatively simple and can be easily implemented in software and / or hardware (potentially leveraging graphical processing units, GPUs, processing, and / or dedicated hardware, e.g., application specific integrated circuits and / or field programmable gate arrays). An advantage of stereo or multi-camera depth imaging, for example, is that a scene containing a subject may be imaged without object-specific lighting and / or other direct manipulation. In other words, a scene may be imaged and processed to determine depth data (i.e., a third dimension in addition to planar image coordinates) without actively interfering with or affecting the scene, i.e., potentially except for general (generic) lighting, essentially passively. 【0100】 Depth images may also be acquired by active techniques. For example, a sheet of light can be scanned over a scene to image its reflections. From the shape and displacement of the imaged (line) reflection, the distance between the reflection (the points on said line, e.g., all points in the image after a complete scan of the scene) and a reference, e.g., a light source and / or a camera, can be calculated relatively easily, for example, using triangulation methods. Another type of active depth image that can be applied uses a structured light 3D scanner, which can be seen as a more complex version of the light sheet triangulation described above, and has additional advantages such as requiring less (or no) physical displacement of the camera and / or light source to fully qualify the depth values of the scene. 【0101】 Depth information can be acquired by a time-of-flight camera, LIDAR, or radar system. A possible advantage of time-of-flight camera depth imaging is that images can be collected substantially instantaneously, without scanning, for example, a point, line, structured light pattern, laser, wave, or generally any "active" (e.g., time-varying, e.g., scanning) analyzer across the scene. Other potential principles for depth imaging include interferometric techniques (e.g., relying on coherent light), coded aperture imaging, and / or possibly other techniques. 【0102】 Furthermore, acquiring reference image / spatial data step 102 may also include (e.g., substantially simultaneously) acquiring images (e.g., conventional 2D images and / or depth image data) of the object from different viewpoints (e.g., camera viewpoints). Thus, a camera system may also provide any of the foregoing data simultaneously from different viewpoints, e.g., to view the object from at least two different angles, e.g., to acquire image / spatial data from different camera positions (e.g., using different cameras in a camera system). Thus, even if depth or 3D data is not used, monitoring the position of the subject may still be possible by explicitly detecting movement in (any of) at least two different image planes. 【0103】 It will be understood that the comments above regarding image / spatial data apply equally to the reference data regarding live tracking data discussed further below. The reference data and live tracking data are generally of the same type, nature, and configuration, given that they are acquired by the same camera system, preferably with the same configuration settings. 【0104】 It should be noted that the camera diagnostic imaging system does not need to be connected to a system (e.g., an X-ray system), e.g., mechanical, electronic, and / or data processing integration of the camera system into the diagnostic imaging system is not required. The position and orientation of the camera system (or its individual camera components) do not need to be precisely determined with respect to the diagnostic imaging system (e.g., with respect to the radiation beam axis of a projection X-ray system); it is sufficient simply that the subject or relevant anatomical structures of the subject are observable by the camera, e.g., fall within the image frame. Therefore, complex calibration and / or alignment procedures are not required. Furthermore, the camera system does not need any input from the diagnostic imaging system, nor does it need to provide any output to the diagnostic imaging system, e.g., via electronic signals and / or interactions between the software of the respective systems. Because the method does not necessarily explicitly determine the position of the object relative to the coordinate system of the diagnostic imaging system, e.g., to check whether the position is correct for a particular examination, precise positioning and / or alignment of the camera system is not strictly required, nor is calibration of the camera coordinate system relative to the coordinate system of the diagnostic imaging system necessary. 【0105】 The method 100 may further include, after the spatial data and / or reference image of the subject is acquired 102 using the camera system (e.g., 114), repeatedly acquiring (103) additional images and / or spatial data (e.g., which may also be referred to as live tracking data) of the subject using the camera system, for example, periodically or substantially continuously acquiring the additional image / spatial data via video surveillance (e.g., the additional image / spatial data may correspond to or include a live video stream or the most recent camera image in the stream). 【0106】 The method also includes step 104 of comparing (e.g., repeatedly) the reference image and / or spatial data of the object, which represents the state of the object substantially at the time the trigger was received, with further image and / or spatial data of the object, which represents a more recent state of the object. For example, the further image and / or spatial data may be compared substantially continuously with the reference, e.g., at a reasonable frequency, which may also correspond to a sampling frequency at which the further image / spatial data is updated (e.g., at least 0.1 Hz, preferably at least 1 Hz, e.g., at least 10 Hz). Even if the additional data is continuously updated, or at least with some frequency, allowing for more or less fluid monitoring of the subject's current condition via camera observation, it will be understood that in a typical approach conventional video capture and processing frequencies may advantageously be used to update the additional image / spatial data at such a constant refresh rate (frames per second, FPS) that is not limited to these exemplary ranges and / or values, for example, in the range of 0.1 Hz to 120 Hz, for example, 10 Hz to 80 Hz, for example, 20 Hz to 60 Hz, for example, 25 Hz, 30 Hz, 40 Hz, or 50 Hz, although this does not necessarily have to mean a constant refresh frequency. 【0107】 Thus, by comparing the current image and / or spatial data with the reference data, any (relative and / or substantial) movement of the subject can be detected in a simple and effective manner. 【0108】 The method includes, at 105, providing an output representing this comparison of the further image and / or spatial data (e.g., a current image, e.g., a recently acquired image) to the reference image and / or spatial data to indicate movement of the subject (e.g., of at least one body part of interest of the subject) relative to a previous state of the subject represented by the reference image and / or spatial data. Thus, the attention of an operator and / or subject can be drawn to undesired movement of the subject (e.g., a patient) after initial preparations (represented by the reference data) to orient the subject are completed and before commencing a diagnostic (e.g., medical) imaging procedure. The output can be presented to the operator (and optionally to the subject) via display monitor(s) or other suitable human interface device. Preferably, the output can be dynamic, for example, by repeatedly updating the output based on a live data stream from the camera system. For example, the output information can be shown on the display by simple numerical value(s), by text strings, and / or in another suitable form, in a graphical representation (e.g., an overlay and / or other type of visualization). 【0109】 Providing an output may also include displaying the results of the comparison, for example, in a continuously (e.g., at some reasonable frequency) updated display format. For example, a difference image can be displayed to the operator (and / or directly to the subject so that the subject can automatically correct their position). Many different ways of visualizing the difference and / or the results of the comparison can be envisioned. For example, additional image and / or spatial data can be displayed on a display monitor (e.g., for the operator and / or subject) on which the difference image (e.g., obtained by image subtraction) can be shown as an overlay, e.g., a color overlay. Thus, differences between the subject's currently observed state relative to its reference state can be highlighted, for example, by a color to mark the differences. It will be appreciated that this can also be achieved by different types of overlays, such as changing image intensity instead of color (e.g., literally highlighting the differences) or creating an outline overlay that outlines the difference regions. For example, the perimeter of image regions where the image difference exceeds a predetermined threshold may be marked by a line, e.g., a solid or dashed line. 【0110】 Embodiments of the present invention provide (e.g., enable) an approach to assist in positioning a patient for a diagnostic imaging examination, e.g., by not requiring an explicit definition of the “correct” posture / positioning (e.g., other than a recorded reference image of the subject after being implicitly guided to this state by an operator) and / or by allowing detection of patient movement regardless of the intended examination, regardless of the patient's body (e.g., specific body shape, anatomical parameters, or even specific medical condition). In principle, embodiments of the present invention do not even need to assume that the patient is human; for example, a method or apparatus according to embodiments may be suitable for assisting in the positioning of human patients (e.g., in typical medical diagnostic applications), but may also be used, without any modification, to assist in the positioning of animal patients (e.g., in veterinary medicine). A system that can easily switch between human and veterinary medicine may not find widespread application, or may even be of very limited use in practice, but this clearly demonstrates the versatility of the approach. For example, methods according to embodiments may be used for patients with non-standard body shapes or characteristics, e.g., as a result of amputations, congenital conditions, etc., without the need for reconfiguration and / or modification. 【0111】 However, in methods according to embodiments of the present invention, comparing 104 the reference image and / or spatial data of the object may also include detecting 106 at least one image feature and / or landmark (a corresponding feature or features) in the reference image and / or spatial data and the further image and / or spatial data. Thus, a relative displacement of at least one image feature and / or landmark between the reference image and the further image and / or spatial data may be determined for use in determining the output. For example, at least one anatomical feature and / or landmark may be automatically detected (e.g., detected and located as a function of camera image coordinates) in the reference image and / or spatial data and the further image and / or spatial data. The anatomical feature and / or landmark may comprise, for example, one or more predetermined landmarks on one or more body parts, such as a shoulder, hip, wrist, finger (e.g., in a general sense or a specific finger, e.g., pinky or thumb), knee, ankle, toe (e.g., in a general sense or a specific toe), and / or landmarks on other anatomical parts of the body. Landmarks may include, for example, points (or, by extension, line segments and / or surface patches) that are recognizable (e.g., easily) by automated processing with high specificity and / or sensitivity. Such points may be salient features of a particular body part, e.g., the easily identifiable ulnar head prominence of the wrist, joint centers, and / or other such visible anatomical features. Such salient features may be easily detected in images, for example, by a suitable algorithm, e.g., by a combination of image processing filters tuned to the particular shape, orientation, boundary shape, and / or other visual (and / or generally spatial) characteristics of the body part (and / or a particular region or portion thereof, e.g., the immediate vicinity of the salient feature to be detected), by a trained machine learning model, and / or by any other suitable method known in the art. 【0112】 For example, a method (and / or apparatus) according to embodiments may be adapted to detect one or more particular image features (corresponding to anatomical features and / or landmarks) and detect and / or quantify movement of the subject based on displacement of such image features (and / or another spatially variable or variable, e.g., change in orientation), e.g., change in position of the anatomical feature and / or landmark in the further image and / or spatial data relative to the position of the same feature and / or landmark in the reference image and / or spatial data. 【0113】 It should be noted that while such automatic detection of at least one anatomical feature and / or landmark may reduce versatility, e.g., substantially universal applicability for patient positioning assistance in diagnostic imaging as discussed above, this is not necessarily the case, or only in a limited sense. For example, embodiments may also be configured to fall back to simpler approaches, e.g., for quantifying (and / or detecting) motion by image differencing (additional image vs. reference image) and / or for calculating at least one measure based on the difference images, e.g., maximum absolute difference, mean absolute difference, a predetermined percentile of the (e.g., absolute) differences, sum of squares, and / or any other such value for characterizing the magnitude of overall displacement. However, (a) when landmark features can be detected, changes in the position of such landmarks can be taken into account, such that motion detection is more sensitive to associated motion as opposed to any changes in image content, and / or the position of the landmarks can be indicated on the image (e.g., overlaid) based on simpler image comparison (e.g., based on difference images), further enhancing the ease with which the operator can verify that the correct position of the subject has been maintained. It should also be noted that such landmark features may be used to easily add 3D information to a 2D representation; for example, the 2D (image) representation may easily show the displacement of the subject within the image plane (e.g., by using a color overlay to highlight changes relative to a reference), while the landmark position may be shown on the visual representation with an indicator showing the depth (out-of-plane position) of the image feature and / or its relative change relative to a reference. 【0114】 Methods according to embodiments may be adapted to detect at least one anatomical feature and / or landmark, e.g., a set of different features and / or landmarks, in any particular reference image / spatial data, without necessarily relying on (i.e., requiring) the presence of each feature and / or landmark, or the presence of a particular subset or combination of anatomical features and / or landmarks. For example, one or more detection algorithms may be used to detect a variety of different anatomical landmarks, e.g., at least one salient point for each joint, bone, and / or other anatomical part of interest, such that, regardless of the context of a particular examination, it is likely that at least one, or at least a few, of the supported landmarks are detectable (and therefore will be detected). Thus, for example, regardless of whether a patient's arm or a patient's head is being examined, at least one or at least some points corresponding to points related to the positioning of the underlying anatomical structures (with a predetermined likelihood) may be detected. For example, for an imaging examination of an arm, bony protrusions of the wrist and elbow may be detected, and the detected displacement of at least one of them is likely related to the (substantial) movement of the arm as a whole. Similarly, for the head, landmark points on the chin, top of the skull, frontal tip of the nose, and / or other such easily detectable points can be used. The applied algorithm does not necessarily require input defining the correct set of landmarks to search; for example, the algorithm may attempt to detect all landmarks and retain only those for which there are no failed detections or for which the estimated detection accuracy is sufficiently high. Landmark detection may also be performed by a trained machine learning algorithm, such that the training of the model implicitly takes into account the co-occurrence of certain features to determine a set of detected features that is internally consistent (e.g., corresponds to combinations typically encountered in its training data). 【0115】 The landmark / feature detection process is preferably agnostic, e.g., it preferably does not take into account a particular geometric model of the subject and / or the subject's body parts. It should be noted that such landmark detection algorithms can be adapted to detect landmarks (e.g., in any combination from a library of supported landmark features) without requiring manual selection of a procedure or prior knowledge of the specific procedure being performed. Indeed, even if an inaccurate point is identified, e.g., a landmark intended as the center of the patella is detected in a reference camera image of the patient's elbow, this need not indicate a problem. Thus far, the detection of this feature and / or landmark point is sufficiently robust, i.e., patient movement, even if less anatomically relevant, can still be accurately identified and detected by a change in the position of this landmark point, so that the same point can be detected in further image / spatial data. 【0116】 Indeed, according to embodiments of the present invention, approaches for detecting 106 image features and / or landmarks may be used that rely on good detectability and salience of the image features, and not necessarily on a predetermined definition of the corresponding anatomical feature. For example, a filter or combination of filters may be applied to detect, for example, the center of a more or less homogeneous region of a certain size or dimension (e.g., a certain size range). Such an approach may be specifically tailored to detect the center of the patella, but due to its simplicity and robustness, it may also be included as a general feature detector. 【0117】 According to an embodiment, if optional detection of at least one anatomical feature and / or landmark is applied, the position of the at least one anatomical feature and / or landmark, or each, may be compared between the further image / spatial data and the reference image / spatial data to detect movement of the subject. In other words, comparing the reference image and / or spatial data of the subject with the further image and / or spatial data of the subject may include comparing, e.g., comparing the position of, the (or each) anatomical feature and / or landmark in the further image / spatial data to the reference image / spatial data. If multiple features are detected, movement may be characterized by the sum, maximum, minimum, and / or other summary statistics of individual displacements (e.g., displacements for a particular feature represented by the length of a displacement vector). More direct image comparisons, e.g., using difference images, may also be used alternatively (e.g., without requiring any landmark detection) or in combination with such landmark-based approaches. 【0118】 For example, the maximum absolute image difference or maximum displacement vector length of the optical flow map calculated to compare the reference versus the further image may be used as a fallback when the landmark is not detectable, or may be used as a fallback when the landmark is not detectable. A combination of landmark-based and direct image-based motion quantification may be used, for example by a weighted sum or other type of combination of these individual measures to express a value indicative of the object's motion (e.g., motion magnitude). 【0119】 Thus, substantial changes in the position of points indicating the position of anatomical structures or landmarks, such as shoulders, hips, wrists, fingers, knees, ankles, toes, etc. may be automatically detected. The output may indicate the currently detected position (in the further image / spatial data) (corresponding, i.e., associated with the same landmark) and the reference position (in the reference image / spatial data) and / or the difference between said positions, e.g., the magnitude of the displacement of the landmark. 【0120】 Providing an output 105 may also include determining a difference measure indicative of subject movement relative to a reference state based on said comparison 104, and alerting an operator when said difference measure exceeds a predetermined threshold that the subject is no longer in the intended reference position, e.g., has moved substantially relative to established reference data. Thus, the difference measure may be based on direct image difference (or other types of image comparison calculations), and / or on quantification of changes in position of detected image features and / or landmarks. 【0121】 As mentioned above, the location and / or amount of movement can be displayed by using an image overlay. FIG. 2 shows an exemplary visualization of a patient's movement relative to a frozen reference image of the (correctly) positioned patient. Note that FIG. 2 does not accurately represent the effect of a color overlay due to limitations in grayscale representation. Therefore, difference regions are alternatively indicated by a shaded region 21 with a contour line. While such a representation may be used in practice, it will be understood that, according to embodiments of the present invention, a color overlay (e.g., having a different color, e.g., a fully saturated transparent color over a monochrome source background image, e.g., the current camera image in a live stream) may actually be a more convenient form of representing such an overlay. 【0122】 Additionally, anatomical structures or landmarks, or simply salient image features (e.g., points and / or regions in the images that are stably detected in the video stream across the entire image sequence, e.g., local extrema, cusps, centers, or centroids of relatively homogeneous regions) are automatically detected (see above). The locations of such landmarks may be shown separately and / or in an overlay, e.g., as both the current position (determined in the live stream) and a reference position, a vector indicating the displacement between the reference and current positions, and / or in another suitable form. Alternatively and / or additionally, substantial changes in the images (current vs. reference) and / or landmark positions can be used to automatically detect substantial patient motion, e.g., to alert the operator that such substantial motion has occurred. 【0123】 When depth and / or 3D data (e.g., acquired by a depth, stereo, and / or 3D camera system) are used, patient motion can be detected, for example, when the depth (e.g., coordinates of landmark points in the normal direction to the image plane) changes, even when motion in the image plane is below a detection threshold (explicitly or implicitly assessed by an operator). Furthermore, detection of salient points representing anatomical features, for example, is more robust and easier to compute when depth and / or 3D data are used. For example, convex and / or concave regions (of the 3D body surface) can be detected, and their centers used as (likely) landmarks. Thus, the tip of the elbow, the tip of the nose, the center of the chin, the visible ulnar head in the wrist, and / or other such anatomical features can be easily detected with a simple approach. Similarly, saddle points may be anatomically relevant and / or enable robust detection of the same points on a moving body surface (or at least under slight motion, assuming the subject remains still, as typically required for diagnostic imaging procedures). 【0124】 A similar effect can be achieved by 2D imaging in two non-coplanar image planes, for example, by presenting and / or analyzing and / or visualizing two orthogonal (but not limited to) views of a subject acquired from at least two different cameras. 【0125】 The output allows an operator to objectively determine, prior to actual diagnostic image acquisition, whether repositioning of the object is necessary to obtain a good diagnostic (e.g., X-ray) image. This determination can be made by the operator or automatically, for example, by a simple decision algorithm (e.g., a metric representing the magnitude of motion, such as the difference measure described above, exceeding a predetermined threshold) and / or an artificial intelligence-based algorithm, for example, a trained machine learning model. 【0126】 In summary, the method can acquire at least one reference photographic image and / or depth (or 3D) image (or at least spatial data, e.g., 3D surface data in the form of a 3D point cloud or surface mesh) when the operator or controller determines that positioning setup is complete (reference data having been substantially acquired at the time the aforementioned trigger is received). An actual video stream from the same camera system can then be compared (e.g., continuously) with the reference data and, e.g., shown in an overlay. Movement can also be quantified and provided as an output, e.g., generating a warning when substantial movement away from the reference occurs. Deviations between the current camera image and the reference image that indicate a "good" positioning of the subject can be evaluated by an AI system, conventional algorithms, and / or displayed on a monitor for an objective decision by the operator when diagnostic image acquisition is performed as to whether patient repositioning is necessary. 【0127】 The output may be provided, for example, via a display monitor of a console computer for controlling the diagnostic imaging system (e.g., external to the acquisition room), or via a separate monitor dedicated to this purpose (e.g., avoiding the need for any integration with the diagnostic imaging system). 【0128】 The operator (e.g., medical technician, MTA) can be signaled explicitly and / or implicitly (by allowing the operator to compare conditions in a convenient data presentation, e.g., image overlay) if the deviation from the original spatial configuration (frozen in the reference data) is too large to proceed with diagnostic image acquisition. 【0129】 In a second aspect, the present invention relates to an apparatus for detecting movement of at least one body part of a subject in a diagnostic imaging examination. Figure 3 shows a schematic diagram of an apparatus 10 according to an embodiment of the present invention. For example, the diagnostic imaging examination may include an X-ray imaging examination, e.g., projection radiography. Accordingly, the apparatus 10 may be included in a diagnostic imaging system, e.g., an X-ray imaging system, or a workstation for such a system. For example, the X-ray imaging system may be an X-ray projection radiography system. 【0130】 The apparatus 10 may be adapted to detect changes in the position, orientation, and / or other spatial configuration of the subject, or at least the subject's anatomical structure, related to the examination, with respect to a reference state of the subject, e.g., so that the subject is correctly positioned for the examination. Thus, the apparatus may be adapted to assist in the positioning of the patient in the preparation steps of an imaging session, e.g., by checking for unwanted movements of the subject (e.g., patient) after the initial preparation to bring the subject into the correct spatial configuration for the examination and before actually performing the diagnostic imaging acquisition. For example, an operator (e.g., MTA) may place the patient in a position (generally, spatial configuration) that is considered suitable or desirable, e.g., optimal, for the intended diagnostic imaging examination. 【0131】 The apparatus 10 may comprise a processor, data storage memory, input, output, user interface, and / or other commonly known means for carrying out techniques such as those described above, e.g., programmed and / or configured accordingly. Thus, the apparatus may comprise a computer (i.e., adapted to be executed by a computer) and a computer program product according to embodiments of the present invention. Additionally or alternatively, the apparatus may comprise hardware specifically designed and / or configured to carry out the method according to the first embodiment of the present invention, e.g., an application specific integrated circuit and / or a field programmable gate array configured to carry out the method according to the first embodiment of the present invention. The apparatus may also comprise a computer. The apparatus may also comprise multiple processors, computers, and / or other processing devices operating in coordination, e.g., using a host-client architecture, a web-based architecture, cluster processing, and / or other forms of distributed processing, data collection, data presentation, and / or data storage. 【0132】 The apparatus comprises a processor 12 and an output 13. The apparatus also comprises an input 14 for receiving a trigger indicating that the current spatial configuration of the subject should be maintained for the diagnostic imaging examination. 【0133】 The input unit 14 may comprise (or be included in) a human interaction interface, e.g., buttons 17, a voice control interface 18, and / or a gesture detection system 19 for detecting gestures made by an operator. For example, once the subject is positioned in a desired position, the operator can provide a trigger to indicate that the subject's current position (i.e., spatial configuration) should be maintained. It will be appreciated that the gesture detection system 19 may comprise the camera system 11, described below, in combination with appropriate processing (gesture detection) performed by the processor 12. Similarly, the voice control interface 18 may comprise a microphone in combination with appropriate processing (voice command recognition) performed by the processor 12. 【0134】 The input 14 may include a proximity and / or position detection system 16 for detecting the proximity of an operator to a subject. For example, the proximity and / or position detection system 16 may include an RFID tag on the operator's body in combination with at least one RFID detection sensor (proximate the subject, i.e., in or near the examination region of the diagnostic imaging system). The proximity / position detection system 16 may include at least one optical gate to detect when the operator leaves the vicinity of the subject (i.e., the examination region). The proximity / position detection system 16 may include a sonar, radar, and / or lidar system, and / or another sensor system for operator presence, proximity, and / or position detection. Thus, a trigger may be generated when proximity detection indicates that the operator has left the vicinity of the subject, or when the operator's position is detected to be substantially removed from the subject, e.g., at a distance that makes direct physical interaction between the operator and the subject impossible and / or impractical, for purposes of assisting in locating the subject. The proximity / position detection system 16 may also use the camera system (in combination with appropriate processing by the processor) to detect when the operator leaves the examination region, for example when the operator leaves the camera image frame of a camera for monitoring the subject's position and / or when the subject is detected to be sufficiently far away from the subject in a camera image frame captured by a further (e.g., long shot) camera specifically dedicated for this purpose. Accordingly, the processor may be adapted to perform scene analysis of the live image stream from the camera system to detect a predetermined condition for generating a trigger and in response thereto generate the trigger, the predetermined condition corresponding to the operator leaving the immediate vicinity of the subject. 【0135】 Additionally or alternatively, input 14 may be adapted to receive a trigger from an automated system for detecting a predetermined reference spatial configuration of a subject, as required for a diagnostic imaging examination, in the live imaging stream provided by camera system 11. Thus, the trigger can be generated using a device that determines the appropriate spatial configuration of the subject for a particular examination and navigates the subject to the desired spatial configuration, as known in the art. Because such an automated system may be implemented by the same processing hardware, the trigger may be, for example, a virtual signal communicated via a memory flag, file, web socket, or similar mechanism for inter-process communication. Such an automated system may also be included in device 10 according to embodiments, but is not necessarily so. 【0136】 The apparatus 10 may also include an artificial intelligence module (e.g., a machine learning processor core) for evaluating the trained machine learning model. For example, this AI module may be included in the automation system described above. The AI module is adapted to generate a trigger signal by taking into account the output of the evaluated model. The trained machine learning model uses as input image and / or spatial data, and / or data obtained, for example, from a camera and / or a 3D surface scanning system 11, and / or data from the diagnostic imaging system, for example, received via an interface with the diagnostic imaging system. Such data received from the diagnostic imaging system may include, for example, device status information of the diagnostic imaging system and / or control input information received by the diagnostic imaging system from user interaction. Thus, the AI module can detect (implicit) regularities in the use of the diagnostic imaging system that indicate that a patient positioning step has been completed. Such implicit regularities and relationships can, for example, be pre-learned by a model based on an appropriate set of training data. It will be apparent that the AI module does not necessarily have to be physically separate from the processor described below; for example, the processor 12 may be adapted to implement the AI module. Alternatively, the AI module may be a dedicated hardware module (e.g., an ML core) for evaluating a trained machine learning model, e.g., a trained neural network. 【0137】 It will also be appreciated that inputs may be combined from different sources to determine the trigger signal to relay to the processor. For example, different user interfaces and / or detection modules may be combined, and their (trigger) outputs may be combined in any suitable (and / or user configurable) manner to arrive at a trigger for use in the processing described below. 【0138】 The apparatus 10 includes a camera and / or 3D scanning system 11 for acquiring images and / or spatial data of a subject. The camera and / or 3D scanning system may include at least one camera positioned to acquire two-dimensional and / or three-dimensional views of the subject and / or at least one relevant body part of the subject. The camera and / or 3D scanning system may comprise at least one optical camera for acquiring two-dimensional images. The camera and / or 3D scanning system may, for example, include multiple cameras positioned at different positions and / or to view the subject from different angles. 【0139】 The camera and / or 3D scanning system may be adapted to acquire depth information. The camera and / or 3D scanning system may comprise a depth camera. The camera and / or 3D scanning system may comprise multiple two-dimensional optical cameras for acquiring two-dimensional images from multiple different viewpoints (e.g., substantially simultaneously). Thus, the camera and / or 3D scanning system (and / or processor) may be adapted to determine depth information from the two-dimensional images, for example, by applying an algorithm for depth estimation from stereo or multi-camera images. 【0140】 The processor 12 is adapted to, upon receipt of the trigger, acquire reference images and / or spatial data of the object using the camera system. The reference images and / or spatial data may be acquired at the moment the trigger is received or a predetermined short time thereafter, and / or the reference images and / or spatial data may be selected from a buffer storing a stream of images and / or spatial data acquired by the camera system, for example, the selection corresponding to a (e.g., most recent) point in time before the trigger was received. 【0141】 The processor is further adapted to acquire further images and / or spatial data of the subject using the camera system after the reference images and / or spatial data of the subject are acquired. 【0142】 The reference image and / or spatial data (and further image and / or spatial data, generally of the same type and nature and typically corresponding to the same setup) may comprise conventional monochrome and / or color digital photographic images in the visible and / or infrared spectrum. The reference (and further) image and / or spatial data may comprise multiple images acquired simultaneously (or at least simultaneously) from different cameras, e.g., from different viewpoints. The reference (and further) image and / or spatial data may comprise 3D and / or depth information. 【0143】 The processor is adapted to compare the reference image and / or spatial data of the object representing a reference state of the object substantially at the time the trigger was received with further image and / or spatial data of the object representing a more recent state of the object. 【0144】 The processor may be adapted to compare the spatial data and / or the reference image of the subject by detecting at least one image feature and / or landmark in the reference image and / or spatial data and the further image and / or spatial data, comparing the position of the at least one image feature and / or landmark between the reference image and / or spatial data, and using it in determining the output. The image feature and / or landmark may include at least one anatomical landmark on a joint, bone, muscle, and / or other externally identifiable anatomical feature of the subject's body. The image feature and / or landmark may, for example, comprise one or more salient image features such that the position of a point on the imaging object (subject) corresponding to this salient image feature can be stably, accurately, and robustly tracked in different images (particularly at least the reference image / spatial data and the further image / spatial data). 【0145】 The processor may be adapted to compare the reference image and / or further image and / or spatial data of the object taking the three-dimensional information into account, for example, by determining 3D points (or surface segments or spatial regions) where corresponding acquired depth (and / or 3D) information in the reference image / spatial data substantially differs from corresponding depth (and / or 3D) information in the further image / spatial data. Such identified points (or surface or spatial regions) may be clustered or otherwise combined (e.g., organized into a suitable data representation) to enable a 3D visual representation of the differences (e.g., in an output image and / or overlay) and / or to quantify the patient's movement (displacement) in its current state relative to the reference state (e.g., for use as or in difference measurements, as discussed further below). 【0146】 The processor is configured to provide output data to an operator and / or the subject via the output 13. The output data represents a comparison of the further image and / or spatial data to the reference image and / or spatial data so as to indicate the subject's motion relative to the subject's reference state. For example, the shape, area and / or volume of the detected (2D or 3D) differences may be presented as (e.g., color) overlays and / or contours on the further image (e.g., a recently acquired image of the subject) and / or a 3D model visualization of the scene (e.g., a 3D visualization of the recently acquired image / spatial data of the subject). For example, a 3D outer surface of the subject (or its relevant body part) may be rendered and the difference regions may be marked with a different color or other characteristic (different from the characteristic values used for the main surface rendering) to highlight the differences. When referring to the overlay display of differences against further (e.g., most recently acquired) image / spatial data, it will be understood that although it may be preferable to visualize the live data stream using difference annotations (overlays) to avoid loss of available information in presentation to the operator due to processing artifacts, much the same effect can be achieved using an overlay of differences against the reference image / spatial data. 【0147】 The output allows an operator to objectively determine, prior to actual diagnostic image acquisition, whether repositioning of the object is necessary to obtain a good diagnostic (e.g., X-ray) image. This determination can be made by the operator or automatically, for example, by a simple decision algorithm (e.g., a metric representing the magnitude of movement above a predetermined threshold) and / or an artificial intelligence-based algorithm, e.g., a trained machine learning model, and / or a combination of the foregoing. 【0148】 The processor 12 may be adapted to repeat the steps of acquiring further image and / or spatial data via the camera system 11 (e.g., periodically and / or substantially continuously to acquire a live stream of further image and / or spatial data), comparing the reference image and / or spatial data to the further image and / or spatial data (e.g., comparing recently acquired further data to the reference data), and providing output data. Thus, at each iteration, the output data may be updated to represent, for example, a current movement of the subject relative to the reference state, such that a dynamic view of the current change in the subject's spatial configuration relative to a previous reference state of the subject is presented. 【0149】 The device may include a user interface, which may include, for example, a display monitor, a mouse, a keyboard, and / or one or more similar human interface devices known in the art. The user interface may be adapted to control the processes discussed above and below, for example, to provide triggers. The user interface may be adapted to interact with an operator, e.g., a medical professional, doctor, nurse, imaging technician, etc. For example, the user interface may be used by an operator to control the device and / or monitor the patient's position during a preparation phase for an imaging session. 【0150】 The output 13 may include, for example, a display monitor 15. The processor 12 may be adapted to present a visual representation of the comparison via the display monitor. The processor 12 may be adapted to repeatedly execute the monitoring loop described above to dynamically update the operator regarding the position (i.e., spatial configuration) of the subject relative to the reference state. 【0151】 The user interface may include an input 14 , but the input 14 is not necessarily (or merely) physically co-located with the output of the user interface, eg, a display monitor 15 . 【0152】 The processor may be adapted to provide as the output data, or as part of the output data, an image overlay showing the comparison in the formation of a difference image, as an overlay, for example a colour overlay, on the further image and / or spatial data. 【0153】 The processor may be adapted to determine difference measurements indicative of object movement relative to a reference state based on the comparison, for example, based on direct image comparison (e.g., difference images) and / or corresponding pairs of image features and / or landmarks in the reference and further image / spatial data. The processor may be adapted to provide output data, the output data including a warning to an operator when the difference measurements exceed a predetermined threshold, to indicate that the subject is no longer in the intended reference position. Additionally or alternatively, if the difference measurements exceed a predetermined threshold, a signal may be provided to the diagnostic imaging system to disable command execution of diagnostic image acquisition until the subject is repositioned (or until the operator overrides such disable signal). 【0154】 In a third aspect, the present invention relates to a diagnostic imaging system, the system being adapted to perform a method according to an embodiment of the first aspect of the invention and / or comprising an apparatus according to an embodiment of the second aspect of the invention. In a fourth aspect, the present invention relates to a workstation for a diagnostic imaging system, the workstation being adapted to perform a method according to an embodiment of the first aspect of the invention and / or comprising an apparatus according to an embodiment of the second aspect of the invention. The diagnostic imaging system may be a diagnostic (e.g. medical or veterinary) x-ray imaging system, for example a projection x-ray imaging system (e.g. for planar projection radiography). 【0155】 For example, FIG. 4 schematically illustrates a diagnostic X-ray projection imaging system 30 according to an embodiment of the present invention. Such an X-ray imaging device typically includes an X-ray detector 31 for acquiring X-ray images of a subject 32 by modulating the characteristics of an X-ray beam 33 emitted by an X-ray tube 34 as it propagates through the subject. Operation of the system is typically controlled by a workstation 35 (e.g., a control console), which may, for example, configure system settings, control (e.g., activate) the X-ray tube 34, and / or acquire images from the detector 31. The workstation may, for example, be configured to view acquired X-ray images. The system may (optionally) be integrated (e.g., at least partially) into the workstation 35, or may be provided as an essentially completely isolated system (e.g., to facilitate upgrades and / or installation in a portable device), comprising an apparatus 10 according to an embodiment of the present invention. The camera system 11 of the apparatus 10 according to an embodiment of the present invention is, for example, configured to monitor a subject 32 such that at least relevant anatomical structures of the subject (the head in the illustrated example) for the diagnostic imaging examination to be performed are included in the view cone 37 of the camera of the camera system. 【0156】 In a fifth embodiment, the invention relates to a computer program product for performing a method according to the first embodiment of the invention when the computer program product is executed on a computer (e.g., an apparatus according to the second embodiment of the invention). Other features or details of features of apparatus (e.g., computer program products, systems, and workstations) according to embodiments of the invention should be apparent in light of the above description of methods according to embodiments of the invention, and / or vice versa.

Claims

[Claim 1] A device for detecting the movement of at least one body part of a subject in a diagnostic imaging examination, wherein the device is A camera and / or a 3D surface scanning system for acquiring spatial data and / or images of the subject, An input unit for receiving a trigger signal indicating that the current spatial configuration of the subject should be maintained for the diagnostic imaging examination, Processor and Output section and It has, The input unit includes a proximity and / or position detection system for detecting the proximity of the operator to the subject, such that it generates the trigger signal by considering when the operator leaves the vicinity of the subject. The aforementioned processor, When the trigger signal is received, the camera and / or three-dimensional surface scanning system is used to acquire spatial data and / or a reference image of the subject, wherein the reference image and / or spatial data represent a reference state of the subject at the substantial time the trigger signal was received. After spatial data and / or reference images of the subject have been acquired, the camera and / or 3D surface scanning system is used to acquire spatial data and / or further images of the subject. The steps include comparing the aforementioned additional images and / or spatial data with the aforementioned reference images and / or spatial data, A step of providing output data to the operator and / or the subject via the output unit, wherein the output data represents the comparison such that it shows the movement of the subject relative to a reference state, and A device configured to perform the following actions. [Claim 2] The trigger signal is generated before the diagnostic imaging test is performed, and the reference image and / or spatial data represent the reference state of the subject before the diagnostic imaging test is performed. The apparatus according to claim 1, wherein the step of acquiring spatial data and / or further images of the subject using the camera and / or three-dimensional surface scanning system is performed before the diagnostic imaging examination is performed, and the comparison shows the movement of the subject before the diagnostic imaging examination is performed. [Claim 3] The apparatus according to claim 1, wherein the processor is configured to repeatedly perform the steps of: acquiring the further image and / or spatial data via the camera and / or three-dimensional surface scanning system; comparing the further image and / or spatial data with the reference image and / or spatial data; and providing the output data to present a dynamic view of the current change in the spatial configuration of the subject relative to a reference state of the subject. [Claim 4] The apparatus according to claim 1, wherein the output unit comprises a display monitor, and the processor is configured to present, via the output data, the shape, area, and / or volume of the two-dimensional and / or three-dimensional difference determined by the comparison, as an overlay and / or contour relating to the visualization of the further image and / or spatial data, and / or as markers and / or annotations associated with the visualization. [Claim 5] The apparatus according to claim 1, wherein the processor is configured to perform the steps of: determining a differential measurement value indicating the movement of the subject relative to a reference state based on the comparison; and outputting a warning to the operator and / or the subject and / or a signal to the diagnostic imaging system when the differential measurement value exceeds a predetermined threshold, such that the output data indicates that the subject is no longer in the reference state. [Claim 6] The apparatus according to claim 1, wherein the camera and / or three-dimensional surface scanning system comprises at least one camera and / or three-dimensional scanning device arranged to obtain two-dimensional and / or three-dimensional views of the at least one body part and / or the subject, and the at least one camera and / or three-dimensional scanning device comprises an optical camera for acquiring monochrome, color and / or multispectral two-dimensional images in the infrared and / or visible spectrum, and / or a plurality of cameras configured to observe the subject from different angles, and / or a depth camera and / or three-dimensional surface imaging system. [Claim 7] The apparatus according to claim 1, wherein the input unit further comprises a human interaction interface, a button, a voice control interface, and / or a gesture detection system. [Claim 8] The apparatus according to claim 1, wherein the proximity and / or position detection system comprises a radio frequency identification tag combined with at least one radio frequency identification tag detection sensor and / or at least one optical gate and / or a sonar, radar and / or lidar system and / or the proximity and / or position detection system is implemented by the processor by detecting and / or tracking the position of the operator in a live stream of images and / or spatial data acquired by the camera and / or three-dimensional surface scanning system. [Claim 9] The apparatus according to claim 1, wherein the input unit further comprises a connection unit for receiving the trigger signal from an automated system for detecting a predetermined reference spatial configuration of the subject, as shown for the diagnostic imaging examination, in a live imaging stream provided by the camera and / or three-dimensional surface scanning system. [Claim 10] The apparatus according to claim 1, further comprising an artificial intelligence module for evaluating a trained machine learning model and generating the trigger signal by considering the output of the evaluated model, wherein the trained machine learning model uses data from the diagnostic imaging system and / or the image and / or spatial data as input, and the data from the diagnostic imaging system comprises control input information received by the diagnostic imaging system from the device status information and / or user interaction of the diagnostic imaging system. [Claim 11] The apparatus according to claim 1, wherein the processor is configured to compare the further images and / or spatial data with the reference image and / or spatial data by detecting at least one image feature and / or landmark in the reference image and / or spatial data and the further images and / or spatial data, and by comparing the positions of the at least one image feature and / or landmark between the reference image and / or spatial data and the further images and / or spatial data. [Claim 12] A diagnostic imaging system comprising the apparatus described in any one of claims 1 to 11. [Claim 13] The diagnostic imaging system according to claim 12, wherein the diagnostic imaging system is an X-ray imaging system or a projection X-ray imaging system. [Claim 14] A method for detecting the movement of at least one body part of a subject in a diagnostic imaging examination, A step of receiving a trigger signal indicating that the current spatial configuration of the subject should be maintained for the diagnostic imaging examination, wherein the trigger signal is generated by a proximity and / or position detection system and the proximity of the operator to the subject is detected, taking into account when the operator leaves the vicinity of the subject. When the trigger is received, the steps include: acquiring spatial data and / or a reference image of the subject using a camera and / or a three-dimensional surface scanning system; After spatial data and / or reference images of the subject have been acquired, the camera and / or 3D surface scanning system is used to acquire further spatial data and / or images of the subject. The steps include comparing the aforementioned additional images and / or spatial data with the aforementioned reference images and / or spatial data, A step of providing the operator and / or the subject with an output representing a comparison of the further image and / or spatial data with the reference image and / or spatial data, thereby indicating the movement of the subject relative to a reference state of the subject represented by the reference image and / or spatial data. A method having [Claim 15] A computer program product for performing the method described in claim 14 when executed on a computer.

Images