Automatic optimal X-ray emitter position detection for mobile X-ray

Abstract

In order to acquire better quality mobile X-ray images, a computer-implemented method is provided for determining a position of an X-ray emitter of a mobile X-ray device. The method comprises the following steps: receiving (210) (i) a camera-acquired image originating from a camera monitoring a patient in an X-ray imaging session, wherein the camera is registered to the origin of the X-ray emitter; (ii) a reference X-ray image of an internal body structure to be examined in an X-ray examination; and (iii) position information of an X-ray detector; detecting (220) and locating a plurality of anatomical landmarks in the camera-acquired image; determining (230) a distance from the X-ray emitter to the patient based on the camera-acquired image; generating (240) a virtual X-ray image of the internal body structure based on a plurality of detected anatomical landmarks, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector; registering (250) the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure; and determining (260) at least one parameter to adjust the position of the X-ray emitter based on the registration result.

Description

Technical Field

[0001] The invention relates to a computer implemented method for determining the position of an X-ray emitter of a mobile X-ray device, an X-ray emitter position determination device, an X-ray imaging system, a computer program product and a computer readable medium. Background Art

[0002] Mobile X-ray, also known as portable X-ray, is an important image acquisition modality. It allows the use of X-ray in places where fixed X-ray imaging is not feasible, such as the emergency department (ED), intensive care unit (ICU), etc. Mobile X-ray is mainly aimed at bedridden patients. Compared with fixed X-ray, it is more challenging to acquire X-ray images on portable X-ray because there are more degrees of freedom compared to fixed X-ray images.

[0003] Figure 1 The basic working principle of the mobile X-ray machine 10 is shown. First, the technician places the X-ray detector 12 on the patient (shown as Figure 1 The technician then manually sets the position of the X-ray emitter 14 so that the desired field of view can be captured by the X-ray detector 12. Finally, the technician acquires an image by activating the X-ray emitter 14. There are many parameters that can seriously affect the image quality, such as the position of the X-ray detector 12 (e.g., coordinates and rotation angle) and the position of the X-ray emitter (e.g., distance from the patient, rotation angle, and voltage).

[0004] US2020 / 0085385Al relates to generating a positioning signal during image acquisition to facilitate positioning of one or more of a patient, an X-ray source, or a detector. Summary of the invention

[0005] Therefore, there may be a need to acquire better quality mobile X-ray images.

[0006] The objects of the invention are solved by the subject-matter of the attached independent claims, wherein further embodiments are contained in the dependent claims.

[0007] According to a first aspect of the invention, there is provided a computer implemented method for determining a position of an X-ray emitter of a mobile X-ray device, comprising:

[0008] a) receiving (i) images derived from camera acquisition by a camera monitoring a patient in an X-ray imaging session, wherein the camera is registered to the origin of the X-ray emitter; (ii) reference X-ray images of internal body structures to be examined in the X-ray examination; and (iii) position information of the X-ray detector;

[0009] b) detecting and locating a plurality of anatomical landmarks in images acquired by the camera;

[0010] c) determining the distance from the X-ray emitter to the patient based on the image acquired by the camera;

[0011] d) generating a virtual X-ray image of the internal body structure based on a plurality of detected anatomical landmarks, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector;

[0012] e) registering the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure; and

[0013] f) determining at least one parameter based on the registration result to adjust the position of the X-ray emitter.

[0014] In other words, the present disclosure proposes a method that can automatically locate the optimal X-ray emitter position for an image using a reference X-ray image (e.g., a previous high-quality image from the same patient) or a reference image from an atlas that is considered appropriate for the imaging situation. With the method disclosed herein, a reduction in the radiation dose received by the patient can be achieved by reducing the number of retakes. In addition, a shortened turnaround time can be achieved by avoiding low-quality images from being sent to the PACS and rejected when they are reviewed. In addition, costs can also be reduced because duplication of multiple efforts can be reduced.

[0015] This will be explained in detail below, especially with regard to Figure 3 The examples shown are explained.

[0016] The step of generating a virtual X-ray image of the internal body structure further comprises:

[0017] generating a pseudo-density image of the patient based on the plurality of detected anatomical landmarks; and

[0018] The pseudo-density image of the patient is projected to the X-ray detector using cone beam projection based on the camera position of the camera, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector to obtain the virtual X-ray image of the internal body structure.

[0019] This will be explained in detail below, especially with regard to Figure 5 The examples shown are explained.

[0020] According to an embodiment of the present invention, the camera comprises a three-dimensional (3D) camera and / or a two-dimensional (2D) camera. The distance from the X-ray emitter to the patient is determined based on depth information in an image acquired by the camera or depth estimation based on a neural network.

[0021] This will be explained in detail below, especially with regard to Figure 3 Step 230 is shown for explanation.

[0022] According to an embodiment of the present invention, the step of registering the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure further comprises:

[0023] applying a pre-trained neural network to align the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure, wherein the pre-trained neural network has been trained to generate residual parameters of the camera position of the camera based on the virtual X-ray image, the reference X-ray image and the plurality of detected anatomical landmarks, wherein the residual parameters of the camera position can be used to transform the virtual X-ray image into the reference X-ray image.

[0024] This will be explained in detail below, especially with regard to Figure 3 The examples shown are explained.

[0025] According to an embodiment of the present invention, the at least one parameter for adjusting the position of the X-ray emitter comprises one or more of the following:

[0026] a parameter for adjusting the distance from the X-ray emitter to the patient; and

[0027] A parameter for adjusting the rotation angle of the X-ray emitter.

[0028] According to an embodiment of the present invention, the computer-implemented method further comprises:

[0029] An instruction signal is provided based on at least one determined parameter to guide a user to manually adjust the position of the X-ray emitter.

[0030] According to an embodiment of the present invention, the computer-implemented method further comprises:

[0031] Based on the at least one determined parameter a control signal is provided, which control signal can be used to control a mobile X-ray robot arm of the mobile X-ray device to adjust the position of the X-ray emitter.

[0032] According to an embodiment of the present invention, the reference X-ray image includes one or more of the following:

[0033] a previously acquired X-ray image of the patient's internal body structure; and

[0034] Reference X-ray images from the atlas.

[0035] According to a second aspect of the present invention, there is provided an X-ray emitter position determination device comprising a processing unit configured to perform the steps of the method according to the first aspect and any associated examples.

[0036] This will be explained in detail below, especially with regard to Figure 2 The examples shown are explained.

[0037] According to a third aspect of the present invention, there is provided an X-ray imaging system, comprising:

[0038] A mobile X-ray device comprising an X-ray emitter;

[0039] a camera mountable to the mobile X-ray device and configured to capture camera-acquired images from a patient in an X-ray imaging session, wherein the camera is registered to an origin of the X-ray emitter;

[0040] X-ray detectors;

[0041] a tracker device attachable to or embedded in the X-ray detector and configured to provide position information of the X-ray detector; and

[0042] The X-ray emitter position determination device according to the second aspect and any associated examples is configured to determine at least one parameter to adjust the position of the X-ray emitter.

[0043] This will be explained in detail below, especially with regard to Figure 2 The examples shown are explained.

[0044] According to an embodiment of the invention, the tracker device comprises one or more of the following: a marker device, a gyroscope and an antenna.

[0045] According to an embodiment of the present invention, the mobile X-ray device further comprises a mobile X-ray robot arm for supporting the X-ray emitter. The X-ray emitter position determination device is configured to provide a control signal to control the mobile X-ray robot arm of the mobile X-ray device to adjust the position of the X-ray emitter.

[0046] According to an embodiment of the present invention, the mobile X-ray device further comprises a display, which is configured to display instructions provided by the X-ray emitter position determination device to guide a user to manually adjust the position of the X-ray emitter.

[0047] The predicted directions are for the X-ray machine: they can be displayed for manual correction by the technician, or automatic correction by a mobile X-ray robotic arm (if present) can be implemented.

[0048] According to another aspect of the present invention, there is provided a computer program product comprising instructions which, when said program is executed by a processing unit, cause said processing unit to perform the steps of the method disclosed herein.

[0049] According to another aspect of the present invention, a computer readable medium is provided, on which the computer program product is stored.

[0050] It should be appreciated that all combinations of the above concepts and the additional concepts discussed in more detail below (as long as these concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of the claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein.

[0051] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In the drawings, like reference characters generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention.

[0053] Figure 1 The basic working principle of a mobile X-ray machine is shown.

[0054] Figure 2 An exemplary X-ray imaging system is illustrated.

[0055] Figure 3 A flow chart describing a computer-implemented method for determining a position of an X-ray emitter of a mobile X-ray device is illustrated.

[0056] Figure 4 An exemplary registration process is illustrated.

[0057] Figure 5 A flow chart describing generation of a virtual X-ray image of an internal body structure according to an embodiment is shown.

[0058] Figure 6 Shows Figure 2 The exemplary operating principle of the exemplary X-ray imaging system shown in FIG. DETAILED DESCRIPTION

[0059] In clinical practice, mobile X-ray systems may be limited in image quality compared to fixed X-ray systems, i.e., poor field of view, missed or cut anatomical structures. Poor images may lead to image retakes, which increases the radiation dose to the patient.

[0060] To this end, a method, apparatus and system are provided, which are aimed at improving image quality during the image acquisition phase and overcoming one or more of the above-mentioned problems of mobile X-ray. Specifically, a system is proposed that can automatically acquire better quality mobile X-ray images. The system disclosed herein can automatically locate the optimal X-ray emitter position for an image using a previous high-quality image from the same patient or a reference image from an atlas that is considered appropriate for the imaging situation.

[0061] Figure 2 An exemplary X-ray imaging system 100 according to an embodiment of the present invention is illustrated. The X-ray imaging system 100 includes a mobile X-ray device 10 having an X-ray emitter 14. Figure 2 As shown, the mobile X-ray device 10 also includes a chassis 16 that supports an arm (e.g., a robotic arm 18) and has a system of wheels 20 for manual or motor movement that allows the equipment to be transported. The robotic arm 18 can move horizontally and / or vertically and supports a head assembly 22 at its end in which the X-ray emitter 14 is located.

[0062] The X-ray imaging system 100 also includes a camera 24 that can be mounted to the mobile X-ray device 10 and is configured to capture camera-acquired images from the patient during an X-ray imaging session. The camera 24 is registered to the origin of the X-ray emitter 14. For example, Figure 2 As shown, the camera 24 can be located in the head assembly 22. In some examples, the camera 24 can be an embedded camera. In some other examples, the camera 24 can be detachably mounted to the head assembly 22. In some examples, the camera 24 can be a two-dimensional (2D) camera, which is configured to capture a scene by using a shooting lens and an image sensor. The image obtained is called a 2D image. In some examples, the camera 24 can be a 3D camera for capturing a three-dimensional (3D) image. The 3D camera can be a rangefinder camera that produces a 2D image showing the distance from a specific point to a point in the scene. The 3D camera can be, for example, a stereo camera, which is a camera type with two or more lenses, and the lens has a separate image sensor or film frame for each lens.

[0063] Figure 2 The illustrated X-ray imaging system 100 also includes a portable X-ray detector 12 that can be arranged behind the patient to measure the flux, spatial distribution, energy spectrum and / or other properties of the X-rays. The portable X-ray detector 12 can be mounted with a tracker device 26, such as a gyroscope, antenna, marker or other device, which helps locate the position of the portable X-ray detector relative to the X-ray emitter 14.

[0064] Figure 2 The illustrated X-ray imaging system 100 also includes an X-ray emitter position determination device 30 configured to determine at least one parameter to adjust the position of the X-ray emitter 14. The X-ray emitter position determination device 30 may include various physical and / or logical components for communicating and manipulating information, which may be implemented as hardware components (e.g., computing devices, processors, logic devices), executable computer program instructions (e.g., firmware, software) to be executed by various hardware components, or any combination thereof, as desired for a given set of design parameters or performance constraints.

[0065] In some embodiments, the X-ray emitter position determination device 30 may be embodied as or in a device such as Figure 2 The mobile X-ray device 10 or mobile device shown. The X-ray emitter position determination device 30 may include one or more microprocessors or computer processors that execute appropriate software. The processing unit of the device 10 may be embodied by one or more of these processors. The software may have been downloaded and / or stored in a corresponding memory, for example, a volatile memory such as RAM or a non-volatile memory such as flash memory. The software may include instructions that configure one or more processors to perform the functions described herein.

[0066] It should be noted that the X-ray emitter position determination device 30 can be implemented with or without a processor, and can also be implemented as a combination of dedicated hardware that performs certain functions and a processor (e.g., one or more programmed microprocessors and associated circuits) that performs other functions. For example, the functional units of the X-ray emitter position determination device 30 can be implemented in the device or apparatus in the form of programmable logic, for example, as a field programmable gate array (FPGA). In general, each functional unit of the device can be implemented in the form of a circuit.

[0067] although Figure 2 It can be shown that the X-ray emitter position determination device 30 is embodied in the mobile X-ray device 10, but it should be understood that in some embodiments, the X-ray emitter position determination device 30 can be embodied as a mobile device or embodied in a mobile device, such as a tablet computer.

[0068] The X-ray emitter position determination device 30 is configured to perform the method disclosed herein. Figure 3 The flowchart shown describes the method in detail.

[0069] Figure 3 A flow chart describing a computer-implemented method 200 for determining the position of an X-ray emitter of a mobile X-ray device is illustrated. The method 200 may be implemented as a device, module, or related component in a set of logic instructions stored in a non-transitory machine or computer-readable storage medium, such as a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), firmware, flash memory, etc.; in configurable logic, such as a programmable logic array (PLA), a field programmable gate array (FPGA), a complex programmable logic device (CPLD); in fixed-function hardware logic using circuit technology, such as an application-specific integrated circuit (ASIC), complementary metal oxide semiconductor (CMOS), or transistor-transistor logic (TTL) technology, or any combination thereof. For example, the computer program code that performs the operations shown in the method 200 may be written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as JAVA, SMALLTALK, C++, Python, or similar programming languages) and traditional procedural programming languages ​​(such as the "C" programming language or similar programming languages). For example, the exemplary method may be implemented as Figure 2 The device 30 shown in FIG.

[0070] In step 210, method 200 includes the following steps: receiving (i) images acquired by a camera from a camera monitoring a patient in an X-ray imaging session, wherein the camera is aligned to the origin of the X-ray emitter; (ii) reference X-ray images of internal body structures to be examined in the X-ray examination; and (iii) position information of the X-ray detector.

[0071] The images captured by the camera can be derived from Figure 2 , camera 24 is shown in the figure, camera 24 monitors the patient during the X-ray imaging session. In some examples, camera 24 can be a camera configured to send a real-time video stream to device 30, and device 30 can have a video processing unit to process the real-time video stream. In some examples, camera 24 can be a camera configured to capture images and send them to device 30, and device 30 can have an image processing unit to process the images. In some examples, the images captured by the camera can include one or more 3D images. In some examples, the images captured by the camera can include one or more 2D images.

[0072] The camera 24 is registered to the origin of the X-ray emitter 14 . Figure 4An exemplary registration process is illustrated. When an object is imaged, its representation is stored in a matrix of pixels, which can be addressed by their coordinates x,y. Typically, the origin (i.e., point 0,0) is located in the upper left corner of the matrix, with the x-axis running from left to right and the y-axis running from top to bottom. Unless the object and camera are rigidly attached to each other, imaging the object twice will result in two different matrices, with two different coordinate systems. Figure 4 In the example of , the patient's nose on image "a" is positioned further to the right and lower than the patient's nose on image "b". The two images can be registered together to evaluate the coordinate transformation that allows one image to be transformed into the other. Since the imaging plane is perpendicular to the axis of the camera, the transformation of the image directly translates into the camera movement required to reacquire an image (if the second image is available).

[0073] In this disclosure, it is proposed to use image registration in two separate instances:

[0074] The transformation from the camera to the emitter coordinate system is constant and can be expressed explicitly when designing the relative positions of the two objects; and

[0075] The change between the position of the emitter during two different imaging sessions may be more Figure 4 The translation and rotation shown are more complex. Therefore, it is proposed to use a neural network (such as a convolutional network) to learn this transformation. This will be explained in detail below.

[0076] Reference X-ray images of internal body structures to be examined in an X-ray examination can be downloaded from a picture archiving and communication system (PACS). The reference X-ray images can be previous high-quality scans of the patient or some reference images or atlases of good quality. In some examples, the reference X-ray images can be collected from different patients.

[0077] Position information of the X-ray detector 12 may be collected from a tracker device 26 attached to the X-ray detector 12 , such as a marker device, a gyroscope, an antenna, or any combination thereof.

[0078] In step 220, method 200 also includes the step of detecting and locating multiple anatomical landmarks in the image acquired by the camera. In some examples, a model of the patient can be determined before imaging so that the imaging parameters conform to the patient's anatomy. The model can include the locations of anatomical landmarks such as shoulders, pelvis, torso, knees, etc. The surface image of the acquired patient can be compared with a pre-modeled surface image library to determine a model corresponding to the patient. The determination can be performed by a neural network trained based on a pre-modeled surface image library. In some examples, the location of the head, shoulders, torso, knees, and ankles can be determined based on a 2D or 3D image. The neural network can be trained to automatically detect landmarks. For example, supervised learning can be applied to anatomical landmark positioning. See, for example, Gite, S., Mishra, A. and Kotecha, K. (2022), Enhanced lung image segmentation using deep learning, Neural Computing and Applications, 1-15.

[0079] In step 230, method 200 also includes a step of determining the distance from the X-ray emitter to the patient based on the image captured by the camera. If the camera is a 3D camera, the distance from the X-ray emitter to the patient can be determined based on the depth information in the image captured by the camera. If the camera is a 2D camera, the distance from the X-ray emitter to the patient can be determined based on a neural network-based depth estimation. For example, self-supervised learning can be applied to distance or depth estimation. See, for example, Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, MM, & Reid, I. (2019). Unsupervised scale-consistent depth and ego-motion learning from monocular video. Advances in neural information processing systems, 32.

[0080] In step 240 , the method 200 further includes the step of generating a virtual X-ray image of the internal body structure based on the plurality of detected anatomical landmarks, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector.

[0081] Figure 5 A flow chart describing one implementation of step 240 is shown.

[0082] In step 310 of step 240 , a pseudo-density image of the patient is generated based on the plurality of detected anatomical landmarks.

[0083] In step 320 of step 240 , a pseudo-density image of the patient is projected onto the X-ray detector using cone beam projection based on the camera position of the camera, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector to obtain a virtual X-ray image of the internal body structure.

[0084] In other words, a virtual X-ray image can be generated in two steps. First, anatomical landmarks are used to generate a pseudo-density image of the patient, for example, by a neural network. Such a network can be trained using annotated image pairs (e.g., CT images and corresponding masks). The neural network can be a convolutional network. Adversarial training can be used to train the model. For example, see Park, T., Liu, MY, Wang, TC, & Zhu, JY (2019). Semantic image synthesis with spatially-adaptive normalization. In Proceedings of the IEEE / CVF conference on computer vision and pattern recognition (pp. 2337-2346). The resulting pseudo-density image is then projected onto a detector given a camera position, a distance from the patient, and a relative detector position using cone beam projection. The image obtained is a virtual X-ray image.

[0085] Back to Figure 3 In step 250, the method 200 further includes the step of registering the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure.

[0086] In some examples, a pre-trained neural network can be applied to align a virtual X-ray image of an internal body structure with a reference X-ray image of the internal body structure. The pre-trained neural network has been trained to generate residual parameters of a camera position of a camera based on a virtual X-ray image, a reference X-ray image, and a plurality of detected anatomical landmarks. The residual parameters of the camera position can be used to transform the virtual X-ray image into a reference X-ray image. For example, the neural network has been trained in the following manner. The neural network accepts three inputs: a reference X-ray image, a virtual X-ray image, and an anatomical landmark map. The output of the model is the residual parameters of the camera position. These parameters can be applied to transform the virtual image into a reference image. The required training images are artificially sampled from pseudo-CT projections using static detector parameters and a flexible emitter. The alignment result is used to predict the direction of how to adjust the position of the emitter. The neural network can be a convolutional network. Self-supervised learning can be applied to train the model. For example, see Dalca, AV, Balakrishnan, G., Guttag, J., & Sabuncu, MR (2018, September). Unsupervised learning for fast probabilistic diffeomorphic registration. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 729-738). Springer, Cham.

[0087] In step 260, the method 200 further includes a step of determining at least one parameter based on the result of the registration to adjust the position of the X-ray emitter. In other words, the registration result is used to predict the direction of how to adjust the position of the emitter. The at least one parameter may include one or more of the following: a parameter for adjusting the distance from the X-ray emitter to the patient; and a parameter for adjusting the rotation angle of the X-ray emitter.

[0088] In some examples, the device 30 may provide an instruction signal based on at least one determined parameter to guide a user to manually adjust the position of the X-ray emitter. In some examples, the instruction signal may be a voice signal for guiding a technician to manually correct the position of the X-ray emitter. In some examples, the instruction signal may be a display instruction for guiding a technician to manually correct the position of the X-ray emitter. In some other examples, the device 30 may provide a control signal based on at least one determined parameter, which control signal may be used to control the mobile X-ray robot arm 18 of the mobile X-ray device 10 to adjust the position of the X-ray emitter 14.

[0089] Figure 6 Shows Figure 2 An exemplary operating principle of the exemplary X-ray imaging system 100 is shown.

[0090] The mobile X-ray machine 10 is placed in front of the patient (indicated by "a"). The X-ray detector 12 is placed behind the patient.

[0091] The technician can download a reference X-ray image (indicated by "b") from the PACS. It can be a high-quality previous scan or some reference images or atlas of high quality. The reference X-ray image is provided to the device 30. The camera 24 sends the image acquired by the camera to the device 30, for example, a real-time video stream or image.

[0092] Apparatus 30 may include a first neural network, also referred to as neural network A, to predict anatomical landmarks and distances to the patient (indicated by "c") based on images acquired by a camera in a video of the patient.

[0093] The apparatus 30 may include a second neural network, also referred to as neural network B, to predict a virtual X-ray image using anatomical landmarks (indicated by "d") and X-ray emitter (indicated by "f") and detector positions (indicated by "e"). The virtual X-ray image is generated in two steps. The 3D anatomical landmarks from neural network A are used to generate a pseudo-density image of the patient by neural network B. Such a network can be trained using annotated image pairs (e.g., CT images and corresponding masks). The resulting pseudo-density image is projected using cone beam projection to the detector at a given camera position, distance from the patient, and relative detector position. The obtained image is a virtual X-ray image.

[0094] The apparatus 30 may include a third neural network, also referred to as neural network C, to register a virtual X-ray (indicated by "h") with a reference X-ray image (indicated by "i") using anatomical landmarks (indicated by "g"). The neural network C has been trained in the following manner. It takes three inputs: a reference X-ray image, a virtual X-ray image and a map of anatomical landmarks. The output of the model is the residual parameters of the camera position. These parameters can be used to transform the virtual image into the reference image. The required training images are artificially sampled from pseudo-CT projections using static detector parameters and a flexible emitter. The registration results are used to predict directions as to how to adjust the position of the emitter.

[0095] The predicted directions (indicated with a "j") are used on the X-ray machine: they can be displayed for manual correction by the technician, or automatic correction by moving the X-ray robot arm (if present) can be achieved.

[0096] The methods, devices, and systems disclosed herein can automatically locate the optimal X-ray emitter position for an image using a previous high-quality image from the same patient or a reference image from an atlas that is deemed appropriate for the imaging situation, and can automatically acquire better quality mobile X-ray images. The methods, devices, and systems disclosed herein can reduce the number of retakes, thereby achieving a reduction in the radiation dose received by the patient. The methods, devices, and systems disclosed herein can avoid low-quality images being sent to a PACS and rejected upon review, thereby achieving reduced turnaround time. The methods, devices, and systems disclosed herein can also reduce costs because multiple work repetitions can be reduced.

[0097] In a further exemplary embodiment of the present invention, a computer program or a computer program element is provided, which is characterized by being adapted to execute the method steps of the method according to one of the preceding embodiments on a suitable system.

[0098] Therefore, the computer program element can be stored on a computer unit, which can also be part of an embodiment of the present invention. The computing unit can be suitable for executing the steps of the method described above or inducing the execution of the steps of the method described above. In addition, it can be suitable for operating the parts of the device described above. The computing unit can be suitable for automatically operating and / or executing the user's command. The computer program can be loaded into the working memory of a data processor. The data processor can thus be equipped to perform the method of the present invention.

[0099] This exemplary embodiment of the invention covers both a computer program that right from the beginning uses the invention and a computer program that, by means of an up-date, turns an existing program into a program that uses the invention.

[0100] Furthermore, the computer program element can provide all necessary steps for implementing the procedures of an exemplary embodiment of the method as described above.

[0101] According to another exemplary embodiment of the present invention, a computer-readable medium, such as a CD-ROM, is proposed, wherein the computer-readable medium has a computer program element stored on the computer-readable medium, the computer program element being described in the preceding section.

[0102] The computer program may be stored and / or distributed on suitable media, such as optical storage media or solid-state media provided together with or as part of other hardware, but the computer program may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0103] However, the computer program may also be present on a network such as the World Wide Web and can be downloaded from such a network into a working memory of a data processor. According to a further exemplary embodiment of the present invention, a medium for making a computer program element available for downloading is provided, the computer program element being arranged to perform a method according to one of the previously described embodiments of the present invention.

[0104] It must be noted that embodiments of the present invention are described with reference to different subject matters. Specifically, some embodiments are described with reference to method type claims, while other embodiments are described with reference to device type claims. However, it will be understood by a person skilled in the art from the above and following descriptions that, unless otherwise indicated, any combination of features belonging to one type of subject matter, in addition to any combination of features, any combination between features relating to different subject matters is also considered to be disclosed by the present application. However, all features can be combined to provide synergistic effects that exceed the simple sum of the features.

[0105] Although the present invention has been described and illustrated in detail in the drawings and the foregoing description, such description and illustration should be considered illustrative or exemplary rather than restrictive. The present invention is not limited to the disclosed embodiments. Other variations of the disclosed embodiments can be understood and implemented by those skilled in the art in practicing the claimed invention by studying the drawings, the disclosure, and the dependent claims.

[0106] In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. Although certain measures are recited in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A computer-implemented method for determining the position of an X-ray emitter of a mobile X-ray device, include: Receiving (210) (i) images derived from camera acquisition by a camera monitoring a patient in an X-ray imaging session, wherein the camera is registered to the origin of the X-ray emitter; (ii) reference X-ray images of internal body structures to be examined in the X-ray examination; and (iii) position information of the X-ray detector; detecting (220) and locating a plurality of anatomical landmarks in an image acquired by the camera; determining (230) a distance from the X-ray emitter to the patient based on the image captured by the camera; generating (240) a virtual X-ray image of the internal body structure based on a plurality of detected anatomical landmarks, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector; generating (310) a pseudo-density image of the patient based on the plurality of detected anatomical landmarks; and projecting (320) the pseudo-density image of the patient to the X-ray detector using cone beam projection based on the camera position of the camera, the distance from the X-ray emitter to the patient, and the position information of the X-ray detector to obtain the virtual X-ray image of the internal body structure, registering the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure (250); and At least one parameter is determined (260) based on the registration result to adjust the position of the X-ray emitter.

2. The computer-implemented method of claim 1, in, The camera includes a three-dimensional 3D camera and a two-dimensional 2D camera; and Wherein, the distance from the X-ray emitter to the patient is determined based on depth information in the image captured by the camera or depth estimation based on a neural network.

3. The computer-implemented method according to claim 1 or 2, in, The step of registering the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure further comprises: applying a pre-trained neural network to align the virtual X-ray image of the internal body structure with the reference X-ray image of the internal body structure, wherein the pre-trained neural network has been trained to generate residual parameters of the camera position of the camera based on the virtual X-ray image, the reference X-ray image and the plurality of detected anatomical landmarks, wherein the residual parameters of the camera position can be used to transform the virtual X-ray image into the reference X-ray image.

4. The computer-implemented method according to claim 1 or 2, in, The at least one parameter for adjusting the position of the X-ray emitter comprises one or more of the following: a parameter for adjusting the distance from the X-ray emitter to the patient; and A parameter for adjusting the rotation angle of the X-ray emitter.

5. The computer-implemented method according to claim 1 or 2, further comprising: include: An instruction signal is provided based on at least one determined parameter to guide a user to manually adjust the position of the X-ray emitter.

6. The computer-implemented method of claim 1 or 2, further comprising: include: Based on the at least one determined parameter a control signal is provided, which control signal can be used to control a mobile X-ray robot arm of the mobile X-ray device to adjust the position of the X-ray emitter.

7. The computer-implemented method according to claim 1 or 2, in, The reference X-ray image includes one or more of the following: a previously acquired X-ray image of the patient's internal body structure; and Reference X-ray images from the atlas.

8. An X-ray emitter position determination device (30) comprising a processing unit configured to perform the steps of the method according to any of the preceding claims.

9. An X-ray imaging system (100), include: A mobile X-ray device (10) comprising an X-ray emitter (14); a camera (24) mountable to the mobile X-ray device and configured to capture camera-acquired images from a patient during an X-ray imaging session, wherein the camera is registered to an origin of the X-ray emitter; X-ray detector (12); a tracker device (26) attachable to or embedded in the X-ray detector and configured to provide position information of the X-ray detector; and The X-ray emitter position determination device according to claim 8, configured to determine at least one parameter to adjust the position of the X-ray emitter.

10. The X-ray imaging system according to claim 9, in, The tracker device includes one or more of the following: Marker equipment; Gyroscope; and antenna.

11. The X-ray imaging system according to claim 9 or 10, in, The mobile X-ray device also includes a mobile X-ray robot arm for supporting the X-ray emitter; and Wherein, the X-ray emitter position determination device is configured to provide a control signal to control the mobile X-ray robot arm of the mobile X-ray device to adjust the position of the X-ray emitter.

12. The X-ray imaging system according to claim 9 or 10, further comprising: include: A display is configured to display instructions provided by the X-ray emitter position determination device to guide a user to manually adjust the position of the X-ray emitter.

13. A computer program product comprising instructions for causing a processing unit to perform the steps of the method according to any one of claims 1 to 7 when said program is run by the processing unit.

14. A computer readable medium having stored thereon instructions which, when executed by a processing unit, cause the processing unit to perform the steps of the method according to any one of claims 1 to 7.

Images