Systems and methods for computing and visualizing position indicators of target anatomy

Abstract

The invention relates to a system for visualizing a position indicator of a target anatomy. The system includes a processor configured to receive an image from an image device, the image including target anatomy information, process the received target anatomy information using a neural network to predict at least one location indicator of a location of the target anatomy, and determine a location of the target anatomy using the at least one location indicator. A visual representation of the position indicator of the target anatomy is generated based on the analysis of the neural network, where the visual representation is visualized on the display, where the visual representation indicates by the position indicator whether the target anatomy is in an optimal position suitable for the medical imaging procedure. The invention also relates to a method for generating a visual representation of a position indicator of a target anatomy.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging. Specifically, the present invention relates to the field of visualization of position indicators of a target anatomical structure during X-ray imaging and / or fluoroscopic imaging, and to a method for generating a visual representation of the position indicator of the target anatomical structure. Background Art

[0002] During medical imaging, a key element in obtaining clinically valuable medical images is correct patient positioning. Depending on the projection, correct patient positioning requires a great deal of experience. The quality of patient positioning is judged based on the medical images received from the target anatomical structure. In daily clinical practice, patients are positioned based on the experience of the X-ray equipment / system user. Medical staff usually judge the corresponding positions of the bones or other anatomical elements in the medical image that indicate the position of the target anatomical structure. Especially for orthopedic images, because the position of the target anatomical structure is not ideal, this may lead to retakes, thus bringing additional radiation to the patient. Summary of the Invention

[0003] Therefore, there may be a need for a system for allowing a user to position a target anatomical structure, wherein the position should correspond to correct patient positioning to obtain good-quality medical imaging.

[0004] The object of the present invention is to provide a system that allows the user of a medical imaging device / system to correctly position the target anatomical structure, in particular a system that visualizes the actual position of the target anatomical structure to the user.

[0005] The object of the present invention is solved by the subject matter of the independent claims, wherein further embodiments are incorporated into the dependent claims. It should be understood that the following aspects of the present invention apply equally to the method, medical system (such as an X-ray system), computer program unit, and computer-readable medium. Therefore, any feature, function, step, and / or element described below with reference to one aspect of the present disclosure applies equally to any other aspect of the present disclosure.

[0006] According to a first aspect of the present invention, there is provided a system for visualizing a position indicator of a target anatomical structure. The system includes a processor configured to receive an image from an image device, the image including target anatomical structure information, and process the received target anatomical structure information using a neural network to predict at least one position indicator of the position of the target anatomical structure. The processor is further configured to generate a visual representation of the position indicator of the target anatomical structure based on an analysis of the neural network, wherein the visual representation is visualized on a display, and wherein the visual representation indicates whether the target anatomical structure is in a suitable position for a medical imaging procedure by the position indicator.

[0007] In the context of the present invention, the term "visualization" can be understood as describing an optical illustration or rendering of a position indicator. The visualization can be displayed on any device capable of indicating to a user, in a visual or optical form, a position indicator of any target anatomical structure. For example, the visualization can be performed in the interface of a computer or in the medical imaging device itself.

[0008] In the context of the present invention, the term "position indicator" can be understood as describing a marker, feature, and / or sign that is configured to visually present, in particular to a user, the position of a target anatomical structure. In particular, the indicator is configured and designed such that it indicates the position relevant to taking a medical image.

[0009] In the context of the present invention, the term "target anatomical structure" can be understood as describing an anatomical structure that should be examined using a medical imaging device (such as an X-ray device and / or a fluoroscopy device). The target anatomical structure can be any part of a patient's body to be examined by a medical imaging device. In particular, the present invention can focus on joint images, where it is often very challenging to evaluate corrective actions regarding how to improve positioning, but the present invention is not limited to joint imaging.

[0010] In the context of the present invention, the term "optimal position" can be understood as describing a position suitable for a medical imaging procedure. When the optimal position is obtained, the target anatomical structure does not have to be repositioned, which reduces the retaking of medical images and improves the quality of the taken medical images. Thus, with the correct position, the quality of the medical image taken from the correctly positioned target anatomical structure is improved.

[0011] As described herein, the present invention allows for obtaining clinically valuable medical images, such as valuable X-ray photographs. The key element is the correct positioning of the patient, in particular the correct positioning of the patient's body part, i.e., the target anatomical structure. The correct positioning may depend on the projection and requires a great deal of experience from a radiologist. Retrospective positioning visualization and prospective positioning visualization are proposed. Thus, the present invention as described in various embodiments herein is capable of correctly positioning the target anatomical structure before (prospectively) or after (retrospectively) taking a medical image. Thus, the user can even improve the patient positioning before taking a medical image. In addition, such visualization is easily understandable because the position indicator and its ideal relative position are well-known features for judging patient positioning in clinical practice.

[0012] According to an exemplary embodiment of the present invention, the position indicator of the target anatomical structure may be a set of position indicators of the bone contour. In particular, the position indicator may include two or more bone contours of the target anatomical structure. Bone contours typically occur in pairs, so it is advantageous to use at least two bone contours to determine the position quality of the target anatomical structure. The bone contours may be corresponding bone contours in pairs, which is a well-known feature in clinical practice for determining the position of a target anatomical structure (such as a joint or condyle). On the other hand, the position indicator may include more than two bone contours, so the position indicator may not be limited to at least two bone contours or a pair of bone contours. The corresponding amount of bone contours for the position indicator may depend on the target anatomical structure to be examined.

[0013] According to an exemplary embodiment of the present invention, the bone contour for position indication may be at least one of the contour of the condyle or the contour of the joint space. For example, for a lateral protrusion of the knee joint, it is important that the lateral condyle and the medial condyle overlap well, and for an anteroposterior protrusion of the ankle joint, the medial and lateral joint spaces should be clearly visible. The bone contour may be, for example, the contour of the lateral / medial joint surface of the talus of the tibia and / or the contour of the condyles (such as the femoral condyle and the humeral condyle), which are commonly used in clinical practice for repositioning the patient. Other examples of such bone contours are the contours on both sides of the joint space in the lateral and anteroposterior posterior protrusions present in the knee, ankle or elbow. The bone contours may occur in pairs, and the position of the target anatomical structure may be derived from this pair of bone contours. The above list of contours is not restrictive, and other position indicators may also be used.

[0014] According to an exemplary embodiment of the present invention, the visual representation may include a display of the position indicator of the target anatomical structure superimposed on the background image of the target anatomical structure, wherein the background image is at least a real-time representation of the target anatomical structure. Thus, by using the superimposition on the background image, the positioning indicator can be associated with the corresponding target anatomical structure, and the user can clearly determine from this superimposed visualization whether the position of the target anatomical structure is correct. The real-time representation may be received from an image device. The image device may be part of a system for visualization or may be an external component. At least the image device may communicate with the system for visualization to provide the image data of the image device to the system, particularly to the processor. Thus, the image device is configured to provide image information about the target anatomical structure and the background image. In other words, according to the information received from the image device, the system (particularly the processor) is configured to derive information about the target anatomical structure and / or the background image to use this information to visualize the position indicator. The real-time representation of the target anatomical structure may be any illustration suitable for visually indicating the target anatomical structure to the user.

[0015] According to an exemplary embodiment of the present invention, the background image may be at least one of a real-time image of the target anatomical structure, a real-time depth image of the target anatomical structure, or a real-time schematic image of the target anatomical structure. Depending on the technology used by the imaging device, the background image may be displayed / shown as one of the above images. In particular, the imaging device may be a multi-dimensional imaging device configured to generate at least one of 2D or 3D images. For example, a depth imaging device configured to capture a depth image or a depth image map of the target anatomical structure may be used to generate a depth image. This image may be presented to the user as a background image via visualization. Another example may be a direct live image captured by a camera as the imaging device, where a video of the target anatomical structure (e.g., a video showing a patient's knee) is used as the background image. The schematic image of the target anatomical structure may be an image in which the outline of the target anatomical structure is shown, which schematically shows the (external) shape of the target anatomical structure. When using a real-time image, the user may be able to move the target anatomical structure until the correct (ideal) position of the target anatomical structure is achieved, so that a medical image with good quality can be generated.

[0016] According to an exemplary embodiment of the present invention, the neural network may be trained using a data set composed of an X-ray image of the target anatomical structure, a depth image of the target anatomical structure, and an RGB image of the target anatomical structure. In the images used for training the neural network, relevant contours indicating the position of the target anatomical structure may be annotated, where the annotated position is at least one of the correct alignment position suitable for medical imaging and / or the misaligned position of the target anatomical structure. The neural network is trained with the information mentioned herein so as to be able to predict relevant position indicators, such as relevant bone contour pairs. The neural network may be a trained deep neural network, where the present invention is not limited to such a neural network. The annotation of the relevant position indicators is performed by a person with the necessary medical expertise. The annotated training data may include, for example, an X-ray image and a depth image or an RGB image, where the bone contour is annotated in the X-ray image. This information is transferred to the depth and / or RGB image, and the network is trained to predict the position of the contour based on the depth or RGB image. If the system is supposed to indicate a quality measurement, the training data of the neural network may also include X-ray images, depth images, and / or RGB images (one or more or a combination of each image) in which the quality is annotated. In addition, the trained neural network may be used in the system for visualization to predict position indicators on the image, such as bone contour pairs. The image may be a live stream of a depth and / or RGB image.

[0017] According to an exemplary embodiment of the present invention, the visual representation of the position indicator may include different line types for different positions. The different line types may be solid lines, dashed lines, and / or dotted lines or any combination thereof. When visualizing, for example, different position indicators, each position indicator may be indicated by a different line type. On the other hand, when the position indicator may include at least two bone contours, each bone contour may be indicated by a different line type to distinguish these different bone contours in the visualization. For example, the line type may indicate the lateral condyle and / or the medial condyle. In the drawings, the illustration of different line types regarding the position indicator will be described in more detail.

[0018] The visualization may also allow for an assessment of the rotational direction for improving patient positioning by indicating, for example, the laterality of the bone contour. Based on the relative positions of the bone contours, where each bone contour is indicated by a different line type, the user may derive how to correct the position of the target anatomy by rotation. Figure 5 More details are described.

[0019] According to another embodiment of the present invention, the quality of the position may be indicated by different colors in the visual representation. For example, to indicate good quality, which means the ideal correct position of the target anatomy, the position indicator includes green. On the other hand, when indicating that the quality is not ideal, orange may be selected as the color indicator, or for a poor quality case, red may be selected.

[0020] According to an exemplary embodiment of the present invention, the visual representation may further include guiding elements configured to guide the user to the correct position of the target anatomy suitable for a medical imaging procedure. For example, the guiding elements may be at least one arrow or a plurality of arrows for indicating the direction of movement. The indicated direction of movement may be the direction in which the target anatomy may be moved to be aligned / located in the ideal position. Thus, the guiding elements may be used to improve the visualization of the user's corrective actions.

[0021] According to an exemplary embodiment of the present invention, when the position indicator may show that the target anatomy is not in the optimal position, the processor may also be configured to use the guiding elements to indicate to the user how to align the target anatomy. The processor may be configured to compare the imaging position with the ideal position of the target anatomy and may calculate a corrective movement to reach the ideal position based on the comparison result.

[0022] According to an exemplary embodiment of the present invention, when the position indicator shows that the target anatomy is not in the optimal position, the processor is also configured to use the position indicator to indicate that the system geometry of the medical imaging system has not been correctly adjusted.

[0023] The processor can communicate with a corresponding medical imaging system, and the visualization can use a position indicator to indicate whether the position of the target anatomy must be adjusted or whether the system geometry (e.g., the tube angle of an X-ray device) is incorrect. The tube angle that should be corrected can be derived from the corresponding position indicator. For example, when the position indicator can be at least two bone contours and they are spaced apart from each other, the user can conclude that the tube angle needs to be corrected.

[0024] According to an exemplary embodiment of the present invention, the guiding element can be at least one of a visual guiding element or an acoustic guiding element displayed on a display. The guiding element can be a visual guiding element presented together with the visualization of the position indicator on the background image. Additionally or alternatively, the guiding element can be an acoustic guiding element. Different guiding elements that allow guiding the user can be applied.

[0025] According to an exemplary embodiment of the present invention, the system can further include an interface configured to allow a user to adjust the display of the visual representation of the target anatomy. The interface can be part of the system for visualization or can also be an external part. For example, the system for visualization can use a processor communicating with a computer or a computer network, where the interface is part of the computer or the computer network. Additionally, the interface can be part of a medical imaging device communicating with the system for visualization.

[0026] According to an exemplary embodiment of the present invention, the system can also be configured to adjust the visual representation when the alignment / position of the target anatomy changes, where the position indicator adapts to the change in the alignment of the target anatomy. In particular, when the background image of the visualization is a real-time view or real-time image of the target anatomy, the movement of the target anatomy can be directly displayed / shown. The system for visualization is configured to adjust the position indicator according to the real-time image / view received from the image device during the movement of the target anatomy. For example, the processor can use a trained neural network to adjust the position indicator for the real-time view / image of the target anatomy.

[0027] According to an exemplary embodiment of the present invention, the background image can be at least one of a medical image of the target anatomy, an RGB image of the target anatomy, a depth image of the target anatomy, or a schematic image of the target anatomy received before generating the visual representation, where the visual representation is superimposed on the background image of the target anatomy to indicate whether the imaged target anatomy is in the optimal position by the position indicator.

[0028] By visualizing medical images as background images, the system can retrospectively visualize the location of the target anatomical structure. The user can derive whether the location is correct from the visualization and can correct the location, which means repositioning the target anatomical structure to perform a reshoot of the medical image. For example, a pair of bone contours can be shown on an X-ray image, and the user can be guided to reposition for a reshoot. In a retrospective scenario, the background image is most likely an X-ray image at the exposure time point or an RGB, depth, or schematic image.

[0029] According to a second aspect of the invention, there is provided a method for generating a visual representation of a location indicator of a target anatomical structure. The method comprises the steps of: receiving target anatomical structure information from an image device, wherein the image device receives an image of the target anatomical structure, processing the received target anatomical structure information using a neural network to predict at least one location indicator of the target anatomical structure, generating a visual representation of the location indicator of the target anatomical structure based on an analysis of the neural network, displaying the visual representation on a display, and indicating whether the location of the target anatomical structure indicated by the location indicator is suitable for a medical imaging procedure.

[0030] The method may also be configured to perform the steps of representing functions as described in the embodiments of the system for visualization.

[0031] According to a third aspect of the invention, there is provided a computer program product. There is provided a computer program product or computer program unit, characterized in that it is adapted to perform the method steps of a method according to one of the foregoing embodiments on a suitable system. The computer program product may comprise instructions which, when the program is executed by a computer, cause the computer to perform the method of any of the embodiments described above. Thus, the computer program unit may be stored on a computer unit which may also be part of an embodiment of the invention. The computing unit may be adapted to execute or cause the execution of the steps of the above method. The computing unit may be adapted to operate automatically and / or execute the commands of a user. The computer program may be loaded into the working memory of a data processor. Thus, the data processor may be equipped to perform the method of the invention. This exemplary embodiment of the invention encompasses computer programs that use the invention from the start and computer programs that turn existing programs into programs that use the invention by updating. In addition, the computer program unit may be able to provide all the necessary steps to implement the process of the exemplary embodiments of the method described above.

[0032] According to another aspect of the present invention, there is provided a medical imaging system, wherein the medical imaging system includes a system for visualization according to any of the embodiments described herein. The medical imaging system can be an X-ray system and / or a fluoroscopy system. The medical imaging system equipped with the system as described in various embodiments herein is capable of indicating to the user or visualizing the correct position of the target anatomical structure, and can prevent reshooting due to the incorrect position of the target anatomical structure. In addition, due to the correct position of the target anatomical structure, the image quality is increased.

[0033] According to another aspect of the present invention, there is provided a computer-readable medium, such as a CD-ROM, on which a computer program unit is stored, and the computer program unit is described in the previous part. The computer program can be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium provided together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. However, the computer program can also be presented via a network such as the World Wide Web and can be downloaded from such a network into the working memory of a data processor. The computer-readable medium can include instructions that, when executed by a computer, cause the computer to execute the method of any one of the embodiments described herein.

[0034] It must be noted that the embodiments of the present invention are described with reference to different subjects. Specifically, some embodiments are described with reference to method-type claims, while other embodiments are described with reference to system / device-type claims. However, those skilled in the art will understand from the above and following descriptions that, unless otherwise stated, any combination between features related to different subjects is also considered to be disclosed in this application, in addition to any combination of features belonging to one type of subject. However, all features can be combined together to provide a synergistic effect, rather than just a simple addition of features. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] From the examples of the embodiments to be described below, the above and other aspects of the present invention are obvious and will be explained with reference to the examples of the embodiments. The present invention will be described in more detail below with reference to the examples of the embodiments, but the present invention is not limited thereto.

[0036] Figure 1 The visualization of a position indicator according to an embodiment of the present invention is shown.

[0037] Figure 2 Another visualization of a position indicator according to an embodiment of the present invention is shown.

[0038] Figure 3Shows another visualization of a position indicator according to an embodiment of the present invention.

[0039] Figure 4 Shows a further visualization of a position indicator according to an embodiment of the present invention.

[0040] Figure 5 Shows a comparison of visualizations of the same type at different positions according to an embodiment of the present invention.

[0041] Figure 6 Shows a flowchart of different steps performed by a system for visualizing a position indicator according to an embodiment of the present invention.

[0042] List of reference numerals:

[0043] 100 System

[0044] 101 Image device

[0045] 102 Processor

[0046] 103 Image data

[0047] 104 Neural network

[0048] 105 Visualization

[0049] 106 Display

[0050] 107 User

[0051] 108 Background image

[0052] 109a, b Position indicator

[0053] 210 Guide element

[0054] 310, 311 X-ray image

[0055] 412 Fibular contour

[0056] 413 Posterior contour of the articular surface of the talus for the tibia

[0057] 414 Anterior contour of the articular surface of the talus for the tibia Detailed description

[0058] Figure 1 Shows a visualization 105 of a position indicator 109 according to an embodiment of the present invention. The visualization 105 can be displayed on a display or an interface (not shown). In Figure 1 it, the visualization includes a background image 108, which is a depth image of the target anatomical structure, where different depths of the image (where the true depth information is continuous information, rather than as Figure 1The discrete information shown is schematically illustrated with different shadings. The background image can also be a real-time view / image of the target anatomical structure, such as a real-time depth image of the target anatomical structure, a real-time schematic image of the target anatomical structure, or a real-time RGB image of the target anatomical structure. At least two position indicators 109a and 109b are shown, which indicate pairs of bone contours, highlighting the displacement between the upper lateral contour and the upper medial contour of the talus. Different line types are used to distinguish different contours belonging to the position indicators. In this case, the line types are used to distinguish the upper lateral contour and the upper medial contour of the talus. The dashed position indicator 109b shows the lateral articular surface of the talus contour, and the solid position indicator 109a shows the medial articular surface of the talus contour. Since the lines do not overlap, the user can conclude from the visualization that the position of the target anatomical structure is not correctly set and needs to be corrected. Therefore, the user of the system for visualization can easily observe that the patient positioning is not ideal before taking a medical image. The user can now reposition the patient until the condyles overlap sufficiently, which can be achieved if almost a single condyle contour can be seen. For example, the positioning quality can be indicated to the user by switching from red or orange (if mispositioned) to green (if correctly positioned).

[0059] Figure 2 Another visualization 105 of a position indicator according to an embodiment of the present invention is shown. In Figure 2 a and Figure 2 b, the target anatomical structure is the ankle of the foot. The visualization 105 includes at least two position indicators 109a, 109b, indicating the bone contours of the talar condyles, similar to the Figure 1 position indicators shown. The background image 108 is different from the Figure 1 background image. In Figure 2 , the background image 108 is a schematic diagram of the foot, showing the contour of the foot. In Figure 2 , the position indicators 109 visualize a mispositioned foot because the position indicators 109a and 109b do not overlap, i.e., do not overlap with each other to form a single bone contour. In contrast, in the Figure 2 visualization of b, the correct and ideal position of the target anatomical structure is shown. After the user performs repositioning, the correct position as shown in Figure 2 b can be achieved. In addition, Figure 2 a guiding element 210 is shown, which is an arrow that visually indicates to the user that the target anatomical structure must be repositioned. For example, the arrow 210 can indicate the direction in which the foot must be rotated to the correct position. In the Figure 2 case shown, the arrow must point up or down.

[0060] Figure 3Shows another visualization 105 of the position indicator 109 according to an embodiment of the present invention. The visualization includes an X-ray image 311 and at least two position indicators 109a, b. The position indicator 109 includes two bone contours of the lateral / medial articular surfaces of the talus of the tibia. In addition, Figure 3 Shows a retrospective visualization 105 of the bone contour pair 109a, b, highlighting the displacement between the talar condyles, which highly indicates the quality of patient positioning. As a retrospective visualization 105, the X-ray image is received before the processor calculates the position indicator 109 using a neural network. In this example, color can be used to indicate quality, while the line type visualizes the lateral condyle 109b and the medial condyle 109a.

[0061] Figure 4 Shows another visualization 105 of the position indicator 109 according to an embodiment of the present invention. Figure 4 The target anatomy in [[]] is the anterior and posterior prominences of the ankle joint. As the position indicator 109, the posture indicating bone contours around the ankle joint space are used. The left side ( Figure 4 a) shows a retrospective visualization of the bone contours. This means that the background image 108 is an X-ray image of the target anatomy (ankle). The right side ( Figure 4 b) shows a prospective visualization 105, which is a real-time overlay based on a schematic image of the background image 108 as the ankle contour and the predicted posture indicating contours 414, 412, 413. 412 shows the fibular contour, 413 shows the posterior contour of the talar joint surface of the tibia, and 414 shows the anterior contour of the talar joint surface of the tibia. Thus, as Figure 4 shown, more than two bone contours can also be used to display the position of the target anatomy, so that the position indicator can include multiple bone contours.

[0062] Figure 5 Shows a comparison of visualizations 105 of the position indicator at different positions of the target anatomy according to an embodiment of the present invention. The two contours shown are part of one position indicator. In all Figure 5 a) to f), the dashed line type indicates the contour of the lateral articular surface of the talus of the tibia, and the solid line indicates the contour of the medial articular surface of the talus of the tibia. Based on the displayed contours, the user can correct the position by appropriate repositioning. In practice, the positioning will be improved by leg rotation (5b and 5c) or by changing the tube angle (5e and 5f). Figure 5 a) and Figure 5 d) show a perfect position without position error. In particular, the offset of the position indicator (indicated by the solid line and the dashed line in Figure 5 ) and the contours of the condyles show the rotation, movement of the target anatomy, and the change of the position indicator due to the movement, thus enabling adjustment.Figure 5 a) to c) show the offset of the contour caused by leg rotation. This means that if the leg rotates, the bone contours may cross each other. On the other hand, when the bone contours are spaced apart from each other and thus do not cross each other, it may be necessary to correct the tube angle. Figure 5 (d) to (f) show the contour offset caused by the tube angle. Therefore, the change in the tube angle can cause the bone contours to deviate from each other. It is also possible to combine the correction of the position of the target anatomy by rotation and by the tube angle.

[0063] Figure 6 A flowchart showing different steps performed by a system 100 for visualizing a position indicator 109 according to an embodiment of the present invention is shown. The system 100 for visualizing the position indicator 109 for the target anatomy includes a processor 102 configured to receive an image 103 or image information from an image device 101, the image including target anatomy information, to process the received target anatomy information using a neural network 104 to predict at least one position indicator 109 of the position of the target anatomy. The processor is further configured to generate a visual representation 105 of the position indicator 109 of the target anatomy based on an analysis of the neural network 104, wherein the visual representation 105 is visualized on a display 106. The visual representation 105 indicates whether the target anatomy is in the optimal position for a medical imaging procedure by the position indicator 109. A user 107 can interact with the system 100. For example, a guidance element generated from the system 100, particularly from the processor 102, can guide the user 107 to the correct position of the target anatomy suitable for a medical imaging procedure. The display 106 or any other interface is configured to allow the user 107 to adjust the display of the visual representation on the display. Non-limiting examples of user adjustments are adjusting the color for different quality levels, adjusting the limits to separate different quality levels, adjusting the line type and thickness of the lines, and adjusting the background image type (RGB, depth, or schematic). Figure 6The described system is capable of performing a method for generating a visual representation 105 of a location indicator of a target anatomical structure. The method includes the following steps: receiving target anatomical structure information 103 from an image device 101, where the image device 101 generates an image of the target anatomical structure. The step of generating an image of the target anatomical structure can be understood as describing that the image device can receive an image from an (RGB, depth) camera and / or generate an image from a corresponding camera. On the other hand, the image device itself can be a camera, where additional image processing components can be added. The method further includes the following steps: processing 102 the received target anatomical structure information using a neural network 104 to predict at least one location indicator 109 of the target anatomical structure, generating a visual representation 105 of the location indicator 109 of the target anatomical structure based on an analysis of the neural network 104, displaying the visual representation 105 on a display 106, and indicating whether the location of the target anatomical structure indicated by the location indicator 109 is suitable for a medical imaging procedure.

[0064] Although the invention has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive. The invention is not limited to the disclosed embodiments. Other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the dependent claims.

[0065] In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality of elements or steps. A single processor or other unit may implement the functions of several items recited in the claims. The fact that certain measures are recited in mutually different dependent claims does not mean that a combination of these measures cannot be advantageous. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A system for visualizing position indicators of a target anatomical structure, comprising: A processor configured to: Receive an image from an imaging device, the image including target anatomical structure information, Process the received target anatomical structure information using a neural network to predict at least one position indicator of the position of the target anatomical structure, Generate a visual representation of the position indicator of the target anatomical structure based on the analysis of the neural network, wherein the visual representation is visualized on a display, Wherein the visual representation indicates whether the target anatomical structure is in an optimal position suitable for a medical imaging procedure by the position indicator, Wherein the position indicator of the target anatomical structure is a set of position indicators of bone contours, in particular, the position indicator includes two or more bone contours of the target anatomical structure.

2. The system according to claim 1, Among them, The bone contour of the position indicator is at least one of the contour of the condyle or the contour of the joint space.

3. The system according to any one of the preceding claims, Among them, The visual representation includes a display of the position indicator of the target anatomical structure superimposed on a background image of the target anatomical structure, Wherein the background image is at least a real-time representation of the target anatomical structure.

4. The system according to claim 3, Among them, The background image is at least one of a real-time image of the target anatomical structure, a real-time depth image of the target anatomical structure, or a real-time schematic image of the target anatomical structure.

5. The system according to any one of the preceding claims, Among them, The neural network is trained using a data set composed of X-ray images of the target anatomical structure, depth images of the target anatomical structure, and / or RGB images of the target anatomical structure, Wherein, in the images used for training the neural network, annotations indicate relevant bone contours of the position of the target anatomical structure, Wherein the annotated positions are at least one of the correct alignment positions suitable for medical imaging and / or the misaligned positions of the target anatomical structure.

6. The system according to any one of claims 1 to 5, Among them, The visual representation of the position indicator includes different line types for different bone contours, Wherein the quality of the position is indicated by different colors in the visual representation.

7. The system according to any one of the preceding claims, Among them, The visual representation further includes a guiding element configured to guide the user to the correct position of the target anatomical structure suitable for a medical imaging procedure.

8. The system according to any one of the preceding claims, Among them, When the position indicator shows that the target anatomical structure is not in the optimal position, the processor is further configured to indicate that the system geometry of the medical imaging system is not correctly adjusted using the position indicator.

9. The system according to any one of claims 7 or 8, Among them, The guiding element is at least one of a visual guiding element or an acoustic guiding element displayed on the display.

10. The system according to any one of the preceding claims, the system further includes: an interface configured to allow a user to adjust the display of the visual representation of the target anatomical structure.

11. The system according to any one of the preceding claims, Among them, the system is further configured to adjust the visual representation when the alignment of the target anatomical structure changes, wherein the position indicator is adapted to the change in the alignment of the target anatomical structure.

12. The system according to any one of the preceding claims, Among them, the background image is at least one of a medical image of the target anatomical structure received before generating the visual representation, an RGB image of the target anatomical structure, a depth image of the target anatomical structure, or a schematic image of the target anatomical structure, wherein the visual representation is superimposed on the background image of the target anatomical structure to indicate whether the imaged target anatomical structure is in the optimal position by the position indicator.

13. A method for generating a visual representation of a position indicator of a target anatomical structure, the method comprising the steps of: receiving target anatomical structure information from an image device, wherein the image device generates an image of the target anatomical structure, processing the received target anatomical structure information using a neural network to predict at least one position indicator of the target anatomical structure, generating a visual representation of the position indicator of the target anatomical structure based on the analysis of the neural network, displaying the visual representation on a display, indicating whether the position of the target anatomical structure is suitable for a medical imaging process by the position indicator, wherein the position indicator of the target anatomical structure is a set of position indicators of a bone contour, in particular, the position indicator includes two or more bone contours of the target anatomical structure.

14. A computer program product comprising instructions that, when executed by a computer, cause the computer to perform the method according to claim 13.

Images