Assistance for scapular positioning in chest X-ray imaging

Abstract

The present invention relates to assisting in positioning of the scapula in chest X-ray imaging. A system and associated method for assisting positioning of a subject in chest X-ray imaging is provided, the system comprising an optical detection device 110, a user interface 130, and a processor 120 connected to the optical detection device 110 and the user interface 130. The processor 120 is thereby configured to perform the steps of receiving an optical image signal of a back view of a subject S, determining a current positioning of a scapula of the subject S based on the optical image signal, the current positioning of the scapula being evaluated with respect to whether and / or to what extent the scapula overlaps with the lung field of the subject to be imaged, and determining feedback for positioning the subject S and / or its scapula based on the determined current positioning of the scapula. The user interface 130 is configured to provide feedback for positioning the subject.

Description

[Technical Field]

[0001] The present invention relates to medical imaging, and more particularly to a computer-implemented method, a system, and a computer program for assisting subject positioning in chest X-ray imaging. [Background technology]

[0002] In medical imaging, such as X-ray imaging, proper subject positioning can be considered important to achieve diagnostic quality X-ray images. Summary of the Invention [Problem to be solved by the invention]

[0003] For chest x-rays, the scapulae must be rotated outside the lung fields because if they are not, important parts of the lung fields may be partially obscured, making the image difficult to interpret.

[0004] If scapular positioning results in lung field shielding or overlap, image acquisition may need to be repeated, which is time-consuming, causes longer occupation of the X-ray imaging equipment, and results in higher radiation doses to the patient. The required subject positioning is therefore often not easy or very cumbersome, so detailed instructions by the operator are required to achieve proper scapular positioning. Furthermore, time pressure and lack of experience can lead to improper subject positioning, which reduces the diagnostic quality of the X-ray images.

[0005] Therefore, there may be a need for improved means to at least assist in positioning a subject in a manner that allows medical images to be acquired with the scapula in a desired positioning. [Means for solving the problem]

[0006] The object of the present invention is solved by the subject matter of the independent claims, further embodiments are incorporated in the dependent claims.

[0007] According to a first aspect, there is provided a computer-implemented method for assisting subject positioning in chest X-ray imaging, comprising the steps of receiving optical image signals of a dorsal view of the subject, and determining a current positioning of the subject's scapula based on the optical image signals, the current positioning of the scapula being evaluated with respect to whether and / or to what extent the scapula overlaps the subject's lung field being imaged. The method further comprises determining feedback for positioning the subject and / or its scapula based on the determined current positioning of the scapula, and providing the feedback for positioning the subject.

[0008] In this way, the required positioning of the subject and / or the required positioning of their scapula, which positioning is rather cumbersome and not easy to achieve, can be automatically assisted by automatically determining appropriate instructions to achieve good scapular positioning and providing such instructions to an operator, e.g., a radiographer. Furthermore, the above method is performed without radiation, since optical image signals, e.g., from a camera, are used, thereby limiting or even reducing the radiation dose to the subject.

[0009] In other words, in chest imaging, it is desirable for the scapula to be rotated outside the lung field, because otherwise important parts of the lung field may be masked and partially occluded, and the method allows for evaluation and improvement of scapular positioning with regard to the impact of positioning on imaging quality.

[0010] As used herein, a dorsal view of a subject or an optical image thereof can be understood as an image of the subject's back at the level of the chest and scapula. Optical images can thereby be understood to be distinguished from X-ray images as images taken without radiation, and can be acquired by an optical detection device, such as an optical camera, a depth-resolved camera, etc., having a known relative position to the focal point of the X-ray device, e.g., the X-ray tube, used in actual X-ray imaging.

[0011] Depth information can be understood as, for example, pixel-by-pixel information about the distance from the object to the optical detection device and / or X-ray device. Depth information can also include a depth map, from which, for example, bumps, depressions, flattening, etc. of the object can be recognized.

[0012] The feedback, which may be output graphically, e.g., via a display or the like, or audibly, e.g., via loudspeakers, headphones, etc., may indicate, at least in a sufficient manner, that the positioning is already correct, i.e., the feedback may confirm the correct positioning. However, if there is a deviation between the current positioning and the desired target positioning, the feedback may indicate how the positioning of the subject and / or scapula should be changed to comply with the target or desired positioning, which does not cover or overlap the lung fields of the subject being imaged.

[0013] As used herein, the optical image signal may indicate the outward rotation of the scapula relative to the torso and / or center of the subject's body, whereby with sufficient outward rotation, good visualization of the lung fields may be achieved.

[0014] In one embodiment, determining the current positioning of the scapula may include determining the positioning of the subject's arm and / or wrist from the optical image signal, which indicates the current positioning of the scapula. For example, the subject may undergo an examination assuming that the wrist is positioned on the subject's hips and / or back. The above method allows this to be automatically checked from the measured optical image signal, e.g., a camera signal, and feedback and / or warnings can be communicated to the operator as needed. Furthermore, in not all cases, the subject may be asked to position the wrist on the hips and / or back, as this is not always possible for the subject, e.g., due to physical constraints. Therefore, the patient may be asked to use a handhold attached to, for example, an X-ray imaging device, e.g., a detector. In this case, instead of detecting the wrist, the subject's forearm may be detected and used to determine the position of the scapula.

[0015] According to one embodiment, a set of landmarks on or in the subject can be derived from the optical image signal to assess the current positioning of the scapula. For example, a set of landmarks indicating the position of the scapula can be automatically detected in or from the optical image signal, e.g., via a deep convolutional neural network. If landmarks are detected only on the RGB channels of an optical detection device, their corresponding positions in 3D space can be inferred from the depth channel or estimated using a stereo, i.e., multi-view, camera device. Furthermore, it may also be possible to calculate distance estimates from a single RGB camera using a trained neural network. As an example, given a set of detected landmarks, their constellations can be analyzed and compared to a desired constellation for a good quality X-ray image of the scapula positioning. This can be achieved, for example, by deriving a plane spanned by landmarks on the subject's left and right shoulders, elbows, and wrists, or by landmarks on the back, and / or by calculating angulation angles and comparing these angles with thresholds for achieving good scapular positioning, which can be obtained from clinical studies, etc. In this way, scapular positioning can be determined in a simple manner and with high accuracy, without the use of radiation.

[0016] In one embodiment, a geometric relationship indicative of the current positioning of the scapula can be determined from the set of landmarks. For example, the geometric relationship can indicate a desired constellation of good quality for the positioning of the scapula. By way of example, the constellation of the set of landmarks can be evaluated by grouping the landmarks, for example, into a triangle, calculating the angulation angles, and comparing them to a previously learned threshold angle, for example, for rotating the scapula completely outside the lung field. In this way, the positioning of the scapula can be determined in a simple manner and with high accuracy without the use of radiation.

[0017] According to one embodiment, a plane spanning one or more limbs of the subject can be determined from a set of landmarks, and the determined plane can be compared to a target value to derive the current positioning of the scapula. For example, the plane or planes can be spanned by back landmarks and / or shoulder landmarks and / or spanned by the subject's elbow and wrist. In this way, the positioning of the scapula can be determined in a simple manner and with high accuracy without the use of radiation.

[0018] In one embodiment, at least one angle between the subject's arm and their torso and / or their body center, and / or the X-ray imaging device detector used for chest X-ray imaging is determined from a set of landmarks, and the at least one determined angle is compared with a target value to derive the current positioning of the scapula. For example, the angulation angle can be calculated and compared with a threshold value for achieving good scapular positioning, which can be obtained from clinical studies, etc. In this way, the positioning of the scapula can be determined in a simple manner and with high accuracy without using radiation.

[0019] According to one embodiment, planes and / or angles can be determined for both sides of the subject, i.e., both scapulae, and the symmetry and / or congruence of both sides can be determined to derive the current positioning of the scapulae. In this way, the positioning of the scapulae can be determined in a simple manner and with high accuracy without the use of radiation.

[0020] In one embodiment, one or more contours of the subject and / or one or more surface characteristics of the subject can be derived from at least the optical image signal to assess the current positioning of the scapula. For example, instead of or in addition to detecting and / or determining landmarks, other features that predict the positioning of the scapula can be automatically detected and assessed. These features can include the contour, e.g., a portion of the contour, or surface characteristics of the subject, e.g., curvature. In this way, the positioning of the scapula can be determined in a simple manner and with high accuracy without the use of radiation.

[0021] According to one embodiment, the feedback can include or form a trigger signal configured to control and / or prevent image acquisition based on scapular positioning. For example, the method can be implemented in or connected to an acquisition system of an X-ray imaging device, such that a warning is transmitted to an operator if the subject moves their scapula immediately before acquisition, e.g., after the operator leaves the acquisition room. Furthermore, the method can enable disabling of an acquisition release button if such a potential quality issue is detected. In this manner, X-ray image acquisition can be controlled based on scapular positioning.

[0022] In one embodiment, the optical image signal can be received by a classifier and / or model trained on annotated training data, where the classifier determines the current positioning of the scapula based at least on the optical image signal. For example, the optical image signal can be acquired and provided by an optical detection device, which can be an RGB camera, an RGB-D camera, i.e., a depth-resolved camera, a stereo camera device, etc. The classifier and / or model can be configured to map the optical image signal to a prediction of scapula overlap, and such classifier and / or model can be trained on sufficient, e.g., annotated, optical image signal-target positioning data or pairs. In this manner, several camera devices can be used to provide the optical image signal.

[0023] According to one embodiment, depth information data can be received from a depth channel of an optical detection device used to acquire an optical image signal of a back view of the subject. For example, the depth information can be received from a depth-resolving camera having a known relative position to the focal spot of an X-ray tube, such as mounted on the X-ray tube head.

[0024] In one embodiment, the depth information data can be received directly from a 3D depth map based on at least an optical image signal. For example, instead of using a two-step approach of first detecting features such as landmarks, contours, etc., and then evaluating them, a single forward model trained in an end-to-end manner can be used.

[0025] According to one embodiment, the depth information data can be determined based on a stereo optical detection device used to acquire optical image signals of a rear view of the subject.

[0026] According to one embodiment, the depth information data can be received from a classifier trained on the annotated training data, and such classifier determines the current positioning of the scapula based at least on the optical image signal. For example, features derived from or detected in the optical image signal and / or the depth information data can be fed to a classifier, e.g., a neural network, trained on the annotated data. Furthermore, the classifier can be configured and / or trained to take into account additional factors such as BMI, subject thickness, or the subject's limb proportions. In this way, the positioning of the scapula can be determined in a simple manner and with high accuracy without the use of radiation.

[0027] According to a second aspect, there is provided a system for assisting subject positioning in chest X-ray imaging. The system can be configured to perform the method according to the first aspect. The system includes an optical detection device, a user interface, and a processor connected to the optical detection device and the user interface. The processor is configured to receive optical image signals of a dorsal view of the subject, determine a current positioning of the subject's scapula based on the optical image signals, the current positioning of the scapula being evaluated with respect to whether it overlaps or does not overlap with the subject's lung field being imaged and / or the degree of overlap, and determine feedback for positioning the subject and / or its scapula based on the determined current positioning of the scapula. The user interface is further configured to provide feedback for positioning the subject.

[0028] In this way, the required positioning of the subject and / or their scapular positioning, which is rather cumbersome and not easy to achieve, can be automatically assisted by automatically determining appropriate instructions to achieve good scapular positioning and providing such instructions to an operator, e.g., an X-ray technician.

[0029] For example, the optical detection device can be mounted at a known relative position to the focal point of an X-ray imaging device used for X-ray imaging. By way of example, the optical detection device can be a single camera such as an RGB camera, a depth-resolved camera such as an RGB camera with a depth channel, a time-of-flight optical detection device, a stereo camera device, etc.

[0030] The processor may utilize a classifier or model to determine (e.g., predict) the positioning of the scapula from the optical image signals. Optionally, the classifier or model may be configured to further consider depth information data, such as may be provided by a depth channel of an optical detection device, or by a stereo camera device.

[0031] In one embodiment, for example, a system can be integrated into or connected to the X-ray imaging device to disable the acquisition release button if the scapular positioning does not meet or match the target positioning.

[0032] According to a third aspect, there is provided a computer program configured, when executed by a processor, to perform the method of the first aspect and / or to control a system according to the second aspect.

[0033] According to a fourth aspect, there is provided a computer-readable storage or transmission medium for storing or transmitting a computer program according to the third aspect.

[0034] It should be noted that the above embodiments can be combined with each other regardless of the aspect involved. Thus, methods can be combined with structural features of devices and / or systems of other aspects, and similarly, devices and systems can be combined with features of each other and with features described above in relation to methods.

[0035] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0036] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [Brief explanation of the drawings]

[0037] [Figure 1] 1 is a schematic block diagram illustrating a system for assisting subject positioning in chest X-ray imaging, according to one embodiment. [Figure 2A] 1A-1C are diagrams that schematically illustrate determining scapular positioning, according to one embodiment; [Figure 2B] 1A-1C are diagrams that schematically illustrate determining scapular positioning, according to one embodiment; [Figure 3] 1 is a flow chart illustrating a method for assisting subject positioning in chest X-ray imaging, according to one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0038] 1 shows in a schematic block diagram a system 100 configured to assist in positioning a subject S in chest x-ray imaging, which may utilize an x-ray device having a radiation source 210, e.g., an x-ray tube, and a detector 220. The system 100 includes an optical detection device 110, a processor 120, and a user interface 130.

[0039] The optical detection device 110 is configured to capture a rear view of the subject S in an optical image signal. This can be implemented in different forms, such as, for example, a single RGB camera, a depth-resolved camera, an RGB-D camera, a time-of-flight optical detection device, a stereo camera setup, etc. The optical detection device 110 can be positioned with a known relative position to the focal point of the X-ray tube, and can, for example, be mounted on the radiation source 210.

[0040] The processor 120 is connected to the optical detection device 110 and the user interface 130. The processor 120 is configured with a random access memory that stores a computer program suitable for processing optical image signals received from the optical detection device 110. The processor 120 can further be configured to access a classifier and / or model 122, for example, trained based on optical image signal-scapula positioning pairs, configured to map a prediction of scapula-lung field overlap to the optical image signals received from the optical detection device. The processor 120 is further configured to receive the optical image signals from the optical detection device 110 and, based on the optical image signals, determine a current positioning of the subject S's scapula, where the current positioning of the scapula is evaluated with respect to whether and / or to what extent the scapula overlaps the subject's lung field being imaged. Further, processor 120 is configured to determine feedback for positioning subject S and / or its scapula based on the determined current positioning of the scapula. The feedback may include graphical feedback, audio feedback, etc. suitable for providing information to an operator or medical staff as to whether the subject's positioning is already correct or whether and / or how the positioning should be changed to conform to a desired target positioning.

[0041] 2A schematically illustrates determining scapular positioning, in which a set of landmarks 140 on or of subject S are derived from optical image signals to determine and / or assess the current positioning of the scapula. The set of landmarks 140 may be determined by processor 120 from optical image signals received from optical detection device 110, for example, by utilizing one or more imaging analysis techniques and / or classifiers and / or models 122. For example, the set of landmarks 140 may include one or more landmarks indicative of or formed by body characteristics of subject S, and FIG. 2A illustrates landmarks 140 located on the arm and / or elbow, wrist, forearm, or other suitable body part of subject S.

[0042] 2B schematically illustrates that the processor 120 can be configured to determine a geometric relationship indicative of the current positioning of the scapula from a set of landmarks 140. For example, a plane spanning one or more limbs of the subject can be determined from the set of landmarks, and the current positioning of the scapula can be derived by comparing the determined plane with a target value. For example, the plane or planes can be spanned by landmarks on the back and / or by landmarks on the shoulders and / or by the subject's elbow and wrist. By way of example, the constellation of landmarks 140 can be evaluated by grouping them into triangles B (back), L (left side), and R (right side), calculating the angles between L, B, and R, and comparing them to a threshold angle for fully rotating the scapula outside the lung field.

[0043] 3 shows in a schematic flow chart a computer-implemented method for assisting subject positioning in chest x-ray images, which method can be performed by system 100 as described above.

[0044] In step S1, an optical image signal of a rear view of the subject S is received. The optical image signal may be acquired and provided by the optical detection device 110, and such optical image signal may include, for example, one or more images, image frames, etc.

[0045] In step S2, based on the optical image signals, the current positioning of the scapula of the subject S is evaluated with respect to whether and / or to what extent the scapula overlaps with the subject's lung field being imaged. For example, the current positioning can be determined by processor 120 as described above.

[0046] In step S3, feedback is provided to position subject S and / or their scapula based on the determined current positioning of the scapula. For example, the feedback can be determined by processor 120 as described above.

[0047] In step S4, feedback for positioning the subject S can be provided via the user interface 130 as described above.

[0048] Optionally, determining the current positioning of the scapula includes determining, from the optical image signal, a positioning of the arm and / or wrist of the subject S indicative of the current positioning of the scapula.

[0049] Optionally, a set of landmarks 140 on or of the subject S are derived from the optical image signals to assess the current positioning of the scapula.

[0050] Optionally, a geometric relationship indicative of the current positioning of the scapula is determined from the landmark set 140 .

[0051] Optionally, a plane spanning one or more limbs of the subject S is determined from the set of landmarks 140, and the determined plane is compared to a target value to derive the current positioning of the scapula.

[0052] Optionally, at least one angle between the subject S's arm and its torso and / or its body center and / or the detector plane of the X-ray imaging device is determined from the set of landmarks, and the at least one determined angle is compared with a target value to derive a current positioning of the scapula.

[0053] Optionally, a set of landmarks 140 is determined on both sides of the subject S, i.e., on both scapulae, and symmetry and / or congruence between the two sides is determined to assess the current positioning of the scapulae.

[0054] Optionally, one or more contours of the subject and / or one or more surface properties of the subject S are derived from at least the optical image signal in order to assess the current positioning of the scapula.

[0055] Optionally, the optical image signal data is received by a classifier trained on the annotated training data, the classifier determining a current positioning of the scapula based on at least the optical image signal.

[0056] Optionally, the depth information data is received from a depth channel of the photodetector 110 .

[0057] Optionally, the depth information data is received directly from a 3D depth map based on at least the optical image signal.

[0058] Optionally, the depth information data is determined based on a stereo optical detection device used to acquire optical image signals of a rear view of the subject S.

[0059] Optionally, the feedback includes or forms a trigger signal configured to control and / or prevent image acquisition based on the positioning of the scapula. For example, the system 100 can be connected to the radiation source 210 and / or the detector 220 to control image acquisition based on the determined positioning and / or feedback.

[0060] In another exemplary embodiment, a computer program or computer program product is provided, characterized in that it is configured to perform on the system 100 the method steps of a method according to one of the previous embodiments.

[0061] Thus, a computer program can be stored to be executed by the processor 120, which may be part of the embodiments. This processor unit can be configured to perform or cause the execution of the steps of the above-mentioned methods. Furthermore, the processor unit can be configured to operate the components of the above-mentioned devices and / or systems. The computing unit can be configured to operate automatically and / or to execute user instructions. The computer program can be loaded into the working memory of the data processor. Thus, the data processor can be configured to perform the method according to one of the above-mentioned embodiments.

[0062] Furthermore, the computer program may provide all the steps necessary to perform the procedures of the exemplary embodiments of the methods described above.

[0063] According to another exemplary embodiment of the present invention, a computer readable medium such as a CD-ROM, USB stick, etc. is presented, the computer readable medium having a computer program stored thereon, such computer program being as described in the preceding section.

[0064] The computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as over the Internet or other wired or wireless telecommunications systems.

[0065] However, the computer program may also be presented over a network such as the World Wide Web and downloaded into the working memory of a data processor from such a network. According to another exemplary embodiment of the invention, a medium for making a computer program available for downloading is provided, the computer program being configured to perform a method according to one of the aforementioned embodiments of the invention.

[0066] The embodiments of the present invention are described with reference to various subject matters. In particular, some embodiments are described with reference to method-type claims, and other embodiments are described with reference to apparatus-type claims. However, those skilled in the art will understand from the above and below description that, unless otherwise specified, any combination of features belonging to one type of subject matter, as well as any combination between features relating to different subject matters, is disclosed in the present application. However, all features can be combined to provide a synergistic effect greater than the simple sum of the features.

[0067] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered exemplary or explanatory and not restrictive. The invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure and the dependent claims.

[0068] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be interpreted as limiting their scope. The following describes embodiments of the present invention. (Appendix 1) 1. A computer-implemented method for assisting subject positioning in chest x-ray imaging, comprising: receiving an optical image signal of a rear view of the subject; determining a current positioning of the subject's scapula based on the optical image signal, wherein the current positioning of the scapula is evaluated as to whether and / or to what extent the scapula overlaps with the subject's lung field being imaged; determining feedback for positioning the subject and / or the scapula based on the determined current positioning of the scapula; providing feedback for positioning the subject; A method having the following. (Appendix 2) 2. The method of claim 1, wherein the step of determining the current positioning of the scapula includes determining a positioning of the subject's arm and / or wrist from the optical image signal, the positioning being indicative of the current positioning of the scapula. (Appendix 3) 3. The method of claim 1 or 2, wherein a set of landmarks on or of the subject are derived from the optical image signals to assess the current positioning of the scapula. (Appendix 4) 4. The method of claim 3, wherein a geometric relationship indicative of the current positioning of the scapula is determined from the set of landmarks. (Appendix 5) 5. The method of claim 3 or 4, wherein a plane spanning one or more limbs of the subject is determined from the set of landmarks, and the determined plane is compared to a target value to derive the current positioning of the scapula. (Appendix 6) 6. The method of any one of claims 3 to 5, wherein at least one angle between the subject's arm and its torso and / or its body center and / or a detector plane of an X-ray imaging device is determined from the set of landmarks, and the at least one determined angle is compared to a target value to derive the current positioning of the scapula. (Appendix 7) 7. The method of any one of claims 3 to 6, wherein the set of landmarks is determined for both sides of the subject or for both scapulae of the subject, and symmetry and / or congruence of both sides is determined to assess the current positioning of the scapulae. (Appendix 8) 8. The method of any one of claims 1 to 7, wherein one or more contours of the subject and / or one or more surface characteristics of the subject are derived from at least the optical image signal to assess the current positioning of the scapula. (Appendix 9) 9. The method of any one of claims 1 to 8, wherein the optical image signal is received from a classifier or model trained on annotated training data, and the classifier or model determines the current positioning of the scapula based on at least the optical image signal. (Appendix 10) 10. The method of any one of claims 1 to 9, wherein depth information data is received from a depth channel of an optical detection device used to acquire the optical image signal of the rear view of the subject. (Appendix 11) 10. The method of any one of claims 1 to 9, wherein depth information data is received directly from a 3D depth map based on at least the optical image signal. (Appendix 12) 10. The method of any one of claims 1 to 9, wherein depth information data is determined based on a stereo optical detection device used to acquire the optical image signals of the rear view of the subject. (Appendix 13) 13. The method of any one of claims 1 to 12, wherein the feedback comprises or forms a trigger signal configured to control and / or prevent image acquisition based on the current positioning of the scapula. (Appendix 14) A system for assisting subject positioning in chest X-ray imaging, comprising: an optical detection device; A user interface; a processor connected to the optical detection device and the user interface; wherein the processor: receiving an optical image signal of a rear view of the subject; determining a current positioning of the subject's scapula based on the optical image signals, wherein the current positioning of the scapula is evaluated as to whether and / or to what extent the scapula overlaps with the subject's lung field being imaged; determining feedback for positioning the subject and / or their scapula based on the determined current positioning of the scapula; wherein the user interface provides the feedback for positioning the subject. (Appendix 15) 16. A computer program configured, when executed by a processor, to perform the method of any one of claims 1 to 13 and / or to control the system of claim 14. [Explanation of symbols]

[0069] 100 systems 110 Optical detection device 120 processors 121 memory 122 Classifiers and / or Models 130 User Interface 140 Landmark Set 210 Radiation Source 220 detector

Claims

1. 1. A method of operating a system for assisting subject positioning in chest X-ray imaging, the system comprising: an optical detection device; A user interface; a processor connected to the optical detection device and the user interface; and the processor: receiving an optical image signal of a rear view of the subject from the optical detection device; determining a current positioning of the subject's scapula based on the optical image signal, the current positioning of the scapula including determining the current positioning of the scapula by assessing whether and / or to what extent the scapula overlaps with the subject's lung field being imaged; determining feedback for positioning the subject and / or the scapula based on the determined current positioning of the scapula; providing said feedback to said user interface; How to perform.

2. 2. The method of claim 1, wherein the step of determining the current positioning of the scapula comprises determining a positioning of the subject's arms and / or wrists from the optical image signals, and determining the current positioning of the scapula based on the determined positioning of the arms and / or wrists.

3. The method of claim 1 , wherein a set of landmarks on or of the subject are derived from the optical image signals to determine the current positioning of the scapula.

4. The method of claim 3 , wherein a geometric relationship indicative of the current positioning of the scapula is determined from the set of landmarks.

5. 4. The method of claim 3, wherein a plane spanning one or more limbs of the subject is determined from the set of landmarks, and the determined plane is compared to a target value to determine the current positioning of the scapula.

6. 4. The method of claim 3, wherein at least one angle between the subject's arm and its torso and / or its body center and / or a detector plane of an X-ray imaging device is determined from the set of landmarks, and the at least one determined angle is compared with a target value to determine the current positioning of the scapula.

7. 7. The method of claim 3, wherein the set of landmarks is determined for each side of the subject or for each scapula of the subject, and symmetry and / or congruence of both sides is determined to assess the current positioning of the scapula.

8. 7. The method according to claim 1, wherein one or more contours of the subject and / or one or more surface characteristics of the subject that can be used to determine the current positioning of the scapula are derived from at least the optical image signal, and the derived contours and / or surface characteristics are used to determine the current positioning.

9. The method of claim 1 , wherein a classifier or model trained on annotated training data determines the current positioning of the scapula based on at least the optical image signal.

10. A method described in any one of claims 1 to 6, wherein the optical image signal received in the receiving step includes depth information data representing the distance from the optical detection device to the subject, and the depth information data is received from a depth channel of the optical detection device.

11. A method described in any one of claims 1 to 6, wherein the optical image signal received in the receiving step includes depth information data representing the distance from the optical detection device to the subject, and the depth information data includes a depth map.

12. 7. The method according to claim 1, wherein the optical detection device is a stereo optical detection device, and the optical image signal received in the receiving step includes depth information data determined by the stereo optical detection device, the depth information data representing a distance from the optical detection device to the object.

13. 7. The method of claim 1, wherein the step of determining the feedback further comprises determining feedback comprising or forming a trigger signal configured to control and / or prevent chest x-ray imaging based on the current positioning of the scapula.

14. A system for assisting subject positioning in chest X-ray imaging, comprising: an optical detection device; A user interface; a processor connected to the optical detection device and the user interface; wherein the processor: receiving an optical image signal of a rear view of the subject from the optical detection device; determining a current positioning of the subject's scapula based on the optical image signal, the current positioning of the scapula including determining the current positioning of the scapula by assessing whether and / or to what extent the scapula overlaps with the subject's lung field being imaged; determining feedback for positioning the subject and / or their scapula based on the determined current positioning of the scapula; providing said feedback to said user interface; To run the system.

15. A computer program that causes a computer to execute the method described in any one of claims 1 to 6.

Images