Chest X-ray system and method

Abstract

The chest x-ray system includes a camera for capturing video of the patient being imaged, an x-ray imaging head, and an x-ray detector. The camera, x-ray imaging head, and x-ray detector can be translated. The patient's head is first identified and the chin of the head is then identified. The chin is then used as a reference point to translate the camera into position for chest x-ray imaging.

Description

Technical Field

[0001] The present invention relates to a system and method for performing a chest X-ray.

Background Art

[0002] There are many different imaging diagnostic techniques. Among these, X-ray imaging technology is widely used for clinical diagnostic medical imaging. For example, there are many different clinical applications for different organs that can be examined by X-ray medical images.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Many hospitals and other medical institutions lack the necessary positioning devices and thus do not have the equipment to perform even basic imaging procedures. If an image is obtained without proper position control, the image is not suitable for medical diagnostic imaging and the patient may have to receive a second or third dose of X-ray radiation due to inaccurate position control. High radiation doses are, of course, undesirable for health reasons for the patient.

[0004] There are various causes of the acquired images that are not suitable for diagnostic purposes, including human error and external factors. Human error can be, for example, the result of inexperienced physicians, and external factors can include movement by the patient during X-ray imaging. If an image is taken at an unintended position, the patient can be repositioned and the X-ray image can be retaken.

[0005] It is preferable to assist the physician in obtaining the correct patient position before X-ray imaging in order to improve X-ray image quality, increase clinical diagnostic efficiency, and optimize the clinical workflow.

Means for Solving the Problems

[0006] This invention is defined by the claims.

[0007] According to an embodiment according to one aspect of the present invention, a chest X-ray system, a camera for capturing a video of a patient to be imaged, an X-ray imaging head and an X-ray detector, a support system for translating the camera and the X-ray imaging head and the X-ray detector, a controller, an output system and having, wherein the controller translates the camera to a position where the head of the patient is identified as being captured within the video, identifies the jaw of the head, and uses the jaw as a reference point for translating the camera, the X-ray head, and the X-ray detector to positions for chest X-ray imaging is adapted to, a chest X-ray system is provided.

[0008] This system can move the camera between a position for imaging the patient's head and a position for imaging the patient's chest. To position the camera in a position suitable for capturing a desired chest X-ray, the camera is first positioned to identify the patient's head. The camera is moved or the patient is advised to move until the head is identified within the camera image.

[0009] Next, the jaw can be identified and used as a reference point. Thus, the present invention is based on the recognition that the positioning of the X-ray source and the X-ray detector for chest X-rays can be selected using the jaw as a reference. This provides a more reliable method for locating the desired camera, X-ray tube source, and detector for chest X-rays because the distance from the jaw to the chest is fixed within a more constant distance than the variable chest height between patients.

[0010] The camera is attached, for example, to an X-ray tube head having an X-ray source and a collimator. The X-ray tube head moves in alignment with the detector. Thus, the camera is positionally fixed relative to the X-ray head and the detector such that the position of the camera is known in the coordinate space of the X-ray head and the detector.

[0011] The controller, for example, identifies a plurality of features of the head including the jaws, determines, from the identified features, the orientation of the head having a yaw angle, a pitch angle, and a roll angle relative to a desired orientation of the head, determines the necessary changes to the orientation of the head to reach the desired orientation, and controls the output system to provide to the patient instructions to assist with the necessary changes to the orientation of the head before using the jaws as a reference point. is adapted to

[0012] Thus, the system ensures that the head is in the desired position before using the jaw position as a reference point. The desired orientation of the head has, for example, a Frankfurt plane perpendicular to the viewing direction of the camera.

[0013] Features of the head include, for example, the tip of the nose, the jaws, the left corner of the left eye and the upper right corner of the right eye, optionally the left corner of the mouth and the right corner of the mouth.

[0014] When the yaw angle exceeds a yaw threshold, the instructions include, for example, instructions to rotate the head left or right. When the pitch angle exceeds a pitch threshold, the instructions include, for example, instructions to tilt the head up or down. When the roll angle exceeds a roll threshold, the instructions include, for example, instructions to tilt the head left or right.

[0015] The controller preferably translates the camera to a position for chest X-ray imaging and then identifies the body position of the patient, and controls the output system to provide to the patient instructions to assist with the necessary changes to the body position for a chest X-ray.

[0016] In this way, the patient can be instructed to move the body to the desired position most suitable for the chest X-ray image.

[0017] For example, the controller, in order to identify the body position, the position of the spine between the shoulders, the right shoulder, the left shoulder, the right elbow, the left elbow, the right wrist, the left wrist, the mid-spine position, and the base-spine position is adapted to identify some or all of the body features having.

[0018] Next, the controller, in order to identify the body position, the tilt angle of the shoulders around the spinal axis, the elevation of the left and right arms, the flexion of the right or left elbow, and the flexion of the body around the waist, as well as providing instructions to the patient to improve an undesirable body shape is adapted to determine one or more body shapes having.

[0019] The camera is, for example, a visible light camera. Thus, it is used to detect the surface head and body features from the captured images.

[0020] The present invention is also a computer-implemented method for preparing a patient for a chest X-ray, translating the camera, the X-ray head and the X-ray detector to a position identified as the head of the patient being captured within the video stream generated by the camera; identifying the jaw of the head; Providing an instruction to translate the camera, X-ray head, and X-ray detector using the jaw as a reference point, or to translate the camera, X-ray head, and X-ray detector to a position for chest X-ray imaging using the reference point Providing a computer-implemented method having the same

[0021] The method includes Identifying a plurality of features of the head including the jaw Determining the orientation of the head having a yaw angle, pitch angle, and roll angle relative to a desired orientation of the head from the identified features Determining a required change to the orientation of the head to reach the desired orientation Controlling the output system to provide an instruction to the patient to assist with the required change to the orientation of the head before using the jaw as a reference point And may include

[0022] The method preferably further includes After translating the camera to a position for chest X-ray imaging Identifying the body position of the patient Controlling the output system to provide an instruction to the patient to assist with the required change to a desired body position for a chest X-ray And also includes

[0023] The present invention also provides a computer program including computer program code means adapted to implement the method as defined above when the program is executed on a controller of the system as defined above

[0024] These and other aspects of the invention will be apparent from and will be elucidated with reference to the embodiments described hereinafter

[0025] To better understand the present invention and to more clearly show how it can be implemented, reference is now made, by way of example only, to the accompanying drawings.

Brief Description of the Drawings

[0026]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Modes for Carrying Out the Invention

[0027] The present invention will be described with reference to the drawings.

[0028] The detailed description and specific examples illustrate exemplary embodiments of apparatuses, systems, and methods, but are for illustrative purposes only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatuses, systems, and methods of the present invention will be better understood from the following description, the appended claims, and the accompanying drawings. It is to be understood that the figures are merely schematic and are not drawn to scale. Also, it is to be understood that the same reference numerals are used throughout the drawings to indicate the same or similar parts.

[0029] The present invention provides a chest X-ray system comprising a camera for capturing a video of a patient to be imaged, an X-ray imaging head, and an X-ray detector. The camera, the X-ray imaging head, and the X-ray detector can be translated. The patient's head is first identified, and the jaw of the head is identified. The jaw is then used as a reference point for translating the camera to a position for chest X-ray imaging.

[0030] Previously, physicians had to estimate the correct patient position for all patients based on the physicians' experience. This is a time-consuming method. The automated approach of the present invention does not rely on the experience of different physicians. In particular, the face position is detected and converted to face landmarks, especially to identify the jaw. This can be achieved by projecting information from a 2D image to 3D points. By analyzing the 3D point information, the posture of the head as well as the position of the jaw can be determined.

[0031] The system can provide guidance to the patient to correct the patient's head pose.

[0032] Facial recognition is combined with body skeleton recognition, for example, to perform a chest X-ray system. Therefore, the system determines the relative position between the patient's head and the patient support (which may be a standing panel or a patient bed), particularly the jaw position. Based on this, the system can guide the movement of the patient support (standing panel and X-ray head or table) to accurately align the chest area with the X-ray imaging system.

[0033] The system can also provide guidance to the patient to correct the patient's body posture in order to further improve inaccurate positions during chest X-rays. The use of head detection makes it possible to more accurately determine the chest height and enables patients with different heights.

[0034] The operation sequence includes the patient getting on (or sitting on) the stand or lying on the patient table. Then, the system gives positioning instructions so that the doctor can guide the patient to the most appropriate position for a chest X-ray. Then, the patient has the correct position for X-ray exposure.

[0035] Figure 1 shows an X-ray system 100 having an X-ray head 102 with an X-ray source 104 and a camera 106, and an X-ray detector 108. The X-ray detector in this example is part of a wall stand as used for X-ray chest imaging of a patient 110 in a seated position as shown. The X-ray detector, camera, and X-ray source are carried by a support system 109 that can translate them relative to the patient. As will be described below, the camera generates a 2D depth image, for example, based on time-of-flight measurement.

[0036] The X-ray head 102 (source 104 and camera 106) and the X-ray detector 108 have adjustable positions (all fixed to each other) so that they can be directed towards the patient's chest or the patient's head by moving the support system 108 as represented by the arrow 112.

[0037] FIG. 1 shows a controller 112 for processing camera images and controlling an output device such as a display 114.

[0038] The X-ray detector may instead be part of a patient treatment table.

[0039] FIG. 2 shows a patient 110 on a treatment table 120 incorporating an X-ray detector 108, with an X-ray head 102 covering the top. FIG. 2 shows the X-ray head 102 aligned with the patient's head and also shows the resulting X-ray image of the skull.

[0040] FIG. 3 again shows a patient 110 on a treatment table 120 incorporating an X-ray detector 108, with an X-ray head 102 covering the top. FIG. 2 shows the X-ray head 102 aligned with the patient's chest and also shows the resulting chest X-ray image.

[0041] In the case of head (skull) X-rays, the head is in the anterior-posterior direction relative to the X-ray head. The head should be oriented by adjusting the position of the jaw so that the Frankfurt plane is perpendicular to the X-ray detector.

[0042] In chest X-rays, as shown in FIG. 4, various features including both costophrenic angles should be visible on both sides of the upper part 130 of the lungs and the lower part 140 of the diaphragm. The lung structure and the spine should be distinguishable behind the heart.

[0043] To make the upper part of the lungs visible in the image, proper alignment between the patient and the X-ray head and X-ray detector (e.g., a wall stand detector) is required. The present invention is based on the use of the position of the jaw as a reference point. The length between the jaw and the top of the lungs is approximately constant even among patients of very different heights.

[0044] This is schematically shown in FIG. 5, which shows two patients of different heights. In each case, the distance A between the jaw and the top of the lungs is approximately constant, but the distances B and C to the central point of the spine are different.

[0045] When using body points to identify the chest region, these points are obtained, for example, from the depth information of a 3D camera, and typically, a body center point such as the center point of the spine is used. However, distances B and C vary significantly for different patient heights. The patient's height typically ranges from 1.4 to 1.9 meters.

[0046] Figure 6 shows a method of preparing a patient for a chest X-ray.

[0047] In step 150, the camera, X-ray head, and X-ray detector are moved to a position where the patient's head is identified as being captured within the video stream generated by the camera.

[0048] In step 152, the jaw of the head is identified, and in step 154, the jaw is used as a reference point to translate the camera, X-ray head, and X-ray detector to a position for chest X-ray imaging using the reference point.

[0049] Figure 7 shows method 200 for processing an image of the head to obtain the position of the jaw and, in addition, to provide instructions to enable the correct head pose.

[0050] In step 202, the positions of the X-ray head and detector are adjusted to enable X-ray imaging of the head (skull). For example, this includes adjusting the vertical height to a height position suitable for skull examination.

[0051] In step 204, the camera acquires the patient's video stream.

[0052] In step 206, image processing is performed. This enables determining, in step 208, whether a single face can be identified in the camera image.

[0053] If a face can be identified, at step 210, the trained model is used to find face position landmarks. These landmarks include the jaw as described above. Based on these landmarks, the algorithm performs recognition using the trained face model.

[0054] The algorithm can then determine the face angle, for example, using the rotation matrix 212 and Euler angle transformation 214 described below.

[0055] At step 216, it is determined whether the head pose is correct. If not, the user interface can give an instruction at step 218 to assist the doctor and patient in repositioning the head to the desired position.

[0056] When the head comes to the correct position, the jaw is identified as the reference position at step 220.

[0057] The camera image used for the head pose is, for example, a 2D image from a 3D camera. Image preprocessing uses, for example, a median blur operation to reduce image noise. The size of the image is derived and the image center point is obtained.

[0058] Face landmarks are detected using a known training model such as Kazemi V, Sullivan J. "One Millisecond Face Alignment with an Ensemble of Regression Trees" (Computer Vision and Pattern Recognition, IEEE, 2014: 1867 - 1874).

[0059] This model obtains, for example, six points on the face, namely, the tip of the nose, the jaw, the left corner of the left eye, the upper right corner of the right eye, the left corner of the mouth, and the right corner of the mouth.

[0060] From these six points, since the head is aligned with the detector, for example a wall stand detector, the determination of the face position is made. Therefore, the position of the face should be determined relative to the wall stand detector. For this purpose, the center of the image is compared with the face position and a tolerance value is set. If the center deviation is greater than a certain number of pixels (depending on the resolution of the detector, for example 65 pixels), an instruction is provided to reposition the head or the X-ray head and the X-ray detector (i.e., the wall stand detector).

[0061] When the deviation is less than the threshold amount, the face is approximately at the center of the image plane. Then, this method performs the determination of the head pose.

[0062] The aim is to determine the position (U, V, W) of the head as a 3D point P in world coordinates. If the rotation R (3×3 matrix) and translation t (3×1 vector) of the world coordinates with respect to the camera coordinates are known, the position (X, Y, Z) of each point P in camera coordinates is It can be calculated using TIFF0007700968000001.tif82111.

[0063] The matrix R and the vector t are obtained based on the stand coordinates.

[0064] If the right pose (R and t) is known, the 2D position of the 3D face points on the image can be predicted by projecting the 3D points onto the 2D image. In other words, if R and t are known, the point P in the image can be found for each of the imaged 3D points.

[0065] Therefore, each of the six face points can be mapped to a 3D position in world coordinates. For this purpose, the 3D camera generates a color 2D depth image. These two images are generated simultaneously by the 3D camera.

[0066] Therefore, the 3D point positions of each face landmark are obtained. The 3D point positions are converted to the angles between the axes in order to estimate the pose (direction) of the face.

[0067] First, convert the 3D points to the quaternion system. The quaternion system extends the complex numbers. When (x, y, z) is the unit vector in the axis direction and θ is the axis rotation angle, the quaternion of (x, y, z) is [cos(θ / 2), x*sin(θ / 2), y*sin(θ / 2), z*sin(θ / 2)], which can be expressed as (w, x, y, z).

[0068] This quaternion can be converted to Euler angles by TIFF0007700968000002.tif2488.

[0069] The rotation angles (Φ, θ, φ) represent the yaw, pitch, and roll of the head. After these are obtained, advice can be provided to the patient to adjust the head position according to the set threshold. For example, if the yaw is greater than 25 degrees, the patient is advised to return to the central position from the left or right. if the pitch is greater than 10 degrees, the patient is advised to look up or down to point at the detector, and if the roll is greater than 15 degrees, the patient is advised not to tilt the head to the left or right and to keep the head vertical.

[0070] Figure 8 shows the remaining part of method 300 for preparing a chest X-ray.

[0071] Using the position of the jaw, the camera, X-ray head, and X-ray detector are moved to the positions for the chest X-ray.

[0072] This translation is performed in step 154 (as shown in Figure 6). Since the tip of the jaw can be aligned with, for example, the upper end of the stand-up (wall-mounted) panel, this position is based on the position of the face relative to the wall-mounted detector.

[0073] Compare the edges of the image of the standing panel with the position of the jaw and set the tolerance. If the deviation is greater than the threshold value, advice is provided. If the jaw point is higher, advice is given to move the wall stand to a higher position. If the jaw is lower, advice is given to move the wall mount to a lower position.

[0074] Alternatively, it may be desirable to move the upper part of the wall stand panel to an offset position fixed relative to the jaw, for example, a fixed distance below the jaw position, for example, 5 cm.

[0075] Similar to the head pose inspection, the body position can also be evaluated to provide further instructions to the patient (optionally via a doctor) to improve the body position for a chest X-ray.

[0076] In step 302, it is determined whether the body is recognized. If not, the patient may be too close to the camera, and in that case, advice and instructions are given in step 304.

[0077] For the analysis of the body position, the depth image and the 2D image from the 3D camera can be used together with the body skeleton recognition.

[0078] For image preprocessing to reduce noise, the median blur process was used again.

[0079] After confirming that the standing height is suitable for a chest X-ray examination, the human body posture is also considered.

[0080] For example, if the body is tilted around the vertical axis (for example, when the patient is in a standing posture rather than a sitting posture), the patient is not standing towards the camera (i.e., the X-ray source).

[0081] The 3D position of the skeleton can be checked using several points that can be captured through a 3D camera. These points are obtained by landmark detection in step 306. Figure 9 shows the head (H), neck (N), spine at shoulder height (Sp_S), left shoulder (LS), left elbow (LE), left wrist (LW), left hand (LH), right shoulder (RS), right elbow (RE), right wrist (RW), right hand (RH), spine at mid height (Sp_Mid), and spine at base height (Sp_Base).

[0082] Based on these points, the angle between any pair of axes can be calculated. Each individual axis is defined by two points.

[0083] Returning to Figure 8, various angles can be calculated.

[0084] In step 308, body tilt is detected. This can be based on the angle between the line [from N to Sp_Mid] and [from LS to RS]. If the angle is less than 85 degrees, advice can be given to keep the body from tilting.

[0085] In step 310, the raising of the right hand is detected. This can be based on the angle between the line [Sp_S - RS] and [RS - RE]. If the angle is less than 65 degrees, advice can be provided to keep the right hand from being raised.

[0086] In step 312, the raising of the left hand is detected. This can be based on the angle between the line [Sp_S - LS] and [LS - LE]. If the angle is less than 65 degrees, advice can be provided to keep the left hand from being raised.

[0087] In step 314, the bending of the right elbow is detected. This can be based on the angle between the line [RS - RE] and [RE - RW]. If the angle is greater than 15 degrees, advice can be given to keep the right elbow from bending.

[0088] In step 316, the bending of the left elbow is detected. This can be based on the angle between lines [LS―LE] and [LE―LW]. If the angle is greater than 15 degrees, advice can be given not to bend the left elbow.

[0089] In step 318, the tilting of the head is detected. This can be based on the angle between lines [H―N] and [N―Sp_S]. If the angle is greater than 11 degrees, advice can be given not to tilt the head.

[0090] Despite the X-ray tube head being positioned for a chest X-ray, the head can remain within the camera's field of view (with the head in the upper region of the image). Thus, the camera typically has a much wider field of view than the X-ray source. For example, the detector size is 43 cm × 43 cm corresponding to a half-angle aa from a light source of, for example, 6.8 degrees. An example of a 3D camera has a field of view for depth images of 58.4 degrees (horizontal) × 45.5 degrees (vertical) and a field of view for 2D color images of 63.1 degrees (horizontal) × 49.4 degrees (vertical).

[0091] In step 320, bending at the waist is detected. This can be based on the angle between lines [Sp_S―Sp_Mid] and [Sp_Mid―Sp_Base]. If the angle is greater than 11 degrees, advice can be provided not to bend at the waist.

[0092] Some angle calculations can use four points, for example, [N―Sp_Mid] and [RS―LS] for lateral body tilt.

[0093] If it is determined in step 322 that the body position is correct, a chest X-ray image is taken in step 324. Otherwise, in step 304, advice is continuously provided repeatedly while the patient adjusts their body position.

[0094] Variations to the disclosed embodiments can be understood and effected by persons skilled in the art in carrying out the claimed invention, from a study of the drawings, the disclosure and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0095] A single processor or other unit can fulfill the functions of several items recited in the claims.

[0096] 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 advantageously.

[0097] A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless electric communication systems.

[0098] It should be noted that when the term "adapted to" is used in the claims or the description, the term "adapted to" is intended to be equivalent to the term "configured to".

[0099] No reference signs in the claims should be construed as limiting the scope.

Claims

1. A chest X-ray system comprising: a camera for capturing a video of a patient to be imaged; an X-ray imaging head and an X-ray detector; a support system for translating the camera, the X-ray imaging head, and the X-ray detector; a controller; an output system ; wherein the controller is adapted to: translate the camera to a position where the head of the patient is identified as being captured within the video; identify the jaw of the head; use the jaw as a reference point for translating the camera, the X-ray head, and the X-ray detector to positions for chest X-ray imaging . A chest X-ray system.

2. The controller is further adapted to identify a plurality of features of the head including the jaw, determine a direction of the head having yaw, pitch, and roll angles relative to a desired direction of the head from the identified features, determine a necessary change to the direction of the head to reach the desired direction, and control the output system to provide instructions to the patient to assist with the necessary change to the direction of the head before using the jaw as a reference point . The system according to claim 1.

3. The system according to claim 2, wherein the desired direction has a Frankfurt plane perpendicular to the viewing direction of the camera.

4. The system according to any one of claims 2 to 3, wherein the features of the head include the tip of the nose, the jaw, the left corner of the left eye and the right corner of the right eye, and optionally the left corner and the right corner of the mouth.

5. When the yaw angle exceeds a yaw threshold, the instructions include instructions to rotate the head left or right, and / or When the pitch angle exceeds a pitch threshold, the instructions include instructions to tilt the head up or down, and / or When the roll angle exceeds a roll threshold, the instructions include instructions to tilt the head left or right . The system according to any one of claims 2 to 4.

6. After translating the camera to a position for chest X-ray imaging, the controller is further adapted to identify the body position of the patient, and control the output system to provide instructions to the patient to assist with the necessary change to a desired body position for chest X-ray . The system according to any one of claims 1 to 5.

7. To identify the body position, the controller uses the position of the spine between the shoulders, the right shoulder, the left shoulder, the right elbow, the left elbow, the right wrist, the left wrist, the mid-spine position, and the base-spine position The system according to claim 6, adapted to identify some or all of the body features.

8. The controller, for identifying the body position, the tilt angle of the shoulders around the spinal axis, the elevation of the left and right arms, the flexion of the right or left elbow, and the flexion of the body around the waist, and providing the patient with instructions for improving undesirable body shapes The system according to claim 7, adapted to determine one or more body shapes having.

9. The system according to any one of claims 1 to 8, wherein the camera is a visible light camera.

10. A computer-implemented method for preparing a patient for a chest X-ray, comprising: translating a camera, an X-ray head, and an X-ray detector to a position where the head of the patient is identified as being captured within a video stream generated by the camera; identifying the jaw of the head; using the jaw as a reference point to translate the camera, the X-ray head, and the X-ray detector, or providing instructions to translate the camera, the X-ray head, and the X-ray detector to a position for chest X-ray imaging using the reference point A computer-implemented method having.

11. identifying a plurality of features of the head including the jaw; determining, from the identified features, the orientation of the head having a yaw angle, a pitch angle, and a roll angle relative to a desired orientation of the head; determining a necessary change to the orientation of the head to reach the desired orientation; controlling an output system to provide the patient with instructions to assist with the necessary change to the orientation of the head before using the jaw as a reference point The method according to claim 10, having.

12. providing instructions to rotate the head left or right if the yaw angle exceeds a yaw threshold, and / or providing instructions to tilt the head up or down if the pitch angle exceeds a pitch threshold, and / or providing instructions to tilt the head left or right if the roll angle exceeds a roll threshold The method according to claim 11, having.

13. After translating the camera to a position for chest X-ray imaging, identifying the body position of the patient; controlling an output system to provide the patient with instructions to assist with the necessary changes to the desired body position for the chest X-ray The method according to claim 10, having

14. Computer program code means adapted to perform the method according to any one of claims 10 to 13 when a program is executed on a controller of a system according to any one of claims 1 to 9.

Images