Control methods for cone-beam CT devices, cone-beam CT devices and media

Abstract

This invention discloses a control method for a cone-beam CT (CBCT) device, the CBCT device itself, and a medium. The CBCT device includes a column, a camera, and a laser beam. The control method includes: acquiring a facial image through the camera and performing key point detection on the facial image to obtain facial key points; determining whether the facial posture is normal based on the facial key points; if normal, activating the laser and extracting the laser beam position from the facial image; driving the column to move in a first direction based on the laser beam position and the facial key points; and controlling the CBCT device to perform CT imaging when the laser beam position reaches a first designated position. This control method for the CBCT device can automatically adjust the imaging position and posture for different patients, thereby improving image quality, reducing the rate of defective images, reducing radiation exposure to patients, and extending the machine's lifespan.

Description

Technical Field

[0001] This invention relates to the field of head positioning technology, and more particularly to a control method for a cone-beam CT device, a cone-beam CT device, and a medium. Background Technology

[0002] In related technologies, the head adjustment method in CBCT (Cone Beam CT) involves doctors manually adjusting the motor and observing the laser beam position to determine if the head position is appropriate. However, this method of observation by the human eye has significant drawbacks. Different doctors may have different interpretations of the standard, leading to inconsistent positioning, which affects the image quality of the CBCT machine, impacts diagnostic imaging, and in severe cases, results in defective images. Furthermore, constant adjustments to the CBCT machine increase the radiation source load and reduce its lifespan. Summary of the Invention

[0003] One objective of this invention is to provide a control method for a cone-beam CT device that automatically adjusts the imaging position and posture for different patients, thereby improving the quality of the images, reducing the rate of defective images, reducing radiation exposure to patients, and extending the lifespan of the machine.

[0004] The second objective of this invention is to provide a cone-beam CT device.

[0005] A third objective of this invention is to provide a computer-readable storage medium.

[0006] To achieve the above objectives, a first aspect of the present invention provides a control method for a cone-beam CT device, the cone-beam CT device including a column, a camera, and a laser beam, the control method comprising: acquiring a facial image through the camera and performing key point detection on the facial image to obtain facial key points; determining whether the facial posture is normal based on the facial key points; if normal, activating the laser beam and extracting the laser beam position from the facial image; driving the column to move in a first direction based on the laser beam position and the facial key points; and controlling the cone-beam CT device to perform CT imaging when the laser beam position reaches a first designated position.

[0007] The control method of the cone-beam CT device in this invention pre-judges the facial posture by acquiring a facial image through a camera and performing key point detection on the image. Based on these key points, the device's posture is then assessed for normality. If the facial posture is normal, the device's imaging position is adjusted by activating the laser. The device automatically extracts the laser beam position and drives the column to move according to this position until the laser beam reaches the designated location for CT imaging. The relative position of the laser beam on the face indicates the position of the cone-beam CT imaging area relative to the patient's head. This allows for automatic adjustment of the imaging position and posture for different patients, improving image quality, reducing the rate of defective images, minimizing radiation exposure, and extending the machine's lifespan.

[0008] In addition, the control method for the cone-beam CT device proposed in the above embodiments of the present invention may also have the following additional technical features:

[0009] According to one embodiment of the present invention, the control method further includes: determining whether the face image contains a complete face; if not, driving the column to move in a set direction; if yes, performing the step of key point detection on the face image.

[0010] According to one embodiment of the present invention, the step of determining whether the facial posture is normal based on the facial key points includes: calculating a first pitch angle, a first yaw angle, and a first roll angle based on the facial key points; and determining whether the facial posture is normal based on the first pitch angle, the first yaw angle, and the first roll angle.

[0011] According to an embodiment of the present invention, the first pitch angle is calculated by the following formula:

[0012]

[0013]

[0014] Among them, KeyPt 51 KeyPt represents the highest key point in the middle of the nose. 16 KeyPt represents the lowest keypoint in the center of the face. 51 .y represents the key point KeyPt 51 The coordinates of KeyPt in the first direction 51 .x represents a keypoint (KeyPt). 51 In the coordinates of the second direction, Pitch represents the first pitch angle, and k1 is a first preset constant;

[0015] And / or, the first yaw angle is calculated using the following formula:

[0016]

[0017]

[0018] Among them, KeyPt 97 This indicates the key point located in the middle of the left eye's key points; Yaw represents the first yaw angle; and k2 is the second preset constant.

[0019] And / or, the first roll angle is calculated using the following formula:

[0020] RollTan = (KeyPt) 97 .x-KeyPt 96 .x) / (KeyPt 97 .y-KeyPt 96 .y)

[0021]

[0022] Among them, KeyPt 96 This indicates the key point located in the middle of the eye among the key points of the right eye; Roll represents the first roll angle; k3 is the third preset constant.

[0023] According to an embodiment of the present invention, the step of determining whether the face posture is normal based on the first pitch angle, the first yaw angle and the first roll angle includes: determining whether the absolute values ​​of the first pitch angle, the first yaw angle and the first roll angle are all less than or equal to a first preset threshold; if so, the face posture is determined to be normal, otherwise the face posture is determined to be abnormal.

[0024] According to an embodiment of the present invention, the control method further includes: providing prompts in at least one of the following ways: issuing a first prompt message when the absolute value of the first pitch angle is greater than the first preset threshold, to prompt the patient to perform a pitch operation; issuing a second prompt message when the absolute value of the first yaw angle is greater than the first preset threshold, to prompt the patient to perform a head-shaking operation; and issuing a third prompt message when the absolute value of the first roll angle is greater than the first preset threshold, to prompt the patient to perform a head-turning operation.

[0025] According to one embodiment of the present invention, after determining that the face pose is normal, the control method further includes: determining the key point KeyPt. 51 and the key point KeyPt 16 If the straight line formed coincides with the second designated position, a fourth prompt message is issued to prompt the patient to move; if it coincides, the step of activating the laser beam is performed.

[0026] According to an embodiment of the present invention, extracting the laser beam position from the face image includes: determining all laser beam rows in the face image and recording the row coordinates of each laser beam row, wherein the row coordinates are the coordinates of the laser beam row in the first direction; calculating the mean of all row coordinates and using the mean as the laser beam position; wherein all pixels in the laser beam row satisfy the condition that the difference between the R pixel value and the G pixel value is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold.

[0027] According to one embodiment of the present invention, the laser beam position reaching a first designated position includes: the laser beam position and a key point KeyPt 31 The coordinates in the first direction coincide, where KeyPt 31 This refers to the key point in the facial contour that is the second highest in the first direction.

[0028] According to an embodiment of the present invention, during the process of controlling the cone-beam CT device to perform CT imaging, the control method further includes: obtaining a second pitch angle, a second yaw angle, and a second roll angle based on the current face image; determining whether the absolute values ​​of the second pitch angle, the second yaw angle, and the second roll angle are greater than a first preset threshold; and controlling the cone-beam CT device to stop CT imaging if any one of the second pitch angle, the second yaw angle, and the second roll angle is greater than the first preset threshold.

[0029] According to an embodiment of the present invention, during the process of controlling the cone-beam CT device to perform CT imaging, the control method further includes: calculating a first difference between the third pitch angles, a second difference between the third yaw angles, and a third difference between the third roll angles of two frames of face images spaced apart by a first preset time interval; and controlling the cone-beam CT device to stop CT imaging when any one of the absolute values ​​of the first difference, the second difference, and the third difference is greater than a fourth preset threshold.

[0030] To achieve the above objectives, a second aspect of the present invention provides a cone-beam computed tomography (CBCT) device, the device comprising: a column, a camera, and a controller, wherein the controller includes a memory, a processor, and a computer program stored in the memory, and the computer program, when executed by the processor, implements the control method as described above.

[0031] To achieve the above objectives, a third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the control method as described above.

[0032] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0033] Figure 1 This is a flowchart of a control method for a cone-beam CT device according to an embodiment of the present invention;

[0034] Figure 2 This is a flowchart of a face image determination method according to an embodiment of the present invention;

[0035] Figure 3 This is a flowchart of an embodiment of the present invention for determining whether a face pose is normal based on facial key points;

[0036] Figure 4 This is a flowchart of step S22 of an embodiment of the present invention;

[0037] Figure 5 This is a flowchart illustrating whether facial key points satisfy a second specified position according to an embodiment of the present invention;

[0038] Figure 6 This is a flowchart illustrating the extraction of laser beam position from a face image according to an embodiment of the present invention;

[0039] Figure 7 This is a flowchart of the CT imaging process performed by a cone-beam CT device according to an embodiment of the present invention;

[0040] Figure 8 This is a flowchart of one embodiment of the present invention for determining any two frames of face images;

[0041] Figure 9 This is a schematic diagram of facial key points according to an embodiment of the present invention;

[0042] Figure 10 This is a schematic diagram of pitch angle, yaw angle, and roll angle according to an embodiment of the present invention;

[0043] Figure 11 This is a schematic diagram of the structure of a cone-beam CT device according to an embodiment of the present invention;

[0044] Figure 12 This is a front view of a cone-beam CT device according to an embodiment of the present invention. Detailed Implementation

[0045] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0046] The following will refer to the instruction manual appendix. Figure 1-12 The control method, cone-beam CT device, and medium of the cone-beam CT device according to embodiments of the present invention are described in detail below.

[0047] The cone-beam CT device of this embodiment can be applied to dedicated CBCT in various directions, such as the oral cavity, ear, nose, and other parts of the head, for example, oral CBCT.

[0048] In an embodiment of the present invention, the cone-beam CT device includes a column, a camera, and a laser, both of which are mounted on the column. The column is movable and can move up and down according to control commands; the camera is used to capture facial images. For example, the cone-beam CT device may include a base and a column. The column includes a movable part, a fixed part, and a positioning mechanism. The bottom end of the movable part is fixed to the base, and the movable part is slidably disposed on the fixed part. After the position of the movable part relative to the fixed part changes, it can be positioned by the positioning mechanism, so that the movable part and the fixed part are relatively fixed at that position. The aforementioned movable column corresponds to the movable part in this example.

[0049] Figure 1 This is a flowchart of a control method for a cone-beam CT device according to an embodiment of the present invention.

[0050] In embodiments of the present invention, such as Figure 1 As shown, the control method for the cone-beam CT device includes:

[0051] S1: Acquire a face image through a camera and perform key point detection on the face image to obtain the face key points.

[0052] The camera can be mounted on the cone-beam CT scanner or on a separate bracket. The camera's position is adjustable. During use, the camera height is adjusted according to the patient's head height at the time of the scan, ensuring that at least part of the patient's face is within the camera's field of view. For example, for a standing cone-beam CT scanner, the height can be adjusted based on the patient's height; for a seated cone-beam CT scanner, the height can be adjusted based on the patient's head height after sitting down.

[0053] Specifically, when controlling the cone-beam CT scanner, facial images can be acquired in real time via a camera at a frequency of 30-60 fps (frames per second). If a complete face is not captured in the facial image before keypoint detection, the detection will be incomplete, affecting subsequent keypoint assessment. Therefore, after acquiring the facial image, a preliminary assessment (such as determining whether the image contains the patient's complete face) should be performed before keypoint detection.

[0054] In one embodiment of the present invention, such as Figure 2 As shown, the control method of the cone-beam CT device further includes: determining whether the face image contains a complete face; if not, driving the column to move in a set direction; if so, performing a key point detection step on the face image.

[0055] Specifically, determining whether a face image contains a complete face can be done by extracting features from the face image and determining whether the extracted features contain all the features of a complete face. If the features of the face image contain all the features of a complete face, then the face image captured by the camera contains a complete face. If the features of the face image do not contain all the features of a complete face, then the face image captured by the camera does not contain a complete face. If the face image captured by the camera does not contain a complete face, the column is driven to move in a set direction. The set direction can be the same as the direction of the incomplete part of the face image relative to the whole face image. For example, if the features of the captured face image do not include the chin feature, and the face image is missing the chin area, and the direction of the chin area relative to the whole face image is downward, then the column is driven to move downward so that the missing chin area can enter the camera's shooting area. If the features of the captured face image do not include the forehead feature, and the face image is missing the forehead area, and the direction of the forehead area relative to the whole face image is upward, then the column is driven to move upward so that the missing forehead area can enter the camera's shooting area. During the movement of the pillar, the camera continues to capture facial images in real time until the captured image contains a complete face, at which point the pillar stops moving. Facial landmark detection is then performed on the captured image of the complete face. If the initial facial image captured by the camera already contained a complete face, then there is no need to drive the pillar; facial landmark detection can proceed directly.

[0056] More specifically, to improve the efficiency of keypoint detection, a facial region can be cropped from the acquired facial image containing the complete face. Keypoint detection is then performed only on this facial region. The cropped facial region is then fed into a facial keypoint algorithm to obtain results such as... Figure 9 The facial landmarks shown.

[0057] Optionally, the facial landmark algorithm can detect 98 landmarks, and the specific distribution of the 98 landmarks is as follows: Figure 9 As shown. Facial landmark detection algorithms can also be 68-point landmark detection, 106-point landmark detection, etc., and are not limited here.

[0058] It should be noted that keypoints can be identified using neural network algorithms. The identified keypoints include at least those used to determine facial pose. A neural network framework is pre-built, and then trained using training samples labeled with these keypoints to obtain a neural network model capable of identifying these keypoints. For example, the keypoints to be identified are those used later in the text to calculate pitch, yaw, and roll angles.

[0059] S2 determines whether the facial pose is normal based on facial key points.

[0060] If the facial pose meets the preset shooting requirements, it is normal; otherwise, it is abnormal. Facial pose can be represented by facial key points, such as the relative positions between key points, including angle, orientation, distance, etc.

[0061] Facial pose is represented using key points, and facial pose standards are set based on these representations. This allows for the determination of whether a facial pose meets the preset standards; if it does, the facial pose is considered normal, and if not, it is considered abnormal. The facial pose standards are set based on whether the shooting requirements are met. For example, shooting requirements may include facing the side of the camera and facing directly forward.

[0062] Specifically, the normality of a person's facial posture can be determined using three dimensions: pitch angle, yaw angle, and roll angle. The specific forms of these three dimensions are as follows: Figure 10 As shown, the pitch angle represents the degree to which the head tilts up or down, the yaw angle represents the degree to which the head tilts left or right, and the roll angle represents the degree to which the head turns left or right.

[0063] Facial pose is represented by rotation angles in three spatial directions calculated based on key points, such as pitch, yaw, and roll angles. Facial pose standards are determined by performing rotation tests in two directions on the side of the face facing the camera, with the face pointing directly forward. This establishes the limits of rotation in each direction, thus defining the facial pose standard. This eliminates the need for precise calibration during camera installation. For example, if a cone-beam computed tomography (CBCT) camera can capture images at a certain angle (less than the angle at which CBCT cannot capture images), the pitch angle at that position is the facial pose standard for one direction. If the pitch exceeds this angle, the facial pose is considered abnormal; otherwise, it is normal. Similarly, the pitch angle for tilting the head, the yaw angle for left and right rotation, and the roll angle for left and right tilt correspond to facial pose standards in five directions. Of course, the thresholds for facial pose standards can be equal in symmetrical directions. The specific direction is determined by the sign of the pitch, yaw, and roll angles, which will be discussed in detail later.

[0064] Of course, it is also possible to make specific judgments based on distance, for example, to identify... Figure 9 Calculate the height difference between midpoints 64 and 68. Set a distance standard such as 5 pixels. If point 64 is more than 5 pixels higher than point 68, it means the face is tilted, which is abnormal. It should be tilted towards point 64 to adjust.

[0065] It should be noted that, in the description of the order of key point positions in the embodiments of the present invention, it indicates that the point is located in... Figure 9 The locations shown in the keypoints correspond to the facial feature points at those locations, but do not mean that facial landmark detection must include all of them. Figure 9 All key points in the calculation should be detected; however, detecting all of them is also possible. If only the key points involved in calculating position, pose, etc., in this embodiment are detected, then the calculation can be performed based on the neural network model, referring to [the relevant parameters] when labeling samples. Figure 9 Simply mark the corresponding point in the location.

[0066] In one embodiment of the present invention, such as Figure 3 As shown, determining whether a face pose is normal based on facial landmarks can include:

[0067] S21, calculate the first pitch angle, first yaw angle and first roll angle based on the facial key points.

[0068] Specifically, the first pitch angle is calculated using the following formula:

[0069]

[0070]

[0071] Among them, KeyPt 51 KeyPt represents the highest key point in the middle of the nose. 16 KeyPt represents the lowest keypoint in the center of the face. 51 .y represents the key point KeyPt 51 Coordinates in the first direction, KeyPt 51 .x represents a keypoint (KeyPt). 51 In the coordinates of the second direction, Pitch represents the first pitch angle. k1 is the first preset constant, and asin is the arcsine function.

[0072] The first direction is Figure 9 The middle vertical direction, the second direction is Figure 9 In practical applications, the left and right directions can be referenced. Figure 9 The relative positions of the first and second directions to the face are used to make adaptive adjustments.

[0073] The first yaw angle is calculated using the following formula:

[0074]

[0075]

[0076] Among them, KeyPt 97 This represents the key point located in the middle of the left eye's key points, with Yaw representing the first yaw angle. k2 is the second preset constant, and asin is the arcsine function.

[0077] The first roll angle is calculated using the following formula:

[0078] RollTan = (KeyPt) 97 .x-KeyPt 96 .x) / (KeyPt 97 .y-KeyPt 96 .y)

[0079]

[0080] Among them, KeyPt 96 This represents the keypoint located in the middle of the right eye's keypoints, with Roll representing the first roll angle. k3 is the third preset constant, and atan is the arctangent function.

[0081] It should be noted that k1, k2, and k3 can be adjusted according to actual needs; they can be the same or different. For example, if the angles can be normalized to radians, these three constants can be preset. For example, the symbols at each angle can be adjusted to change the positive or negative value representing the patient's head tilt; of course, these three values ​​can also be 1 or -1.

[0082] Specifically, the first direction is the Y-axis direction, and the second direction is the X-axis direction. Before calculating the first roll angle according to the formula, the KeyPt is first determined. 97 Is .x equal to KeyPt? 96 If .x is equal to 0, then execute Roll = 0; if KeyPt is equal to 0, then execute Roll = 0. 97 .x is not equal to KeyPt 96 If the first roll angle is .x, then the first roll angle is calculated according to the formula above. After obtaining the first roll angle, it is rounded down. The formula for calculating the first roll angle is as follows:

[0083] Roll = (int)Roll

[0084] Taking 98 keypoint detection as an example, see Figure 9 The aforementioned KeyPt 51 KeyPt represents the key point numbered 51. 16 KeyPt represents the key point numbered 16. 97 KeyPt represents the key point numbered 97. 96 This indicates the key point numbered 96.

[0085] It should be noted that the key points used in the formulas for calculating pitch, yaw, and roll angles can be found by referring to... Figure 9 The location of key points in the image is determined by selecting alternative key points, such as using key points in similar locations, which allows for the calculation of the corresponding angles in various ways.

[0086] S22, determine whether the face posture is normal based on the first pitch angle, the first yaw angle and the first roll angle.

[0087] In one embodiment of the present invention, such as Figure 4 As shown, determining whether the face posture is normal based on the first pitch angle, first yaw angle, and first roll angle includes:

[0088] S221, determine whether the absolute values ​​of the first pitch angle, the first yaw angle and the first roll angle are all less than or equal to the first preset threshold.

[0089] S222, if yes, then the face pose is determined to be normal; otherwise, the face pose is determined to be abnormal.

[0090] Specifically, the first pitch angle, the first yaw angle, and the first roll angle are used to represent the face pose, and the first preset threshold is a preset face pose standard.

[0091] For example, when the absolute values ​​of k1, k2, and k3 are 1, the first preset threshold can be taken within the range of 3-7 degrees, such as 5 degrees. If the absolute values ​​of k1, k2, and k3 are not 1, they can also be taken within the range of 3-7 degrees and multiplied by the corresponding absolute value of k1, k2, or k3. For example, when the first preset threshold is 5 degrees, if the absolute values ​​of the first pitch angle, the first yaw angle, and the first roll angle are all less than or equal to 5 degrees, the facial posture is considered normal; if the value of any one of the first pitch angle, the first yaw angle, and the first roll angle is greater than 5 degrees, the facial posture is considered abnormal. In cases of abnormal facial posture, the patient can be prompted to adjust their posture.

[0092] It should also be noted that the first preset thresholds for the first pitch angle, the first yaw angle, and the first roll angle can be the same or different. Specifically, they can be set according to the imaging effect of CT imaging. A smaller threshold can be set in the direction that has a relatively large impact on the imaging effect, and a larger threshold can be set in the direction that has a relatively small impact on the imaging effect.

[0093] In one embodiment, a first preset threshold can be set according to the post-processing requirements after cone-beam CT imaging. A panoramic image can be generated based on the position of the central incisor in the CT image, or the central incisor can be identified based on the CT image. If the left and right rotation angles are too large, the central incisor may be in an off-center position of the entire set of teeth, resulting in inaccurate or unidentifiable identification, and thus the panoramic image may not be generated. In this case, the first preset threshold corresponding to the yaw angle can be set slightly smaller. Secondly, the first preset threshold corresponding to the roll angle can also be set slightly smaller, while the first preset threshold corresponding to the pitch angle can be set slightly larger. This ensures that the imaging requirements are met without requiring too frequent adjustments, which could increase the patient's anxiety.

[0094] For example, the first preset threshold corresponding to the first roll angle is 4.5 degrees, the first preset threshold corresponding to the first yaw angle is 4.5 degrees, and the first preset threshold corresponding to the first pitch angle is 5.5 degrees.

[0095] In one example of the present invention, when the first pitch angle is greater than the corresponding first preset threshold, a first prompt message is issued to prompt the patient to perform a pitching motion; when the first yaw angle is greater than the corresponding first preset threshold, a second prompt message is issued to prompt the patient to perform a head-shaking motion; and when the first roll angle is greater than the corresponding first preset threshold, a third prompt message is issued to prompt the patient to perform a head-turning motion.

[0096] Specifically, patients can adjust their head posture based on the display animation, voice prompts, or the doctor's guidance. If the first pitch angle indicates an abnormal facial posture, the doctor will instruct the patient to tilt their head up or down. If the first yaw angle indicates an abnormal facial posture, the doctor will instruct the patient to shake their head to the left or right. If the first roll angle indicates an abnormal facial posture, the doctor will instruct the patient to tilt their head to the left or right. In other words, the sign of each angle determines the current orientation of the patient's head, allowing for adjustments in the opposite direction.

[0097] It should be noted that the pitch angle, yaw angle, and roll angle calculated above can be adjusted by setting the values ​​of k1, k2, and k3. This can change the sign of the corresponding angles. In other words, the sign of an angle in a direction indicates that the patient's head is tilted to one side in that direction, while the sign indicates that the patient's head is tilted to the other side in that direction. Specifically, the values ​​of k1, k2, and k3 can be preset and adjusted.

[0098] For example, if the first pitch angle is positive and greater than the first preset threshold, it indicates that the patient is in a head-up position, and the patient should be prompted to slightly lower their head. If the first pitch angle is negative and greater than the first preset threshold, it indicates that the patient is in a head-down position, and the patient should be prompted to slightly raise their head. If the first yaw angle is positive and greater than the first preset threshold, it indicates that the patient is in a head-to-right position, and the patient should be prompted to slightly shake their head to the left. If the first yaw angle is negative and greater than the first preset threshold, it indicates that the patient is in a head-to-left position, and the patient should be prompted to slightly shake their head to the right. If the first roll angle is positive and greater than the first preset threshold, it indicates that the patient is in a left-tilt position, and the patient should be prompted to tilt to the right. If the first roll angle is negative and greater than the first preset threshold, it indicates that the patient is in a right-tilt position, and the patient should be prompted to tilt to the left.

[0099] For example, with a first preset threshold of 5 degrees, when the first pitch angle is negative and greater than 5 degrees, a voice prompt is issued: "Please raise your head slightly." When the first pitch angle is positive and greater than 5 degrees, a voice prompt is issued: "Please lower your head slightly." When the first yaw angle is positive and greater than 5 degrees, a voice prompt is issued: "Please shake your head slightly to the left." When the first yaw angle is negative and greater than 5 degrees, a voice prompt is issued: "Please shake your head slightly to the right." When the first roll angle is positive and greater than 5 degrees, a voice prompt is issued: "Please tilt your head slightly to the right." When the first roll angle is negative and greater than 5 degrees, a voice prompt is issued: "Please tilt your head slightly to the left." The patient can also adjust their head posture according to the image guidance on the display screen. This allows the patient to clearly understand how to adjust their posture to quickly meet the shooting conditions.

[0100] It should be noted that when issuing voice prompts based on the calculation results of the first pitch angle, the first yaw angle, and the first roll angle, the specific angles that can be used to guide the patient to look up, shake their head, or turn their head may also be included.

[0101] More specifically, as the patient adjusts their head according to the voice prompts and the image guidance on the display screen, the camera captures facial images in real time and calculates the adjusted pitch angle, yaw angle, and roll angle until all the adjusted pitch angle, yaw angle, and roll angle are less than or equal to the first preset threshold. If all are less than or equal to 5 degrees, the facial posture is considered normal.

[0102] S3, if normal, turns on the laser and extracts the laser beam position from the face image.

[0103] Specifically, activating the laser can be achieved by turning it on to emit a laser beam. Before activating the laser, assuming the face is in a normal posture, it can be determined whether the face is in a second designated position. This second designated position is determined based on the relative position of the camera's imaging area and the CT imaging area. In the left-right direction of the face, when the face is in the desired first position within the CT imaging area, it is in the second position of the image captured by the camera; this second position is the second designated position. For example, if the patient's head is in the center area of ​​the cone-beam CT's radiation source and detector (the first position) in the left-right direction of the face, which improves the CT imaging effect, and the face is in the middle area of ​​the image captured by the camera (the second position), then the second designated position can be the center position of the face in the image captured by the camera within the imaging area. Specifically, it can refer to the center line of the image in the left-right direction of the face, or it can be a central area symmetrical to the center line.

[0104] In one embodiment of the present invention, such as Figure 5 As shown, after determining that the facial posture is normal, the control method of the cone-beam CT device also includes: determining key points KeyPt. 51 and KeyPt 16 If the line connecting the two points coincides with the second designated position, a fourth prompt message is issued to prompt the patient to move; if they coincide, the step of activating the laser is executed. The second designated position can be the center line of the image captured by the camera in the left-right direction of the face, or a central area of ​​a certain width defined to the left and right of that center line.

[0105] Specifically, KeyPt 51 and KeyPt 16The straight line connecting these points represents the highest keypoint in the middle of the nose and the lowest keypoint in the middle of the face. When the keypoint KeyPt... 51 and KeyPt 16 When the straight line connecting the points coincides with the second designated position, it indicates that the patient's head position has been adjusted from the left-right direction of the face. If the key point is KeyPt... 51 and KeyPt 16 If the straight line formed does not coincide with the second designated position, a fourth prompt message is issued to prompt the patient to move. This fourth prompt message has the same format as the previous prompt messages and can be either image guidance information on the display screen or voice prompts. For example, when the key point KeyPt... 51 and KeyPt 16 If the straight line connecting the two points is to the right of the second position, a voice prompt will be issued: "Please move the patient to the left." Simultaneously, a line representing the second designated position will appear on the display screen. The patient can move according to the display screen, ensuring their nose tip lands on this line. Once the patient has moved to the second designated position, the laser will be activated.

[0106] The aforementioned overlap is broad, and can mean that the connecting line strictly overlaps with the center line, or that they are within a preset distance range, or that the connecting line is located in a set central area.

[0107] Based on whether the face is in the second designated position, the position of the patient's head in the left and right directions of the face can be adjusted, thereby achieving more accurate CT imaging.

[0108] After activating the laser, it's necessary to extract the laser beam's position on the face and determine if it has reached a first designated position. This first designated position is determined based on the relative positions of the camera's imaging area and the CT imaging area during the scan. The laser beam position relative to the CT imaging area is fixed. Vertically, when the face is in the desired third position within the CT imaging area, the laser beam illuminates a fourth position on the face; this fourth position can then be considered the first designated position. For example, a facial feature, such as the inner corner of the eye, can be selected as the alignment point. When the patient is in the desired position within the CT imaging area, the laser beam illuminates the inner corner of the eye, and the face is within the camera's image acquisition area. During the adjustment process, the laser beam's position can be determined based on the facial image captured by the camera to ensure it reaches the inner corner of the eye. The laser beam can be adjusted together with the cone-beam CT imaging module. When the laser beam reaches the first designated position, the cone-beam CT imaging area also covers the patient's head, meaning the patient's head position meets the cone-beam CT imaging conditions.

[0109] It should be noted that during the adjustment of the laser beam, the face remains within the area captured by the camera in the vertical direction and will not move out of that area.

[0110] It should be noted that the first and second designated positions restrict the patient's head position from the first and second directions, respectively, so as to provide more accurate prompts for the patient to adjust their head position in order to meet the shooting conditions as soon as possible.

[0111] In one embodiment of the present invention, such as Figure 6 As shown, extracting the laser beam position from a face image includes:

[0112] S31, determine all laser beam rows in the face image and record the row coordinates of each laser beam row, where the row coordinates are the coordinates of the laser beam row in the first direction. A laser beam row is the row of pixels in the image corresponding to the face after the laser beam illuminates it.

[0113] When a laser beam shines on a person's face, it causes a change in the color or brightness of that area. Therefore, the laser beam line can be identified based on the color difference. The laser beam line can be accurately identified based on its color characteristics in the image, or the number of pixels in each line that satisfy those characteristics. Limiting the number of pixels in each line that satisfy those characteristics can avoid inaccurate identification caused by intermittent laser beam patterns.

[0114] S32, calculate the mean of all row coordinates and use the mean as the laser beam position.

[0115] In one embodiment, the laser beam used is red, and the R pixel value (also called the red value) on the original face image illuminated by the laser beam is at its maximum. Furthermore, all pixels in the laser beam row satisfy the following conditions: the difference between the R pixel value and the G pixel value (also called the green value) is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value (also called the blue value) is greater than a third preset threshold.

[0116] Specifically, after the laser is turned on, a raw image of the face with the laser beam is acquired, and the width and height of the raw face image are extracted. The raw face image is then searched row by row. If the difference between the R pixel value and the G pixel value in a row is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold, this row is determined to be a laser beam row, and the row coordinates of this laser beam row are recorded. The row coordinates are the Y-coordinates of this row. Furthermore, the conditions for identifying laser beam rows can be further restricted: the proportion of pixels whose R pixel value and G pixel value difference is greater than the second preset threshold, and whose R pixel value and B pixel value difference is greater than the third preset threshold, exceeds a certain threshold, such as 50%.

[0117] The second and third preset thresholds can be set as needed, such as the second preset threshold being 50 to 200 and the third preset threshold being 50 to 200. The specific settings need to be adjusted according to the on-site environment.

[0118] More specifically, after judging the pixel values ​​of all rows in the original face image, N laser beam rows that meet the above pixel requirements can be obtained. The average row coordinates of the N laser beam rows are taken as the position of the laser beam. Alternatively, the number of pixels corresponding to the laser beam row that meet the above color difference condition can be obtained, and the average row coordinates of the pixels can be used as the position of the laser beam row.

[0119] The laser beam position can be calculated using the following formula:

[0120]

[0121] Where H is the laser beam position, and N is the number of rows of laser beams identified. For example, the number of rows where the difference between the R pixel value and the G pixel value is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold, is h. i The row coordinates of the laser beam line to be identified in the first direction are defined as follows: the row coordinates of pixels whose difference between R pixel value and G pixel value is greater than a second preset threshold, and whose difference between R pixel value and B pixel value is greater than a third preset threshold.

[0122] Alternatively, the laser beam position can be calculated using the following formula:

[0123]

[0124] Where H represents the laser beam position, and M represents the number of pixels in the identified laser beam row that meet the color difference condition. A laser beam row is defined as a row where the number of pixels meeting the color difference condition exceeds a preset number. For example, the color difference condition is that the difference between the R pixel value and the G pixel value is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold. A laser beam row is defined as a row where the proportion of pixels meeting this color difference condition exceeds 50%. P i The row coordinates of pixels that meet the color difference conditions, such as the row coordinates of pixels in the first direction where the difference between the R pixel value and the G pixel value is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold.

[0125] The first direction can be perpendicular to the direction of the line, and the second direction is perpendicular to the first direction. For standing or sitting cone-beam CT, the first direction can be vertical and the second direction can be horizontal.

[0126] Similarly, if the laser beam used is of a different color, the laser beam line at the irradiated location can be identified based on the color.

[0127] S4, based on the position of the laser beam and the key points of the face, drives the column to move in the first direction.

[0128] After obtaining the laser beam position, it is also necessary to compare the laser beam position with the facial key points (KeyPt). 31 Whether the row coordinates coincide. Typically, the laser beam position is difficult to achieve the required position in one go; in this case, the drive column needs fine-tuning. If H-KeyPt 31 If y < 0, then drive the movement upwards of abs(H-KeyPt). 31 .y), otherwise drive the downward movement of abs(H-KeyPt). 31 .y).

[0129] S5, when the laser beam reaches the first designated position, control the cone-beam CT device to perform CT imaging.

[0130] In one embodiment of the present invention, the laser beam position reaching a first designated position includes: the laser beam position and a key point KeyPt. 31 The coordinates in the first direction coincide, where KeyPt 31 This indicates the second highest key point in the face contour key points in the first direction, which can be the Y-axis direction.

[0131] By properly setting the relative positions of the laser, camera, and cone-beam CT imaging module, adjustments can be made to the camera position before face detection. The adjustments in S4 are fine-tuning and will not cause the face to exceed the camera's imaging area.

[0132] In one embodiment of the present invention, such as Figure 7 As shown, the control method for the cone-beam CT device during CT imaging also includes:

[0133] S51, based on the current face image, obtain the second pitch angle, the second yaw angle, and the second roll angle.

[0134] Specifically, the calculation formulas for the second pitch angle, the second yaw angle, and the second roll angle are the same as those for the first pitch angle, the first yaw angle, and the first roll angle, and will not be repeated here.

[0135] S52, determine whether the absolute values ​​of the second pitch angle, the second yaw angle and the second roll angle are greater than the first preset threshold.

[0136] S53, if any of the absolute values ​​of the second pitch angle, the second yaw angle, and the second roll angle are greater than the first preset threshold, the cone-beam CT device is controlled to stop imaging.

[0137] Specifically, during the imaging process of a cone-beam CT scanner, the patient cannot remain completely still. Significant patient movement can severely impact the quality of the CT scan, necessitating the cone-beam CT scanner to stop imaging. While the cone-beam CT scanner is imaging, the camera acquires real-time facial images. Based on these images, the second pitch angle, second yaw angle, and second roll angle are calculated using the aforementioned formula. If any of the absolute values ​​of these angles exceeds a first preset threshold, it indicates significant patient movement in one or more directions, severely affecting CT image quality, and the cone-beam CT scanner is stopped. If the absolute values ​​of these angles are all less than or equal to the first preset threshold, it indicates slight patient movement, which has a minimal impact on imaging quality, and the cone-beam CT scanner continues imaging.

[0138] It should be noted that the first preset threshold can be set within the range of 3-7 degrees, such as 5 degrees. The first preset thresholds for the first pitch angle, first yaw angle, and first roll angle can be the same or different, depending on the CT imaging effect. A smaller threshold can be set in the direction that has a relatively greater impact on the imaging effect, and a larger threshold can be set in the direction that has a relatively smaller impact on the imaging effect. For example, the first preset threshold for the first roll angle is 4.5 degrees, the first preset threshold for the first yaw angle is 4.5 degrees, and the first preset threshold for the first pitch angle is 5.5 degrees.

[0139] In one embodiment of the present invention, such as Figure 8 As shown, in order to prevent patient movement from affecting the image quality during the CT imaging process, the control method of the cone-beam CT device also includes:

[0140] S55, calculate the first difference between the third pitch angle, the second difference between the third yaw angle, and the third difference between the third roll angle of two frames of face images with a first preset time interval.

[0141] Specifically, during the shooting process, the camera monitors two frames of data at a first preset time interval in real time, and calculates the difference between the pitch angle, yaw angle, and roll angle between the two frames at the first preset time interval. If the absolute value of the difference between the pitch angle, yaw angle, or roll angle between the two frames at the first preset time interval is within a fourth preset threshold, then CT shooting continues.

[0142] S56, when any one of the absolute values ​​of the first difference, the second difference, and the third difference is greater than the fourth preset threshold, the cone-beam CT device is controlled to stop CT imaging.

[0143] Specifically, the fourth preset threshold can be set within the range of 3-7 degrees. For example, if the value is 5 degrees, when the absolute value of the difference between the pitch angle, yaw angle, or roll angle at any interval of the first preset time is greater than 5 degrees, the cone-beam CT device will stop CT imaging. The main reason for this situation is facial movement and back-and-forth swaying. Facial changes can be either rapid or slow. Larger deviations have a significant impact on image quality and affect the image reconstruction effect. Imaging should be terminated in advance according to the degree of deviation to reduce the rate of bad images and lower the radiation dose to the patient.

[0144] The first preset time period can be set according to shooting needs, and can be adjusted based on the shooting effect. In one embodiment, the first preset time can be set according to the camera's shooting frequency; the faster the camera's shooting frequency, the shorter the first preset time can be set.

[0145] Meanwhile, doctors outside the lead room can remotely observe the patient's condition in real time through images projected onto a touch screen. Doctors can also use a voice module to remind patients to maintain their condition and can stop the recording immediately if any abnormality is detected.

[0146] The control method of the cone-beam CT device in this invention involves capturing a facial image using a camera, detecting key points in the facial image, adjusting the facial posture based on these key points, activating the laser after the facial posture meets requirements, extracting the laser beam position from the facial image, and driving the column to move so that the laser beam position reaches the designated location before controlling the cone-beam CT device to perform CT imaging. This control method can automatically adjust the imaging position and posture for different patients, resulting in optimal image quality, reduced defective images, decreased radiation exposure to patients, and extended machine lifespan.

[0147] In one implementation, after the facial pose adjustment is completed, the cone-beam CT imaging stage begins. At this point, the system enters a real-time background monitoring state. The control method for the cone-beam CT device specifically includes:

[0148] (1) Real-time acquisition of patient images;

[0149] (2) Determine if there is a patient in the image, such as whether there is a complete patient face. If no patient is detected, it means that the cone-beam CT detector or X-ray source has rotated to the front of the person and blocked the camera. Repeat steps 1) and 2) and continue to wait. If a complete patient face is detected in the patient image, proceed to step 3).

[0150] (3) Obtain a face image through the camera, and perform key point detection on the face image to obtain face key points. For example, intercept the face area of the patient and send it into the face key point algorithm for face key point detection. The face key point detection is implemented by an artificial intelligence method, and 98-point key point detection is adopted. The specific steps can refer to the foregoing key point detection steps and will not be elaborated here.

[0151] (4) Calculate the pitch angle (Pitch), yaw angle (Yaw), and roll angle (Roll) through the face key points. The calculation method can refer to the foregoing part and will not be elaborated here.

[0152] (5) Judge whether the face pose of the patient is normal through the pitch angle, yaw angle, and roll angle. The specific steps can refer to the foregoing judgment process of whether the face pose is normal and will not be elaborated here.

[0153] Further, the control method of the cone beam CT device may further include:

[0154] Calculate the pitch angle, yaw angle, and roll angle of two face images separated by the first preset time period. The first frame: pitch angle PitchB, yaw angle YawB, and roll angle RollB; the second frame: pitch angle PitchC, yaw angle YawC, and roll angle RollC. If abs(PitchC - PitchB) < th1 and abs(YawC - YawB) < th1 and abs(RollC - RollB) < th1, prompt the patient to maintain the state. For example, th1 is 0 - 3 degrees. If abs(PitchC - PitchB) > th1 or abs(YawC - YawB) > th1 or abs(RollC - RollB) > th1, it is considered abnormal and the shooting is terminated.

[0155] Wherein, the first preset time period can be the time interval between two adjacent frames or the time interval between multiple frames.

[0156] Further, when the first preset time period is the time interval between multiple frames, if at least one of abs(PitchC - PitchB), abs(YawC - YawB), and abs(RollC - RollB) within the first preset time period is greater than th2, and th2 < th1, then for this first preset time period, calculate the difference between the corresponding angles of two frames within the second preset time period. If this difference is greater than th3, it is considered abnormal and the shooting should be terminated. For example, if abs(PitchC - PitchB) is greater than th2, calculate the difference between the pitch angles of the corresponding two frames. If this difference is greater than th3, it is considered abnormal.

[0157] In other words, if the angle changes rapidly within a certain period of time, it is considered an abnormality and filming should be stopped.

[0158] For example, taking a camera at 30fps as an example, the first time period is 600ms, which is an interval of 20 frames, the second preset time period is 300ms, which is an interval of 10 frames, th1 is 3 degrees, th2 is 2.5 degrees, and th3 is 2 degrees.

[0159] Based on the control method of the cone-beam CT device described above, the present invention also proposes a cone-beam CT device.

[0160] In embodiments of the present invention, such as Figure 11 As shown, the cone-shaped CT device 100 includes: a column 10, a camera 20, and a controller 30. The controller 30 includes a memory, a processor, and a computer program stored in the memory 30. When the computer program is executed by the processor, it implements the control method of the cone-shaped CT device as described above.

[0161] Figure 12 This is a front view of a cone-beam CT device according to an embodiment of the present invention.

[0162] like Figure 12 As shown, the cone-beam CT device 100 includes a base 1, a fixed column 2, a sliding column 3, a laser 4, a touch screen 5, a detector 6, a cantilever 7, a radiation source 8, a side-view imaging module 9, a C-arm 10, and a camera 11.

[0163] The laser 4, touch screen 5, and C-arm 10 are all fixed to the sliding column 3 and can move up and down relative to the fixed column 2 together with the sliding column 3. During imaging, the patient is located in the imaging area and faces the sliding column 3. The detector 6 and the radiation source 8 can be positioned relative to each other on the C-arm 10. The laser 4 can emit a horizontal laser beam, illuminating a horizontal laser line on the patient's face.

[0164] It should be noted that, with the positions of other modules remaining unchanged, the first designated position will change as the position of laser 4 changes. For example, when laser 4 is in one position, the first designated position is the tip of the patient's nose, while in another higher position, the first designated position may be the inner corner of the eye.

[0165] The touchscreen display 5 is used to set imaging parameters, such as selecting a predetermined imaging model by inputting settings for adults or children. Optionally, during the setting of these parameters, the various components of the cone-beam CT device 100 are relatively fixed so as not to interfere with the doctor's parameter setting via the touchscreen display 5. As another example, during the setting of these parameters, some components of the cone-beam CT device 100 are movable, but can be designed to avoid the location where the doctor sets the parameters.

[0166] The touchscreen display 5 is also used during patient positioning to show the patient's head position in real time, providing guidance for accurate positioning. Simultaneously, the touchscreen display 5 is a movable screen (similar to a tablet) that uses wireless communication. Doctors can hold it in their hands to set parameters and then place it opposite the patient for guidance. Furthermore, adjusting device parameters and guiding the patient's head positioning are both achieved through the same touchscreen display 5, thus saving on equipment costs.

[0167] The camera 11 is embedded in the middle of the upper bezel of the touch display 5 and can be integrated with the touch display 5.

[0168] Based on the above-described control method for cone-beam CT devices, this invention also proposes a computer-readable storage medium.

[0169] In an embodiment of the present invention, a computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, it implements the control method of the cone-beam CT device as described above.

[0170] The control method, cone-beam CT device, and medium of this invention involve capturing facial images using a camera, detecting key points in the facial images, adjusting the facial posture based on these key points, activating the laser after the facial posture meets requirements, extracting the laser beam position from the facial image, and driving a column to move so that the laser beam reaches a designated position before controlling the cone-beam CT device to perform CT imaging. This control method allows for automatic adjustment of the imaging position and posture for different patients, resulting in optimal image quality, reduced defective images, decreased radiation exposure to patients, and extended machine lifespan.

[0171] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0172] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0173] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0174] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0175] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0176] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0177] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0178] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A control method for a cone-beam CT device, characterized in that, The cone-beam CT device includes a column, a camera, and a laser; the control method includes: The camera captures a facial image, and key point detection is performed on the facial image to obtain facial key points. Determine whether the facial posture is normal based on the aforementioned facial key points; If normal, the laser is turned on, and the laser beam position is extracted from the face image; Based on the position of the laser beam and the key points of the face, the column is driven to move in the first direction; When the laser beam reaches the first designated position, the cone-beam CT device is controlled to perform CT imaging.

2. The control method for the cone-beam CT device according to claim 1, characterized in that, The control method further includes: Determine whether the face image contains a complete face; If not, then drive the column to move in the set direction; If so, then perform the step of key point detection on the face image.

3. The control method for the cone-beam CT device according to claim 1, characterized in that, The step of determining whether a face pose is normal based on the facial key points includes: Calculate the first pitch angle, the first yaw angle, and the first roll angle based on the facial key points; The facial posture is determined based on the first pitch angle, the first yaw angle, and the first roll angle.

4. The control method for the cone-beam CT device according to claim 3, characterized in that, The first pitch angle is calculated using the following formula: in, This refers to the highest key point in the middle of the nose. This refers to the lowest keypoint in the middle of the face among the keypoints of the facial contour. Indicate key points Coordinates in the first direction Indicate key points Coordinates in the second direction, Pitch Indicates the first pitch angle. This is the first preset constant; And / or, the first yaw angle is calculated using the following formula: in, This indicates the key point located in the middle of the left eye's key points. Yaw This represents the first yaw angle. This is the second preset constant; And / or, the first roll angle is calculated using the following formula: in, This indicates the key point located in the middle of the right eye. Roll Indicates the first roll angle, This is the third preset constant.

5. The control method for the cone-beam CT device according to claim 3, characterized in that, The step of determining whether the face posture is normal based on the first pitch angle, the first yaw angle, and the first roll angle includes: Determine whether the absolute values ​​of the first pitch angle, the first yaw angle, and the first roll angle are all less than or equal to a first preset threshold. If so, the face pose is considered normal; otherwise, the face pose is considered abnormal.

6. The control method for the cone-beam CT device according to claim 5, characterized in that, The control method further includes: Prompt using at least one of the following methods: When the absolute value of the first pitch angle is greater than the first preset threshold, a first prompt message is issued to prompt the patient to perform a pitch operation. When the absolute value of the first yaw angle is greater than the first preset threshold, a second prompt message is issued to prompt the patient to perform a head-shaking operation. When the absolute value of the first roll angle is greater than the first preset threshold, a third prompt message is issued to prompt the patient to turn their head.

7. The control method for the cone-beam CT device according to claim 4, characterized in that, After determining that the facial pose is normal, the control method further includes: Determine the key points and the key points mentioned Does the straight line formed by the two lines coincide with the second specified position? If they do not overlap, a fourth prompt message is issued to alert the patient to move. If they coincide, then proceed with the step of activating the laser beam.

8. The control method for the cone-beam CT device according to claim 1, characterized in that, Extracting the laser beam position from the face image includes: All laser beam rows in the face image are identified, and the row coordinates of each laser beam row are recorded, wherein the row coordinates are the coordinates of the laser beam row in the first direction; Calculate the mean of all row coordinates and use the mean as the position of the laser beam; Wherein, all pixels in the laser beam row satisfy the condition that the difference between the R pixel value and the G pixel value is greater than a second preset threshold, and the difference between the R pixel value and the B pixel value is greater than a third preset threshold.

9. The control method for the cone-beam CT device according to claim 1, characterized in that, The laser beam position reaches the first designated position, including: The laser beam position and key points The coordinates in the first direction coincide, where, This refers to the key point located at the second highest position in the first direction, as described in the facial contour key points.

10. The control method for the cone-beam CT device according to claim 1, characterized in that, During the process of controlling the cone-beam CT device to perform CT imaging, the control method further includes: Based on the current face image, the second pitch angle, the second yaw angle, and the second roll angle are obtained; Determine whether the absolute values ​​of the second pitch angle, the second yaw angle, and the second roll angle are greater than a first preset threshold. If any of the absolute values ​​of the second pitch angle, the second yaw angle, and the second roll angle are greater than the first preset threshold, the cone-beam CT device is controlled to stop CT imaging.

11. The control method for cone-beam CT according to claim 1, characterized in that, During the process of controlling the cone-beam CT device to perform CT imaging, the control method further includes: Calculate the first difference between the third pitch angle, the second difference between the third yaw angle, and the third difference between the third roll angle of two face images with a first preset time interval; When any one of the absolute values ​​of the first difference, the second difference, and the third difference exceeds a fourth preset threshold, the cone-beam CT device is controlled to stop CT imaging.

12. A cone-beam CT device, characterized in that, The device includes: a column, a camera, and a controller, wherein... The controller includes a memory, a processor, and a computer program stored in the memory, which, when executed by the processor, implements the control method as described in any one of claims 1-11.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the control method as described in any one of claims 1-11.

Images