WO2021056452A1

WO2021056452A1 - Method and apparatus for detecting position of patient, radiotherapy device and readable storage medium

Info

Publication number: WO2021056452A1
Application number: PCT/CN2019/108670
Authority: WO
Inventors: 李大梁
Original assignee: 西安大医集团股份有限公司
Priority date: 2019-09-27
Filing date: 2019-09-27
Publication date: 2021-04-01
Also published as: CN114430670A

Abstract

A method and apparatus for detecting the position of a patient, a radiotherapy device and a computer-readable storage medium. The radiotherapy device comprises a patient fixing mechanism (11), a first camera mechanism (12) and a second camera mechanism (13). The method comprises: when a patient has been fixed to the patient fixing mechanism (11), photographing at least one marker (20) by means of the first camera mechanism (12) so as to obtain a first image, and photographing the least one marker (20) by means of the second camera mechanism (13) so as to obtain a second image, the marker (20) being a position indicator (101) attached to the body surface of the patient; and obtaining the position (102) of the at least one marker (20) in space on the basis of the positions of the at least one marker (20) in the first image and the second image; and acquiring posture position data (103) of the patient on the basis of the position of the at least one marker (20) in space. Monitoring of the movement of the patient during treatment may be achieved.

Description

Patient position detection method and device, radiological medical equipment, and readable storage medium

Technical field

The present disclosure relates to the medical field, and in particular to a method and device for detecting the position of a patient, radiological medical equipment, and computer-readable storage media.

Background technique

Patient position detection has important applications in many medical activities. For example, in the process of radiotherapy (radiotherapy for short, which refers to the elimination of lesions with radiation, which is a physical therapy for tumors), it is necessary to align the patient's tumor target area with the isocenter of the radiotherapy equipment so that the radiation can be accurately irradiated to the patient's tumor Target area, the tumor target area cells are killed by high-dose radiation, while the surrounding normal tissue cells are not damaged. However, in the course of treatment, patients often cannot maintain a posture for a long time, and their body may move, resulting in a decrease in treatment accuracy. For example, in the course of radiotherapy, if the patient's body moves, causing the patient's target area to deviate from the center of the radiotherapy equipment, this will cause the radiation to not be accurately irradiated to the patient's target area, which may not only affect the therapeutic effect of the tumor target area, but also It may also increase the damage to the normal tissue cells around it.

Summary of the invention

The present disclosure provides a method and device for detecting the position of a patient, radiological medical equipment, and a computer readable storage medium, which can realize the detection of the patient's movement during treatment.

In a first aspect, the present disclosure provides a method for detecting the position of a patient, the method is applied to a medical device, the medical device includes a patient fixing mechanism, a first camera mechanism, and a second camera mechanism, and the method includes:

When the patient is fixed on the patient fixing mechanism, at least one marker attached to the patient's body surface is captured by the first camera mechanism to obtain a first image, and the second camera mechanism is used to capture the first image. The at least one marker is taken to obtain a second image; wherein, the marker is a position indicator that is attached to the patient's body surface and can emit or reflect visible light, and the first image and the second image are both Visible light image

Obtaining the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image;

Based on the position of the at least one marker in space, the posture position data of the patient is obtained.

In a possible implementation manner, each of the markers is a luminous body, and each marker is obtained based on the position of the at least one marker in the first image and the second image. Before the position of the marker in space, the method further includes:

Based on the brightness difference between the at least one marker and the background in the first image and the second image, the at least one marker is identified in the first image and the second image, respectively.

In a possible implementation manner, a reflective material is provided on the surface of each of the markers, and when the patient is fixed on the patient fixing mechanism, at least one marker is marked by the first camera mechanism. The first image is obtained by shooting the object, and the second image is obtained by shooting the at least one marker by the second camera mechanism, including:

When the patient is fixed on the patient fixing mechanism, the first image is captured by the first camera mechanism that provides light to the at least one marker, and the first image is obtained by providing light to the at least one marker. The second image is captured by the second camera mechanism;

Correspondingly, before the obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, the method further includes:

In a possible implementation manner, at least two markers of different colors are attached to the body surface of the patient. Position, before obtaining the position of each of the markers in space, the method further includes:

Based on the color difference between the different markers in the first image and the second image, each of the markers is identified in the first image and the second image, respectively.

In a possible implementation, obtaining the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image includes:

The spatial coordinate value of the marker in the second direction is obtained based on the planar coordinate value of any of the markers in the second direction in the first image, and the spatial coordinate value of the marker in the second direction is obtained based on any of the markers in the first image. The plane coordinate value in the first direction in the second image obtains the spatial coordinate value of the marker in the first direction, based on the plane coordinate value of any marker in the third direction in the first image and the At least one of the plane coordinate values in the third direction in the second image obtains the spatial coordinate value of the marker in the third direction;

Wherein, the first direction is the shooting direction of the first camera mechanism, the second direction is the shooting direction of the second camera mechanism, the first direction is perpendicular to the second direction, and the first direction is perpendicular to the second direction. The three directions are respectively perpendicular to the first direction and the second direction.

In a second aspect, the present disclosure also provides a patient position detection device, which is applied to radiological medical equipment, the radiological medical equipment includes a patient fixing mechanism, a first camera mechanism, and a second camera mechanism, and the device includes:

The photographing module is used to photograph at least one marker attached to the patient's body surface through the first photographing mechanism to obtain a first image when the patient is fixed on the patient fixing mechanism. The second imaging mechanism takes the at least one marker to obtain a second image; wherein, the marker is a position indicator that is attached to the body surface of the patient and can emit or reflect visible light, and the first image and the The second images are all visible light images;

A first processing module, configured to obtain the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image;

The second processing module is used to obtain body position data of the patient based on the position of the at least one marker in space.

In a possible implementation manner, each of the markers is a luminous body, and the device further includes a first identification module,

The first recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The brightness difference between the at least one marker and the background in the first image and the second image, and the at least one marker is identified in the first image and the second image, respectively.

In a possible implementation manner, a reflective material is provided on the surface of each of the markers, and the photographing module is further used for when the patient is fixed on the patient fixing mechanism, by pointing to the at least one The first image is captured by the first camera mechanism that provides light to the marker, and the second image is captured by the second camera mechanism that provides light to the at least one marker; correspondingly, the The device also includes a second identification module,

The second recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The brightness difference between the at least one marker and the background in the first image and the second image, and the at least one marker is identified in the first image and the second image, respectively.

In a possible implementation manner, at least two markers of different colors are attached to the body surface of the patient, and the device further includes a third recognition module,

The third recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The color difference between the different markers in the first image and the second image, each of the markers is identified in the first image and the second image, respectively.

In a possible implementation manner, the first processing module is further configured to:

In a third aspect, the present disclosure also provides a radiological medical equipment, the radiological medical equipment includes a processor and a memory, the memory stores program instructions, and the processor is configured to call the program instructions in the memory to Perform any of the above-mentioned patient position detection methods.

In a fourth aspect, the present disclosure also provides a computer-readable storage medium, the computer storage medium stores a computer program, the computer program includes program instructions, the program instructions are configured to cause the The processor executes any of the above-mentioned methods for detecting the position of the patient.

It can be seen from the above technical solutions that the present disclosure can obtain two visible light images containing markers based on visible light imaging in radiological medical equipment, so as to obtain the position of the markers in space in the two visible light images, and use the markers to interact with the patient. The attachment relationship of the body surface is used to obtain the patient's posture and position data, which can then realize the detection of the patient's movement during the treatment process. Since the equipment for realizing the technical solution of the present disclosure can be easily obtained (for example, the patient fixing mechanism can be a bed or a support, the camera mechanism can be a camera, and the marker can be tape or simple geometry), the present disclosure can help reduce the realization of the patient position The equipment required for the detection is required, and it can play a supplementary or alternative patient position detection function when other patient position monitoring methods are unavailable or fail.

Description of the drawings

FIG. 1 is a schematic diagram of an application scenario of a patient position detection method provided by an embodiment of the present disclosure;

2 is a schematic flowchart of a method for detecting the position of a patient provided by an embodiment of the present disclosure;

3 is a schematic diagram of the principle of obtaining the position of a marker in space based on the position of a marker in an image in a method for detecting the position of a patient according to an embodiment of the present disclosure;

4 is a schematic flowchart of a method for detecting a patient's position according to another embodiment of the present disclosure;

Figure 5 is a structural block diagram of a patient position detection device provided by an embodiment of the present disclosure;

Fig. 6 is a structural block diagram of a radiological medical equipment provided by an embodiment of the present disclosure.

detailed description

In order to make the principles and advantages of the present disclosure clearer, the following further describes the embodiments of the present disclosure in detail with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the usual meanings understood by those with ordinary skills in the field to which this disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components.

Fig. 1 is a schematic diagram of an application scenario of a method for detecting a position of a patient provided by an embodiment of the present disclosure. 1, the patient position detection method is applied to medical equipment, the medical equipment includes a patient fixing mechanism 11 (including a bed body 111 and a handstand 112 on the bed body 111), a first camera mechanism 12, and a second camera Organization 13. In the scene shown in FIG. 1, the patient lies flat on the bed 111 in the patient fixation mechanism 11, with his right hand resting on the armrest 112 in the patient fixation mechanism 11, and on the patient's head, left shoulder, and right A marker 20 (a position indicator attached to the body surface of the patient and capable of reflecting or emitting visible light is attached to the body surface of the shoulder and the right hand. In FIG. 1, it includes a support rod with the bottom fixed on the body surface of the patient). And the structure of the sphere fixed on the top of the support rod as an example). The first imaging mechanism 12 is arranged above the bed 111 and takes pictures from the front of the patient, and the second imaging mechanism 13 is arranged on one side of the bed 111 in the horizontal direction and takes pictures from the left side of the patient. It should be understood that, in order to ensure the accuracy of position detection, on the basis of the structure shown in FIG. 1, mechanical structures such as brackets, fasteners and/or rails can be used to fix the shooting position and shooting direction of the first camera mechanism 12 as well as The shooting position and shooting direction of the second camera mechanism 13 and the mechanical structure may be a part of the patient fixing mechanism 11. When the patient's body is substantially fixed by the patient fixing mechanism 11 and the required marker 20 is attached to the body, the position of the patient can be detected according to the method provided in the embodiment of the present disclosure, and the result obtained can be used, for example, to monitor whether the patient has deviated In order to provide the treatment position, or provide the patient's posture position data needed for the treatment activity, and so on.

It should be noted that the application scenarios and radiological medical equipment shown in Fig. 1 are only an example, which can be changed adaptively according to different usage needs. For example, the patient fixing mechanism 11 can also be used to fix an upright posture. The patient's support, the first camera mechanism 12 and the second camera mechanism 13 may be respectively located on the front and rear sides of the patient, and at least one marker 20 may all be provided on the patient's head or body, etc., which will not be listed here.

Fig. 2 is a schematic flowchart of a method for detecting the position of a patient provided by an embodiment of the present disclosure. It should be noted that the method of the embodiments of the present disclosure can be applied to any medical activity or radiological equipment that needs to detect the position of a patient, such as image-guided radiotherapy (Image-Guided Radio Therapy, IGRT), intracranial tumor resection surgery Or other surgical operations involving patient position detection, etc. It should be understood that the patient refers to the subject of these medical activities, for example, a patient who needs radiotherapy or surgery. In an example, the patient position detection method can be installed on radiological medical equipment (for example, radiotherapy equipment, imaging equipment, operating table, etc.) in the form of software, so as to realize the patient position detection process in medical activities. As an example, the execution subject of the method may be, for example, the radiological medical equipment, a control device connected to the radiological medical equipment, a processor of the radiological medical equipment, or a server connected to the radiological medical equipment, etc. . Referring to Fig. 2, the method for detecting the position of a patient may include the following steps.

In step 101, when the patient is fixed on the patient fixing mechanism, at least one marker attached to the patient's body surface is captured by the first imaging mechanism to obtain a first image, and the second imaging mechanism is used to capture at least one marker. Take the second image.

In an example, as shown in FIG. 1, four markers 20 are attached to the four different positions of the patient's body surface, and the first camera mechanism 12 and the second camera mechanism 13 respectively align the four markers in different shooting directions. The marker 20 is photographed. During the shooting process, the shooting position and shooting direction of the first camera mechanism 12 are fixed, and the shooting position and shooting direction of the second camera mechanism 13 are fixed. After the shooting is completed, the first camera mechanism 12 and the second camera mechanism 13 can actively provide the first image and the second image through a wired or wireless connection, or they can also be separately from the first camera through a wired or wireless connection. The first image and the second image are acquired at the mechanism 12 and the second camera mechanism 13. The transmission process may be partially or completely performed inside the radiological medical equipment, and the transmission process may include storing the image data in the memory In the link. In this way, the first image and the second image can be obtained separately, and it can be understood that both the first image and the second image contain the respective images of the four markers 20.

It should be noted that in order for the first camera mechanism and the second camera mechanism to capture all the markers in different orientations, the shooting position and shooting direction need to be compatible with the number and position of the markers. Adjust at least one of these two aspects adaptively before starting the test. Of course, you can configure the shooting position and shooting direction of the two camera mechanisms so that the viewing range covers all possible locations of markers as much as possible, so as to save the need to adapt the subsequent markers after changing the shooting positions and shooting directions of the two camera mechanisms. It is troublesome to calculate the position of an object in space.

In step 102, the position of the at least one marker in space is obtained based on the position of the at least one marker in the first image and the second image.

In an example, as shown in FIG. 1, the shooting position and shooting direction of the first camera mechanism 12, and the shooting position and shooting direction of the second camera mechanism 13 are all fixed by the mechanical structure, and therefore can be based on these known The position of the four markers 20 in the space is obtained from the position of the four markers 20 in the first image and the second image. For example, the surface of the bed 111 is a horizontal plane, and the first camera mechanism 12 photographs the patient lying on the bed 111 from above in the vertical direction, so that the four markers 20 in the first image relative to the boundary of the bed 111 The position coordinates of the four markers 20 can be used as the projected coordinates of the four markers 20 in the horizontal plane; moreover, the second camera mechanism 12 takes pictures from the left side of the patient in the horizontal direction at the same height as the surface of the bed 111, so that the second The distance between each marker 20 in the image and the surface of the bed 111 can be used as the projection coordinate of the marker 20 in the vertical direction. Assuming that the horizontal plane is the XY plane and the vertical direction is the Z axis, the coordinate values of the four markers 20 on the X axis and the Y axis can be obtained according to the positions of the four markers 20 in the first image, and the coordinate values of the four markers 20 on the X axis and the Y axis can be obtained according to the four The position of the marker 20 in the second image obtains the coordinate values of the four markers 20 on the Z axis. In this way, the positions of all the markers 20 in space are obtained.

Fig. 3 is a schematic diagram of the principle of obtaining the position of a marker in space based on the position of a marker in an image in a method for detecting a position of a patient provided by an embodiment of the present disclosure. Referring to FIG. 3, taking three markers 20 located at different positions as an example, the first imaging mechanism 12 takes the first image P1 on the XY plane by shooting in the opposite direction of the Z-axis direction, and the second imaging mechanism 13 faces the X-axis direction. The second image P2 on the YZ plane is obtained by shooting in the opposite direction of, and the origin of the XYZ space coordinate system is at the lower left corner of the first image P1 and the lower right corner of the second image P2. Therefore, in the case of ignoring image distortion, it can be considered that the projected coordinates of the marker 20 on the first image P1 include the X-axis and Y-axis coordinate values of its spatial coordinate values, and the marker 20 is in the second image. The projected coordinates on P2 include the Z-axis coordinate value and the Y-axis coordinate value in the space coordinate value. As shown in Figure 3, among the three markers: the projection coordinates of the highest marker 20 on the first image P1 are (x1, y1), and the projection coordinates on the second image P2 are (z1, y1), From this, the spatial coordinate values (x1, y1, z1) of the marker 20 can be obtained; the projection coordinates of the marker 20 with the middle height on the first image P1 are (x2, y2), and the projection on the second image P2 The coordinates are (z2, y2), from which the spatial coordinate values (x2, y2, z2) of the marker 20 can be obtained; the projection coordinates of the lowest marker 20 on the first image P1 are (x3, y3), The projected coordinates on the second image P2 are (z3, y3), from which the spatial coordinate values (x3, y3, z3) of the marker 20 can be obtained. It can be seen that when the shooting direction of the first camera mechanism and the shooting direction of the second camera mechanism are perpendicular to each other, the position of the at least one marker in space can be obtained as follows (the shooting direction of the first camera mechanism is The first direction, the shooting direction of the second camera mechanism is the second direction, and the third direction is perpendicular to the first direction and the second direction respectively): Based on the plane coordinate value of any marker in the second direction in the first image To the spatial coordinate value of the marker in the second direction (for example, the spatial coordinate value x1 in the X-axis direction is obtained based on the plane coordinate value x1 in the X-axis direction in the first image P1), based on any marker in the first image The plane coordinate value in the first direction in the second image obtains the space coordinate value of the marker in the first direction (for example, based on the plane coordinate value z1 in the Z axis direction in the second image P2, the space in the Z axis direction is obtained Coordinate value z1), based on at least one of the plane coordinate value in the third direction of any marker in the first image and the plane coordinate value in the third direction in the second image to obtain the space of the marker in the third direction Coordinate values (for example, based on the plane coordinate value y1 in the Y axis direction in the first image P1, and/or the plane coordinate value y1 in the Y axis direction in the second image P2, to obtain the space coordinate value y1 in the Y axis direction When the two plane coordinate values are different, for example, the average value can be used as the space coordinate value). It should be understood that, depending on the choice of the origin of the spatial coordinate system, the above process may involve coordinate conversion or related processes.

It should be understood that, in addition to obtaining the position of the marker in space based on the relative positional relationship between the marker in the image and other image elements (such as the image boundary or the object boundary), it can also be based on the marker in the image. Get the position of the marker in space from the pixel coordinates (the transformation relationship between the pixel coordinates and the space position can be obtained from the shooting position and shooting direction of the two camera mechanisms, or it can be calibrated through experiments. The data can be, for example, in a table The form is stored in the memory).

In another example, the above step 102 may include obtaining transformation data required to obtain the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image (for example, detecting two camera mechanisms) According to the shooting position and shooting direction, the original transformation data is corrected to ensure the accuracy of the position of the obtained marker in space), the transformation data may be, for example, that the plane where the first image is located is XY The plane, the plane where the second image is located is the data of the YZ plane, which can also be, for example, the transformation relationship between the pixel coordinates and the spatial position obtained from the shooting positions and shooting directions of the two camera mechanisms. In this way, the process of pre-configuring the transformation data can be omitted, and corrections can be made in time when the shooting positions and shooting directions of the two camera mechanisms change, thereby improving the accuracy of patient position detection.

It should also be understood that when the shooting direction of the first camera mechanism and the shooting direction of the second camera mechanism are not perpendicular to each other (that is, the included angle between each other is not 90°), the angle value of the included angle can be determined from each The plane coordinate values of each marker in the first image and the second image obtain the space coordinate value of the marker. For example, referring to Figure 3, the plane where the first image P1 is located can be fixed as the XY plane, and the plane where the second image P2 is located is the plane obtained by rotating the YZ plane around the Y axis. In this case, you can refer to the method described above. From the projection coordinates of the marker on the first image P1, the spatial coordinate values of the marker in the X-axis direction and the Y-axis direction are obtained, and the spatial coordinate value of the marker in the Z-axis direction is based on the marker in the second image The projection coordinates on P2 are combined with the angle between the two shooting directions to be obtained through trigonometric operations. Of course, depending on the way the spatial coordinate system is established, the first image and the second image may not be on the XY plane, YZ plane, or XZ plane. In this case, the first image needs to be based on the general spatial geometry calculation method. The angle between the plane where the second image is located and each coordinate axis calculates the position of each marker in space according to the projection coordinates of each marker on the first image and the second image. The related spatial geometric operations and coordinate transformation operations are well known to those skilled in the art, and will not be repeated here.

In step 103, the posture position data of the patient is obtained based on the position of the at least one marker in the space.

It should be noted that the posture position data of the patient is used to represent the posture of the patient and the position of each part required for medical activities or radiological medical equipment, and may be the spatial coordinates of at least one selected position point on the patient's body The value can also be the offset of at least one selected location point on the patient's body relative to its initial position, and can be in the form of a picture or a table.

In an example, the posture position data of the patient is expressed as the offset of the positions in space of the three markers 20 located on the patient's head, left shoulder, and right shoulder in FIG. 1 from their initial positions. , Is used to indicate the movement of the patient's breast tumor target area relative to the beginning of treatment, so that treatment will be stopped immediately when any deviation is detected to exceed the specified value to prevent radiation from irradiating the surrounding normal tissue cells to cause damage. In this example, the above-mentioned step 103 may include calculating the distance value between the spatial position of each marker 20 and its initial spatial position, and issuing or executing a stop radiation output when any obtained distance value exceeds a predetermined threshold. Control instruction.

It should be understood that since the number of markers 20 and the location of their attachment on the patient's body surface can be determined in advance, the position of the markers in space can be obtained in advance through theoretical calculations or experimental determinations on this basis. The transformation relationship to the posture position data of the patient, so that the required posture position data of the patient can be obtained based on the position of the marker obtained in step 102 in space. In addition, the transformation relationship from the pixel coordinates to the spatial position in the above step 102 can be combined with the transformation relationship from the position of the marker in space to the posture position data of the patient here, that is, it can be determined by theoretical calculation or experiment. Obtain the transformation relationship from the position of the at least one marker in the first image and the second image to the patient's posture position data, and use the transformation relationship to directly obtain the position of the at least one marker in the first image and the second image The patient's posture position data (at this time, the process of obtaining the position of at least one marker in space based on the position of the at least one marker in the first image and the second image is implicit in the transformation relationship).

It should also be understood that in the patient position detection process or the patient position monitoring process based on the process (ie, the patient position detection process is continuously repeated), the number and attachment positions of the markers attached to the patient's body surface should be kept constant. It can be changed, and by fixing the shooting positions and shooting directions of the two camera mechanisms, the overhead required to obtain the position of at least one marker in space each time can be reduced. Moreover, according to the different posture position data of the patient that needs to be obtained, the number of markers attached to the patient's body surface and the attachment position should be changed accordingly. For example, for the detection of the position of the patient's head, a single marker attached to the tip of the patient's nose may already meet the demand, while the markers attached to the patient's limbs may be possible for the detection of the patient's head position. Is not needed.

It can be seen that in the embodiments of the present disclosure, the position of the marker in space can be obtained by shooting the marker by the first camera mechanism and the second camera mechanism, and the attachment relationship between the marker and the patient's body surface can be used to obtain the patient. The posture and position data can realize the detection of the patient’s movement during the treatment process. Since the equipment for implementing the technical solution of the present disclosure can be easily obtained (for example, the patient fixing mechanism can be a bed, a chair, or a bracket, the camera mechanism can be a camera, a camera or an image sensor, and the marker can be a simple tape or ring belt. Therefore, the present disclosure can help reduce the hardware requirements required to realize patient position detection.

Fig. 4 is a schematic flowchart of a method for detecting a patient's position according to another embodiment of the present disclosure. To the extent possible, the method provided in the embodiments of the present disclosure can be combined with any of the above-described implementations of the patient position detection method. Referring to Fig. 4, the method may include the following steps.

In step 301, when the patient is fixed on the patient fixing mechanism, the first image is captured by the first camera mechanism that provides light to at least one marker, and the second image is captured by the second camera mechanism that provides light to the at least one marker. The second image.

That is, the first imaging mechanism and the second imaging mechanism may be equipped with lighting components to provide illumination to the object while shooting. In an example, as shown in FIG. 1, the first camera mechanism 12 can use a illuminating lamp provided next to the lens to provide visible light illumination at its shooting position, and the second camera mechanism 13 can use a illuminating lamp provided next to the lens. The visible light illumination is provided to the front of the shooting position, which can help improve the imaging effect of the first image and the second image, and is beneficial to improve the detection accuracy of subsequent position detection.

Correspondingly, reflective materials (such as reflective paints, reflective films, blazed gratings, etc.) may be provided on the surface of the marker, and the wavelength band with higher reflectivity can be adapted to the wavelength band provided by the camera mechanism. In this way, the marker can have relatively high brightness in the first image and the second image, and it is easier to distinguish it from other objects and the background.

In step 302, based on the brightness difference between the at least one marker in the first image and the second image and the background, at least one marker is identified in the first image and the second image, respectively.

It is understandable that in the case where the marker can have relatively high brightness in the first image and the second image, the marker can be more easily identified from the first image and the second image through image processing technology , And/or filter out the background and object details with relatively low brightness other than the marker from the first image and the second image to improve the recognition effect.

In one example, the brightness and contrast of the first image can be adjusted to make the brightness difference on both sides of the marker edge more obvious, and then the contour line of each marker can be identified by extracting the edge. In the process, other contour lines or The boundary line may not be recognized as an edge because the brightness difference on both sides is not large enough. In this way, in the processed first image, each marker can be easily identified by the shape, and then the location of each marker can be obtained; because the image details that may affect the recognition are filtered out in a large range, the above process can be It is relatively fast and accurate. Similarly, the same or similar processing can also be performed on the second image.

It should be understood that, in addition to providing illumination through the camera mechanism and reflecting light on the surface of the marker to achieve the above effects, it is also possible to use luminous bodies (for example, objects with luminescent paint on the surface, lamps, thin-film light-emitting devices, etc.) as the marker In order to enable the marker to have relatively high brightness in the first image and the second image, the imaging mechanism may not need to provide illumination at this time, and can help to improve the problem that the marker cannot be irradiated due to light shielding and cannot be recognized.

In step 303, based on the color difference between different markers in the first image and the second image, each marker is identified in the first image and the second image, respectively.

It should be understood that in the process described above, at least one marker can be viewed as a whole, and when there are multiple markers, each marker is not distinguished, which can save the algorithm overhead of image recognition, but It may not be able to deal with situations where the number of recognized markers changes (for example, a spherical object enters the shooting range in the scene of FIG. 1) or the positions of two markers are exchanged.

In this regard, when there are multiple markers, colors can be used to distinguish the markers. For example, three markers that emit red, green, and blue light can be used, or the red, green, and blue markers can be used separately under the illumination of the imaging mechanism. Blue and green markers. In this way, after identifying the positions of all markers in the first image and the second image, different markers can be distinguished according to the color of the image area at the corresponding position. Therefore, when an unexpected situation occurs such as the number of recognized markers changes, the corresponding processing can be performed according to the color of the marker, for example, the spherical object entering the shooting range does not have a predetermined color to exclude it. To ensure the accuracy of identification.

In step 304, the position of the at least one marker in space is obtained based on the position of the at least one marker in the first image and the second image.

In step 305, the posture position data of the patient is obtained based on the position of the at least one marker in the space.

It should be understood that the above steps 301 to 305 can be implemented with reference to the above description of the patient position detection method as shown in FIG. 1, which will not be repeated here.

In another example, the visible light imaging-based patient position detection method described in the embodiment of the present disclosure can be combined with non-visible light imaging to better realize each process in radiotherapy. For example, since the position where the marker is attached to the patient's body surface can be regarded as fixed, when performing image registration between X-ray transmission images or computed tomography images, it can be obtained based on the recognition of the marker. The attachment location point can be used to help reduce the amount of calculation for image registration, or the attachment location point can be used to verify the accuracy of image registration. Based on this, more accurate image registration can be achieved under a smaller radiation dose.

In yet another example, the use of the equipment in the embodiments of the present disclosure can help achieve rapid positioning of the patient. For example, the allowable space area of each marker can be pre-configured when the positioning is completed, and at the beginning of the positioning, it can be judged in real time whether each marker is in its allowable space area through the images collected by the two camera mechanisms. Guide the positioning according to the deviation obtained by the judgment until each marker is in its allowable space area. Since the marker can be quickly identified by the processing component based on the difference in brightness with the surrounding environment, and the marker that emits or reflects visible light and the visible light camera are easily available device components, a simple and fast response positioning of the device can be realized Guidance method. In addition, it can also monitor whether each marker is in its allowable space area in real time during the subsequent treatment process, and interrupt the treatment process when any marker moves out of its allowable space area to quickly respond to patients that may occur during the treatment process The unexpected situation of the sudden movement of the body is more conducive to timely detection of the unexpected situation than the non-visible light imaging device, which takes time for imaging and the device is more complicated.

Fig. 5 is a structural block diagram of a patient position detection device provided by an embodiment of the present disclosure. The device of the embodiments of the present disclosure can be applied to any medical activity or radiological equipment that needs to detect the position of a patient, such as image-guided radiotherapy (Image-Guided Radio Therapy, IGRT), intracranial tumor resection surgery, or other related patient position Surgical procedures for testing, etc. It should be understood that the patient refers to the subject of these medical activities, for example, a patient who needs radiotherapy or surgery. In an example, the patient position detection device may be installed on radiological medical equipment (for example, radiotherapy equipment, imaging equipment, operating table, etc.) in the form of software, so as to realize the patient position detection process in medical activities. Referring to Figure 5, the patient position detection device includes:

The photographing module 41 is used to photograph at least one marker attached to the patient's body surface through the first photographing mechanism to obtain a first image when the patient is fixed on the patient fixing mechanism. The second camera mechanism captures the at least one marker to obtain a second image; wherein the marker is a position indicator attached to the body surface of the patient;

The first processing module 42 is configured to obtain the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image;

The second processing module 43 is configured to obtain body position data of the patient based on the position of the at least one marker in space.

In a possible implementation manner, the first processing module 42 is further configured to:

It should be understood that, according to the optional implementation of the patient position detection method described above, the patient position detection device can implement any one of the above patient position detection methods through corresponding structures and configurations, and the specific details will not be repeated. .

In the example corresponding to Fig. 5, the patient position detection device is presented in the form of a functional unit/functional module. The "unit/module" here can refer to an Application Specific Integrated Circuit (ASIC), a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and/or other functions that can provide the above-mentioned functions. Device. Exemplarily, at least part of the functions of at least one of the aforementioned units and modules may be implemented by a processor executing program codes stored in the memory.

Fig. 6 is a structural block diagram of a radiological medical equipment provided by an embodiment of the present disclosure. Referring to FIG. 6, the radiological medical equipment includes a processor 41 and a memory 42, wherein program instructions are stored in the memory 42, and the processor 41 is configured to call the program instructions in the memory 42 to execute any of the above-mentioned patients. Location detection method.

The processor 41 may include a central processing unit (CPU, single-core or multi-core), a graphics processing unit (GPU), a microprocessor, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), Digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, or multiple integrated circuits used to control program execution.

The memory 42 may include read-only memory (Read-Only Memory, ROM) or other types of static storage devices that can store static information and instructions, random access memory (Random Access Memory, RAM), or other types that can store information and instructions The dynamic storage device can also include electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disc storage, optical disc storage (Including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store desired program codes in the form of instructions or data structures and can be used by a computer Any other media accessed, but not limited to this. The memory can be set independently or integrated with the processor.

In a specific implementation, as an embodiment, the processor 41 may include one or more CPUs. In specific implementation, as an embodiment, the foregoing radiological medical equipment may include multiple processors. Each of these processors can be a single-CPU (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

The above-mentioned radiological medical equipment may include a general-purpose computer equipment or a special-purpose computer equipment. In a specific implementation, the radiological medical equipment may include any one of a radiation source, optical components (such as slits, beam expanders, collimators, lenses, etc.), computed tomography devices, X-ray imaging devices, and operating tables. There are many types of computer equipment, which can be desktop computers, portable computers, network servers, PDAs (Personal Digital Assistant, PDA), mobile phones, tablet computers, wireless terminal devices, communication devices, embedded devices, or devices with similar structures.

The embodiment of the present disclosure also provides a computer storage medium for storing a computer program used in any of the above-mentioned patient position detection methods, and the computer program includes program instructions. By executing the stored program, any of the above-mentioned patient position detection methods provided in the present disclosure can be realized.

Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a device (equipment), or a computer program product. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The computer program is stored/distributed in a suitable medium, provided with other hardware or as a part of the hardware, and may also be distributed in other forms, such as through the Internet or other wired or wireless telecommunication systems.

This application is described with reference to the flowcharts and/or block diagrams of the methods, devices (equipment) and computer program products of the embodiments of the present disclosure. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

The above are only the embodiments of the present disclosure and are not intended to limit the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the claims of the present disclosure. Within the scope of protection.

Claims

A method for detecting the position of a patient, applied to medical equipment, the medical equipment including a patient fixing mechanism, a first camera mechanism, and a second camera mechanism, the method includes:

When the patient is fixed on the patient fixing mechanism, at least one marker attached to the patient's body surface is captured by the first camera mechanism to obtain a first image, and the second camera mechanism is used to capture the first image. The at least one marker is taken to obtain a second image; wherein, the marker is a position indicator that is attached to the patient's body surface and can emit or reflect visible light, and the first image and the second image are both Visible light image

Obtaining the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image;

Based on the position of the at least one marker in space, the posture position data of the patient is obtained.
The method according to claim 1, wherein at least two markers of different colors are attached to the body surface of the patient, and in the first image and the second image based on the at least one marker Before obtaining the position of each of the markers in space, the method further includes:

Based on the color difference between the different markers in the first image and the second image, each of the markers is identified in the first image and the second image, respectively.
The method according to claim 1, wherein a reflective material is provided on the surface of each of the markers, and when the patient is fixed on the patient fixing mechanism, at least one The first image is obtained by shooting the marker, and the second image is obtained by shooting the at least one marker by the second camera mechanism, including:

When the patient is fixed on the patient fixing mechanism, the first image is captured by the first camera mechanism that provides light to the at least one marker, and the first image is obtained by providing light to the at least one marker. The second image is captured by the second camera mechanism;

Correspondingly, before the obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, the method further includes:

Based on the brightness difference between the at least one marker and the background in the first image and the second image, the at least one marker is identified in the first image and the second image, respectively.
The method according to claim 1, wherein each of the markers is a luminous body, and each of the markers is obtained based on the position of the at least one marker in the first image and the second image. Before the position of the marker in space, the method further includes:

Based on the brightness difference between the at least one marker and the background in the first image and the second image, the at least one marker is identified in the first image and the second image, respectively.
The method according to any one of claims 1 to 4, wherein based on the position of the at least one marker in the first image and the second image, the position of the at least one marker in space is obtained Location, including:

The spatial coordinate value of the marker in the second direction is obtained based on the planar coordinate value of any of the markers in the second direction in the first image, and the spatial coordinate value of the marker in the second direction is obtained based on any of the markers in the first image. The plane coordinate value in the first direction in the second image obtains the spatial coordinate value of the marker in the first direction, based on the plane coordinate value of any marker in the third direction in the first image and the At least one of the plane coordinate values in the third direction in the second image obtains the spatial coordinate value of the marker in the third direction;

Wherein, the first direction is the shooting direction of the first camera mechanism, the second direction is the shooting direction of the second camera mechanism, the first direction is perpendicular to the second direction, and the first direction is perpendicular to the second direction. The three directions are respectively perpendicular to the first direction and the second direction.
A patient position detection device is applied to radiological medical equipment. The radiological medical equipment includes a patient fixing mechanism, a first camera mechanism, and a second camera mechanism. The device includes:

The photographing module is used to photograph at least one marker attached to the patient's body surface through the first photographing mechanism to obtain a first image when the patient is fixed on the patient fixing mechanism. The second imaging mechanism takes the at least one marker to obtain a second image; wherein, the marker is a position indicator that is attached to the body surface of the patient and can emit or reflect visible light, and the first image and the The second images are all visible light images;

A first processing module, configured to obtain the position of the at least one marker in space based on the position of the at least one marker in the first image and the second image;

The second processing module is used to obtain the posture position data of the patient based on the position of the at least one marker in the space.
The device according to claim 6, wherein each of the markers is a luminous body, and the device further comprises a first identification module,

The first recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The brightness difference between the at least one marker and the background in the first image and the second image, and the at least one marker is identified in the first image and the second image, respectively.
The device according to claim 6, wherein a reflective material is provided on the surface of each of the markers, and the photographing module is further used for when the patient is fixed on the patient fixing mechanism, by pointing to the at least The first image is captured by the first camera mechanism that provides illumination for one marker, and the second image is obtained by the second camera mechanism that provides illumination for the at least one marker; correspondingly, the first image is captured by the second camera mechanism that provides illumination for the at least one marker; The device also includes a second identification module,

The second recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The brightness difference between the at least one marker and the background in the first image and the second image, and the at least one marker is identified in the first image and the second image, respectively.
The device according to claim 6, wherein at least two markers of different colors are attached to the body surface of the patient, and the device further comprises a third identification module,

The third recognition module is configured to, before obtaining the position of each marker in space based on the position of the at least one marker in the first image and the second image, based on the The color difference between the different markers in the first image and the second image, each of the markers is identified in the first image and the second image, respectively.
The device according to any one of claims 6 to 9, wherein the first processing module is further configured to:

The spatial coordinate value of the marker in the second direction is obtained based on the plane coordinate value of any of the markers in the second direction in the first image, and the spatial coordinate value of the marker in the second direction is obtained based on any of the markers in the first image. The plane coordinate value in the first direction in the second image obtains the spatial coordinate value of the marker in the first direction, based on the plane coordinate value of any marker in the third direction in the first image and the At least one of the plane coordinate values in the third direction in the second image obtains the spatial coordinate value of the marker in the third direction;

Wherein, the first direction is the shooting direction of the first camera mechanism, the second direction is the shooting direction of the second camera mechanism, the first direction is perpendicular to the second direction, and the first direction is perpendicular to the second direction. The three directions are respectively perpendicular to the first direction and the second direction.
A radiological medical equipment, wherein the radiological medical equipment comprises a processor and a memory, and program instructions are stored in the memory, and the processor is configured to call the program instructions in the memory to execute claims 1 to 5 Any of the methods described in.
A computer-readable storage medium, wherein the computer storage medium stores a computer program, the computer program includes program instructions, and the program instructions are configured to cause the processor to execute such as The method of any one of claims 1 to 5.