Image segmentation method and device, image guidance system, and radiotherapy system

Abstract

The present application provides an image segmentation method and device, an image guidance system, and a radiotherapy system, which belong to the field of radiotherapy technology. After acquiring a target image including a marker, the image guidance system can first perform image processing on the target image to obtain an alternative segmentation image with relatively large marker clarity, and then use an image segmentation algorithm to segment the alternative segmentation image to obtain a marker image. In this way, it can be ensured that the marker included in the target image can be reliably segmented, that is, the segmentation reliability of the image segmentation method is high.

Description

Technical Field

[0001] The present disclosure relates to the field of radiotherapy technology, and in particular to an image segmentation method and device, an image guidance system, and a radiotherapy system. Background Art

[0002] Image guided radiation therapy (IGRT) is a technique that determines the tumor offset by registering images. In order to improve the registration accuracy, a metal marker (referred to as a gold marker) can generally be set inside or on the patient's body so that the image to be registered can contain the gold marker, and accordingly, the image can be directly registered with reference to the position of the gold marker. When performing image registration based on the gold marker, it is generally necessary to segment the image to be registered to obtain a gold marker image that only includes the gold marker. This process can also be called image segmentation.

[0003] In the related art, an edge detection algorithm (such as the candy algorithm) is generally used to perform image segmentation on the image to be registered to obtain a gold label image. However, the segmentation reliability of this segmentation method is low. Summary of the invention

[0004] The embodiments of the present disclosure provide an image segmentation method and device, an image guidance system, and a radiotherapy system, which can solve the problem of low segmentation reliability of the segmentation method in the related art. The technical solution is as follows:

[0005] In one aspect, a method for image segmentation is provided, the method comprising:

[0006] acquiring a target image including the marker;

[0007] Performing image processing on the target image to obtain a candidate segmented image, wherein the clarity of the marker in the candidate segmented image is greater than the clarity of the marker in the target image;

[0008] An image segmentation algorithm is used to segment the candidate segmented image to obtain a marker image corresponding to the marker.

[0009] In another aspect, an image segmentation device is provided, the device comprising:

[0010] An acquisition module, used for acquiring a target image including a marker;

[0011] A processing module, configured to perform image processing on the target image to obtain a candidate segmented image, wherein the clarity of the marker in the candidate segmented image is greater than the clarity of the marker in the target image;

[0012] The segmentation module is used to segment the candidate segmentation image using an image segmentation algorithm to obtain a marker image corresponding to the marker.

[0013] On the other hand, an image guidance system is provided, comprising: a processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the image segmentation method as described in the above aspects.

[0014] On the other hand, a storage medium is provided, wherein instructions are stored in the storage medium, and when the storage medium is run on a processing component, the processing component executes the image segmentation method as described in the above aspects.

[0015] In another aspect, a radiotherapy system is provided, the radiotherapy system comprising: a patient support device, a host and an image guidance system; the image guidance system is the system as described in the above aspect, or the image guidance system comprises the device as described in the above aspect;

[0016] The host is connected to the image guidance system and the patient support device respectively, the image guidance system is used to determine the offset of the patient's tumor based on the segmented gold mark image, and send the offset of the tumor to the host, and the host is used to adjust the position of the patient support device based on the offset of the tumor.

[0017] The technical solution provided by the embodiments of the present disclosure has at least the following beneficial effects:

[0018] In summary, the embodiments of the present disclosure provide an image segmentation method and device, an image guidance system, and a radiotherapy system. After acquiring a target image including a marker, the image guidance system can first perform image processing on the target image to obtain an alternative segmentation image with relatively large marker clarity, and then use an image segmentation algorithm to segment the alternative segmentation image to obtain a marker image. In this way, it can be ensured that the marker included in the target image can be reliably segmented, that is, the segmentation reliability of the image segmentation method is high.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 is a structural schematic diagram of a radiotherapy system provided by an embodiment of the present disclosure;

[0022] Figure 2 It is a schematic diagram of setting a gold mark provided by an embodiment of the present disclosure;

[0023] Figure 3 is a flow chart of an image segmentation method provided by an embodiment of the present disclosure;

[0024] Figure 4 is a flow chart of another image segmentation method provided by an embodiment of the present disclosure;

[0025] Figure 5 is a schematic diagram of a processing process for image segmentation provided by an embodiment of the present disclosure;

[0026] Figure 6 is a flow chart of a method for obtaining an alternative segmented image provided by an embodiment of the present disclosure;

[0027] Figure 7 is a flow chart of another method for obtaining an alternative segmented image provided by an embodiment of the present disclosure;

[0028] Figure 8 is a schematic diagram of another processing process for image segmentation provided by an embodiment of the present disclosure;

[0029] Fig. 9 is a flow chart of another method for obtaining an alternative segmented image provided by an embodiment of the present disclosure;

[0030] Fig.10 is a structural block diagram of an image segmentation device provided by an embodiment of the present disclosure;

[0031] Fig.11 is a structural block diagram of another image segmentation device provided by an embodiment of the present disclosure;

[0032] Fig.12 is a structural block diagram of another image segmentation device provided by an embodiment of the present disclosure;

[0033] Fig.13 It is a structural schematic diagram of an image guidance system provided in an embodiment of the present disclosure.

[0034] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0035] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0036] Figure 1 Schematic diagram of a radiotherapy system provided by an embodiment of the present disclosure. Figure 1 As shown, the radiotherapy system may include a patient support device 01 , a host 02 , and an image guidance system 03 .

[0037] Optionally, the patient support device 01 may be Figure 1 The treatment bed shown in the figure can, of course, also be other devices for supporting patients, such as a treatment chair. The host 02 can be a control device. The image guidance system 03 can be an IGRT system. The host 02 can establish a communication connection with the patient support device 01 and the image guidance system 03, and the communication connection can be a wired connection or a wireless connection.

[0038] During the radiotherapy process, the image guidance system 03 can use IGRT technology to track the position of the target object (e.g., the patient's tumor) and send the target offset of the target object to the host 02. The host 02 can flexibly adjust the position of the patient support device 01 based on the received target offset to achieve image guidance for the patient. Optionally, the principle of the image guidance system 03 tracking the position of the target object is:

[0039] An image-guided device is used to obtain a projection image (a two-dimensional image) and register it with the reference image to obtain the offset of the target object. Registering two images can mean taking a designated image as a reference image and the other image as the image to be registered. The purpose of registration is to make the coordinates of all points on the image to be registered consistent with those on the reference image. Since the real-time projection image of the target object is generally an image acquired in real time during radiotherapy or positioning, that is, an image collected on site, the real-time projection image of the target object can be used as the image to be registered.

[0040] Optionally, the reference image can be: a digitally reconstructed radio (DRR) image reconstructed based on a computed tomography (CT) image of the target object collected when formulating a treatment plan. Or, a DRR image reconstructed based on a magnetic resonance (MR) image of the target object collected when formulating a treatment plan. Or, an image collected after the positioning is completed, such as a two-dimensional projection image directly collected after the positioning is completed or a DRR image reconstructed based on a cone beam computed tomography (CBCT) image collected after the positioning is completed. Because the image collected after the positioning is completed is no longer affected by the positioning error, the accuracy of using the image after the positioning is completed as the reference image to align with the real-time projection image is higher.

[0041] Optionally, in order to further improve the registration accuracy, a marker can be implanted in the patient's body, or a marker can be attached to the patient's body surface, so that the final registered reference image and the two-dimensional projection image can both include the marker. In this way, during registration, the two images can be registered based on the markers in the two images. The marker can be a metal marker made of metal material (abbreviated as gold marker).

[0042] For example, at least three non-collinear markers may be set. Figure 2 , a marker B1 may be set at the patient's two temples and nose tip respectively. If the target object is located in the body, at least three non-collinear markers may be set at the patient's spine.

[0043] By setting at least three non-collinear markers, the offset can be determined comprehensively by combining the position of each marker during registration. In this way, the image guidance system 03 can register images with reference to the positions of multiple markers at different angles, and accordingly, the registration accuracy can be further improved.

[0044] When two images are registered using a marker, since the image includes not only the gold marker but also other tissues (such as bone resistance), it is necessary to perform image segmentation on the two images to be registered in advance to obtain an image including only the marker. The following embodiment of the present disclosure describes an image segmentation method, which has good segmentation reliability.

[0045] Figure 3 is a flowchart of an image segmentation method provided by an embodiment of the present disclosure, which can be applied to Figure 1 In the image guided system 03 shown. Figure 3 As shown, the method may include:

[0046] Step 301: Acquire a target image including a marker.

[0047] Optionally, the marker can be placed on the patient's body surface or body before positioning or formulating a treatment plan. In this way, the image guidance system 03 can reliably obtain the target image including the marker. For example, the image guidance system 03 can use an image guidance device to obtain the target image.

[0048] Step 302: Perform image processing on the target image to obtain a candidate segmented image.

[0049] After acquiring the target image, the image guidance system 03 can further process the target image to obtain an alternative segmented image including a marker with greater clarity than the target image, that is, the clarity of the marker in the alternative segmented image is greater than the clarity of the marker in the target image.

[0050] Step 303: Use an image segmentation algorithm to segment the candidate segmentation image to obtain a marker image corresponding to the marker.

[0051] After obtaining the candidate segmented image, the image guidance system 03 may use an image segmentation algorithm to segment the candidate segmented image to obtain a marker image including only the markers.

[0052] In summary, the embodiment of the present disclosure provides an image segmentation method. After acquiring a target image including a marker, the image guidance system can first perform image processing on the target image to obtain an alternative segmentation image with relatively large marker clarity, and then use an image segmentation algorithm to segment the alternative segmentation image to obtain a marker image. In this way, it can be ensured that the marker included in the target image can be reliably segmented, that is, the image segmentation method has a high segmentation reliability.

[0053] Figure 4 is a flow chart of a marker segmentation method provided by an embodiment of the present disclosure, which can be applied to Figure 1 In the image guided system 03 shown. Figure 4 As shown, the method may include:

[0054] Step 401: Acquire a target image including a marker.

[0055] Optionally, as described in the above embodiment, the marker can be placed on the patient's body surface or body before positioning or formulating a treatment plan. In this way, the image guidance system can reliably obtain the target image including the marker. Moreover, since the marker image is clear, the reliability of image guidance can be improved.

[0056] Based on the setting time of the marker, it can be determined that the target image may include:

[0057] A two-dimensional projection image of a target object at a target shooting angle, wherein the two-dimensional projection image can be acquired by an image guidance system using an image guidance device during a positioning stage or a treatment stage. Accordingly, it can be determined that in order to acquire the two-dimensional projection image, the marker should be placed inside or on the surface of the patient before positioning.

[0058] Alternatively, the cone beam electronic scanning CBCT image of the target object can be obtained by the image guidance system using the image guidance device after the positioning is completed and before the treatment. Accordingly, it can be determined that in order to obtain the CBCT image, the marker should be set inside or on the surface of the patient before the positioning. And, for example, the image guidance device can be used to first obtain multiple reference two-dimensional projection images of the target object at different shooting angles, and then reconstruct and generate a CBCT image based on the multiple reference two-dimensional projection images.

[0059] Alternatively, a digitally reconstructed radiation DRR image of the target object at a target shooting angle is generated based on the CBCT image.

[0060] Alternatively, a CT image of the target object. Accordingly, it can be determined that in order to obtain the CT image, the marker should be placed inside or on the body of the patient before formulating a treatment plan.

[0061] Alternatively, a DRR image of the target object at a target shooting angle is generated based on the CT image.

[0062] Alternatively, it may be an MR image or a DRR image reconstructed based on the MR image at a target shooting angle. The target shooting angles described in the above embodiments may be shooting angles used by the image guidance device to obtain real-time projection images during treatment.

[0063] Step 402: pre-process the target image.

[0064] Optionally, in the embodiment of the present disclosure, after acquiring the target image, the image guidance system may pre-process the target image to obtain an image with better display effect.

[0065] For example, the preprocessing may be image smoothing processing. Accordingly, the noise interference of the processed target image is less. Of course, the preprocessing may also be other image processing for correcting the target image, which is not limited in the embodiments of the present disclosure.

[0066] Example, reference Figure 5 , which shows a target image 10 and an image 20 obtained by preprocessing the target image 10. Both images include markers, and the only difference is in the display effect.

[0067] Step 403: perform image processing on the preprocessed target image to obtain a candidate segmentation image.

[0068] Combination Figure 5 It can be seen that the display effect of the marker in the processed target image is still poor, that is, it is difficult to see the location of the marker clearly. Therefore, in order to ensure the subsequent segmentation accuracy, the image guidance system can first perform image processing on the target image to obtain an alternative segmented image. The purpose of the image processing is to improve the display clarity of the marker. That is, the clarity of the marker in the obtained alternative segmented image can be greater than the clarity of the marker in the target image.

[0069] As an optional implementation, refer to Figure 6 , step 403 may include:

[0070] Step 4031A: perform image blur processing on the target image.

[0071] Optionally, the image guidance system 03 may perform image blurring processing on the target image by using a blurring processing algorithm to blur out the marker in the target image and blend the marker into the background of the target image to obtain a new reference image, wherein the background may be an image other than the marker.

[0072] For example, continue to refer to Figure 5 , which also shows the blurred image 30. As can be seen from the figure, the clarity of the marker B1 in the blurred image 30 is much smaller than that in the target image 20 before the blurred image.

[0073] Step 4032A: perform image subtraction processing on the target image before image blur processing and the target image after image blur processing to obtain an alternative segmented image.

[0074] Optionally, after the target image is blurred, the image guidance system 03 can obtain an alternative segmented image by subtracting the target image 30 after blurring from the target image 20 before blurring based on an image subtraction method. Image subtraction can refer to: the pixel value of a point in the target image 20 before blurring minus the pixel value of the point in the target image 30 after blurring.

[0075] For example, continue to refer to Figure 5 , which also shows the candidate segmentation image 40 obtained by the final subtraction process. As can be seen from the figure, the marker B1 can be clearly displayed in the candidate segmentation image 40.

[0076] The above steps 4031A and 4032A may also be collectively referred to as: obtaining a candidate segmented image by performing a background removal operation on the target image.

[0077] Optionally, the image obtained by the image subtraction process can be multiplied by itself to obtain an alternative segmented image with a clearer marker display effect. The image multiplication can mean: the pixel value of each point in the image to be processed is multiplied by the pixel value of each point, and the two multiplied points are the same point.

[0078] By means of the self-multiplication process, the grayscale gradient between the pixel points at the position where the marker is located and the pixel points at other positions in the candidate segmentation image can be further enhanced, that is, the display of the marker can be further made clearer.

[0079] As an optional implementation method, taking the target image as a CT image or a CBCT image of the target object as an example, Figure 7 Another image processing method is shown, that is, step 403 may include:

[0080] Step 4031B: convert the target image into an image in the digital imaging and communications in medicine (DICOM) format.

[0081] Optionally, to facilitate subsequent image processing operations, the image guidance system may first convert the acquired target image into an image in DICOM format.

[0082] Step 4032B: convert the pixel value of each point in the target image into a CT value.

[0083] Then, the image guidance system can convert the pixel value of each point in the target image into a CT value, and the unit of the CT value can be (hounsfield, HU). The CT value can be used to measure the absorption rate of the received radiotherapy rays by human tissue.

[0084] Step 4033B: Obtain the CT values ​​of the markers and each target object in the target image.

[0085] After converting the pixel value of each point into a CT value, the image guidance system can further obtain the markers in the target image and the CT value of each target object.

[0086] Step 4034B: Based on the CT value and the preset reference threshold, the target image is normalized to obtain a candidate segmentation image.

[0087] The reference threshold may be a threshold for filtering the CT value, and the reference threshold may be pre-set in the image guidance system. After determining the CT value of the marker and each target object in the target image, the image guidance system may compare the magnitude relationship between the CT value of the marker and each target object and the reference threshold, and flexibly adjust the CT value of the marker and each target object based on the comparison result to complete the image normalization process and obtain the candidate segmented image.

[0088] For example, the image guidance system can set the CT value of the target object other than the marker in the target image whose CT value is less than the reference threshold as the first threshold, and does not change the CT value of the target object other than the marker in the target image whose CT value is greater than or equal to the reference threshold, to obtain an alternative segmented image. In addition, the image guidance system can also set the CT value of the marker in the target image to a second threshold different from the first threshold. In this way, the normalization processing of the target image is completed, and the alternative segmented image is obtained.

[0089] As another optional implementation, before step 403, the method may further include:

[0090] First, the image guidance system acquires a reference image, and the positions of the markers in the reference image and the markers in the target image can correspond one to one. For example, the image guidance system can first acquire the target shooting angle of the target image, and then acquire the reconstructed three-dimensional image, and the target DRR image of the three-dimensional image at the target shooting angle. The target DRR image is the reference image finally acquired.

[0091] Optionally, the image guidance system may filter the reconstructed three-dimensional image to obtain a three-dimensional image including only the markers, and determine the DRR image generated at the target shooting angle based on the three-dimensional image including only the markers as the target DRR image. The reconstructed three-dimensional image may be a CBCT image.

[0092] Then, the image-guided system constructs one or more reference regions of interest (ROIs) in the acquired reference image, each of which may include one or more markers, and the area of ​​each ROI is smaller than the area of ​​the reference image. Thus, constructing an ROI in a reference image can also be understood as intercepting a target area including a marker in the reference image.

[0093] Optionally, the image guidance system can determine the actual position of the marker in the reference image based on the position of the target point of the marker, and then the image guidance system can further construct (also called outline) a ROI including the marker in the two-dimensional projection image through an image processing algorithm.

[0094] Example, reference Figure 8 , which shows a reference image P1 including a marker B1, and a ROI constructed in the reference P1 including the marker B1.

[0095] Optionally, the target point may be any point on the marker. Of course, in order to improve the reliability of acquiring the marker, the target point may be the center point of the marker. Accordingly, the position of the target point may be the coordinates of the center point of the marker.

[0096] Correspondingly, such as Fig. 9 As shown, step 403 may include:

[0097] Step 4031C: Map one or more reference ROIs into the target image, and correspondingly obtain one or more reference target ROIs.

[0098] Recombination Figure 8 After constructing the ROI, the image-guided system can further map the ROI into the target image P2, thereby correspondingly obtaining one or more reference target ROIs, each of which includes a complete image of the marker.

[0099] Step 4032C: Use one or more reference target ROIs as candidate segmentation images.

[0100] Finally, the image-guided system may determine one or more reference target ROIs as candidate segmentation images including the landmarks.

[0101] Since the area of ​​the reference target ROI is relatively small relative to the area of ​​a complete image, the information included in the reference target ROI is also relatively small. Thus, when the candidate segmented image is subsequently processed, the algorithm cost adopted is low, the processing efficiency is also high, and since the reference target ROI includes the complete image of the marker, the processing reliability is also good.

[0102] Step 404: Use an image segmentation algorithm to segment the candidate segmentation image to obtain a marker image corresponding to the marker.

[0103] After obtaining the candidate segmented image, the image guidance system may use an image segmentation algorithm to perform segmentation processing on the candidate segmented image to obtain a marker image including only the marker.

[0104] Optionally, the image segmentation algorithm can be the Otsu threshold algorithm, which can also be called the maximum inter-class variance method or the Otsu algorithm. The principle of using the Otsu threshold algorithm to segment the candidate segmented image is: the candidate segmented image is binarized according to the threshold value obtained by the Otsu threshold algorithm so that the inter-class variance of the foreground and background of the candidate segmented image is maximized. Using this method to segment the image is not only simple to calculate, but also not easily affected by the brightness and contrast of the image, and the effect is better. Of course, the image segmentation algorithm can also be other segmentation algorithms, and the disclosed embodiment does not limit the segmentation algorithm used.

[0105] For example, Figure 5 and Figure 8 The final obtained marker image 00 is shown. After obtaining the marker image 00, the image guidance system can obtain the offset of the target object by comparing the position of the marker in the two images to be registered.

[0106] It should be noted that the order of the steps of the image segmentation method provided in the embodiment of the present disclosure can be appropriately adjusted. Any technician familiar with the technical field can easily think of a changed method within the technical scope disclosed in the present disclosure, and the method should be included in the protection scope of the present disclosure, so it will not be repeated here.

[0107] In summary, the embodiment of the present disclosure provides an image segmentation method. After acquiring a target image including a marker, the image guidance system can first perform image processing on the target image to obtain an alternative segmentation image with relatively large marker clarity, and then use an image segmentation algorithm to segment the alternative segmentation image to obtain a marker image. In this way, it can be ensured that the marker included in the target image can be reliably segmented, that is, the image segmentation method has a high segmentation reliability.

[0108] Fig.10 is a structural block diagram of an image segmentation device provided by an embodiment of the present disclosure, which can be applied to Figure 1 In the image guided system 03 shown. Fig.10 As shown, the device may include:

[0109] The acquisition module 501 is used to acquire a target image including a marker.

[0110] The processing module 502 is used to perform image processing on the target image to obtain a candidate segmented image.

[0111] The clarity of the marker in the candidate segmented image is greater than the clarity of the marker in the target image.

[0112] The segmentation module 503 is used to segment the candidate segmentation image using an image segmentation algorithm to obtain a marker image corresponding to the marker.

[0113] As an optional implementation, the processing module 502 can be used to: perform a background removal operation on the target image to obtain an alternative segmented image. The background is an image other than the marker. For example, the processing module 502 can be used to perform image blurring on the target image, and perform image subtraction on the target image before and after the image blurring to obtain an alternative segmented image.

[0114] Optionally, in the disclosed embodiment, the target image may include: a two-dimensional projection image of the target object at the target shooting angle. Or, a cone beam electronic scanning CBCT image of the target object. Or, a digitally reconstructed radiation DRR image of the target object at the target shooting angle generated based on the CBCT image. Or, an electronic scanning CT image of the target object. Or, a DRR image of the target object at the target shooting angle generated based on the CT image.

[0115] As another optional implementation: the processing module 502 can be used to filter the target image to obtain an image that only includes the markers and use it as an alternative segmented image.

[0116] Optionally, if the target image is a CT image or a CBCT image of the target object, the processing module 502 can be used to: obtain the CT values ​​of the markers and each target object in the target image, and perform image normalization processing on the target image based on the CT value and a preset reference threshold to obtain an alternative segmented image.

[0117] Optional, such as Fig.11 As shown, the apparatus may further include: a first conversion module 504, configured to convert the target image into an image in a medical digital imaging and communication DICOM format before acquiring the CT values ​​of the markers and each target object in the target image.

[0118] Optionally, the processing module 502 may be used to: based on the CT value and a preset reference threshold, set the CT value of the target object other than the marker in the target image whose CT value is less than the reference threshold as a first threshold to obtain an alternative image.

[0119] Optional, combined Fig.11 The device may also include: a setting module 505, used to set the CT value of the marker in the target image as a second threshold.

[0120] Optional, combined Fig.11 The device may further include: a second conversion module 506, configured to convert the pixel value of each point in the target image into a CT value before acquiring the CT value of the marker and each target object in the target image.

[0121] Optional, Fig.12It is a structural block diagram of another image segmentation device provided in an embodiment of the present disclosure.

[0122] like Fig.12 As shown, the device may also include:

[0123] The image acquisition module 507 may be used to acquire a reference image.

[0124] The positions of the markers in the reference image correspond one-to-one to the positions of the markers in the target image.

[0125] The construction module 508 may be used to construct one or more reference regions of interest (ROIs) in the reference image, wherein the reference ROIs include one or more markers.

[0126] Accordingly, as another optional implementation manner, the processing module 502 may be configured to map one or more reference ROIs into the target image, obtain one or more reference target ROIs accordingly, and use the one or more reference target ROIs as candidate segmentation images.

[0127] Optionally, the image acquisition module 507 may be used to:

[0128] Get the target shooting angle of the target image.

[0129] Obtain a reconstructed three-dimensional image.

[0130] Obtain a target DRR image of the reconstructed three-dimensional image at a target shooting angle, and use the target DRR image as a reference image. For example, the image acquisition module 507 can be used to filter the reconstructed three-dimensional image to obtain a three-dimensional image that only includes the marker, and obtain a target DRR image of the three-dimensional image that only includes the marker at a target shooting angle.

[0131] Optionally, the reconstructed three-dimensional image may be a CBCT image.

[0132] Optionally, the processing module 502 may be used to: pre-process the target image, and perform image processing on the pre-processed target image to obtain a candidate segmented image. The pre-processing may include: image smoothing processing.

[0133] Optionally, the image segmentation algorithm may be an Otsu threshold algorithm.

[0134] In summary, the embodiment of the present disclosure provides an image segmentation device. After acquiring a target image including a marker, the device can first perform image processing on the target image to obtain a candidate segmentation image with relatively large marker clarity, and then use an image segmentation algorithm to segment the candidate segmentation image to obtain a marker image. In this way, it can be ensured that the marker included in the target image can be reliably segmented, that is, the segmentation reliability of the image segmentation device is high.

[0135] Regarding the image segmentation device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0136] Optional, reference Fig.13 , in the disclosed embodiment, Figure 1 The image guidance system 03 shown may include: a processor 031 and a memory 032. The memory 032 may store instructions, which are loaded and executed by the processor 031 to achieve the following: Figure 3 or Figure 4 The image segmentation method shown.

[0137] Optionally, the embodiment of the present disclosure further provides a storage medium, in which instructions may be stored. When the storage medium is run on the processing component, the processing component may be caused to execute the following Figure 3 or Figure 4 The image segmentation method shown.

[0138] The above description is only an optional embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An image segmentation method, characterized in that: The method comprises: acquiring a target image including the marker; Performing image processing on the target image to obtain a candidate segmented image, wherein the clarity of the marker in the candidate segmented image is greater than the clarity of the marker in the target image; Using an image segmentation algorithm to segment the candidate segmented image to obtain a marker image corresponding to the marker; Wherein, the method further comprises: Acquire a target shooting angle of the target image; obtaining a reconstructed three-dimensional image; Acquire a target DRR image of the reconstructed three-dimensional image at the target shooting angle, use the target DRR image as a reference image, and position of the markers in the reference image corresponds one-to-one to the positions of the markers in the target image; Constructing one or more reference regions of interest ROIs in the reference image, each of the reference regions of interest ROIs comprising one or more markers; Accordingly, performing image processing on the target image to obtain a candidate segmented image includes: Mapping the one or more reference regions of interest ROIs into the target image to obtain one or more reference target ROIs accordingly; The one or more reference target ROIs are used as candidate segmentation images.

2. The method according to claim 1, characterized in that The target image includes: A two-dimensional projection image of the target object at the target shooting angle; or, a cone beam electronic scanning CBCT image of the target object; Alternatively, a digitally reconstructed radiation DRR image of the target object at the target shooting angle generated based on the CBCT image; Or, an electronically scanned CT image of the target object; Alternatively, a DRR image of the target object at the target shooting angle is generated based on a CT image.

3. The method according to claim 1, characterized in that The step of acquiring a target DRR image of the reconstructed three-dimensional image at the target shooting angle includes: filtering the reconstructed three-dimensional image to obtain a three-dimensional image that only includes the marker; A target DRR image of the three-dimensional image including only the marker is acquired at the target shooting angle.

4. The method according to claim 1, characterized in that: The reconstructed three-dimensional image is a CBCT image.

5. The method according to claim 1, characterized in that The step of performing image processing on the target image to obtain a candidate segmented image includes: Preprocessing the target image, wherein the preprocessing includes: image smoothing; Perform image processing on the preprocessed target image to obtain an alternative segmentation image.

6. The method according to claim 1, characterized in that The image segmentation algorithm is the Otsu threshold algorithm.

7. An image segmentation device, characterized in that: The device comprises: An acquisition module, used for acquiring a target image including a marker; An image acquisition module is used to acquire a target shooting angle of the target image; acquire a reconstructed three-dimensional image, acquire a target DRR image of the reconstructed three-dimensional image at the target shooting angle, and use the target DRR image as a reference image, wherein the markers in the reference image correspond one-to-one to the marker positions in the target image; A construction module, configured to construct one or more reference regions of interest ROIs in the reference image, each of the reference regions of interest ROIs comprising one or more markers; A processing module, configured to map the one or more reference regions of interest ROIs into the target image, and correspondingly obtain one or more reference target ROIs, and use the one or more reference target ROIs as candidate segmentation images, wherein the clarity of the marker in the candidate segmentation image is greater than the clarity of the marker in the target image; The segmentation module is used to segment the candidate segmentation image using an image segmentation algorithm to obtain a marker image corresponding to the marker.

8. An image guidance system, characterized in that: The image guidance system comprises: a processor and a memory, wherein instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the image segmentation method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores instructions, and when the storage medium is run on the processing component, the processing component executes the image segmentation method according to any one of claims 1 to 6.

10. A radiotherapy system, characterized in that: The radiotherapy system comprises: a patient support device, a host and an image guidance system; the image guidance system is the system according to claim 8, or the image guidance system comprises the device according to claim 7; The host is connected to the image guidance system and the patient support device respectively, the image guidance system is used to determine the target offset of the target object based on the segmented marker image, and send the target offset to the host, and the host is used to adjust the position of the patient support device based on the target offset.

Images