Tumor localization method, electronic device, and storage medium

Abstract

The present disclosure provides a tumor positioning method, an electronic device and a storage medium, relates to the technical field of medical treatment, in particular to the technical field of radiotherapy, and is used to solve the problems of low efficiency and accuracy of tumor positioning in the prior art. The method comprises the following steps: acquiring a planning image and a real-time image of a reference object which is associated with a motion trajectory of a tumor to be positioned; determining boundary mask information of the reference object according to the planning image; determining deformation information of the reference object according to the planning image and the real-time image; determining the motion trajectory of the reference object according to the boundary mask information and the deformation information; and positioning and tracking the tumor to be positioned according to the motion trajectory of the reference object.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of medical treatment, in particular to the technical field of radiotherapy, and specifically to a tumor positioning method, an electronic device and a storage medium. BACKGROUND

[0002] At present, one of the key technologies of radiotherapy is to keep accurate positioning of the tumor during treatment. In particular, tumors that move with the breath, such as lung tumors, liver tumors and pancreatic tumors, are very difficult to accurately position at each moment due to the extremely low contrast of the tumor in the projection image and the interference of the surrounding tissue.

[0003] In the process of tumor positioning, some other human tissues (which can be referred to as surrogates, reference objects, surrogates, etc.) in the projection image, such as diaphragm and chest wall, usually have good contrast and clarity. And its motion trajectory has high correlation with the tumor, so these surrogates can be used for tumor positioning and tracking.

[0004] The general surrogate tracking method is usually based on the gradient information of the collected image, and uses polynomial fitting of the boundary of the surrogate to determine the motion trajectory of the surrogate, and then performs tumor positioning and tracking. However, the polynomial fitting of the boundary of the surrogate needs to manually initialize the polynomial coefficients, and when performing tumor positioning and tracking, the motion trajectory prior model of the surrogate needs to be trained, which is cumbersome and has poor stability, thereby resulting in low efficiency and accuracy of tumor positioning. SUMMARY

[0005] The present disclosure provides a tumor positioning method, an electronic device and a storage medium, which can improve the efficiency and accuracy of tumor positioning.

[0006] In a first aspect, the present disclosure provides a tumor positioning method, comprising: acquiring a planning image and a real-time image of a reference object having correlation with a motion trajectory of a tumor to be positioned; determining boundary mask information of the reference object according to the planning image; determining deformation information of the reference object according to the planning image and the real-time image; determining the motion trajectory of the reference object according to the boundary mask information and the deformation information; and performing positioning and tracking on the tumor to be positioned according to the motion trajectory of the reference object.

[0007] In some embodiments, determining the boundary mask information of the reference object according to the planning image comprises: determining a three-dimensional mask of the reference object according to the planning image; converting the three-dimensional mask into a two-dimensional mask, and performing morphological reconstruction on the two-dimensional mask to obtain the boundary mask information.

[0008] In some embodiments, the planning image comprises a plurality of planning sub-images of the reference object acquired continuously along a preset anatomical direction; the three-dimensional mask of the reference object is determined according to the planning image, comprising: for each planning sub-image, determining a reference region to which the reference object belongs according to the planning sub-image; performing polynomial fitting on gradient information of the reference region in the planning sub-image to obtain boundary information of the reference object in the planning sub-image; and combining the boundary information of the reference object corresponding to each planning sub-image to obtain the three-dimensional mask of the reference object.

[0009] In some embodiments, the morphological reconstruction is performed on the two-dimensional mask to obtain the boundary mask information, comprising: performing erosion processing and smoothing processing on the two-dimensional mask in sequence to obtain a processed two-dimensional mask; determining the boundary mask of the reference object in a first direction according to gradient information of the processed two-dimensional mask; and performing inflation processing on a second direction of the reference object based on the boundary mask of the reference object in the first direction and a structural element to obtain the boundary mask information.

[0010] In some embodiments, the boundary mask information comprises a plurality of sub-masks of the reference object; the motion trajectory of the reference object is determined according to the boundary mask information and the deformation information, comprising: for each sub-mask, determining a deformation amount of the sub-mask according to the sub-mask and the deformation information corresponding to the sub-mask; and determining the motion trajectory of the reference object according to the deformation amount of each sub-mask.

[0011] In some embodiments, the positioning and tracking of the tumor to be positioned is performed according to the motion trajectory of the reference object, comprising: obtaining a motion trajectory mapping model; the motion trajectory mapping model is used to represent a mapping relationship between the motion trajectory of the reference object and a motion trajectory of the tumor to be positioned; and the positioning and tracking of the tumor to be positioned is performed according to the motion trajectory of the reference object and the motion trajectory mapping model.

[0012] In some embodiments, the motion trajectory of the reference object comprises an actual motion amount of the reference object at each motion point; the positioning and tracking of the tumor to be positioned is performed according to the motion trajectory of the reference object, comprising: obtaining a normal motion amount of the reference object; and the positioning and tracking of the tumor to be positioned is performed according to the actual motion amount of the reference object at each motion point and the normal motion amount.

[0013] In some embodiments, the reference object comprises at least one of the following: diaphragm, lung wall, and lung apex.

[0014] In a second aspect, the disclosure also provides an electronic device, comprising: a processor and a memory configured to store processor-executable instructions; wherein the processor is configured to execute the instructions to implement any of the optional tumor positioning methods in the first aspect.

[0015] Thirdly, this disclosure also provides a non-volatile storage medium storing a computer program, which, when read and executed, implements any of the optional tumor localization methods in the first aspect described above.

[0016] The tumor localization method disclosed herein can determine the boundary mask information of a reference object based on a planned image, and determine the deformation information of the reference object based on both the planned and real-time images. Then, the motion trajectory of the reference object can be determined based on the boundary mask information and the deformation information, facilitating subsequent localization and tracking of the tumor to be located based on the motion trajectory of the reference object. Thus, this application eliminates the need for manual initialization of polynomial coefficients and training of prior models, improving the efficiency and accuracy of tumor localization. Attached Figure Description

[0017] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0018] Figure 1 This is a schematic diagram of a tumor localization system provided in an embodiment of the present disclosure;

[0019] Figure 2 A schematic flowchart of a tumor localization method provided in an embodiment of this disclosure;

[0020] Figure 3 A flowchart illustrating yet another tumor localization method provided in this disclosure embodiment;

[0021] Figure 4 A schematic diagram of a scenario for a tumor localization method provided in an embodiment of this disclosure;

[0022] Figure 5 A schematic flowchart illustrating yet another tumor localization method provided in this disclosure embodiment;

[0023] Figure 6 A schematic flowchart illustrating yet another tumor localization method provided in this disclosure embodiment;

[0024] Figure 7 A schematic flowchart illustrating yet another tumor localization method provided in this disclosure embodiment;

[0025] Figure 8 A schematic flowchart illustrating yet another tumor localization method provided in this disclosure embodiment;

[0026] Figure 9 This is a schematic diagram of the structure of a tumor localization device provided in an embodiment of the present disclosure;

[0027] Figure 10 This is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0028] The technical solutions in the embodiments of the present disclosure will be clearly and completely described in combination with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present disclosure.

[0029] In the description of the present disclosure, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present disclosure and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present disclosure. In addition, the terms "first", "second", "third" are only for description purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second", "third" can be explicitly or implicitly included one or more of the features. In the description of the present disclosure, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0030] In the description of the present disclosure, the word "exemplary" is used to mean "serving as an example, instance, or illustration." Any embodiment described as "exemplary" in the present disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the present disclosure. In the following description, for the purpose of explanation, details are set forth. It is apparent to those skilled in the art that the present disclosure can be practiced without using these specific details. In other instances, well-known structures and processes are not described in detail in order to avoid obscuring the description of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed.

[0031] It should be noted that the method of the embodiments of the present disclosure is executed in the tumor positioning device, and the processing object of each tumor positioning device exists in the form of data or information, such as time, which is actually time information. It can be understood that if the size, quantity, position, etc. are mentioned in subsequent embodiments, they all exist in corresponding data for the tumor positioning device to process, and specific details are not described here.

[0032] As described in the background, in the process of tumor localization, some other human tissues (which can be referred to as surrogates, reference objects, surrogates, etc.) in the projection image, such as diaphragm, chest wall, etc., usually have good contrast and clarity. And its motion trajectory and tumor motion have high correlation, so these surrogates can be used for tumor localization tracking.

[0033] The general surrogate tracking method is usually based on the gradient information of the collected image, and uses polynomial fitting of the boundary of the surrogate to determine the motion trajectory of the surrogate, and then performs tumor localization tracking. However, the polynomial fitting of the boundary of the surrogate needs to manually initialize the polynomial coefficients, and when performing tumor localization tracking, the motion trajectory prior model of the surrogate needs to be trained, the process is cumbersome, the stability is poor, and then the efficiency and accuracy of tumor localization are low.

[0034] Based on the above technical problems, the tumor localization method provided by the embodiments of the present disclosure can determine the boundary mask information of the reference object according to the planning image, and determine the deformation information of the reference object according to the planning image and the real-time image. Then, the motion trajectory of the reference object can be determined according to the boundary mask information and the deformation information, so as to facilitate subsequent localization tracking of the tumor to be located according to the motion trajectory of the reference object. In this way, the present application does not need to initialize the polynomial coefficients by manual intervention, and does not need to train the prior model, thereby improving the efficiency and accuracy of tumor localization.

[0035] The tumor localization method described above can be applied to a tumor localization system. Figure 1 A scene schematic diagram of a tumor localization system provided by the embodiments of the present disclosure can include an image acquisition device 101, a tumor localization device 102 and a storage server 103.

[0036] The image acquisition device 101 is a device for acquiring the tumor site and the surrounding normal tissue of a target object (such as a patient to be treated, an experimental object, a phantom, etc.). In some embodiments, the image acquisition device 101 can be a cone-beam computed tomography (CBCT) device.

[0037] Referring to Figure 1 , the image acquisition device 101 can include a gantry 1011, a ball tube 1012, a detector 1013, and a support device 1014. The gantry 1011 can be a rotatable gantry. The ball tube 1012 can be an imaging ray emitter, such as a kilovolt (KV) X-ray. The detector 1013 can be a detection plate opposite the ball tube 1012, such as an X-ray detection plate. The support device 1014 is used to support and move the target object, and can be a treatment bed.

[0038] In some embodiments, the rotation of the gantry 1011 can drive the tube 1012 to perform 360-degree projection around the target object while the target object is on the support device 1014. After the imaging rays pass through the target object, the projection data of the projection performed by the tube 1012 can be projected onto the detector 1013, and the detector 1013 can acquire the projection data. Then, the medical image (e.g., a CBCT image) of the target object can be obtained by data reconstruction based on the acquired projection data of multiple projections.

[0039] In the embodiments of the present disclosure, the image acquisition device 101 is configured to acquire a real-time image of a reference object in a target object. Then, the real-time image can be uploaded to the tumor positioning device 102, so that the tumor positioning device 102 performs a subsequent tumor positioning method based on the real-time image.

[0040] The tumor positioning device 102 is configured to determine a motion trajectory of the reference object in the target object based on the real-time image acquired by the image acquisition device 101 and the planning image obtained from the storage server 103, and to track and position a tumor to be positioned in the target object according to the motion trajectory of the reference object.

[0041] In some embodiments, the tumor positioning device 102 can be a computer device with a graphical user interface (GUI), which includes one or more processors, a memory, and one or more application programs. For example, the tumor positioning device 102 can include a tumor positioning system application program, and the processor of the tumor positioning device executes the tumor positioning system application program to implement the tumor positioning method provided in the embodiments of the present disclosure.

[0042] In the embodiments of the present disclosure, the entity of the tumor positioning device 102 can be a terminal or a server with a display, and the embodiments of the present disclosure do not limit the entity.

[0043] Optionally, the terminal can be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer.

[0044] Optionally, the server can be an image server. The image server is configured to provide background service for the image acquisition device 101. In some embodiments, the image server can be a standalone physical server, or a server cluster or distributed file system composed of multiple physical servers, or at least one of cloud servers providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content distribution network, and big data or artificial intelligence platform, etc. The number of image servers can be more or less in some embodiments, which is not limited in the embodiments of the present disclosure. Of course, the image server can also include other functions to provide more comprehensive and diversified services.

[0045] Further, in some embodiments, the tumor positioning device 102 can run a computer system including a processor configured to implement the tumor positioning method provided by the embodiments of the present application.

[0046] Optionally, the tumor positioning device 102 can also be connected with a radiotherapy device, so that the radiotherapy device can adjust the position of the target object on the radiotherapy device according to the motion trajectory of the reference object displayed by the tumor positioning device 102.

[0047] In some embodiments, the implementation environment of the tumor positioning method can also include a gamma knife treatment head, an accelerator treatment head or other radiotherapy heads, which can be arranged on a gantry to emit treatment rays such as gamma rays and MV level X rays. Thus, the implementation environment constitutes a radiotherapy system, and accordingly, the tumor positioning device 102 is also configured to perform image registration based on the real-time images acquired by the image acquisition device 101, and then perform pre-treatment positioning adjustment or real-time image guidance during treatment based on the image registration result.

[0048] The storage server 103 is configured to store medical data of the target object, such as case type of the target object, radiotherapy plan (including planned image of the reference object in the target object), radiotherapy dose, etc. In the embodiments of the present disclosure, the storage server 103 can also be configured to store the real-time images acquired by the image acquisition device 101, the motion trajectory of the reference object generated by the image server 102, etc. The storage server 103 can send the planned image of the reference object in the target object to the tumor positioning device 102 when the tumor positioning device 102 performs the tumor positioning method provided by the embodiments of the present application, so that the tumor positioning device 102 performs subsequent tumor positioning method based on the planned image.

[0049] The following is based on the tumor positioning method provided by the embodiments of the present application. Figure 1The tumor positioning system shown in the figure introduces the tumor positioning method provided by the embodiments of the present disclosure.

[0050] The tumor positioning method provided by the embodiments of the present disclosure is applied to the tumor positioning device 102 in the system shown in the figure. Figure 1 Figure 2 The figure shows a flowchart of a tumor positioning method provided by the embodiments of the present disclosure. As shown in the figure, the tumor positioning method includes S201-S205. Figure 2

[0051] S201, the tumor positioning device acquires a planning image and a real-time image of a reference object having correlation with the motion trajectory of the tumor to be positioned.

[0052] As described in the background, if the tumor positioning is performed only according to the real-time image of the reference object, the efficiency and accuracy are low. In the embodiments of the present disclosure, the tumor positioning device can not only acquire the real-time image of the reference object, but also acquire the planning image of the reference object. In this way, by comparing the planning image and the real-time image, the motion trajectory of the reference object can be quickly and accurately determined, and then the tumor positioning can be quickly and accurately performed.

[0053] Optionally, the planning image can be a CT image. Compared with a two-dimensional KV projection image, the CT image is a three-dimensional image, which can be more beneficial to the segmentation of the reference object (such as diaphragm and other tissues).

[0054] In some embodiments, the reference object includes at least one of the following: diaphragm, lung wall, lung apex. The motion trajectory of the reference object and the motion trajectory of the tumor to be positioned are usually strongly correlated, that is, having correlation. In this way, by determining the motion trajectory of the reference object having correlation with the motion trajectory of the tumor to be positioned, the positioning and tracking of the tumor to be positioned can be realized.

[0055] S202, the tumor positioning device determines the boundary mask information of the reference object according to the planning image.

[0056] Specifically, when the reference object moves, usually the boundary of the reference object moves, that is, the motion trajectory of the reference object is usually strongly correlated with the boundary of the reference object. For example, when the reference object is the diaphragm, the diaphragm will move with the breathing of the human body. When the person inhales, the diaphragm contracts, and the top of the diaphragm (i.e. the upper boundary of the diaphragm) descends; when the person exhales, the diaphragm relaxes, and the top of the diaphragm rises. Therefore, after acquiring the planning image, the tumor positioning device can determine the boundary mask information of the reference object according to the planning image, so as to facilitate the subsequent determination of the motion trajectory of the reference object.

[0057] S203, the tumor positioning device determines the deformation information of the reference object according to the planning image and the real-time image.

[0058] ​​Specifically, the reference object can deform during the treatment of the human body. When the reference object deforms, its shape also changes accordingly. Therefore, by monitoring the position change and distance change of the reference object, the deformation of the reference object can be determined. Therefore, after the planning image and the real-time image are acquired, the tumor positioning device can determine the deformation information of the reference object according to the planning image and the real-time image, so as to accurately determine the motion trajectory of the reference object subsequently.

[0059] In some embodiments, the tumor positioning device can compare the planning image and the real-time image to determine the deformation information of the reference object.

[0060] For example, assuming that the planning image is a CT image and the real-time image is a KV image, since the CT image is usually used to reconstruct a three-dimensional image, the tumor positioning device can acquire a Digitally Reconstructed Radiograph (DRR) projection of the CT image.

[0061] Since the KV image is usually based on a sequence of images at multiple angles, for each angle KV image, the tumor positioning device can acquire the KV image and the DRR projection at the angle, and determine a two-dimensional deformation field of the KV image and the DRR projection at the angle, and then obtain a deformation field image corresponding to the two-dimensional deformation field. The deformation information of the reference object can be obtained through the deformation field image.

[0062] S204, the tumor positioning device determines the motion trajectory of the reference object according to the boundary mask information and the deformation information.

[0063] Specifically, since the boundary mask information can clearly outline the contour of the reference object, the positions of a plurality of key feature points on the boundary of the reference object can be determined through the boundary mask information of the reference object. These feature points can be vertices on the boundary of the reference object, points with large curvature change, etc.

[0064] When the reference object deforms, the shape of the boundary mask also changes accordingly. Therefore, by monitoring the relative position change and distance change between each feature point on the boundary mask, the local deformation of the reference object can be inferred.

[0065] With the passage of time, the above position updating process is repeatedly performed. The tumor positioning device can record the position of the reference object at each time (determined by the boundary mask and the deformation information) to form a position sequence. This position sequence can be used to construct the motion trajectory of the reference object.

[0066] Optionally, the tumor positioning device can use curve fitting or other methods, such as polynomial fitting, spline fitting, etc., to connect these discrete position points into a continuous trajectory curve, thereby clearly showing the motion trajectory of the reference object.

[0067] Optionally, the tumor positioning device can also collect other auxiliary information of the reference object, such as the texture features inside the reference object, the relative position relationship with the surrounding tissues, etc. For example, the change direction of the internal texture of the reference object can assist the tumor positioning device in judging the motion direction of the reference object, the relative displacement of the reference object and the surrounding fixed tissues, etc., thereby further correcting the motion trajectory and improving the accuracy of the motion trajectory determination.

[0068] S205, the tumor positioning device determines the motion trajectory of the reference object.

[0069] Specifically, when determining the motion trajectory of the reference object, the tumor positioning device can first establish the relative position relationship between the reference object and the tumor to be positioned. For example, the tumor positioning device can determine the relative position of the reference object and the tumor to be positioned through medical imaging (such as CT, MRI, etc.). The tumor positioning device can achieve the determination of the relative position by marking the center coordinates, boundary range, etc. of the reference object and the tumor to be positioned on the image.

[0070] Then, the tumor positioning device can determine the fixed geometric relationship between the reference object and the tumor to be positioned. For example, the reference object and the tumor to be positioned are connected, contained, or have a certain angle and distance interval.

[0071] After determining the motion trajectory of the reference object, the tumor positioning device can convert the motion trajectory of the reference object into the potential motion trajectory of the tumor to be positioned according to the previously established relative position relationship.

[0072] Optionally, the tumor positioning device can also use coordinate transformation and geometric translation, rotation, etc. to achieve the conversion of the motion trajectory of the reference object and the potential motion trajectory of the tumor to be positioned. For example, if the motion trajectory of the reference object is represented by a series of coordinate points in the Cartesian coordinate system "(X, Y, Z)", and the position offset of the tumor to be positioned relative to the reference object is "(△a, △b, △c)", then the motion trajectory point of the tumor to be positioned can be represented as (X+△a, Y+△b, Z+△c).

[0073] In some embodiments, since the physiological motion of the human body (such as breathing, heartbeat, etc.) will have a periodic effect on the position of the tumor to be positioned and the reference object, the tumor positioning device can also analyze the law of these physiological motions, separate or integrate them with the motion trajectory of the reference object, thereby accurately determining the motion trajectory of the reference object.

[0074] For example, assuming that the motion trajectory of the reference object contains displacement caused by respiratory motion, and the motion of the tumor to be positioned has a certain correlation (such as synchronous movement) with the respiratory motion, the tumor positioning device can determine the position of the tumor to be positioned according to different stages of the respiratory cycle by analyzing the respiratory signal (such as obtained by a respiratory belt), thereby improving the accuracy of positioning and tracking.

[0075] In some embodiments, in combination with Figure 2 As shown in FIG. 2, the method for determining the boundary mask information of the reference object according to the planning image by the tumor positioning device specifically includes: Figure 3 S301, the tumor positioning device determines the three-dimensional mask of the reference object according to the planning image.

[0076] Specifically, in order to accurately determine the boundary of the reference object and then determine the motion trajectory of the reference object, the tumor positioning device can first determine the three-dimensional mask of the reference object according to the planning image.

[0077] In some embodiments, the planning image can include a plurality of planning sub-images of the reference object continuously acquired along a preset anatomical direction. In this case, the method for determining the three-dimensional mask of the reference object according to the planning image by the tumor positioning device specifically includes: for each planning sub-image, the tumor positioning device can determine the reference region to which the reference object belongs according to the planning sub-image, and perform polynomial fitting on the gradient information of the reference region in the planning sub-image to obtain the boundary information of the reference object in the planning sub-image. Subsequently, the tumor positioning device can combine the boundary information of the reference object corresponding to each planning sub-image to obtain the three-dimensional mask of the reference object.

[0078] For example, as shown in FIG. 4, taking the planning image as a CT image and the reference object as the diaphragm as an example, the preset anatomical direction can be the direction of the coronal plane. In this case, the planning image can include a plurality of coronal plane images (i.e., a plurality of planning sub-images). For each coronal plane image, the tumor positioning device can obtain the reference region to which the diaphragm belongs in each coronal plane image, i.e., the lung cavity 401.

[0079] Figure 4 Optionally, the tumor positioning device can directly load the human lung profile according to the coronal plane image to obtain the lung cavity 401.

[0080] Optionally, the tumor positioning device can directly load the human lung profile according to the coronal plane image to obtain the lung cavity 401.

[0081] ​Optionally, the tumor positioning device can also load the outer contour mask of the human body mask1 according to the coronal image. Then the tumor positioning device can determine the region smaller than the air threshold (such as -800 HU (Hounsfield Unit)) in the coronal image as the air mask mask2. Subsequently, the tumor positioning device can determine the intersection of mask1 & mask2 as the lung cavity 401.

[0082] After obtaining the reference region of the diaphragm, i.e. the lung cavity 401, the tumor positioning device can determine the bottom of the lung cavity as the initial range of the cranial-caudal direction of the diaphragm, i.e. Figure 4 The initial range of the diaphragm 402 is shown.

[0083] Then, in the initial range of the diaphragm 402, the tumor positioning device can determine the gradient information in the cranial-caudal direction, i.e. subtract the adjacent pixels in the cranial-caudal direction in the initial range of the diaphragm 402 (the upper pixel value minus the lower pixel value in the cranial-caudal direction). If the result of the upper pixel value minus the lower pixel value is positive, i.e. the gradient value is positive. This means that the pixel value is decreasing in the cranial-caudal direction, and the upper pixel is brighter than the lower pixel (assuming it is a grayscale image, the larger the pixel value, the brighter it is). On the contrary, if the result of the upper pixel value minus the lower pixel value is negative, i.e. the gradient value is negative. This indicates that the pixel value is increasing in the cranial-caudal direction, and the upper pixel is darker than the lower pixel.

[0084] After obtaining the gradient information, the tumor positioning device can determine the mask with a gradient value greater than a preset threshold as the boundary mask of the diaphragm, and perform polynomial fitting on the boundary mask of the diaphragm to obtain the diaphragm boundary (the left and right diaphragm), i.e. the boundary information of the reference object.

[0085] Subsequently, the tumor positioning device can combine the diaphragm boundary corresponding to each coronal image to obtain a three-dimensional mask of the diaphragm.

[0086] Of course, the tumor positioning device can also use artificial intelligence (AI) technology to determine the three-dimensional mask of the reference object.

[0087] S302, the tumor positioning device converts the three-dimensional mask into a two-dimensional mask, and performs morphological reconstruction on the two-dimensional mask to obtain boundary mask information.

[0088] Specifically, after obtaining the three-dimensional mask of the reference object, since the boundary mask information of the reference object is in two-dimensional space, the tumor positioning device can convert the three-dimensional mask into a two-dimensional mask, and perform morphological reconstruction on the two-dimensional mask to obtain the boundary mask information.

[0089] Morphological reconstruction is an important operation in mathematical morphology. It is based on mask images and aims to reconstruct a new image from a labeled image, under the constraints of the mask image, through morphological operations.

[0090] In this embodiment, during the process of the tumor localization device determining the three-dimensional mask of the reference object based on the planned image, the planned image may contain breathing artifacts (i.e., the position of the organ may be different at different scanning time points, resulting in artifacts such as blurring, ghosting, or deformation on the image). Therefore, the two-dimensional mask obtained by converting the three-dimensional mask may contain false boundaries. In this case, morphological reconstruction can remove the false boundaries in the two-dimensional mask, obtaining accurate and clear boundary mask information.

[0091] In some embodiments, the method for a tumor localization device to perform morphological reconstruction of a two-dimensional mask to obtain boundary mask information specifically includes: the tumor localization device sequentially performing erosion and smoothing processes on the two-dimensional mask to obtain a processed two-dimensional mask, and determining the boundary mask of a reference object in a first direction based on the gradient information of the processed two-dimensional mask. Subsequently, the tumor localization device may perform dilation processing in a second direction of the reference object based on the boundary mask and structuring elements of the reference object in the first direction to obtain boundary mask information.

[0092] Continuing with the diaphragm as the reference object, such as Figure 5 As shown, the tumor localization device can first perform an erosion process on the two-dimensional mask of the diaphragm, i.e., an erosion operation, to obtain the two-dimensional mask 501 after the erosion operation.

[0093] The purpose of erosion is to eliminate small protrusions in a 2D mask, which are likely false boundaries caused by breathing artifacts. Erosion is performed on the 2D mask by selecting appropriate structuring elements (such as small circular or square structuring elements). The erosion operation causes the mask boundaries to shrink inward, thereby removing those discontinuous, small false boundary portions.

[0094] Next, the tumor localization device can perform a smoothing process on the 2D mask after the erosion operation, i.e., a smoothing operation (also known as opening operation smoothing), to obtain a smoothed 2D mask 502. The smoothing operation can reduce the discontinuities at the boundaries of the 2D mask, thereby making it smoother.

[0095] Next, the tumor localization device can determine the boundary mask 503 of the diaphragm in the first direction based on the gradient information of the processed two-dimensional mask.

[0096] Assuming the first direction is the head-to-toe direction, the tumor localization device can use pixels with a gradient greater than 0 in the head-to-toe direction in the processed 2D mask as boundary points, and connect and combine these boundary points to obtain the boundary mask of the diaphragm in the head-to-toe direction.

[0097] Subsequently, the tumor localization device can perform expansion processing based on the boundary mask of the diaphragm in the head-to-toe direction. The expansion structuring element (i.e., the filter kernel) can be [0; 1; 1], and the expansion direction can be from head to toe, thereby obtaining the boundary mask information 504 of the diaphragm.

[0098] In some embodiments, the boundary mask information includes a multi-segment mask of the reference object. In this case, combined with Figure 3 ,like Figure 6 As shown, in S204 above, the method by which the tumor localization device determines the motion trajectory of the reference object based on boundary mask information and deformation information specifically includes:

[0099] S601. For each sub-mask segment, the tumor localization device determines the deformation of the sub-mask based on the sub-mask and the deformation information corresponding to the sub-mask.

[0100] Specifically, as shown in S203 above, the tumor localization device can determine the deformation information of the reference object. For each sub-mask segment, the tumor localization device can obtain the deformation information corresponding to that sub-mask from the deformation information. As shown in S302 above, the tumor localization device can obtain the boundary mask information of the reference object, and then determine each sub-mask segment from the boundary mask information. Subsequently, the tumor localization device can determine the deformation of the sub-mask based on the sub-mask and the deformation information corresponding to the sub-mask.

[0101] For example, assuming the boundary mask information includes n sub-masks of the reference object, the deformation calculation formula for the i-th sub-mask is d. i for:

[0102]

[0103] Here, D(x,y) is the deformation information of pixel (x,y), and mask(x,y) is the sub-mask of pixel (x,y).

[0104] S602. The tumor localization device determines the motion trajectory of the reference object based on the deformation of each sub-mask segment.

[0105] Specifically, after determining the deformation of each sub-mask segment, the tumor localization device can perform deformation calculations on each sub-mask segment based on its deformation, and generate the motion trajectory of the reference object through the sub-mask segment after deformation calculation.

[0106] It should be noted that since the above operation is an operation performed for each image in the KV sequence image, the motion trajectory of the reference object is also a motion trajectory generated for one KV image. The tumor positioning device can select the smoothest estimate from the motion trajectory corresponding to each KV image as the motion trajectory of the reference object, and determine the maximum range of motion (such as the highest point, the lowest point, etc.) of the reference object according to the motion trajectory of the reference object.

[0107] As can be seen from the above, by segmenting the boundary mask information, the deformation amount of each segment of the mask can be accurately obtained, and the motion trajectory of the reference object can be accurately determined, thereby improving the robustness of determining the motion trajectory of the reference object.

[0108] In some embodiments, in combination with Figure 6 As Figure 7 shown, in S205, the method for the tumor positioning device to track the to-be-positioned tumor according to the motion trajectory of the reference object specifically includes:

[0109] S701, the tumor positioning device acquires a motion trajectory mapping model.

[0110] The motion trajectory mapping model is used to represent the mapping relationship between the motion trajectory of the reference object and the motion trajectory of the to-be-positioned tumor.

[0111] Specifically, when generating the motion trajectory mapping model, the position data, motion data, and other data related to the motion trajectory of the to-be-positioned tumor and the reference object need to be collected.

[0112] Optionally, the position data of the to-be-positioned tumor can be regularly acquired by medical imaging technology (such as CT, MRI, or PET-CT). These imaging devices can provide the coordinates of the to-be-positioned tumor in three-dimensional space, and the time interval of each scan should be kept relatively stable, for example, scanned once a week or once every two weeks.

[0113] The motion data of the reference object can also be regularly acquired by medical imaging. During the breathing process, the position and shape of the reference object (such as the diaphragm) will change. The embodiments of the present application can use dynamic MRI or fluoroscopy to record the motion trajectory of the reference object within the breathing cycle and obtain the position information of the reference object at different breathing phases.

[0114] After acquiring the above data related to the motion trajectory, the data can be preprocessed to obtain processed trajectory data.

[0115] The preprocessing can include coordinate system alignment processing and time synchronization processing.

[0116] Since the position of the tumor to be located and the motion data of the reference object can come from different imaging devices or scanning sequences, it is necessary to align their coordinate systems. For example, geometric transformations such as translation, rotation, and scaling are performed to ensure that all data are in a unified spatial coordinate system.

[0117] In addition, since the position of the tumor to be located and the motion of the reference object are time-varying processes, the data need to be time-synchronized to determine the time points of each scan of the tumor to be located and the motion record of the reference object, and arrange them in chronological order to establish an accurate mapping relationship subsequently.

[0118] Then, the tumor position features and reference object motion features in the processed trajectory data can be extracted to establish a motion trajectory mapping model.

[0119] The tumor position features can include three-dimensional coordinates, dynamic features such as the speed of change of the tumor position, and acceleration. These features can help describe the motion state of the tumor to be located at different time points, for example, by calculating the difference in tumor position between two adjacent scans to obtain the position change speed.

[0120] The reference object motion features can include features such as the amplitude of rise and fall, motion speed, and breathing frequency within the breathing cycle. For example, taking the diaphragm as an example, the motion amplitude of the diaphragm can be determined by analyzing the position difference of the diaphragm at the peak of inhalation and exhalation.

[0121] Optionally, when establishing the motion trajectory mapping model, if there is an approximately linear relationship between the position of the tumor to be located and the motion of the reference object, a linear regression model can be considered. If the relationship between the position of the tumor to be located and the motion of the reference object is complex, a nonlinear model can be used. For example, a simple multilayer perceptron (MLP) neural network can be constructed. The input layer of the neural network receives the reference object motion features, the hidden layer performs nonlinear transformation, and the output layer outputs the tumor position features. Through a large amount of data, the neural network is trained to adjust the weights and biases of the network, thereby obtaining an accurate motion trajectory mapping model.

[0122] S702, the tumor positioning device locates and tracks the tumor to be located according to the motion trajectory of the reference object and the motion trajectory mapping model.

[0123] Optionally, in the case where the number of reference objects is multiple, the motion trajectory mapping model can also be a mapping model of the motion trajectories of multiple reference objects and the motion trajectory of the tumor to be located. That is, the tumor positioning device can locate and track the tumor to be located according to the motion trajectories of multiple reference objects and the motion trajectory mapping model.

[0124] In some embodiments, the motion trajectory of the reference object comprises an actual motion amount of the reference object at each motion point. In this case, the method for tracking the location of the tumor according to the motion trajectory of the reference object in S205 comprises: Figure 6 As shown in Figure 8 the above, the method for tracking the location of the tumor according to the motion trajectory of the reference object in S205 comprises:

[0125] S801, the tumor positioning device acquires a normal motion amount of the reference object.

[0126] For example, taking the diaphragm as the reference object, the motion of the diaphragm usually changes reasonably according to the breathing of the human body. In this case, the tumor positioning device can acquire the normal motion amount of the diaphragm.

[0127] S802, the tumor positioning device tracks the location of the tumor according to the actual motion amount and the normal motion amount of the reference object at each motion point.

[0128] Continuing to combine the above example, if the actual motion amount (e.g. the amplitude of rising) of the diaphragm at a certain motion point exceeds the normal motion amount of the diaphragm, it indicates that the patient's breathing is abnormal.

[0129] For another example, the tumor positioning device can set a reference baseline according to the normal motion amount of the diaphragm at each motion point. If the actual motion amount of the diaphragm of the patient exceeds the baseline range (i.e. baseline drift), it may be caused by the baseline drift of the diaphragm as the patient gradually relaxes during treatment.

[0130] In the above two cases, the tumor positioning device can remind the doctor to check the target area of the patient by outputting prompt information.

[0131] Optionally, in the case where the number of reference objects is multiple, the tumor positioning device can also acquire the normal motion range of multiple reference objects. In the process of tracking the location of the tumor to be positioned, the tumor positioning device can acquire the actual motion range of multiple reference objects, and compare it with the normal motion range of multiple reference objects to determine whether the actual motion range of each reference object is abnormal, and further determine whether the breathing state of the patient is abnormal.

[0132] When the tumor positioning device compares the actual motion range of multiple reference objects with the normal motion range of multiple reference objects, it can subtract the normal motion value from the actual motion value of the reference object, and determine whether the difference exceeds a preset range amount. Subsequently, by mapping the difference into a risk coefficient and weighting the risk coefficients of all reference objects, the final risk coefficient can be obtained, and by determining whether the final risk coefficient exceeds a preset threshold, it can be determined whether the breathing state of the patient is abnormal at this time.

[0133] The above mainly describes the scheme of the embodiments of the present application from the method aspect. It can be understood that the tumor positioning device comprises hardware structures and / or software modules corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the present application.

[0134] The embodiments of the present application can divide the functional units of the tumor positioning device according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The above integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical functional division. Actual implementation can have another division manner.

[0135] As shown in Figure 9 The embodiments of the present application provide a tumor positioning device, which comprises a communication unit 901 and a processing unit 902.

[0136] The communication unit 901 is configured to acquire a planning image and a real-time image of a reference object having correlation with a motion trajectory of a tumor to be positioned.

[0137] The processing unit 902 is configured to determine boundary mask information of the reference object according to the planning image.

[0138] The processing unit 902 is further configured to determine deformation information of the reference object according to the planning image and the real-time image.

[0139] The processing unit 902 is further configured to determine the motion trajectory of the reference object according to the boundary mask information and the deformation information.

[0140] The processing unit 902 is further configured to position and track the tumor to be positioned according to the motion trajectory of the reference object.

[0141] In some embodiments, the processing unit 902 is specifically configured to:

[0142] determine three-dimensional mask of the reference object according to the planning image;

[0143] convert the three-dimensional mask into two-dimensional mask, and perform morphological reconstruction on the two-dimensional mask to obtain the boundary mask information.

[0144] In some embodiments, the planning image comprises a plurality of planning sub-images of the reference object acquired continuously along a preset anatomical direction; the processing unit 902 is specifically configured to:

[0145] For each planning sub-image, the reference region to which the reference object belongs is determined according to the planning sub-image;

[0146] The gradient information of the reference region in the planning sub-image is polynomially fitted to obtain the boundary information of the reference object in the planning sub-image;

[0147] The boundary information of the reference object corresponding to each planning sub-image is combined to obtain a three-dimensional mask of the reference object.

[0148] In some embodiments, the processing unit 902 is specifically configured to:

[0149] The two-dimensional mask is sequentially subjected to erosion processing and smoothing processing to obtain a processed two-dimensional mask;

[0150] The gradient information of the processed two-dimensional mask is used to determine the boundary mask of the reference object in the first direction;

[0151] Based on the boundary mask of the reference object in the first direction and a structural element, the second direction of the reference object is subjected to dilation processing to obtain boundary mask information.

[0152] In some embodiments, the boundary mask information comprises a plurality of sub-masks of the reference object; the processing unit 902 is specifically configured to:

[0153] For each sub-mask, the deformation amount of the sub-mask is determined according to the sub-mask and deformation information corresponding to the sub-mask;

[0154] The motion trajectory of the reference object is determined according to the deformation amount of each sub-mask.

[0155] In some embodiments, the processing unit 902 is specifically configured to:

[0156] Obtain a motion trajectory mapping model; the motion trajectory mapping model is used to represent the mapping relationship between the motion trajectory of the reference object and the motion trajectory of the tumor to be positioned;

[0157] The tumor to be positioned is positioned and tracked according to the motion trajectory of the reference object and the motion trajectory mapping model.

[0158] In some embodiments, the motion trajectory of the reference object comprises an actual motion amount of the reference object at each motion point; the processing unit 902 is specifically configured to:

[0159] Obtain a normal motion amount of the reference object;

[0160] According to the actual movement amount and the normal movement amount of the reference object at each movement point, the tumor to be positioned is positioned and tracked.

[0161] In some embodiments, the reference object comprises at least one of: a diaphragm, a lung wall, a lung apex.

[0162] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, comprising at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the tumor positioning method provided by the present disclosure.

[0163] According to embodiments of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable an electronic device to perform the tumor positioning method provided by the present disclosure.

[0164] According to embodiments of the present disclosure, the present disclosure further provides a computer program product comprising a computer program, which, when executed by a processor, implements the tumor positioning method provided by the present disclosure.

[0165] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document. In some embodiments, the electronic device can be the tumor positioning device shown in Figure 1

[0166] As Figure 10 ​As shown, the electronic device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a Read-Only Memory (ROM) 1002 or a computer program loaded into a Random Access Memory (RAM) 1003 from a storage unit 1008. Various programs and data required for the operation of the electronic device 1000 can also be stored in the random access memory 1003. The computing unit 1001, the read-only memory 1002, and the RAM 1003 are connected to each other through a bus 1004. An Input / Output (I / O) interface 1005 is also connected to the bus 1004.

[0167] Various components in the electronic device 1000 are connected to the input / output interface 1005, including an input unit 1006 such as a keyboard, a mouse, and the like, an output unit 1007 such as various types of displays, a speaker, and the like, a storage unit 1008 such as a magnetic disk, an optical disk, and the like, and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0168] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit, a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor, and any appropriate processor, controller, microcontroller, and the like. The computing unit 1001 performs various methods and processes described above, such as the data matching method. For example, in an embodiment, the data matching method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 1008. In an embodiment, part or all of the computer program can be loaded and / or installed on the electronic device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the data matching method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to perform the data matching method by any other appropriate means, such as by means of firmware.

[0169] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) computer hardware, firmware, software, and / or combinations of each to perform the various embodiments. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0170] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowchart and / or block diagram block or blocks. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or entirely on a remote machine or server.

[0171] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disc read-only memories, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a Cathode Ray Tube (CRT) or Liquid Crystal Display (LCD) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0173] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.

[0174] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0175] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0176] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A method for tumor localization, characterized in that, include: Acquire planned and real-time images of a reference object that are correlated with the motion trajectory of the tumor to be located; the planned images include multi-layered planned sub-images of the reference object continuously acquired along a preset anatomical direction; For each layer of the plan sub-image, the reference region to which the reference object belongs is determined based on the plan sub-image; Polynomial fitting is performed on the gradient information of the reference region in the planned sub-image to obtain the boundary information of the reference object in the planned sub-image; The boundary information of the reference object corresponding to each layer of the planning sub-image is combined to obtain a three-dimensional mask of the reference object; The three-dimensional mask is converted into a two-dimensional mask, and the two-dimensional mask is morphologically reconstructed to obtain the boundary mask information of the reference object; Determine the deformation information of the reference object based on the planned image and the real-time image; The motion trajectory of the reference object is determined based on the boundary mask information and the deformation information; Based on the motion trajectory of the reference object, the tumor to be located is located and tracked.

2. The method according to claim 1, characterized in that, The morphological reconstruction of the two-dimensional mask to obtain the boundary mask information includes: The two-dimensional mask is subjected to etch and smoothing processes sequentially to obtain the processed two-dimensional mask; Based on the gradient information of the processed two-dimensional mask, the boundary mask of the reference object in the first direction is determined; Based on the boundary mask and structural elements of the reference object in the first direction, dilation is performed in the second direction of the reference object to obtain the boundary mask information.

3. The method according to claim 1, characterized in that, The boundary mask information includes a multi-segment mask of the reference object; determining the motion trajectory of the reference object based on the boundary mask information and the deformation information includes: For each sub-mask segment, the deformation of the sub-mask is determined based on the sub-mask and the deformation information corresponding to the sub-mask. The motion trajectory of the reference object is determined based on the deformation of each sub-mask segment.

4. The method according to claim 1, characterized in that, The step of locating and tracking the tumor to be located based on the motion trajectory of the reference object includes: Obtain a motion trajectory mapping model; the motion trajectory mapping model is used to represent the mapping relationship between the motion trajectory of the reference object and the motion trajectory of the tumor to be located; The tumor to be located is located and tracked based on the motion trajectory of the reference object and the motion trajectory mapping model.

5. The method according to claim 1, characterized in that, The motion trajectory of the reference object includes the actual amount of motion of the reference object at each motion point; Based on the motion trajectory of the reference object, the tumor to be located is located and tracked, including: Obtain the normal amount of exercise of the reference object; The tumor to be located is located and tracked based on the actual amount of movement of the reference object at each movement point and the normal amount of movement.

6. The method according to any one of claims 1-5, characterized in that, The reference objects include at least one of the following: diaphragm, lung wall, and lung apex.

7. An electronic device, characterized in that, The electronic device includes: processor; A memory configured to store processor-executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1-6.

8. A non-volatile storage medium, characterized in that, The storage medium stores a computer program, which, when read and executed, implements the method described in any one of claims 1-6.

Images