Mark detection method and device and storage medium

Abstract

The invention relates to a mark detection method and device and a storage medium. The method comprises the following steps: acquiring a reference image of a motif, segmenting one or more marks in the motif by using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more marks, and determining detection information of the one or more marks based on the segmentation result. According to the embodiment of the invention, after the reference image of the motif is acquired, the segmentation result of one or more marks in the motif is acquired based on the reference image, so that the detection information of each mark is determined based on the segmentation result, the detection information of the marks has relatively high detection accuracy and stability, the accuracy of the evaluation quality of the reconstructed image is improved, and the accuracy of the evaluation quality of the reconstructed image is improved. And the manual operation frequency is further reduced.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a marker detection method, device and storage medium. Background Art

[0002] Reconstructed images from positron emission tomography (PET-CT) devices are widely used in diagnosis. Therefore, reconstructed images with high contrast and clarity facilitate observation and analysis by doctors.

[0003] According to international standards, six markers of different sizes in the phantom need to be detected, and the quality of the reconstructed image should be evaluated based on the detection information of the markers.

[0004] Currently, manual methods are used to detect markers, but this method has the problem of inaccurate marker detection. Summary of the Invention

[0005] Based on this, it is necessary to provide a mark detection method, device and storage medium that can improve the accuracy of mark detection in response to the above technical problems.

[0006] In a first aspect, the present application provides a marker detection method, comprising:

[0007] Obtain a reference image of the phantom;

[0008] Based on the reference image, segmenting the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0009] Based on the segmentation result, detection information of the one or more markers is determined.

[0010] In one embodiment, the segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0011] In one embodiment, the method further comprises:

[0012] determining a phantom coordinate system of the phantom according to the calculated positions of the one or more markers in the detection information;

[0013] determining a deflection angle between the phantom coordinate system and the reference coordinate system; and

[0014] A target position of the one or more markers is determined based on the deflection angle and the calculated position.

[0015] In one embodiment, determining the target position of the one or more markers based on the deflection angle and the calculated position includes:

[0016] In response to confirming that the deflection angle is smaller than a preset deflection angle and / or in response to a user confirmation operation on an operation interface, the target position is determined according to the calculated position.

[0017] In one embodiment, the method further comprises:

[0018] In response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on an operation interface, adjusting the placement posture of the phantom based on the deflection angle, and re-obtaining a new calculated position of the one or more markers in the phantom;

[0019] Determining a new deflection angle according to the new calculated position and the reference coordinate system until the new deflection angle is less than the preset deflection angle; and

[0020] A new calculated position corresponding to a new deflection angle smaller than the preset deflection angle is used as a target position of the one or more marks.

[0021] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by an imaging device.

[0022] In one embodiment, segmenting the one or more marks in the phantom using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more marks includes:

[0023] Determining, based on the reference image, a mask image or a centroid layer marker position corresponding to the one or more markers; and

[0024] The segmentation result is determined according to the mask image or the centroid layer mark position.

[0025] In one embodiment, the reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0026] In a second aspect, the present application further provides a marking position detection device, comprising:

[0027] An acquisition module, used to acquire a reference image of the phantom;

[0028] a first determining module, configured to segment the one or more marks in the phantom using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more marks; and

[0029] The second determining module is configured to determine detection information of the one or more markers based on the segmentation result.

[0030] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Obtain a reference image of the phantom;

[0032] Based on the reference image, segmenting the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0033] Based on the segmentation result, detection information of the one or more markers is determined.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtain a reference image of the phantom;

[0036] Based on the reference image, segmenting the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0037] Based on the segmentation result, detection information of the one or more markers is determined.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0039] Obtain a reference image of the phantom;

[0040] Based on the reference image, segmenting the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0041] Based on the segmentation result, detection information of the one or more markers is determined.

[0042] The above-mentioned marker detection method, device, and storage medium obtain a reference image of the phantom, and based on the reference image, use a segmentation algorithm to segment one or more markers in the phantom to obtain segmentation results for the one or more markers, and then determine detection information for the one or more markers based on the segmentation results. In the embodiment of the present application, after obtaining a reference image of the phantom, segmentation results for the one or more markers in the phantom are obtained based on the reference image, and then detection information for each marker is determined based on the segmentation results. This ensures that the marker detection information has high detection accuracy and stability, improves the accuracy of the reconstructed image quality evaluation, and further reduces the frequency of manual operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A diagram showing an application environment of a marker detection method in one embodiment;

[0045] Figure 2 Schematic diagram of a flow chart of a marker detection method in one embodiment;

[0046] Figure 3 is a schematic diagram of a phantom in one embodiment;

[0047] Figure 4 A schematic diagram of a label in one embodiment;

[0048] Figure 5 A schematic diagram of another embodiment;

[0049] Figure 6 1 is a flow chart of a method for determining a target position in one embodiment;

[0050] Figure 7 is a flow chart of a method for determining a target position in another embodiment;

[0051] Figure 8 is a flow chart of a method for determining a target position in another embodiment;

[0052] Figure 9 Schematic diagram of a flow chart of a method for determining a segmentation result in one embodiment;

[0053] Figure 10 1 is a flow chart of a method for determining a centroid layer marker position in one embodiment;

[0054] Figure 11 Schematic diagram of a flow chart of a method for determining a centroid layer marker position in another embodiment;

[0055] Figure 12 is a structural block diagram of a mark detection device in one embodiment;

[0056] Figure 13 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0058] The label detection method provided in the embodiment of the present application can be applied to Figure 1 The application environment shown in FIG. The application environment includes a computer device, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data for mark detection. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a mark position detection method is implemented. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0059] In an exemplary embodiment, Figure 2 As shown, a marker detection method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following S201 to S203.

[0060] S201, obtaining a reference image of the phantom.

[0061] The reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0062] As a specific example, according to current standards, the NEMA IEC Body phantom produced by DSC Corporation of the United States is commonly used to test the PET image quality, scatter correction and attenuation correction accuracy, and PET-CT registration accuracy in PET-CT equipment. The phantom is a closed cavity with a fixed cross-sectional shape. One or more markers of different sizes are set in the closed cavity of the phantom, such as Figure 3 As shown in the figure, the closed cavity of the phantom is equipped with 6 small balls, with the centers of the balls coplanar and evenly distributed along the circumference. High-activity liquid can be filled into the 6 small balls, and low-activity liquid can be filled into the phantom (or low-activity liquid can be filled into the small balls, and high-activity liquid can be filled into the phantom). The reference image of the phantom is collected by PET-CT equipment. The reference image is as follows: Figure 4 However, this is not limited to the above, and the number of balls in the phantom can be arbitrarily set as needed.

[0063] In this embodiment, on the one hand, the phantom can be placed on the scanning bed of the PET-CT device, and the PET-CT device is used to scan the phantom to obtain a reference image in a DICOM format or a NIfTI format.

[0064] On the other hand, the reference image of the phantom that has been stored can be obtained from a storage medium of a computer device, or the reference image of the phantom can be obtained from the cloud.

[0065] S202 : Segment one or more marks in the phantom using a segmentation algorithm based on the reference image to obtain segmentation results of the one or more marks.

[0066] The segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0067] Optionally, one or more markers in the phantom can be the small balls in the above embodiments, or can be cubes, ellipsoids, etc. For example, in the NEMA NU2-2007 standard, 4 small balls of different sizes filled with radioactive imaging agent fluorodeoxyglucose solution (FDG solution) are used to simulate hot lesions, which are called hot balls; 2 small balls of different sizes filled with pure water are used to simulate cold lesions, which are called cold balls; the NEMA NU2-2012 standard and the NEMA NU2-2018 standard set 6 hot balls of different sizes. Therefore, each small ball can be a hot ball, a cold ball, or a combination of a hot ball and a cold ball. The number of each small ball and the design of the hot and cold balls are determined according to the actual situation of the NEMA standard. Figure 5 As shown, the marking setting of the phantom corresponding to the NEMA NU2-2012 standard is shown, where balls 1 and 2 are cold balls, balls 3-6 are hot balls, and ball 7 is the lung area.

[0068] In this embodiment, a deep learning network is used to segment a marked mask image from a reference image, and one or more marks in the phantom are segmented based on the mask image and the medical image to be segmented of the phantom to obtain a segmentation result of the one or more marks.

[0069] In one possible implementation, a threshold segmentation algorithm can be used to segment the reference image to obtain the centroid layer marker positions corresponding to one or more markers. Based on the centroid layer marker positions and the medical image to be segmented of the phantom, the one or more markers in the phantom are segmented to obtain the segmentation results of the one or more markers.

[0070] In another possible implementation, a deep learning network is used to segment a marked mask image from a reference image, and a threshold segmentation algorithm is used to segment the reference image to obtain the centroid layer marker positions corresponding to one or more markers. A fused image is obtained based on the mask image and the centroid layer marker positions, and one or more markers in the model are segmented based on the fused image to obtain the segmentation results of one or more markers.

[0071] As non-limiting examples of the threshold segmentation algorithm, it may be or include the maximum inter-class variance method, the global threshold segmentation method, the local threshold segmentation method, etc.

[0072] S203: Determine detection information of one or more markers based on the segmentation result.

[0073] Optionally, the detection information may be the calculated position of the marker, the shape of the marker, the size of the marker, the area of ​​the marker, the volume of the marker, the number of markers, the presence or absence of a marker, and the like.

[0074] In this embodiment, if the detection information is a calculated position, a positioning algorithm can be used to locate the segmentation result to obtain the calculated position of one or more marks; if the detection information is the shape of the mark, an image recognition algorithm can be used to identify the outline of the mark in the segmentation result to obtain the shape of the mark, etc.

[0075] The above-mentioned marker detection method obtains a reference image of the phantom, and based on the reference image, uses a segmentation algorithm to segment one or more markers in the phantom to obtain segmentation results for the one or more markers, and then determines detection information for the one or more markers based on the segmentation results. In the embodiment of the present application, after obtaining a reference image of the phantom, segmentation results for the one or more markers in the phantom are obtained based on the reference image, and then detection information for each marker is determined based on the segmentation results. This ensures that the marker detection information has high detection accuracy and stability, improves the accuracy of the reconstructed image quality evaluation, and further reduces the frequency of manual operations.

[0076] Figure 6 FIG. 1 is a flow chart of a method for determining a target position in an embodiment. Figure 6 As shown, the following steps are included:

[0077] S601 , determining a phantom coordinate system of the phantom according to the calculated positions of one or more markers in the detection information.

[0078] In this embodiment, three relatively symmetrical calculation positions are selected from the calculated positions of each marker. Three indicator lines are drawn outward from these three calculated positions, with each of the three indicator lines being perpendicular to each other. The one of the three indicator lines relative to the vertical ground is used as the Z axis, and the other two indicator lines are used as the X axis and Y axis, respectively, to obtain the phantom coordinate system.

[0079] S602: Determine the deflection angle between the phantom coordinate system and the reference coordinate system.

[0080] In this embodiment, the phantom has a reference coordinate system corresponding to the reference image. Using any coordinate axis in any direction of the phantom coordinate system and the coordinate axis corresponding to the reference coordinate system, the deflection angle between the reference coordinate system and the phantom coordinate system can be determined. For example, based on the X-axis of the phantom coordinate system and the X-axis of the reference coordinate system, the deflection angle between the phantom coordinate system and the reference coordinate system of the phantom is determined to be 0.5 degrees. Thus, the deflection angle between the phantom in the reference image and the phantom in the medical image to be segmented is 0.5 degrees.

[0081] S603: Determine the target position of one or more markers according to the deflection angle and the calculated position.

[0082] In one possible implementation, when the deflection angle is less than a preset deflection angle, the calculated position of one or more markers may be directly used as the target position of the corresponding marker; or Figure 7 As shown, if the deflection angle is less than the preset deflection angle, the calculated position can be manually confirmed to determine if it is correct. If so, the calculated position is used as the target position for the corresponding mark in response to a confirmation operation on the operation interface. Alternatively, the calculated position can be fine-tuned using an algorithm to obtain the target position for the mark. This adjustment is different from the adjustment to the phantom position corresponding to a deflection angle of not less than the preset deflection angle.

[0083] In another possible implementation, when the deflection angle is not less than a preset deflection angle, or when an adjustment instruction is received from an external input, the placement posture of the phantom is adjusted based on the deflection angle, so that the deflection angle of the adjusted phantom is less than the preset deflection angle, and the target position of one or more markers is determined based on the new calculated position of the marker of the adjusted phantom.

[0084] Specifically, the target position of one or more markers is determined based on the deflection angle and the calculated position, including the following two methods:

[0085] The first way: in response to confirming that the deflection angle is smaller than a preset deflection angle and / or in response to a user confirmation operation on an operation interface, the target position is determined according to the calculated position.

[0086] In this embodiment, a confirmation operation input by the user is received, and in response to confirming that the deflection angle is less than the preset deflection angle and / or in response to the user's confirmation operation on the operation interface, the calculated position of one or more marks is used as the target position of the corresponding mark.

[0087] The second method: in response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on the operation interface, the placement position of the phantom is adjusted based on the deflection angle, and the new calculated position of one or more markers in the phantom is re-acquired; based on the new calculated position and the reference coordinate system, a new deflection angle is determined until the new deflection angle is less than the preset deflection angle; and the new calculated position corresponding to the new deflection angle less than the preset deflection angle is used as the target position of one or more markers.

[0088] In this embodiment, combined with Figure 7 and Figure 8 As shown, in response to determining that the deflection angle is not less than the preset deflection angle or in response to the user's adjustment operation on the operation interface, the deflection angle can be output, and the placement posture of the phantom can be adjusted based on the deflection angle.

[0089] Furthermore, a new medical image to be segmented of the adjusted phantom is obtained, and based on the reference image and the new medical image to be segmented, new calculated positions of one or more marks in the phantom are re-obtained, and a new phantom coordinate system is re-obtained based on the new calculated positions. A new deflection angle is determined based on the new phantom coordinate system and the reference coordinate system until the new deflection angle is less than a preset deflection angle, and the new calculated position corresponding to the new deflection angle less than the preset deflection angle is used as the target position of the mark.

[0090] In this embodiment, the target positions of one or more markers are determined by determining the deflection angle between the phantom coordinate system and the reference coordinate system, and based on the deflection angle and the calculated position. Specifically, when the deflection angle is less than a preset deflection angle, and / or in response to a user confirmation operation on an operation interface, in response to a determination that the deflection angle is not less than the preset deflection angle, or in response to a user adjustment operation on the operation interface, the target positions of one or more markers are determined based on the calculated position. This specific implementation can further improve the accuracy of target position determination and the accuracy of image quality assessment, thereby improving the accuracy of medical device imaging based on the quality assessment results.

[0091] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by the imaging device.

[0092] In this embodiment, after outputting the deflection angle, the placement position of the phantom can be kept unchanged, and the raw data acquired by the medical device can be directly reconstructed using the image reconstruction algorithm and the deflection angle. This can compensate for the low image quality caused by inaccurate placement of the phantom in the subsequent image reconstruction process, and provide multiple options for obtaining higher-quality reconstructed images in the subsequent process.

[0093] Compared with previous technical solutions, the method in this embodiment can detect detection information such as the position of the ball when the deflection angle of the phantom is too large, and obtain the deflection angle of the phantom offset, and has high detection accuracy and stability, which can further reduce the frequency of manual operations.

[0094] Figure 9 This is a flow chart of a method for determining a segmentation result in one embodiment. The embodiment of the present application relates to a possible implementation method of how to segment one or more marks in a motif using a segmentation algorithm based on a reference image to obtain a segmentation result of one or more marks, such as Figure 9 As shown, the following steps are included:

[0095] S901 : Determine, based on a reference image, a mask image or a centroid layer marker position corresponding to one or more markers.

[0096] In this embodiment, a deep learning network can be used to segment the reference image to obtain mask images corresponding to one or more markers. For example, a UNET network can be used for segmentation to obtain mask images for each marker. Alternatively, a binarization, dilation, or erosion algorithm can be used to segment the initial image to obtain mask images for each marker.

[0097] When delineating a marker, the centroid of the marker is located using a reference image (for example, if the marker is spherical, the centroid is the center of the sphere). The marker is then delineated to obtain the centroid layer marker position. Because reference images obtained under different experimental conditions can vary significantly, the delineation method requires strong generalization capabilities.

[0098] As a specific non-limiting example, in combination Figure 10 As shown in the figure, taking the small ball as an example, when the reference image is a three-dimensional PET image, the reference image is segmented according to the threshold. The specific method is as follows: each layer of the phantom is divided by the initial threshold X, and the area of ​​the phantom divided by each layer is calculated. If the area and axial length of the divided phantom do not meet its actual size, the initial threshold X is updated to X1, and the phantom is divided again according to X1 until the area of ​​the divided phantom meets the actual area.

[0099] After the phantom is divided, the average background value N of the phantom is calculated based on the first and last phantom layers. Specifically, using the phantom of the starting layer as an example, the first centroid of the phantom is calculated. A circular area with the first centroid as the center and radii R1 and R2 as the radius within the phantom area is then located. The average value of the circular area (e.g., average grayscale value or average RGB value) is used as the background value of the phantom layer. R1 and R2 can be any reasonable values ​​based on actual needs.

[0100] The spheres are preliminarily segmented using twice the average background value (denoted as 2N) as the threshold, and the number of pixels in each layer greater than 2N is counted, and the layer with the largest number of pixels is taken as the sphere center layer (i.e., the centroid layer).

[0101] Calculate the maximum value of each sphere preliminarily segmented in the core layer, and re-segment each sphere in the core layer with half of the maximum value of each sphere. Calculate the second centroid of each sphere in the core layer based on the re-segmentation result, and use the second centroid as the center of the sphere. Combined with the center and radius of each sphere, outline the sphere in the reference image to obtain the center layer mark position (i.e., the centroid layer mark position).

[0102] When the reference image is a two-dimensional PET image of the core layer phantom, the core layer phantom is divided using the initial threshold X, and the area of ​​the divided phantom is calculated. If the area of ​​the divided phantom does not match the actual area, the initial threshold X is updated to X1, and the core layer phantom is re-divided according to X1 until the area of ​​the divided phantom matches the actual area.

[0103] Determine the average pixel value a1 and the maximum pixel value a2 of the segmented phantom. Initially segment the core layer markers using a threshold of 0.9a1 + 0.1a2. Subsequent steps are the same as when the reference image is a 3D PET image to determine the core layer marker positions. However, this is not limiting. Besides using a threshold of 0.9a1 + 0.1a2, the threshold can also be adjusted as needed, for example, to 0.95a1 + 0.05a2.

[0104] Furthermore, if Figure 11 As shown, during the process of outlining the reference image to determine the location of the core layer marker, the computer automatically outlines the sphere in the reference image. The user can determine whether the outlined result meets the requirements. If so, the process ends. If not, the user specifies the core layer. Once the user specifies the core layer, the computer automatically outlines the sphere in the core layer image. Finally, the user again determines whether the outlined result meets the requirements. If so, the process ends. If not, the user manually adjusts the outlined result, achieving one-click, highly accurate outlining.

[0105] Among them, the centroid layer marking position can also be applied to NEMA phantom detection experiments, image quantitative parameter normalization, etc.

[0106] S902: Determine the segmentation result according to the mask image or the centroid layer marker position.

[0107] In this embodiment, the medical image to be segmented of the phantom is segmented according to the mask image or the centroid layer mark position to obtain a segmentation result.

[0108] In an embodiment of the present application, a mask image or centroid layer marker position corresponding to one or more markers is determined based on a reference image; and a segmentation result is determined based on the mask image or centroid layer marker position. Manually outlining markers increases the burden on the user, and the difficulty in controlling the accuracy of manual outlining affects the determination of the centroid layer marker position, leading to inaccurate segmentation results. In an embodiment of the present application, the segmentation result is determined by obtaining the mask image or centroid layer marker position of each marker. This lays the foundation for subsequently determining the marker's detection information based on the segmentation result, greatly reduces the burden on the doctor, and improves the convenience and usability of determining the segmentation result.

[0109] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0110] Based on the same inventive concept, the present application also provides a marker detection device for implementing the aforementioned marker detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more marker detection device embodiments provided below can be found in the above-mentioned limitations of the marker detection method and will not be repeated here.

[0111] In an exemplary embodiment, Figure 12 As shown, a marker detection device is provided, comprising: an acquisition module 11, a first determination module 12 and a second determination module 13, wherein:

[0112] An acquisition module 11 is used to acquire a reference image of the phantom;

[0113] A first determining module 12 is configured to segment one or more markers in the phantom using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more markers; and

[0114] The second determining module 13 is configured to determine detection information of one or more markers based on the segmentation result.

[0115] In one embodiment, the segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0116] In one embodiment, the marker detection device further comprises:

[0117] a third determining module, configured to determine a phantom coordinate system of the phantom based on the calculated positions of one or more markers in the detection information;

[0118] a fourth determining module, configured to determine a deflection angle between the phantom coordinate system and the reference coordinate system; and

[0119] The fifth determination module is used to determine the target position of one or more markers according to the deflection angle and the calculated position.

[0120] In one embodiment, the third determining module includes:

[0121] The first determining unit is configured to determine the target position according to the calculated position in response to confirming that the deflection angle is smaller than a preset deflection angle and / or in response to a user confirmation operation on the operation interface.

[0122] In one embodiment, the third determining module further includes:

[0123] an adjustment unit, configured to adjust the placement position of the phantom based on the deflection angle in response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on the operation interface, and re-acquire a new calculated position of one or more markers in the phantom;

[0124] a second determining unit, configured to determine a new deflection angle according to the new calculated position and the reference coordinate system until the new deflection angle is smaller than a preset deflection angle; and

[0125] The third determining unit is configured to use a new calculated position corresponding to a new deflection angle smaller than a preset deflection angle as a target position of one or more marks.

[0126] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by the imaging device.

[0127] In one embodiment, the first determining module includes:

[0128] a fourth determining unit, configured to determine, based on the reference image, a mask image or a centroid layer marker position corresponding to the one or more markers; and

[0129] The fifth determining unit is configured to determine a segmentation result according to the mask image or the centroid layer marker position.

[0130] In one embodiment, the reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0131] Each module in the aforementioned marker detection device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0132] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 13 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be achieved via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a marker detection method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0133] Those skilled in the art will understand that Figure 13The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0134] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0135] Obtain a reference image of the phantom;

[0136] Based on the reference image, segment the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0137] Based on the segmentation results, detection information of one or more markers is determined.

[0138] In one embodiment, the segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0139] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0140] determining a phantom coordinate system of the phantom based on the calculated positions of the one or more markers in the detection information;

[0141] determining a deflection angle between the phantom coordinate system and the reference coordinate system; and

[0142] Based on the deflection angle and the calculated position, the target position of one or more markers is determined.

[0143] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0144] In response to confirming that the deflection angle is smaller than the preset deflection angle and / or in response to a user confirmation operation on the operation interface, the target position is determined according to the calculated position.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] In response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on the operation interface, adjusting the placement posture of the phantom based on the deflection angle, and re-obtaining a new calculated position of one or more markers in the phantom;

[0147] Determining a new deflection angle according to the newly calculated position and the reference coordinate system until the new deflection angle is less than a preset deflection angle; and

[0148] A new calculated position corresponding to a new deflection angle smaller than the preset deflection angle is used as a target position of one or more marks.

[0149] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by the imaging device.

[0150] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0151] Determining a mask image or centroid layer marker position corresponding to one or more markers based on the reference image; and

[0152] The segmentation result is determined based on the mask image or the centroid layer marker position.

[0153] In one embodiment, the reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0154] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0155] Obtain a reference image of the phantom;

[0156] Based on the reference image, segment the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0157] Based on the segmentation results, detection information of one or more markers is determined.

[0158] In one embodiment, the segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0160] determining a phantom coordinate system of the phantom based on the calculated positions of the one or more markers in the detection information;

[0161] determining a deflection angle between the phantom coordinate system and the reference coordinate system; and

[0162] Determine the target position of one or more markers based on the deflection angle and the calculated position. In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0163] In response to confirming that the deflection angle is smaller than the preset deflection angle and / or in response to a user confirmation operation on the operation interface, the target position is determined according to the calculated position.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0165] In response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on the operation interface, adjusting the placement posture of the phantom based on the deflection angle, and re-obtaining a new calculated position of one or more markers in the phantom;

[0166] Determining a new deflection angle according to the newly calculated position and the reference coordinate system until the new deflection angle is less than a preset deflection angle; and

[0167] A new calculated position corresponding to a new deflection angle smaller than the preset deflection angle is used as a target position of one or more marks.

[0168] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by the imaging device.

[0169] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0170] Determining a mask image or centroid layer marker position corresponding to one or more markers based on the reference image; and

[0171] The segmentation result is determined based on the mask image or the centroid layer marker position.

[0172] In one embodiment, the reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0173] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0174] Obtain a reference image of the phantom;

[0175] Based on the reference image, segment the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and

[0176] Based on the segmentation results, detection information of one or more markers is determined.

[0177] In one embodiment, the segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0179] determining a phantom coordinate system of the phantom based on the calculated positions of the one or more markers in the detection information;

[0180] determining a deflection angle between the phantom coordinate system and the reference coordinate system; and

[0181] Determine the target position of one or more markers based on the deflection angle and the calculated position. In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0182] In response to confirming that the deflection angle is smaller than the preset deflection angle and / or in response to a confirmation operation of the user on the operation interface, the target position is determined according to the calculated position.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0184] In response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on the operation interface, adjusting the placement posture of the phantom based on the deflection angle, and re-obtaining a new calculated position of one or more markers in the phantom;

[0185] Determining a new deflection angle according to the newly calculated position and the reference coordinate system until the new deflection angle is less than a preset deflection angle; and

[0186] A new calculated position corresponding to a new deflection angle smaller than the preset deflection angle is used as a target position of one or more marks.

[0187] In one embodiment, the deflection angle is used to adjust the quality of an image acquired by the imaging device.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0189] Determining a mask image or centroid layer marker position corresponding to one or more markers based on the reference image; and

[0190] The segmentation result is determined based on the mask image or the centroid layer marker position.

[0191] In one embodiment, the reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

[0192] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0193] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0194] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A label detection method, characterized in that: The method comprises: Obtain a reference image of the phantom; Based on the reference image, segmenting the one or more marks in the phantom using a segmentation algorithm to obtain a segmentation result of the one or more marks; and Based on the segmentation result, detection information of the one or more markers is determined.

2. The method according to claim 1, characterized in that The segmentation algorithm includes a machine learning algorithm and / or a threshold segmentation algorithm.

3. The method according to claim 1, characterized in that The method further comprises: determining a phantom coordinate system of the phantom according to the calculated positions of the one or more markers in the detection information; determining a deflection angle between the phantom coordinate system and the reference coordinate system; and A target position of the one or more markers is determined based on the deflection angle and the calculated position.

4. The method according to claim 3, characterized in that Determining the target position of the one or more markers according to the deflection angle and the calculated position includes: In response to confirming that the deflection angle is smaller than a preset deflection angle and / or in response to a user confirmation operation on an operation interface, the target position is determined according to the calculated position.

5. The method according to claim 3 or 4, characterized in that The method further comprises: In response to determining that the deflection angle is not less than a preset deflection angle or in response to a user adjustment operation on an operation interface, adjusting the placement posture of the phantom based on the deflection angle, and re-obtaining a new calculated position of the one or more markers in the phantom; Determining a new deflection angle according to the new calculated position and the reference coordinate system until the new deflection angle is less than the preset deflection angle; and A new calculated position corresponding to a new deflection angle smaller than the preset deflection angle is used as a target position of the one or more marks.

6. The method according to claim 3, characterized in that The deflection angle is used to adjust the quality of an image acquired by an imaging device.

7. The method according to claim 1, characterized in that The step of segmenting the one or more marks in the phantom using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more marks includes: Determining, based on the reference image, a mask image or a centroid layer marker position corresponding to the one or more markers; and The segmentation result is determined according to the mask image or the centroid layer mark position.

8. The method according to claim 1, characterized in that The reference image includes at least one of a phantom standard image, a three-dimensional PET image, and a two-dimensional PET image.

9. A marking detection device, characterized in that: The device comprises: An acquisition module, used to acquire a reference image of the phantom; a first determining module, configured to segment the one or more marks in the phantom using a segmentation algorithm based on the reference image to obtain a segmentation result of the one or more marks; and The second determining module is configured to determine detection information of the one or more markers based on the segmentation result.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images