Standard uptake value normalization method and system

Abstract

The embodiment of the invention provides a standard uptake value normalization method and system, the method is executed by processing equipment, and the method comprises the following steps: obtaining a motif image, a to-be-processed image and a reference standard; iteratively performing first processing on the motif image to obtain a first reference value, and determining the customization standard as a normalization standard in response to the situation that the first reference value does not meet the reference standard; and iteratively performing first processing on the motif image to obtain a second reference value and a processing parameter, and when the second reference value meets a normalization standard, performing second processing on the to-be-processed image based on the processing parameter to obtain a normalized standard uptake value.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a method and system for normalizing a standard uptake value. Background Art

[0002] Standard Uptake Value (SUV) is a semi-quantitative index commonly used in tumor diagnosis by positron emission computed tomography (PET). SUV is widely used in tumor differentiation, efficacy evaluation, and prognosis prediction. Generally speaking, the higher the malignancy of the lesion, the higher the SUV value. However, due to the differences in weight, body surface area, physiological factors of the subjects, and examination procedures of different patients during the test, the accuracy and repeatability of the SUV value are affected. Therefore, it is necessary to normalize the SUV to standardize the factors affecting the SUV value and eliminate the quantitative differences caused by body shape and injection dose to a certain extent. Most of the current SUV normalization methods use image post-processing methods. However, in actual applications, due to reasons such as the model or reconstruction algorithm, some PET / CT devices cannot normalize the recovery coefficient (RC) curve of the phantom image at this time to the range specified by EARL through the post-processing algorithm, so that the SUV of the PET image acquired under the reconstruction conditions cannot be compared across devices, patients, and time, which is difficult to meet clinical needs.

[0003] Therefore, it is hoped to provide a method and system for normalizing standard uptake values ​​to achieve comparability of SUV across devices, patients, and time to meet clinical needs. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for normalizing a standard acquisition value, which is executed by a processing device and includes: acquiring a phantom image, an image to be processed, and a reference standard; iteratively performing a first processing on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determining a customized standard as a normalization standard; iteratively performing the first processing on the phantom image to obtain a second reference value and processing parameters, and when the second reference value satisfies the normalization standard, performing a second processing on the image to be processed based on the processing parameters to obtain a normalized standard acquisition value.

[0005] In some embodiments, the customization criteria may be determined based on obtaining user input parameters.

[0006] In some embodiments, the user input parameter may include the first reference value corresponding to the ball in the phantom.

[0007] In some embodiments, the customized standard includes a maximum restitution coefficient value, an average restitution coefficient value and an average value of a maximum restitution coefficient region, wherein the maximum restitution coefficient value, the average restitution coefficient value and the average value of the maximum restitution coefficient region respectively include an expected value, an upper limit and a lower limit; the customized standard can be determined by the following method: determining the expected value based on the first reference value corresponding to the ball; determining the upper limit and the lower limit based on the expected value.

[0008] In some embodiments, the reference standard may include at least one of EARL V1.0 and EARL V2.0.

[0009] In some embodiments, performing a second processing on the image to be processed based on the processing parameters to obtain a normalized standard uptake value may include: performing the second processing on the image to be processed based on the processing parameters to determine a normalized image; and calculating the normalized standard uptake value based on the normalized image.

[0010] In some embodiments, the phantom image and the image to be processed are acquired based on the same acquisition conditions and reconstruction conditions.

[0011] One or more embodiments of the present specification provide a standard acquisition value normalization system, the system comprising: an acquisition module, for acquiring a model image, an image to be processed and a reference standard; a first determination module, for iteratively performing a first process on the model image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determining a customized standard as a normalization standard; a second determination module, for iteratively performing the first process on the model image to obtain a second reference value and processing parameters, and when the second reference value satisfies the normalization standard, performing a second process on the image to be processed based on the processing parameters to obtain a normalized standard acquisition value.

[0012] One or more embodiments of the present specification provide a standard uptake value normalization device, which includes at least one storage device and at least one processing device; the at least one storage device stores computer instructions; when the at least one processing device executes the computer instructions or part of the instructions, the standard uptake value normalization method described in the above embodiment is executed.

[0013] One or more embodiments of the present specification provide a non-transitory computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the standard uptake value normalization method described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0015] Figure 1 is a schematic diagram of an application scenario of a standard uptake value normalization system according to some embodiments of this specification;

[0016] Figure 2 is an exemplary module diagram of a standard uptake value normalization system according to some embodiments of the present specification;

[0017] Figure 3 is an exemplary flow chart of a method for normalizing a standard uptake value according to some embodiments of the present specification;

[0018] Figure 4A is a schematic diagram of a phantom according to some embodiments of the present specification;

[0019] Figure 4B is a schematic diagram of a phantom image according to some embodiments of the present specification;

[0020] Figure 5 is a schematic diagram showing that an upper bound, a lower bound, an expected value of RCmax in a reference standard shown in some embodiments of this specification and a first reference value corresponding to RCmax meet the reference standard;

[0021] Figure 6 is an exemplary flow chart for determining customization criteria according to some embodiments of this specification;

[0022] Figure 7 is an exemplary flow chart for determining a normalized standard uptake value according to some embodiments of the present specification;

[0023] Figure 8 It is a schematic diagram of semi-quantitative analysis based on normalized SUV according to some embodiments of this specification. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0025] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0026] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0027] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0028] Figure 1 It is a schematic diagram of an application scenario of a standard uptake value normalization system according to some embodiments of this specification.

[0029] like Figure 1 As shown, an application scenario 100 of a standard uptake value normalization system (hereinafter referred to as application scenario 100) may include a medical imaging device 110, a network 120, a terminal device 130, a processing device 140, and a storage device 150. The components in the application scenario 100 may be connected in various ways. For example, Figure 1 As shown, the medical imaging device 110 may be connected to the processing device 140 via the network 120 or directly connected to the processing device 140 (as shown by the double-headed arrow in the dashed line connecting the medical imaging device 110 and the processing device 140). The storage device 150 may be connected to the processing device 140 directly or via the network 120.

[0030] The medical imaging device 110 can scan the scanned object and / or generate data about the scanned object. Exemplarily, the medical imaging device 110 may include a CT device, a PET / CT device, an MRI / CT device, etc. In some embodiments of the present specification, the scanned object may also be referred to as a scanning object, a target object, a target, or a detected object. In some embodiments, the target object may be a patient, an animal, etc. In some embodiments, the target object may also be a phantom, etc. The target object enters the scanning area 115 through the examination bed 116, and the medical imaging device 110 scans the target object to obtain a medical image corresponding to the target object (such as a phantom image, an image to be processed, etc.).

[0031] The network 120 may include any suitable network that facilitates information and / or data exchange of the application scenario 100. In some embodiments, one or more components of the application scenario 100 (e.g., the medical imaging device 110, the terminal device 130, the processing device 140, and the storage device 150) may transmit information and / or data to one or more other components of the application scenario 100 via the network 120. For example, the processing device 140 may obtain a phantom image from the medical imaging device 110 via the network 120. In some embodiments, the network 120 may be any one or more of a wired network or a wireless network. In some embodiments, the network may be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0032] The terminal device 130 may include a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, etc. or any combination thereof. In some embodiments, the terminal device 130 may interact with other components in the application scenario 100 through the network 120. For example, the terminal device 130 may receive data such as a phantom image and an image to be processed sent by the medical imaging device 110. In some embodiments, the terminal device 130 may receive information and / or instructions input by a user (e.g., a user of the medical imaging device 110, such as a doctor), and send the received information and / or instructions to the medical imaging device 110 or the processing device 140 via the network 120. For example, a doctor may input an operation instruction for the medical imaging device 110 through the terminal device 130. In some embodiments, the terminal device 130 may display a phantom image, an image to be processed, etc. In some embodiments, the terminal device 130 may also be integrated with the medical imaging device 110.

[0033] In some embodiments, the terminal device 130 may include a display interface for displaying relevant information of the medical image. For example, the display interface may display a phantom image, an image to be processed, and related image parameters.

[0034] The processing device 140 may process data and / or information obtained from the medical imaging device 110, the terminal device 130 and / or the storage device 150. For example, the processing device 140 may obtain a phantom image, an image to be processed and a reference standard; iteratively perform a first process on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determine the customized standard as the normalization standard; iteratively perform a first process on the phantom image to obtain a second reference value and a processing parameter, and when the second reference value satisfies the normalization standard, perform a second process on the image to be processed based on the processing parameter to obtain a normalized standard acquisition value.

[0035] In some embodiments, the processing device 140 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. The processing device 140 can be directly connected to the medical imaging device 110, the terminal device 130 and the storage device 150 to access the stored or acquired information and / or data. In some embodiments, the processing device 140 can be implemented on a cloud platform. As an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any combination thereof.

[0036] The storage device 150 may store data and / or instructions. In some embodiments, the storage device 150 may store data obtained from the medical imaging device 110, the terminal device 130, and / or the processing device 140. For example, the storage device 150 may store a phantom image obtained by scanning a phantom, etc. In some embodiments, the storage device may also be used to store the EARL standard. In some embodiments, the storage device 150 may store data and / or instructions used by the processing device 140 to execute the exemplary methods described in this specification. In some embodiments, the storage device 150 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 150 may be implemented on a cloud platform.

[0037] In some embodiments, the storage device 150 may be connected to the network 120 to communicate with one or more components of the application scenario 100 (e.g., the medical imaging device 110, the terminal device 130, the processing device 140, etc.). One or more components of the application scenario 100 may access data or instructions stored in the storage device 150 via the network 120. In some embodiments, the storage device 150 may be directly connected to or communicate with one or more components of the application scenario 100. In some embodiments, the storage device 150 may be part of the processing device 140.

[0038] Figure 2is an exemplary module diagram of a standard uptake value normalization system according to some embodiments of this specification. Figure 2 As shown, the standard uptake value normalization system 200 (hereinafter referred to as system 200 ) may include an acquisition module 210 , a first determination module 220 , and a second determination module 230 .

[0039] The acquisition module 210 may be used to acquire a phantom image, an image to be processed, and a reference standard. In some embodiments, the acquisition module 210 may include a medical imaging device 110. For more information about the medical imaging device 110, see Figure 1 .

[0040] In some embodiments, the reference standard may include at least one of EARL V1.0 and EARL V2.0.

[0041] In some embodiments, the phantom image and the image to be processed are acquired based on the same acquisition conditions and reconstruction conditions.

[0042] The first determination module 220 may be configured to iteratively perform a first process on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determine the customized standard as the normalized standard.

[0043] In some embodiments, customization criteria may be determined based on obtaining user input parameters.

[0044] In some embodiments, the user input parameter may include a first reference value corresponding to the ball in the phantom.

[0045] In some embodiments, the customized standard may include a maximum restitution coefficient value, an average restitution coefficient value, and an average value of a maximum restitution coefficient region, wherein the maximum restitution coefficient value, the average restitution coefficient value, and the average value of a maximum restitution coefficient region respectively include an expected value, an upper limit, and a lower limit; the customized standard is determined by the following method: based on the first reference value corresponding to the ball, determining the expected value; based on the expected value, determining the upper limit and the lower limit.

[0046] The second determination module 230 can be used to iteratively perform a first process on the model image to obtain a second reference value and a processing parameter. When the second reference value meets the normalization standard, a second process is performed on the image to be processed based on the processing parameter to obtain a normalized standard acquisition value.

[0047] In some embodiments, the second determination module 230 is further used to perform a second process on the image to be processed based on the processing parameters to determine a normalized image; and calculate a normalized standard uptake value based on the normalized image.

[0048] For more descriptions of the technical features or parameters (such as phantom images, images to be processed, reference standards, first processing, etc.) involved in the above modules, please refer to other parts of this specification (such as Figure 3 ) is described here and will not be repeated here.

[0049] In some embodiments, the system 200 may further include multiple other modules not shown in the figure, for example, a display module with a display function, a communication module for realizing connection and interaction between various modules, etc.

[0050] It should be noted that the above description of the standard uptake value normalization system 200 and its modules is only for the convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 2 The acquisition module 210, the first determination module 220 and the second determination module 230 disclosed in the specification can be different modules in a system, or one module can realize the functions of two or more modules. Such variations are within the protection scope of this specification.

[0051] Figure 3 is an exemplary flow chart of a method for normalizing a standard uptake value according to some embodiments of the present specification. In some embodiments, process 300 may be performed by a standard uptake value normalization system 200 or a processing device 140. Figure 3 As shown, process 300 includes the following steps.

[0052] Step 310: Acquire a phantom image, an image to be processed, and a reference standard.

[0053] The phantom image may refer to an image obtained by image acquisition and image reconstruction based on the perfusion of radioactive substances into the phantom. Image acquisition may refer to obtaining the aggregation of radioactive substances in the phantom, and image reconstruction may refer to imaging based on the aggregation of radioactive substances (such as positron emission tomography, i.e., PET). The phantom includes a plurality of small balls, and the plurality of small balls may represent organs, tissues, etc. in the target object (such as the human body), and the volumes of the plurality of small balls may be different. The following will be explained by taking the phantom including 6 small balls as an example.

[0054] Figure 4A is a schematic diagram of a phantom according to some embodiments of the present specification; Figure 4B is a schematic diagram of a phantom image according to some embodiments of this specification. Figure 4AAs shown, the phantom 410 includes 6 small balls. The phantom image is obtained by perfusing the phantom with radioactive substances and collecting images of the phantom. In some embodiments, when the phantom is perfused with radioactive substances, the perfusion concentration of the background and the 6 small balls in the phantom is 1:10. The phantom image is shown in FIG. Figure 4B As shown, the highlighted part represents 6 small balls and the rest represents the background.

[0055] The image to be processed may refer to an image that needs to be processed for medical analysis. For example, the image to be processed may include a human body image, etc. In some embodiments, the human body image may be a PET image.

[0056] In some embodiments, the phantom image and the image to be processed can be acquired by the processing device controlling the acquisition module 210 to acquire images of the phantom and the patient.

[0057] In some embodiments, the phantom image and the image to be processed can be acquired based on the same acquisition conditions and reconstruction conditions. Exemplarily, the same acquisition conditions may include the same image acquisition time when acquiring the phantom image and the image to be processed, the concentration of radioactive substances injected before acquisition, the scanning speed, the acquisition mode, the attenuation correction, etc.; the same reconstruction conditions may include the same image reconstruction conditions of the phantom image and the image to be processed, such as the same image reconstruction algorithm, etc.

[0058] The reference standard may refer to a standard for normalizing a universal standard uptake value. In some embodiments, the reference standard may include at least one of EARL V1.0 and EARL V2.0. Among them, the EARL standard is a range obtained based on the NEMA IQ phantom database, including the standard range that needs to be met after the RC curve of the 6 small balls in the phantom is normalized, that is, the upper limit, lower limit and expected value. EARL V1.0 and EARL V2.0 are different versions with different publication times. The NEMA IQ phantom refers to a physical model designed and produced based on the standards of the National Electrical manufacturers Association (NEMA), which is mainly used for standardized verification of the performance of the emission computed tomography (ECT) system of nuclear medicine. Exemplarily, Table 1 shows the RCmax values ​​and RCmean values ​​corresponding to the 6 small balls in EARL V1.0, and their corresponding upper limits, lower limits and expected values. Table 1

[0059] Among them, RCmax value refers to the restitution coefficient calculated based on SUVmax, RCmean value refers to the restitution coefficient calculated based on SUVmean, Expected RC, Min RC, Max RC represent the expected value, lower bound and upper bound of RCmax or RCmean respectively, and Sphere Volume refers to the volume of the sphere. For more information about SUVmax and SUVmean, see Figure 7 and its related description.

[0060] The recovery coefficient curve (RC curve) can represent the curve formed by the ratio of the radioactivity ratio of multiple small balls actually monitored after the radioactive material is perfused to the activity ratio of the perfused radioactive material. For example, when the phantom is perfused with radioactive material, the perfusion concentration of 6 small balls is 10, the background perfusion concentration is 1, and the activity ratio is 10 / 1=10; while the perfusion concentration of a small ball actually monitored is 9, the background perfusion concentration is 0.95, and the activity ratio is about 9.47, then the recovery coefficient of the small ball is 9.47 / 10=0.947.

[0061] In some embodiments, the processing device 140 may obtain the reference standard from the storage device 150. The reference standard in the storage device 150 may be input in advance by the user or automatically imported by the system.

[0062] Step 320 , iteratively performing a first process on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determining the customized standard as the normalized standard.

[0063] The first processing may refer to performing image post-processing (such as Gaussian filtering) on ​​the phantom image. Exemplarily, the first processing may include performing multiple iterations of the RC curve of the phantom image through Gaussian filtering, wherein the Gaussian filter size of each iteration may be different.

[0064] The first reference value may refer to an RC parameter obtained by iteratively performing a first processing on the phantom image so that the RC curve of the phantom image meets the reference standard. In some embodiments, the first reference value may include a maximum restitution coefficient value (RCmax), an average restitution coefficient value (RCmean), and a maximum restitution coefficient regional average value (RCpeak). The maximum restitution coefficient regional average value (RCpeak) may refer to a restitution coefficient calculated based on SUVpeak. For more information about SUVpeak, see Figure 7In some embodiments, the first reference value may also be represented by an RC curve, that is, a curve formed by connecting the RC values ​​of the six balls of the phantom obtained after the first processing. Correspondingly, the RC curve corresponding to the first reference value may also include three types corresponding to RCmax, RCmean, and RCpeak, respectively. Exemplarily, the first reference value corresponding to RCmax may be as follows: Figure 5 Curve 513 is shown.

[0065] In some embodiments, the processing device may perform multiple iterative processes on the RC curve of the phantom image through Gaussian filtering to obtain the first reference value.

[0066] In some embodiments, the condition for stopping iteration may include that the iteration reaches a maximum number of times or the first reference value satisfies a reference standard.

[0067] In some embodiments, the processing device can determine whether the first reference value meets the reference standard in a variety of ways based on the RC curve of the phantom image. For example, the processing device can determine whether the first reference value meets the reference standard by determining whether the RC curve corresponding to the first reference value falls within the upper and lower bounds of the RC curve corresponding to the reference standard. In some embodiments, the processing device can determine the difference between the first reference value and the expected value in the reference standard, and determine whether the difference satisfies less than or equal to 10% of the expected value. If so, it can be determined that the first reference value meets the reference standard, that is, the RC curve corresponding to the first reference value falls within the upper and lower bounds of the RC curve corresponding to the reference standard.

[0068] Figure 5 It is a schematic diagram showing that the upper limit, the lower limit, the expected value of RCmax in the reference standard shown in some embodiments of this specification and the first reference value corresponding to RCmax meet the reference standard.

[0069] like Figure 5 As shown, curve 511 represents the curve corresponding to the RCmax value of the six balls of the model image before the first processing; curve 512 represents the curve corresponding to the upper limit of the RCmax value of the six balls of the model in the reference standard; curve 513 represents the curve corresponding to the RCmax value of the first reference value of the six balls of the model; curve 514 represents the curve corresponding to the expected value of the RCmax value of the six balls of the model in the reference standard; curve 515 represents the curve corresponding to the lower limit of the RCmax value of the six balls of the model in the reference standard. Figure 5 It can be seen that the first reference value (curve 513) obtained after multiple iterations of the RC curve (curve 511) of the phantom image falls between the upper limit (curve 512) and the lower limit (curve 515) of the RCmax value of the reference standard, which means that the first reference value meets the reference standard.

[0070] Similarly, the processing device may determine whether the first reference values ​​corresponding to RCmean and RCpeak meet the reference standard based on the same method.

[0071] In some embodiments, in response to the first reference value not satisfying the reference standard, the processing device may determine the customized standard as the normalized standard. The first reference value not satisfying the reference standard may refer to any one of RCmax, RCmean, and Rcpeak not satisfying the range of the upper and lower limits of the RC curves respectively corresponding to the reference standard.

[0072] Customized standards are user-defined normalization standards for standard uptake values.

[0073] In some embodiments, customization criteria may be determined based on user input parameters.

[0074] The user input parameters may refer to the parameters input by the user for determining the customized standard. The user input parameters may include the first reference values ​​corresponding to the six balls in the phantom.

[0075] In some embodiments, the first reference value corresponding to the ball in the phantom input by the user may include an RCmax value, an RCmean value, and an RCpeak value. In some embodiments, the processing device may determine the user input parameter based on the first reference value that does not meet the reference standard. For example, see Figure 5 If the RCmax value corresponding to the curve corresponding to the first reference value (curve 513) does not meet the reference standard, the user can determine the RC values ​​of the six balls as input parameters based on the specific values ​​of the six balls on the curve 513. In some embodiments, the input RC value can be a value within a proximity range (such as 0.1%, 0.2%, etc.) of the RC values ​​of the balls on the curve 513.

[0076] In some embodiments, the customized standard may include a maximum restitution coefficient value, an average restitution coefficient value, and a maximum restitution coefficient region average value, wherein the maximum restitution coefficient value, the average restitution coefficient value, and the maximum restitution coefficient region average value include an expected value, an upper limit, and a lower limit, respectively. The processing device determining the customized standard may include: determining an expected value based on a first reference value corresponding to the ball; determining an upper limit and a lower limit based on the expected value. For more information on related content, see Figure 6 .

[0077] A normalization standard may refer to a standard to which a standard uptake value is normalized.

[0078] In some embodiments, when the first reference value satisfies the reference standard, the processing device may determine the reference standard as the normalized standard.

[0079] In some embodiments, when the first reference value does not satisfy the reference standard, the processing device may determine the customized standard as the normalized standard.

[0080] Step 330, iteratively perform a first processing on the phantom image to obtain a second reference value and a processing parameter. When the second reference value meets the normalization standard, perform a second processing on the image to be processed based on the processing parameter to obtain a normalized standard acquisition value.

[0081] The second reference value may refer to the RC parameter obtained when the first processing is performed iteratively on the RC curve of the phantom image so that the normalized RC curve of the phantom image meets the normalization standard (customized standard). The difference between the second reference value and the first reference value is that the number of iterations in the first processing and the corresponding Gaussian filter size may be different. In some embodiments, the second reference value may include the highest recovery coefficient value (RCmax value), the average recovery coefficient value (RCmean value) and the average value of the highest recovery coefficient area (RCpeak value). In some embodiments, the second reference value may also be represented by an RC curve. Correspondingly, the RC curve corresponding to the second reference value may also include an RCmax curve, an RCmean curve and an RCpeak curve.

[0082] The processing parameter may refer to the size of the Gaussian filter corresponding to the first processing when the first processing is performed on the model image to obtain the second reference value. In some embodiments, the processing parameter may include the size of the Gaussian filter for Gaussian filtering the RCmax curve, RCmean curve, and RCpeak curve corresponding to the second reference value, which may be represented by Filter-max, Filter-mean, and Filter-peak, respectively. In some embodiments, the processing parameter may also include other possible parameters, which are not limited here.

[0083] In some embodiments, the processing device may perform multiple iterations of the RC curve of the phantom image through Gaussian filtering to obtain the second reference value, and record the Gaussian filter size of each iteration as a processing parameter.

[0084] In some embodiments, the iteration is stopped when the second reference value meets the normalization criterion, and the Gaussian filter size at this time is recorded.

[0085] In some embodiments, the method by which the processing device determines whether the second reference value meets the normalization standard is similar to the description of determining whether the first reference value meets the reference standard. For details of the relevant description, please refer to step 320.

[0086] In some embodiments, when the second reference value meets the normalization criterion, the processing device can perform a second process on the image to be processed based on the processing parameter to obtain a normalized standard acquisition value. It is worth noting that the processing parameter for the second process on the image to be processed is the Gaussian filter size of the last first process iterated on the RC curve of the phantom image, that is, the Gaussian filter size when the second reference value meets the normalization criterion.

[0087] The second processing may refer to Gaussian filtering processing performed on the image to be processed based on the parameters to be processed. In some embodiments, the second processing may include performing a Gaussian filtering processing on the image to be processed based on the parameters to be processed.

[0088] The normalized standard uptake value refers to the normalized standard uptake value that can be comparable across devices, patients, and time. That is, the normalized standard uptake value is the standard uptake value that can be obtained for quantitative analysis after eliminating the effects of different devices, different acquisition parameters, and different reconstruction methods and reconstruction parameters to a certain extent.

[0089] In some embodiments, the processing device performs a second processing on the image to be processed based on the processing parameters to obtain a normalized standard uptake value, which may include: performing a second processing on the image to be processed based on the processing parameters to determine a normalized image; and calculating a normalized standard uptake value based on the normalized image.

[0090] In one or more embodiments of the present specification, through the standard uptake value normalization method, a customized normalization standard can be provided when the reference normalization standard cannot meet the application needs, so as to overcome the problem of incomparable standard uptake values ​​caused by different device models or reconstruction algorithms, and achieve comparability of standard uptake values ​​across devices, patients, and time, that is, the standard uptake values ​​can be used for clinical analysis to meet clinical needs.

[0091] Figure 6 600 is an exemplary flow chart for determining customized standards according to some embodiments of the present specification. In some embodiments, process 600 may be performed by the standard intake value normalization system 200 or the processing device 140. Figure 6 As shown, process 600 includes the following steps.

[0092] Step 610, determining an expected value based on the first reference value corresponding to the ball.

[0093] In some embodiments, the processing device may determine the expected value based on the first reference value corresponding to the ball. The first reference value may include values ​​defined under three definitions: RCmax, RCmean, and RCpeak, and the corresponding expected value also corresponds to values ​​defined under three definitions: RCmax, RCmean, and RCpeak. The first reference value may be obtained based on user input. For more information about the first reference value and obtaining the first reference value based on user input, see Figure 3 .

[0094] In some embodiments, the processing device may determine the first reference value corresponding to the ball input by the user as the expected value in the customized standard. Taking the determination of the expected value of the RCmax value in the customized standard as an example, the RCmax values ​​of the six balls input by the customer based on the first reference value under the RCmax definition are RCmax1 to RCmax6, respectively, and the processing device may determine RCmax1 to RCmax6 as the expected values ​​of the RCmax values ​​corresponding to the six balls in the customized standard. The method for determining the expected values ​​of the RCmean value and the RCpeak value is similar and will not be repeated here.

[0095] Step 620, determine the upper bound and the lower bound based on the expected value.

[0096] In some embodiments, the processing device may determine the upper and lower bounds of the RC value corresponding to the customized standard based on the expected value in the customized standard. In some embodiments, the processing device may increase or decrease the expected value corresponding to the customized standard by a preset value to determine the upper and lower bounds in the customized standard. The preset value may be preset in advance based on experience or set by system default. As an example only, the preset value may be 5% of the expected value. When the expected value of the RCmax value of a certain ball in the customized standard is RCmax1, the upper bound of the RCmax value corresponding to the ball is RCmax1*(1+5%), and the lower bound is RCmax1*(1-5%). For exemplary purposes only, Table 2 shows the RCmax values ​​of the customized standards corresponding to the six balls. Table 2

[0097] Among them, Expected RCmax, Min RCmax, and Max RCmax represent the expected value, lower bound, and upper bound of the customized standard RCmax value, respectively, and Sphere Volume refers to the volume of the sphere. The expected value, upper bound, and lower bound defined by RCmean and RCpeak in the customized standard and their determination methods are similar to those of the expected value, upper bound, and lower bound defined by RCmax, and are not described here.

[0098] In some embodiments, the processing device may also determine the customized standard based on the standard determination model, including: processing the first reference value, the reference standard, the device parameter, the acquisition condition, and the reconstruction condition through the standard determination model to determine the customized standard. The standard determination model is a machine learning model, such as a neural network model, a deep neural network, or other custom models.

[0099] In some embodiments, the input of the standard determination model may include a first reference value, a reference standard, device parameters, acquisition conditions, reconstruction conditions, etc. Among them, the device parameters, acquisition conditions, and reconstruction conditions may be determined based on the device (i.e., the medical imaging device 110) that acquires the phantom image and the image to be processed. For more information about the first reference value, reference standard, acquisition conditions, and reconstruction conditions, please refer to other parts of this specification, such as Figure 3 .

[0100] In some embodiments, the output of the standard determination model may include customized standards. The customized standards output by the standard determination model may be represented in the form of a matrix. Each column in the matrix represents three different definitions RCmax, RCmean and RCpeak, and each row represents the expected value, upper bound and lower bound under each definition.

[0101] In some embodiments, the standard determination model can be trained and acquired based on labeled training samples for an initial standard determination model without set parameters. The training samples can be acquired based on historical data, including a large number of reference standards, multiple sets of historical first reference values ​​acquired by multiple iterations of the RC curve of the model image through historical Gaussian filtering, equipment parameters during historical image acquisition and reconstruction, historical acquisition conditions, historical reconstruction conditions, etc. The labels of the training samples can be the upper and lower bounds and expected values ​​corresponding to each set of historical first reference values, and can be acquired through manual annotation based on experience. For example, the values ​​corresponding to the 6 balls in each set of historical first reference values ​​can be determined as the expected values ​​of the 6 balls, and the expected values ​​can be added or subtracted with preset values ​​as the upper and lower bounds to determine the labels.

[0102] An exemplary training process may include: inputting a large number of labeled training samples into the initial standard determination model, updating the parameters of the initial standard determination model through training until the loss function is less than a threshold, converges, or the training cycle reaches a threshold, etc., to obtain a trained standard determination model.

[0103] In one or more embodiments of the present specification, the customized standards determined by the machine learning model are more accurate, and can obtain better normalization effect of standard uptake values, improve efficiency, and save costs.

[0104] In some embodiments, the processing device may send the reference standard and the customized standard to the terminal device 130 , and determine the normalization standard through user selection.

[0105] In some embodiments, the normalization standard can also be determined based on the processing device. For example, a phantom image is acquired, and the RC curve of the phantom image is first processed multiple times based on Gaussian filtering, and the RC curve of the phantom image after iteration is compared with the reference standard and the customized standard, and it is determined whether the error between the expected value of the reference standard and the customized standard exceeds a preset threshold (such as 10% of the expected value), and the standard whose error does not exceed the preset threshold is selected as the normalization standard.

[0106] In one or more embodiments of the present specification, the customized standard determined based on the above method can solve the problem that the reference standard cannot meet clinical needs in some cases, so that the standard uptake value can be normalized smoothly.

[0107] Figure 7 700 is an exemplary flow chart for determining a normalized standard uptake value according to some embodiments of the present specification. In some embodiments, process 700 may be executed by a processing device. Figure 7 As shown, process 700 includes the following steps.

[0108] Step 710: Perform a second process on the image to be processed based on the processing parameters to determine a normalized image.

[0109] The normalized image refers to the image to be processed after the second processing. In some embodiments, the processing device can perform the second processing on the image to be processed based on the processing parameters when the RC curve of the phantom image meets the normalization standard to determine the normalized image. For more information about the second processing, the image to be processed, and the processing parameters, please refer to Figure 3 .

[0110] Step 720, calculating a normalized standard uptake value based on the normalized image.

[0111] The standard uptake value (SUV) includes SUVmax, SUVmean, and SUVpeak. In some embodiments, the standard uptake value of the image to be processed can be obtained based on image-based visual judgment of the image to be processed. For example, image recognition and processing based on machine vision. Among them, SUVmax refers to the maximum value of SUV of all pixels in ROI (Region Of Interest); SUVmean refers to the average value of SUV of all pixels in ROI; SUVpeak refers to the average value of SUV of a small area (such as 1cm) inside ROI. 3 The maximum value among the average SUV values ​​of the pixels in the image.

[0112] In some embodiments, the processing device can further calculate the tumor metabolic volume (MTV) and the total glycolysis (TLG) of the lesion area based on the standard uptake value (SUV). Exemplarily, MTV can be calculated by a percentage threshold method, such as MTV=40%SUVmax; TLG can be determined based on the MTV of the lesion and the SUVmean value in the area, for example, TLG=MTV×SUVmean.

[0113] In some embodiments, in order to achieve the comparability of standard uptake values ​​across devices, patients, and time to meet clinical needs, the processing device can calculate the normalized standard uptake values ​​based on the normalized image to be processed, which can be expressed as u.SUVmean, u.SUVmax, and u.SUVpeak, respectively. Furthermore, the processing device can synchronously update the clinical emerging indicators MTV and TLG based on the u.SUVmean, u.SUVmax, and u.SUVpeak values ​​to obtain the normalized MTV and TLG, which can be expressed as u.MTV and u.TLG, respectively. Among them, the calculation method of u.MTV and u.TLG is the same as the calculation method of MTV and TLG, and the details can be found above.

[0114] The processing device may transmit the determined MTV, TLG and / or u.MTV and u.TLG to the terminal device 130 for clinical application by the user.

[0115] It should be noted that the above descriptions of processes 300, 600, and 700 are only for illustration and description, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to processes 300, 600, and 700 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0116] Figure 8 It is a schematic diagram of semi-quantitative analysis based on normalized SUV according to some embodiments of this specification.

[0117] like Figure 8 As shown, the processing device can scan and reconstruct images based on the PET / CT device, including scanning and reconstructing the phantom and the object to be processed (i.e., the object to be clinically diagnosed) to obtain the phantom image and the image to be processed. For more information on obtaining the phantom image and the image to be processed, please refer to other parts of this manual, such as Figure 1 , Figure 2 , Figure 3 wait.

[0118] In some embodiments, when semi-quantitative analysis of SUV is required, the processing device may determine a normalization standard and determine the normalized SUV based on the normalization standard. Specifically, as follows:

[0119] Continue to see Figure 8 , the processing device can determine the processing parameters based on the steps shown in 810.

[0120] like Figure 8 As shown, 810 includes iteratively performing a first processing on the model image to obtain a first reference value. The processing device can determine whether the first reference value meets the reference standard (i.e., EARL standard, including at least one of EARL V1.0 and EARL V2.0) or the customized standard, and determine the standard met by the first reference value as the normalization standard. For more information about the first reference value, reference standard, customized standard, and determining the normalization standard, please refer to other parts of this specification, such as Figure 3 , Figure 6 wait.

[0121] After the normalization standard is determined, the processing device can determine the processing parameters based on the normalization standard, including: iteratively performing a first processing on the model image to obtain a second reference value and processing parameters, and when the second reference value meets the normalization standard, determining the Gaussian filter size of the last iterative first processing as the processing parameter for the second processing of the image to be processed. The processing device can process the image to be processed based on the processing parameters, obtain the normalized image, calculate the normalized SUV value based on the normalized image, and synchronously modify the MTV and TLG, and generate u.MTV and u.TLG accordingly, and use the generated u.MTV and u.TLG for clinical application. For more information about the second reference value and processing parameters, please refer to other parts of this manual, such as Figure 3 wait.

[0122] In some embodiments, when semi-quantitative analysis of SUV is not required, the processing device can calculate the SUV value (including SUVmax value, SUVmean value and SUVpeak value) of the image to be processed based on the image to be processed by a method based on image visual judgment, and further calculate the MTV and TLG based on the standard uptake value (SUV), and apply the obtained MTV and TLG clinically.

[0123] In some embodiments of the present specification, a standard uptake value normalization device is also provided, which includes at least one storage device and at least one processing device; the at least one storage device stores computer instructions; when the at least one processing device executes the computer instructions or part of the instructions, the standard uptake value normalization method described in any of the above embodiments is executed.

[0124] In some embodiments of the present specification, a non-transitory computer-readable storage medium is also provided, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the standard uptake value normalization method as described in any of the above embodiments.

[0125] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) Through the standard uptake value normalization method, when the reference normalization standard cannot meet the application needs, a customized normalization standard can be provided to overcome the problem of incomparable standard uptake values ​​caused by different device models or reconstruction algorithms, so as to achieve cross-device, cross-patient, and cross-time comparability of standard uptake values ​​to meet clinical needs; (2) The customized standard determined by the machine learning model is more accurate, and a better standard uptake value normalization effect can be obtained, thereby improving processing efficiency.

[0126] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0127] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0128] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0129] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0130] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0131] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0132] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for normalizing a standard uptake value, characterized in that: The method is performed by a processing device and includes: Acquire phantom images, images to be processed, and reference standards; Iteratively performing a first process on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determining a customized standard as a normalized standard; The first processing is iteratively performed on the phantom image to obtain a second reference value and processing parameters, and when the second reference value meets the normalization standard, a second processing is performed on the image to be processed based on the processing parameters to obtain a normalized standard uptake value.

2. The method according to claim 1, characterized in that The customization criteria are determined based on obtaining user input parameters.

3. The method according to claim 2, characterized in that The user input parameter includes the first reference value corresponding to the ball in the phantom.

4. The method according to claim 3, characterized in that The customized standard includes a maximum restitution coefficient value, an average restitution coefficient value, and an average value of a maximum restitution coefficient region, wherein the maximum restitution coefficient value, the average restitution coefficient value, and the average value of a maximum restitution coefficient region respectively include an expected value, an upper bound, and a lower bound; the customized standard is determined by the following method: Determining the expected value based on the first reference value corresponding to the ball; Based on the expected value, the upper bound and the lower bound are determined.

5. The method according to claim 1, characterized in that The reference standard includes at least one of EARL V1.0 and EARL V2.

0.

6. The method according to claim 1, characterized in that The performing a second processing on the image to be processed based on the processing parameters to obtain a normalized standard uptake value comprises: Performing the second processing on the image to be processed based on the processing parameters to determine a normalized image; The normalized standard uptake value is calculated based on the normalized image.

7. The method according to claim 1, characterized in that The phantom image and the image to be processed are acquired based on the same acquisition conditions and reconstruction conditions.

8. A standard uptake value normalization system, characterized in that: The system comprises: An acquisition module, used to acquire a phantom image, an image to be processed, and a reference standard; A first determination module is configured to iteratively perform a first process on the phantom image to obtain a first reference value, and in response to the first reference value not satisfying the reference standard, determine the customized standard as the normalized standard; The second determination module is used to iteratively perform the first processing on the model image to obtain a second reference value and processing parameters, and when the second reference value meets the normalization standard, perform a second processing on the image to be processed based on the processing parameters to obtain a normalized standard acquisition value.

9. A standard uptake value normalization device, characterized in that: The apparatus comprises at least one storage device and at least one processing device; the at least one storage device stores computer instructions; when the at least one processing device executes the computer instructions or part of the instructions, the method according to any one of claims 1 to 7 is executed.

10. A non-transitory computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 7.

Images