A scanning method, system and device for nuclear medicine equipment

Abstract

The embodiments of the present specification provide a scanning method, system and device for nuclear medicine equipment. The scanning method for nuclear medicine equipment includes: acquiring a first scanned image of a patient; determining a first target area in the first scanned image; determining a first signal-to-noise ratio of the first target area; and determining whether a supplemental scan or a rescan is required based on the first signal-to-noise ratio.

Description

Technical Field

[0001] The present specification relates to scanning of nuclear medicine equipment, and more particularly, to a scanning method, system and apparatus for nuclear medicine equipment. Background Art

[0002] Nuclear medicine equipment refers to equipment that uses nuclear science and technology and means to diagnose and treat diseases. Nuclear medicine equipment may include positron emission tomography (PET) equipment, single-photon emission computed tomography (SPECT) equipment, gamma camera equipment, etc. When scanning with nuclear medicine equipment, the quality of the scanned images may vary, and users (such as doctors, operators, etc.) need to rely on experience to confirm whether a supplementary scan or rescan is needed. Obviously, manual judgment by users has low efficiency and accuracy.

[0003] Therefore, a scanning technology for nuclear medicine equipment is needed to confirm whether a supplementary scan or a rescan is needed. Summary of the invention

[0004] A first aspect of an embodiment of the present specification provides a scanning method for a nuclear medicine device, comprising: acquiring a first scanned image of a patient; determining a first target area in the first scanned image; determining a first signal-to-noise ratio of the first target area; and determining whether a supplemental scan or a rescan is required based on the first signal-to-noise ratio.

[0005] In some embodiments, determining the first target area in the first scan image includes: acquiring a second scan image of the patient; identifying a first area based on the second scan image; and determining the first target area in the first scan image based on the first area.

[0006] In some embodiments, determining whether supplemental scanning or rescanning is needed based on the first signal-to-noise ratio includes: comparing the first signal-to-noise ratio with a first threshold; and determining that supplemental scanning or rescanning is needed in response to the first signal-to-noise ratio being less than the first threshold.

[0007] In some embodiments, determining whether supplemental scanning or rescanning is needed based on the first signal-to-noise ratio includes: comparing the first signal-to-noise ratio with a first threshold; in response to the first signal-to-noise ratio being less than the first threshold, determining a second target area in the first scanned image; determining a second signal-to-noise ratio of the second target area; and determining whether supplemental scanning or rescanning is needed based on the second signal-to-noise ratio.

[0008] In some embodiments, the first target area is a liver area, and the second target area is a human body area other than the liver area.

[0009] In some embodiments, the second target area is different from the first target area.

[0010] In some embodiments, determining the need for supplemental scanning or rescanning based on the second signal-to-noise ratio includes: comparing the second signal-to-noise ratio with a second threshold; and determining the need for supplemental scanning or rescanning in response to the second signal-to-noise ratio being less than the second threshold.

[0011] In some embodiments, it also includes: when it is determined that a supplementary scan or a rescan is required, a prompt message is issued.

[0012] A second aspect of an embodiment of the present specification provides a scanning system for nuclear medicine equipment, comprising: an acquisition module, a target area determination module, a signal-to-noise ratio determination module and a supplemental / re-scanning determination module; the acquisition module is used to acquire a first scan image of a patient; the target area determination module is used to determine a first target area in the first scan image; the signal-to-noise ratio determination module is used to determine a first signal-to-noise ratio of the first target area; and the supplemental / re-scanning determination module is used to determine whether a supplemental scan or a re-scan is required based on the first signal-to-noise ratio.

[0013] A third aspect of an embodiment of the present specification provides a scanning device for nuclear medicine equipment, comprising: at least one storage device, including at least one set of instruction sets; and at least one processor for communicating with the at least one storage device, wherein when executing the instruction set, the at least one processor is used to instruct the system to execute the scanning method described in any of the preceding embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1 FIG. 1 is an exemplary schematic diagram of a scanning system 100 for a nuclear medicine device provided in some embodiments of the present specification.

[0016] Figure 2 is an exemplary flow chart of a scanning method 200 for a nuclear medicine device provided in some embodiments of the present specification.

[0017] Figure 3is an exemplary flow chart of a scanning method 300 for determining a first target area provided in some embodiments of the present specification.

[0018] Figure 4 It is an exemplary flow chart of a scanning method 400 for determining whether a supplementary scan or a rescan is required based on a first signal-to-noise according to some embodiments of the present specification.

[0019] Figure 5 It is an exemplary flow chart of a scanning method 500 for determining whether a supplementary scan or a rescan is required based on a first signal-to-noise provided in some other embodiments of the present specification.

[0020] Figure 6 It is an exemplary flow chart of a scanning method 600 for determining whether a supplementary scan or a rescan is required based on a second signal-to-noise according to some embodiments of the present specification.

[0021] Figure 7 is an exemplary module diagram of a scanning system 700 for a nuclear medicine device provided in some embodiments of the present specification. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The embodiments of this specification mainly relate to a scanning method for nuclear medicine equipment, which automatically calculates the SNR (Signal Noise Ratio) value of a region of interest (such as VOI (Volume of Interest) or ROI (Region of Interest)) on a typical organ (such as the liver), and determines whether to recommend a supplementary scan or a rescan based on the SNR value. In the process of determining whether to recommend a supplementary scan or a rescan, a reference area (i.e., an area with reference value outside the atypical organ (such as muscle, brain or other tissues with relatively uniform radionuclide uptake)) can also be introduced and its SNR value can be judged. Through this dual-area (or dual-tissue) judgment method, it can be ensured that only when the signal-to-noise ratio of the typical organ and the reference area is too low at the same time, it will trigger a reminder to the user that there is an image quality problem and recommend a supplementary scan or a rescan, thereby reducing the possibility of misjudgment.

[0024] Figure 1 FIG. 1 is an exemplary schematic diagram of a scanning system 100 for a nuclear medicine device provided in some embodiments of the present specification. Figure 1As shown, the scanning system 100 may include a scanning device 110 , a network 120 , one or more terminals 130 , a processor 140 , and a storage device 150 .

[0025] In some embodiments, the scanning device 110 may include a nuclear medicine device. The nuclear medicine device may include a PET scanning device, a SPECT scanning device, a gamma camera, etc. or any combination thereof. In some embodiments, the scanning device 110 may include a PET scanning device. In some embodiments, the scanning device 110 may include a SPECT scanning device. In some embodiments, the scanning device 110 may include a gamma camera. In some embodiments, the scanning device 110 may also include a CT scanning device, an MR scanning device, etc. In some embodiments, the scanning device 110 may include a PET-CT scanning device. In some embodiments, the scanning device 110 may include a PET-MR scanning device. In some embodiments, the scanning device 110 may include a SPECT-CT scanning device. In some embodiments, the scanning device 110 may include a SPECT-MR scanning device. In some embodiments, the scanning device 110 may include a gamma camera and a CT scanning device. In some embodiments, the scanning device 110 may include a gamma camera and an MR scanning device.

[0026] The network 120 may include any suitable network that can facilitate information and / or data exchange of the scanning system 100. In some embodiments, one or more components of the scanning system 100 (e.g., the scanning device 110, the terminal 130, the processor 140, the memory 150, etc.) may communicate information and / or data with one or more other components of the scanning system 100 via the network 120. For example, the processor 140 may obtain PET scan data and / or CT scan data from the scanning device 110 via the network 120. In some embodiments, the processor 140 may obtain user instructions from the terminal 130 via the network 120.

[0027] The terminal 130 may include a mobile device 131, a tablet computer 132, a laptop computer 133, or any combination thereof. In some embodiments, the terminal 130 may be a part of the processor 140. In some embodiments, the terminal 130 may be used to input user instructions, display scan results, etc. In some embodiments, the terminal 130 may issue a prompt message to prompt the user. In some embodiments, the terminal 130 may be used to display information such as a first signal-to-noise ratio and a second signal-to-noise ratio. In some embodiments, the terminal 130 may be used to display image information (such as PET images, CT images, MR images, etc.).

[0028] The processor 140 may process data and / or information obtained from the scanning device 110, the terminal 130, and / or the memory 150. In some embodiments, the processor 140 may obtain a first scanned image of the patient from the scanning device 110 and determine a target area in the first scanned image. In some embodiments, the processor 140 may determine a signal-to-noise ratio of the target area. In some embodiments, the processor 140 may determine whether a rescan or re-scan is required based on relevant information (such as a signal-to-noise ratio of the target area). In some embodiments, the processor 140 may instruct the terminal 130 to issue a prompt message when it is determined that a rescan or re-scan is required.

[0029] The memory 150 may store data, instructions, and / or any other information. In some embodiments, the memory 150 may store data obtained from the terminal 130 and / or the processor 140. In some embodiments, the memory 150 may store data and / or instructions, and the processor 140 and / or the terminal 130 may execute or use the data and / or instructions to implement the exemplary methods described in this specification. In some embodiments, the memory 150 may be connected to the network 120 to communicate with one or more other components of the scanning system 100 (e.g., the processor 140, the terminal 130, etc.). One or more components of the scanning system 100 may access the data or instructions stored in the memory 150 through the network 120. In some embodiments, the memory 150 may be directly connected to or communicate with one or more other components of the scanning system 100 (e.g., the scanning device 110, the processor 140, the terminal 130, etc.). In some embodiments, the memory 150 may be part of the processor 140.

[0030] Figure 2 2 is an exemplary flow chart of a scanning method 200 for a nuclear medicine device provided in some embodiments of the present specification. The scanning method 200 may include steps 210, 220, 230, and 240. In some embodiments, the scanning method 200 may be executed by the processor 140. In some embodiments, the scanning method 200 may be implemented by a scanning system 700 for PET scanning.

[0031] Step 210 , obtaining a first scan image of the patient. In some embodiments, step 210 may be implemented by the obtaining module 710 .

[0032] In some embodiments, the processor 140 may acquire the first scan image of the patient from the scanning device 110. In some embodiments, the processor 140 may acquire the first scan image of the patient from the memory 150.

[0033] The first scanned image of the patient refers to an image obtained by scanning the patient's body through a nuclear medicine device (such as a PET scanning device, a SPECT scanning device) of the scanning device 110. In some embodiments, the patient can be scanned in multiple beds, that is, each bed scans an area, and there will be an overlap ratio between two adjacent beds. After the scanning is completed, the images of each bed are stitched together, and then a complete image is output.

[0034] Step 220, determining a first target region in the first scanned image. In some embodiments, the first target region can be obtained by identifying the first scanned image using an image recognition model. In some embodiments, the first target region can be obtained by outlining in the first scanned image. In some embodiments, step 220 can be implemented by the target region determination module 720.

[0035] In some embodiments, the first target region refers to a region in the first scanned image used to determine image quality. In some embodiments, the first target region may be a region of interest on a typical organ. In some embodiments, the first target region may include the liver, aortic blood pool, ascending aorta / descending aorta, gluteus maximus, brain region, etc., or any combination thereof.

[0036] In some embodiments, the first target area can be obtained according to a corresponding area mapping in the second scan image.

[0037] In some embodiments, the processor 140 may acquire a second scanned image (such as a CT image or an MR image) of the patient, identify the first region based on the second scanned image, and determine the first target region in the first scanned image based on the first region. For more details on determining the first target region in the first scanned image, see Figure 3 and its related description.

[0038] Step 230 , determining a first signal-to-noise ratio of the first target area. In some embodiments, step 230 may be implemented by the signal-to-noise ratio determination module 730 .

[0039] The first signal-to-noise ratio refers to a ratio of a power spectrum of a signal to noise in the first target area in the first scanned image.

[0040] In some embodiments, the processor 140 may determine the first signal-to-noise ratio by approximately estimating the signal-to-noise ratio of the image. For example, the processor 140 may calculate the ratio of the variance of the signal to the noise of the first target area in the image. The specific calculation process may include: first calculating the local variance of all pixels in the first target area in the image, considering the maximum value of the local variance as the signal variance, and the minimum value of the local variance as the noise variance, then calculating the ratio of the signal variance to the noise variance, and finally correcting it with an empirical formula to obtain the first signal-to-noise ratio of the first target area. In some embodiments, the processor 140 may also determine the first signal-to-noise ratio of the first target area by other means, which is not limited in this specification.

[0041] In some embodiments, the first signal-to-noise ratio may be loaded simultaneously with the first scan image (eg, a PET scan image) and displayed on a display interface for the user to read.

[0042] Step 240 , based on the first signal-to-noise ratio, determine whether a rescan or re-scan is needed. In some embodiments, step 240 may be implemented by the rescan / re-scan determination module 740 .

[0043] In some embodiments, the supplementary scan refers to supplementing the current scan data with a period of time to obtain the supplementary scan data. For example, the current scan data is obtained after 3 minutes of scanning, and the supplementary scan is performed on the basis of the current scan data for 2 minutes to obtain the supplementary scan data; the current scan data and the supplementary scan data can be used together as the basis for generating the first scan image.

[0044] Rescanning refers to rescanning to obtain the first scanned image after rescanning. In some embodiments, the scanning parameters (such as scanning time) of the rescanning can be the same as the current scanning parameters. In some embodiments, the scanning parameters of the rescanning can be different from the current scanning parameters.

[0045] In some embodiments, the processor 140 directly determines whether a rescan or re-scan is required based on the comparison result of the first signal-to-noise ratio of the first target area and the first threshold. In some embodiments, the processor 140 may continue to determine the second target area based on the comparison result of the first signal-to-noise ratio and the first threshold, and then determine whether a rescan or re-scan is required based on the comparison result of the second signal-to-noise ratio of the second target area and the second threshold. For more details on determining whether a rescan or re-scan is required, see Figure 5 And related instructions.

[0046] In some embodiments, the supplemental scan or rescan may be performed on the first target area. In some embodiments, the supplemental scan or rescan may be performed on the bed where the first target area is located. In some embodiments, the supplemental scan or rescan may be performed on the first scanned image of the patient.

[0047] In some embodiments, method 200 may further include step 250 .

[0048] Step 250: When it is determined that supplementary scanning or rescanning is required, a prompt message is issued.

[0049] Prompt information refers to information that can be used to prompt the user of the scanning system 100 involved in the embodiments of this specification. The prompt information can be in the form of images, text, sound, vibration, etc. In some embodiments, the prompt information can be sent to the user through the terminal 130. For example, prompt information in the form of images, text, etc. is sent through the display screen of the terminal 130. For another example, prompt information in the form of vibration is sent through the vibration mode of the terminal 130. For another example, prompt information in the form of sound is sent through the speaker of the terminal 130. In some embodiments, the prompt information may include the time for rescanning, scanning parameters during rescanning, the location for rescanning / re-scanning, the reason for rescanning / or re-scanning, etc., or any combination thereof.

[0050] In some embodiments, if it is determined in step 240 that supplementary scanning or rescanning is not required, step 250 does not need to be performed, and the subsequent scanning is continued or the scanning is terminated according to the current scanning parameters.

[0051] In some embodiments, the processor 140 may execute step 210 after completing the PET scan of the patient's entire body. In some embodiments, the processor 140 may execute step 210 after completing the PET scan of a partial area of ​​the patient (such as a bed scanning area, an upper body area, a lower body area, etc.). In some embodiments, the processor 140 may execute steps 210, 220, 230, and 240 in a loop.

[0052] Figure 3 3 is an exemplary flow chart of a scanning method 300 for determining a first target area provided in some embodiments of the present specification. In some embodiments, the scanning method 300 may be executed by the processor 140. In some embodiments, each step in the scanning method 300 may be executed by the target area determination module 720.

[0053] Step 310: Acquire a second scan image of the patient.

[0054] The second scan image of the patient refers to an image obtained by scanning the patient's body through a scanning device (such as a CT scanning device, an MR scanning device). In some embodiments, the second scan image can be obtained by performing a CT scan on the patient's body through a CT scanning device. In some embodiments, when the patient undergoes a PET-CT scan, a CT scan can be performed based on a CT scanning device first, and then a PET scan can be performed based on a PET scanning device. In some embodiments, the processor 140 can obtain the second scan image of the patient from the CT scanning device or the memory 150.

[0055] Step 320: Identify a first area based on the second scanned image.

[0056] The first region refers to a region in the second scan image that corresponds to the first target region. For example, the first target region may be a liver region in the first scan image, and the first region may be a liver region in the second scan image.

[0057] In some embodiments, the processor 140 can identify the first area in the second scanned image through a machine learning model. The input of the machine learning model is the second scanned image, and the output can be the second scanned image with the first area marked. In some embodiments, the machine learning model can be trained using a GNN neural network model. In some embodiments, the machine learning model can be a pre-trained neural network model, and an interface is provided to be deployed in a product (such as the processor 140, the memory 150). In some embodiments, the machine learning model can be a deep learning model. In some embodiments, the machine learning model can be a model obtained based on 3D vnet segmentation network training.

[0058] In some embodiments, the training sample data may be preprocessed before training the machine learning model. For example, the liver sequence images may be enhanced by CLAHE, and the images may be adjusted to 256*256 size. For another example, the sequence images of the entire liver and the annotated data of the liver region ROI may be stored as .nii format data using the itk tool.

[0059] In some embodiments, the machine learning model can use the network model 2.5D V-net. The improvement of this network based on the traditional V-Net is that it does not have the high hardware GPU requirements required for 3D training, and can fully utilize the channel information of the image. The data with an input size of [256, 256, 64] can be divided into two branches, one branch is a convolution operation in the channel direction, the convolution kernel size is 1x1, and the other branch is a convolution operation in the x, y plane, and the convolution kernel size is 3x3; finally, the two branches can merge the data in the channel direction for the next downsampling operation.

[0060] Step 330: Determine a first target area in the first scanned image based on the first area.

[0061] In some embodiments, the processor 140 may map the first region to the PET space through a registration matrix to determine the first target region in the first scan image. The registration matrix refers to a transformation matrix that transforms the coordinate system in the second scan image to the coordinate system in the first scan image, and the registration matrix may realize the correspondence between the second scan image and the first scan image.

[0062] Figure 3 The scanning method 300 shown can determine the first target area in the first scanned image based on the second scanned image. And because the machine learning model is used to identify the first area in the second scanned image, the process of identifying the first area has the characteristics of fast speed and high accuracy.

[0063] Figure 4 It is an exemplary flow chart of a scanning method 400 for determining whether a supplementary scan or a rescan is required based on a first signal-to-noise ratio provided in some embodiments of the present specification.

[0064] Step 410: compare the first signal-to-noise ratio with a first threshold.

[0065] The first threshold value may be a value preset for the first target area in the first scanned image. In some embodiments, the first threshold value may be determined based on the user's clinical experience with the first scanned image. In some embodiments, the first threshold value may be input by the user through the terminal 130 and stored in the memory 150.

[0066] If the first signal-to-noise ratio is greater than or equal to the first threshold, the processor 140 may determine that the first scan image is qualified.

[0067] If the first signal-to-noise ratio is less than the first threshold, the first scanned image may have several situations:

[0068] First, there is a large amount of noise in the first scanned image. If this is the case, the processor 140 may determine that the first scanned image is unqualified.

[0069] The second is that there is a lesion in the first target area of ​​the first scanned image. In this case, the lesion will affect the calculation of the signal-to-noise ratio, and the processor 140 cannot directly determine whether the first scanned image is qualified, and further analysis is required;

[0070] The third type is that there are obvious artifacts in the first scan image (such as respiratory artifacts that may exist in the liver area). The artifacts will affect the signal-to-noise ratio calculation, and the processor 140 cannot directly determine whether the first scan image is qualified, and further analysis is required.

[0071] In some embodiments, when the first signal-to-noise ratio is less than the first threshold, in order to make the judgment more accurate, the second scanned image and the second target area can be introduced as references, and the determination is made according to the size relationship between the second signal-to-noise ratio and the second threshold. For the specific determination process, please refer to the description of Figure 5 , Figure 6 Description content.

[0072] In some embodiments, if the first signal-to-noise ratio is less than the first threshold, the processor 140 may determine whether there are lesions and / or artifacts in the first target area. In some embodiments, the processor 140 may use, for example, the medical image abnormal point recognition method disclosed in the patent application document with application number CN202110983114.2 to identify the lesions in the first target area. In some embodiments, when the processor 140 determines that there are no lesions and / or artifacts in the first target area, the processor 140 may determine that a rescan or re-scan is required. In some embodiments, when the processor 140 determines that there are lesions and / or artifacts in the first target area, the second scan image and the second target area may be introduced as a reference, and the relationship between the second signal-to-noise ratio and the second threshold may be used to further determine whether a rescan or re-scan is required.

[0073] In some other embodiments, when the first signal-to-noise ratio is less than the first threshold, for the sake of simplicity, the processor 140 may directly determine that supplementary scanning or rescanning is required without further differentiation, that is, execute the following step 420.

[0074] Step 420: In response to the first signal-to-noise ratio being less than a first threshold, determining that a rescan or re-scan is required.

[0075] In some embodiments, when the result of the comparison is that the first signal-to-noise ratio is less than the first threshold, the processor 140 can directly determine whether a supplementary scan or a rescan is required. In some embodiments, the processor 140 can determine the time required for the supplementary scan according to the size of the difference between the first threshold and the first signal-to-noise ratio. For example, if the difference between the first threshold and the first signal-to-noise ratio is equal to 2, it is determined that a supplementary scan of 1 minute is required. If the difference between the first threshold and the first signal-to-noise ratio is equal to 4, it is determined that a supplementary scan of 3 minutes is required. In some embodiments, the processor 140 can determine the time required for the supplementary scan according to the range of the size of the difference between the first threshold and the first signal-to-noise ratio. For example, if the difference between the first threshold and the first signal-to-noise ratio is in the range of 2 to 4, it is determined that a supplementary scan of 1 minute is required. If the difference between the first threshold and the first signal-to-noise ratio is in the range of 4 to 6, it is determined that a supplementary scan of 3 minutes is required. In some embodiments, if the difference between the first threshold and the first signal-to-noise ratio is greater than a preset threshold (e.g., 10), the processor 140 can determine that a rescan is required.

[0076] The numerical values ​​or numerical ranges in the above examples are merely examples and are not intended to limit the embodiments.

[0077] In some embodiments, whether to select rescanning or re-scanning can be set by the user in advance according to the current scanning parameters. For example, if the image quality requirement is high, it can be set to re-scan in response to the first signal-to-noise ratio being less than the first threshold; if the image quality and scanning efficiency are to be taken into consideration, rescanning can be performed in response to the first signal-to-noise ratio being less than the first threshold.

[0078] Figure 4 The scanning method 400 shown can determine whether the image is qualified based on the comparison result of the first signal-to-noise ratio and the first threshold, and then determine whether a supplementary scan or rescan is required; the judgment process is simple and the judgment result has a high accuracy rate.

[0079] Figure 5 It is an exemplary flow chart of a scanning method 500 for determining whether a supplementary scan or a rescan is required based on a first signal-to-noise provided in some other embodiments of the present specification.

[0080] Step 510: compare the first signal-to-noise ratio with a first threshold.

[0081] In some embodiments, details on comparing the first signal-to-noise ratio with the first threshold may refer to step 410 and its related description. In some embodiments, if the first signal-to-noise ratio is less than the first threshold, the processor 140 may perform step 520 as follows for more accurate determination.

[0082] Step 520: In response to the first signal-to-noise ratio being less than the first threshold, determining a second target area in the first scanned image.

[0083] The second target region refers to a human body region used as a reference for comparison with the first target region during scanning, which is different from the first target region. In some embodiments, the second target region may be a tissue region with relatively uniform radionuclide uptake, such as muscle, brain, or other tissue regions. In some embodiments, the second target region may be selected based on clinical experience.

[0084] In some embodiments, the second target area may refer to a human body area other than the liver area. For example, the second target area is a muscle area or a brain area.

[0085] In some embodiments, the process of determining the second target area in the first scanned image may be similar to the process of determining the first target area in the first scanned image. For example, the processor 140 may identify the second area (such as a muscle area, a brain area, etc.) based on the second scanned image; then, the processor 140 may determine the second target area in the first scanned image based on the second area.

[0086] In some embodiments, the processor 140 can identify the second area in the second scanned image through a machine learning model. The input of the machine learning model is the second scanned image, and the output is the second scanned image with the second area marked. In some embodiments, the machine learning model can be trained using a GNN neural network model. In some embodiments, the machine learning model can be a pre-trained neural network model, and an interface is provided to be deployed in a product (such as processor 140, memory 150). In some embodiments, the machine learning model can be a deep learning model. In some embodiments, the machine learning model can be a model obtained by training a 3D vnet or 2.5D V-net segmentation network.

[0087] In some embodiments, the processor 140 may identify the first region and the second region based on the same machine learning model. In some embodiments, the processor 140 may identify the first region and the second region based on different machine learning models, respectively.

[0088] In some embodiments, the processor 140 may map the second region to the PET space through a registration matrix to determine the second target region in the first scan image. The registration matrix refers to a transformation matrix that transforms the coordinate system in the second scan image to the coordinate system in the first scan image, and the registration matrix may realize the coincidence of the second scan image and the first scan image.

[0089] Step 530: Determine a second signal-to-noise ratio of a second target area.

[0090] The second signal-to-noise ratio refers to the ratio of the power spectrum of the signal to the noise in the second target area in the first scanned image. In some embodiments, the processor 140 can determine the second signal-to-noise ratio by approximately estimating the image signal-to-noise ratio. For example, the processor 140 can calculate the ratio of the variance of the signal to the noise in the second target area in the image. The specific calculation process may include: first calculating the local variance of all pixels in the second target area in the image, considering the maximum value of the local variance as the signal variance, and the minimum value of the local variance as the noise variance, then finding the ratio of the signal variance to the noise variance, and finally correcting it with an empirical formula to obtain the second signal-to-noise ratio of the second target area. In some embodiments, the processor 140 may also determine the second signal-to-noise ratio of the second target area in other ways, which is not limited in this specification.

[0091] Step 540: Determine whether supplemental scanning or rescanning is required based on the second signal-to-noise ratio.

[0092] In some embodiments, the processor 140 may compare the second signal-to-noise ratio with a second threshold. When the second signal-to-noise ratio is less than the second threshold, the processor 140 may determine that a rescan or re-scan is required. When the second signal-to-noise ratio is greater than or equal to the second threshold, the processor 140 may determine that a rescan or re-scan is not required. For details on how to determine whether a rescan or re-scan is required based on the second signal-to-noise ratio, see the description of Figure 6 Description content.

[0093] Figure 5 The scanning method 500 shown can reduce the possibility of misjudgment by adding a judgment option of the signal-to-noise ratio of a reference area, using a dual-area judgment before making a decision on rescanning or rescanning. In some embodiments, there may be lesions and / or artifacts in the first target area that affect the calculation of the signal-to-noise ratio. In this case, the second signal-to-noise ratio of the second target area is used as a supplement to determine whether a rescanning or rescanning is needed, which can make the judgment of the quality of the scanned image (such as the first scanned image) more accurate. In some embodiments, when the processor cannot acquire the first target area (such as the first scanned image of the patient does not include the first target area), the processor can skip the steps of determining the first target area and judging the first signal-to-noise ratio, directly determine the second target area, and determine whether a rescanning or rescanning is needed based on the second signal-to-noise ratio.

[0094] Figure 6 It is an exemplary flow chart of a scanning method 600 for determining whether a supplementary scan or a rescan is required based on a second signal-to-noise ratio provided in some embodiments of the present specification.

[0095] Step 610: compare the second signal-to-noise ratio with a second threshold.

[0096] The second threshold refers to a value preset for the second target area in the first scanned image. In some embodiments, the second threshold can be determined based on the user's clinical experience with the first scanned image. In some embodiments, the second threshold can be input by the user through the terminal 130 and stored in the memory 150. In some embodiments, the second threshold can be equal to the first threshold. In some embodiments, the second threshold can be unequal to the first threshold.

[0097] Step 620: In response to the second signal-to-noise ratio being less than the second threshold, determining that supplemental scanning or rescanning is required.

[0098] If the second signal-to-noise ratio is less than the second threshold, the processor 140 may determine that there may be a large amount of noise in the first scanned image, which is unqualified and needs to be re-scanned or re-scanned. In some embodiments, through the two-layer judgment that the first signal-to-noise ratio is less than the first threshold and the second signal-to-noise ratio is less than the second threshold, the processor 140 can more accurately judge the quality of the first scanned image, thereby more accurately determining whether to perform re-scanning or re-scanning.

[0099] Step 630 : In response to the second signal-to-noise ratio being greater than or equal to the second threshold, determining that a lesion and / or an artifact exists in the first target area.

[0100] Since the signal-to-noise ratio of the first scanned image is generally relatively uniform, if the second signal-to-noise ratio is greater than or equal to the second threshold, the processor 140 can determine that the first scanned image is qualified. However, since lesions and / or artifacts will cause the first signal-to-noise ratio to increase, the first target area may be caused by lesions and / or artifacts. Therefore, the processor 140 can preliminarily determine that there may be lesions and / or artifacts in the first target area based on the second signal-to-noise ratio being greater than or equal to the second threshold, so as to remind the user (such as medical staff) to pay attention.

[0101] Figure 6 The scanning method 600 shown can make a decision on whether to perform a supplementary scan or a rescan based on the result of comparing the second signal-to-noise ratio of the second target area with the second threshold, and can also determine whether there is a lesion and / or an artifact in the first target area. The scanning method 600 can effectively reduce the possibility of misjudgment by adding a judgment option of the signal-to-noise ratio of a reference area.

[0102] The following will take the case where the first target area is the liver area and the second target area is the gluteus maximus as an example to illustrate the methods of some embodiments of the present application.

[0103] In some embodiments, the scanning device 110 can perform a CT scan on the patient from head to toe to obtain a second scanned image of the patient's entire body; and perform a PET scan on the patient from head to toe to obtain a first scanned image of the patient. On this basis, the processor 140 can first identify the liver area based on the second scanned image, and then use the registration matrix to map the liver area in the second scanned image to the PET space, thereby determining the liver area in the first scanned image. Then, the processor can determine the first signal-to-noise ratio of the first scanned image of the liver area, and compare the first signal-to-noise ratio with a preset first threshold. If the first signal-to-noise ratio is greater than or equal to the preset first threshold, it is determined that the first scanned image of the liver area is qualified.

[0104] In some embodiments, if the first signal-to-noise ratio is less than a preset first threshold, it can be determined that the first scan image of the liver region is unqualified and needs to be re-scanned or re-scanned.

[0105] In some embodiments, if the first signal-to-noise ratio is less than a preset first threshold, it may also be caused by lesions and / or artifacts in the liver area. In this case, the processor can further obtain a first scan image of the gluteus maximus. Specifically, the processor 140 can identify the gluteus maximus based on the second scan image, and then use the registration matrix to map the gluteus maximus in the second scan image to the PET space, thereby determining the gluteus maximus in the first scan image. Then, the processor 140 can determine the second signal-to-noise ratio of the first scan image of the gluteus maximus, and compare the second signal-to-noise ratio with the preset second threshold. If the second signal-to-noise ratio is less than the second threshold, it means that the first scan image of the patient is unqualified, and it is determined that a supplementary scan or rescan is required. If the second signal-to-noise ratio is greater than or equal to the second threshold, it means that the first scan image of the liver area is qualified, and the liver area may have lesions and / or artifacts. Then the system 100 can issue a prompt message to indicate that there may be lesions and / or artifacts in the liver area.

[0106] In some embodiments, the processor 140 may perform the above steps after acquiring the first scanned image of the patient's entire body, and perform a supplementary scan or a rescan on the patient's entire body area according to whether a supplementary scan or a rescan is required. In some embodiments, the processor may perform the above steps during a PET scan. For example, when the PET scan process is to scan from head to toe in sequence according to the bed number, the processor 140 may perform the above corresponding steps after the liver area scan is completed (or the gluteus maximus scan is completed), and according to the result of whether a supplementary scan or a rescan is required, prompt information is promptly sent to the user so that the user can adjust the scanning strategy in time.

[0107] In some embodiments, the first target area and the second target area can be interchangeable. For example, the first target area can be the gluteus maximus, and the second target area can be the liver area. Further, the first area and the second area can be interchangeable, and the first threshold and the second threshold can be interchangeable.

[0108] Figure 7 700 is an exemplary module diagram of a scanning system 700 for a nuclear medicine device provided in some embodiments of the present specification. In some embodiments, the scanning system 700 may include an acquisition module 710, a target region determination module 720, a signal-to-noise ratio determination module 730, and a supplemental / re-scan determination module 740. In some embodiments, each module in the scanning system 700 for a nuclear medicine device may be implemented by the processor 140.

[0109] The acquisition module 710 may be used to acquire information / data during the scanning process. In some embodiments, the acquisition module 710 may be used to acquire a first scanned image of a patient.

[0110] The target region determination module 720 may be used to determine a specific target region. In some embodiments, the target region determination module 720 may be used to determine a first target region in the first scanned image. In some embodiments, the target region determination module 720 may be used to determine a second target region in the first scanned image.

[0111] The signal-to-noise ratio determination module 730 may be used to determine the signal-to-noise ratio of each region in the first scanned image. In some embodiments, the signal-to-noise ratio determination module 730 may be used to determine a first signal-to-noise ratio of a first target region. In some embodiments, the signal-to-noise ratio determination module 730 may be used to determine a second signal-to-noise ratio of a second target region.

[0112] The fill / re-scan determination module 740 can be used to determine whether fill-scan or re-scan is needed. In some embodiments, the fill / re-scan determination module 740 can determine whether fill-scan or re-scan is needed based on a first signal-to-noise ratio. In some embodiments, the fill / re-scan determination module 740 can determine whether fill-scan or re-scan is needed based on a second signal-to-noise ratio.

[0113] The beneficial effects that can be achieved by the embodiments of the present specification may include but are not limited to: (1) the signal-to-noise ratio of the region of interest on a typical organ can be automatically calculated to recommend whether a supplementary scan or rescan is needed, and the calculation process is simple and the calculation results are accurate; (2) by considering the signal-to-noise ratio of the reference area, dual-area judgment can be achieved. Only when the signal-to-noise ratio of the scanned images of the target area and the reference area is lower than the corresponding threshold at the same time, will a prompt for supplementary scan or rescan be triggered, thereby reducing the possibility of misjudgment; (3) timely judgment and prompts can be issued during the scanning process, without having to wait until the patient's whole body scan is completed before supplementary scan or rescanning, thereby saving operation time, shortening scanning repetition time, and improving user experience.

[0114] The embodiments of this specification are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0118] Obviously, those skilled in the art can make various changes and modifications to the embodiments of this specification without departing from the spirit and scope of the embodiments of this specification. Thus, if these modifications and variations of the embodiments of this specification fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A scanning method for a nuclear medicine device, comprising: Acquiring a first scan image of the patient; determining a first target area in the first scanned image; determining a first signal-to-noise ratio of the first target area; as well as Determining whether supplemental scanning or rescanning is required based on the first signal-to-noise ratio includes: comparing the first signal-to-noise ratio with a first threshold; In response to the first signal-to-noise ratio being less than the first threshold, determining a second target area in the first scanned image; determining a second signal-to-noise ratio of the second target area; and Based on the second signal-to-noise ratio, determine whether supplemental scanning or rescanning is needed.

2. The scanning method according to claim 1, wherein: The determining a first target area in the first scanned image includes: acquiring a second scan image of the patient; Based on the second scanned image, identifying a first area; and Based on the first area, the first target area in the first scanned image is determined.

3. The scanning method according to claim 1, wherein: The determining whether supplemental scanning or rescanning is required based on the first signal-to-noise ratio includes: comparing the first signal-to-noise ratio to a first threshold; and In response to the first signal-to-noise ratio being less than the first threshold, it is determined that a rescan or a rescan is required.

4. The scanning method according to claim 1, wherein: The first target area is the liver area, and the second target area is a human body area other than the liver area.

5. The scanning method according to claim 1, wherein: The second target area is different from the first target area.

6. The scanning method according to claim 1, wherein: The determining, based on the second signal-to-noise ratio, that supplemental scanning or rescanning is required includes: comparing the second signal-to-noise ratio with a second threshold; In response to the second signal-to-noise ratio being less than the second threshold, it is determined that a rescan or a rescan is required.

7. The method according to claim 1, wherein: Also includes: When it is determined that supplementary scanning or rescanning is required, a prompt message is issued.

8. A scanning system for a nuclear medicine device, comprising: An acquisition module, a target area determination module, a signal-to-noise ratio determination module, and a supplemental / re-scanning determination module; The acquisition module is used to acquire a first scan image of the patient; The target area determination module is used to determine a first target area in the first scanned image; The signal-to-noise ratio determination module is used to determine a first signal-to-noise ratio of the first target area; as well as The supplement / re-scanning determination module is used to determine whether supplement or re-scanning is needed based on the first signal-to-noise ratio, including: comparing the first signal-to-noise ratio with a first threshold; In response to the first signal-to-noise ratio being less than the first threshold, determining a second target area in the first scanned image; determining a second signal-to-noise ratio of the second target area; and Based on the second signal-to-noise ratio, determine whether supplemental scanning or rescanning is needed.

9. A scanning device for nuclear medicine equipment, comprising: at least one storage device including at least one set of instructions; as well as At least one processor for communicating with the at least one storage device, wherein when executing the instruction set, the at least one processor is used to instruct the apparatus to execute the scanning method according to any one of claims 1 to 7.

Images