Intelligent calculation method of PET-CT scanning range

Abstract

The application relates to an intelligent PET-CT scanning range calculation method, which comprises the following steps: S10, acquiring a planar positioning image for positioning of CT scanning, performing binary processing on the planar positioning image, acquiring a first picture and a pixel value range of a patient body part in the first picture; S20, based on the first picture and the pixel value range, adopting a pixel traversal strategy to determine the positions of a head part and a shoulder part relative to a scanning bed respectively; S30, according to basic information of a patient, a to-be-scanned region, the positions of the head part and the shoulder part relative to the scanning bed respectively, determining a bed position range of a to-be-scanned region of the patient in PET scanning, so that a PET system realizes full-automatic PET scanning of the to-be-scanned region based on the bed position range. The above method automatically calculates a scanning range, and reduces the operation complexity of an operator.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to an intelligent calculation method for PET-CT scan range. Background Technology

[0002] PET (Positron Emission Tomography) is a technique that uses nuclides that emit positrons to label compounds that can participate in blood flow or metabolic processes in human tissues, thereby obtaining images of the human body in transverse, coronal, and sagittal sections.

[0003] PET-CT combines two technologies to fuse medical images generated by PET and CT, providing diagnostic information for clinical physiology and pathology.

[0004] PET-CT offers clear imaging, high accuracy, and high sensitivity, making it ideal for early cancer detection. Currently, when hospitals perform PET-CT scans, users first need to select a scanning protocol. This protocol includes information such as the patient's body parts to be scanned, the equipment parameters, and a description of the scanning process. When the operator begins scanning the patient, a whole-body film is first taken as a localization image. The PET-CT scan area is then delineated on this localization image, and the software performs both CT and PET scans based on the delineated area. PET scanning is not a continuous scan but rather a segmented scan performed at the bed level. Within a single bed unit, data is acquired over a specific range, and then the data is reconstructed into a medical image.

[0005] After data collection is complete, doctors can select specific beds for reconstruction. When reconstructing only some beds, offline, unconventional reconstructions may be performed on a specific body part (such as the heart), such as dynamic reconstruction or gated reconstruction. If the data for this body part is distributed across multiple beds, the resulting images from unconventional reconstructions may be problematic. In fact, for some body parts, such as the head or heart, data can be acquired with just one PET bed. This requires operators to adjust the scan range to ensure the body part is covered by the area of ​​a single PET bed. This increases the complexity of the operation, as operators need to determine both the overall scan range and, according to different protocols, ensure that a specific body part is covered by the area of ​​a single PET bed. Furthermore, issues such as forgetting to do so, incorrect range selection, and longer scan times due to the increased number of beds may occur. Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an intelligent calculation method for PET-CT scanning range, which automatically calculates the scanning range and reduces the operational complexity for operators.

[0008] (II) Technical Solution

[0009] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0010] In a first aspect, embodiments of the present invention provide an intelligent calculation method for PET-CT scan range, comprising:

[0011] S10. Obtain a planar positioning image from a CT scan for localization, perform binarization processing on the planar positioning image, and obtain a first image and the pixel value range of the patient's body parts in the first image.

[0012] S20. Based on the first image and the pixel value range, a pixel traversal strategy is adopted to determine the position of the head range and the shoulder relative to the scanning bed.

[0013] S30. Based on the patient's basic information and the position of the area to be scanned, the head area, and the shoulder area relative to the scanning bed, determine the bed range to which the patient's area to be scanned belongs in the PET scan, so that the PET system can perform fully automatic PET scanning of the area to be scanned based on the bed range.

[0014] Optionally, the planar localization image for localization from the CT scan includes:

[0015] The position of the scanning bed Bed (Start) and the scanning range Bed (start) - Bed (end) corresponding to the initial alignment of the planar positioning image, the pixel size PX in the planar positioning image, the width Width of the planar positioning image, and the height Height of the planar positioning image.

[0016] Optionally, S10 includes:

[0017] The planar positioning image is binarized, and the pixel value of the patient's body parts in the planar positioning image is recorded as 255, and the other pixel values ​​are recorded as 0, to obtain the first image and the pixel value of the patient's body parts in the first image is 255.

[0018] Optionally, S20 includes:

[0019] S21. Based on the pre-defined coordinate information, the top left corner of the first image is the origin (0,0), the X-axis direction is from the left to the right of the first image, and the Y-axis direction is from the top to the bottom of the first image.

[0020] S22. Starting from pixel A (Width / 2, 0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate B (hsx, hsy) with a y-value greater than 0, then take the pixel coordinate B with a y-value greater than 0 as the starting position of the patient's head, hsx = Width / 2, hsy > 0.

[0021] S23. Starting from pixel C(Width*3 / 4,0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate D(SHx,SHy) with a y-value greater than 0, then take the pixel coordinate D with a y-value greater than 0 as the starting position of the patient's shoulder, SHx = Width*3 / 4, SHy > 0.

[0022] S24. Based on the position Bed(Start) of the scanning bed corresponding to the starting point of the planar positioning image and the pixel coordinates B and D, obtain the starting positions of the patient's head and shoulders relative to the scanning bed.

[0023] S25. Based on the predefined scanning bed length, obtain the head range of the patient's head relative to the scanning bed.

[0024] Optionally, S24 includes:

[0025] The pixel coordinates B(hsx,hsy) of the patient's head correspond to the position of the scanning bed Bed(head);

[0026] Bed(head)=Bed(start)+PX*hsy;

[0027] Bed(start) is the position of the scanning bed corresponding to the starting point of the planar positioning image, and PX is the size of the pixel in the planar positioning image;

[0028] S25 includes:

[0029] The predefined length of the scanning bed is SR, the starting position of the patient's head relative to the scanning bed is Bed(head), and the ending position of the scanning is Bed(HE) = Bed(head) + SR;

[0030] The scanning range of the patient's head relative to the scanning bed is [Bed(head),Bed(HE)].

[0031] Optionally, S24 includes:

[0032] The pixel coordinates D(SHx,SHy) of the patient's shoulder correspond to the position Bed(SH) of the scanning bed;

[0033] Bed(SH)=Bed(start)+SHy*PX.

[0034] Bed(start) is the position of the scanning bed corresponding to the starting point of the planar positioning image, and PX is the size of the pixel in the planar positioning image.

[0035] Optionally, S30 includes:

[0036] When the patient's area to be scanned is the heart region, the distance from the heart position to the shoulder position along the Y-axis is 10 ± 2 cm, marked as D(SC).

[0037] The pixel coordinates D of the patient's shoulder correspond to the scan bed position Bed(SH), and the scan start position corresponding to the heart is Bed(Car).

[0038] Bed(Car) = Bed(SH) + D(SC);

[0039] If the predefined scanning bed length is SR, then the scanning start position of the scanning bed corresponding to the heart is Bed (Car), and the scanning end position is Bed (CE).

[0040] Bed(CE) = Bed(Car) + SR

[0041] The scanning range for the cardiac region is [Bed(Car),Bed(CE)].

[0042] Optionally, S30 includes:

[0043] When the patient's area to be scanned is the lung region, the distance from the lung position to the shoulder position along the Y-axis is marked as P(SC).

[0044] The pixel coordinates D of the patient's shoulder correspond to the scan bed position: Bed(SH), and the scan start position of the lungs corresponding to the scan bed is: Bed(F).

[0045] Bed(F) = Bed(SH) + P(SC);

[0046] If the predefined scanning bed length is SR, then the scanning start position for the lungs is Bed(F), and the scanning end position is Bed(FS).

[0047] Bed(FS) = Bed(F) + SR

[0048] The scanning range for the lung region is [Bed(F),Bed(FS)].

[0049] Secondly, embodiments of the present invention also provide an operating console, including: a memory and a processor; the memory stores computer program instructions, and the processor executes the computer program instructions stored in the memory, specifically performing any of the methods described in the first aspect above.

[0050] (III) Beneficial Effects

[0051] The method of this invention, based on protocol information, uses intelligent calculation methods to automatically calculate the scanning range of the PET system, ensuring that the corresponding human body part is covered by the area of ​​a PET bed. This reduces the operational complexity for operators.

[0052] The method of this invention utilizes planar positioning images (plain films) from CT scans to identify the starting positions of the patient's head and shoulders. Based on these starting positions, the specific scanning range relative to the scanning bed is determined. The PET system then performs intelligent scanning based on this determined range, effectively saving the patient's scanning time. Simultaneously, it can acquire better offline reconstruction data, resulting in higher quality reconstructed images. During the scanning process, the doctor does not need to manually determine the bed position, and the scanning area identified by the method according to this invention completely covers the area to be tested, ensuring scanning accuracy. Attached Figure Description

[0053] Figure 1 A flowchart illustrating an intelligent calculation method for PET-CT scanning range according to an embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram illustrating the positional relationship between the bed and the human body during a PET scan, as shown in one embodiment.

[0055] Figure 3 This is a schematic diagram of a plain human body in a CT scan, as shown in one embodiment.

[0056] Figure 4 To Figure 3 A schematic diagram of the flat area data after binarization;

[0057] Figure 5 To Figure 4 The image in the diagram includes an illustration of the coordinate origin.

[0058] Figure 6 To Figure 5 This is a diagram illustrating how to iterate through the images to find the starting position of the human head.

[0059] Figure 7 For based on Figure 6 A schematic diagram showing the starting position of the human head determined by the method described above;

[0060] Figure 8 To Figure 5 This is a diagram illustrating how to iterate through the images to find the starting position of the shoulder.

[0061] Figure 9 Based on Figure 4 A schematic diagram of the head region defined in the image shown.

[0062] Figure 10 Based on Figure 4 A schematic diagram of the area of ​​the heart as defined in the image shown;

[0063] Figure 11 This is a schematic diagram showing the starting and ending positions of a human body radiograph relative to the scanning bed. Detailed Implementation

[0064] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0065] Currently, PET scans collect data on a per-bed basis, covering a specific area with some overlap between adjacent beds. Figure 2 As shown, the scanning ranges of bed 1 and bed 2 overlap. During PET data acquisition, the device moves the bed to the beginning of the bed, stays there for a period of time, collects data for one bed's range, and then moves to the beginning of the next bed, until data for all beds has been collected. Data reconstruction is also based on the bed data. When the number of beds collected is N, the beds selected for reconstruction are [RS, RE], where RS and RE are consecutive and both less than N. This results in overlapping data during reconstruction, leading to less than ideal results. N is a natural number greater than or equal to 2.

[0066] The method of this invention can intelligently identify the area of ​​the bed to be scanned before PET system scanning, thereby effectively saving doctors' operation time and patients' waiting time. At the same time, effective PET detection data can be obtained through the intelligently identified bed area, and the reconstruction of these PET detection data can be carried out independently, effectively ensuring the quality of the reconstructed image.

[0067] Additionally, it should be noted that planar positioning images, i.e., flat images, have x and y axes, while the scanning bed only has a position, corresponding to the Y-axis coordinates in the image. In PET scanning, the scanning bed moves only in one direction, such as along the Y-axis of the planar positioning image. Therefore, in this embodiment of the invention, the position relative to the scanning bed is only a numerical value, not a coordinate. That is, in this embodiment of the invention, the starting point of the scanning bed can correspond to the position where Y=0 in the planar positioning image; therefore, the position of the scanning bed can be calculated based on the Y-axis value.

[0068] Example 1

[0069] like Figure 1As shown, this embodiment of the invention provides an intelligent calculation method for PET-CT scanning range. The execution subject of this method can be an operating console, that is, an operating console integrating the PET detection system program. Specifically, the intelligent calculation method for PET-CT scanning range includes the following steps:

[0070] S10. Obtain a planar positioning image from a CT scan for localization, perform binarization processing on the planar positioning image, and obtain a first image and the pixel value range of the patient's body parts in the first image.

[0071] For example, the planar positioning image used for localization in the CT scan may include: the position of the scanning bed corresponding to the starting point of the planar positioning image (Bed(Start)) and the scanning range (Bed(start)-Bed(end)), such as... Figure 11 As shown, the pixel size PX, the width Width, and the height Height of the planar positioning image are defined.

[0072] In other words, before using CT equipment to obtain plain films, doctors can set the position information of Bed (Start) and Bed (End), so that the above-mentioned Bed (Start) and Bed (End) data are recorded in the obtained plain film images.

[0073] Understandably, the planar positioning image is binarized, and the pixel value of the patient's body parts in the planar positioning image is recorded as 255, while other pixel values ​​are recorded as 0, resulting in the first image and the pixel value of the patient's body parts in the first image being 255.

[0074] S20. Based on the first image and the pixel value range, a pixel traversal strategy is adopted to determine the position of the head range and the shoulder relative to the scanning bed.

[0075] For example, in a specific implementation, step S20 may include the following sub-steps:

[0076] S21. Based on the pre-defined coordinate information, the top left corner of the first image is the origin (0,0), the X-axis direction is from the left to the right of the first image, and the Y-axis direction is from the top to the bottom of the first image.

[0077] S22. Starting from pixel A (Width / 2, 0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate B (hsx, hsy) with a y-value greater than 0, then take the pixel coordinate B with a y-value greater than 0 as the starting position of the patient's head, hsx = Width / 2, hsy > 0.

[0078] S23. Starting from pixel C(Width*3 / 4,0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate D(SHx,SHy) with a y-value greater than 0, then take the pixel coordinate D with a y-value greater than 0 as the starting position of the patient's shoulder, SHx = Width*3 / 4, SHy > 0.

[0079] S24. Based on the position Bed (Start) of the scanning bed corresponding to the initial alignment of the planar positioning image and the pixel coordinates B and D, obtain the initial positions of the patient's head and shoulders relative to the scanning bed.

[0080] S25. Based on the predefined scanning bed length, obtain the head range of the patient's head relative to the scanning bed.

[0081] S30. Based on the patient's basic information and the position of the area to be scanned, the head area, and the shoulder area relative to the scanning bed, determine the bed range to which the patient's area to be scanned belongs in the PET scan, so that the PET system can perform fully automatic PET scanning of the area to be scanned based on the bed range.

[0082] This embodiment utilizes planar positioning images (plain films) from CT scans to identify the starting positions of the patient's head and shoulders. Based on these starting positions, the specific scanning range relative to the scanning bed is determined. The PET system then performs intelligent scanning based on this determined range, effectively saving the patient's scanning time. Simultaneously, it can acquire better offline reconstruction data, resulting in better reconstruction performance. During the scanning process, the doctor does not need to manually determine the bed position, and the scanning area identified by the method according to this embodiment completely covers the area to be tested, ensuring scanning accuracy.

[0083] Example 2

[0084] To better understand the method of Embodiment 1 above, the following will be combined with... Figures 2 to 10 This paper provides a detailed explanation of the method for intelligently calculating the PET scan range in PET-CT scans.

[0085] like Figure 2 As shown, Figure 2This diagram illustrates the positional relationship between the bed and the human body in a PET scan acquired using a PET-CT scanner. In existing technology, when performing a PET scan, the bed is first moved to the starting position of bed 1, and data is then acquired. This acquisition captures data between the starting and ending positions of bed 1, with the entire length of the bed denoted as SR. After data acquisition at bed 1 is complete, the bed is moved to the starting position of bed 2, and data acquisition at bed 2 is performed. This process continues until data acquisition at bed 5 is complete. The entire scanning range is set by the operator and can only be calculated based on the entire bed occupancy.

[0086] Therefore, the intelligent calculation method for PET-CT scanning range provided in this embodiment can effectively solve the problem of time-consuming and cumbersome operator settings. The execution subject of this embodiment's method can be a computing device such as an operating console or any electronic device integrated with a PET-CT system. The method of this embodiment may include the following steps:

[0087] Step 1: In this embodiment, the PET-CT scanning protocol is associated with the corresponding human body parts, and the part information is stored in the protocol content. After the user selects the protocol to scan, the patient's scanning area information / scanning part information can be determined.

[0088] The list below shows the human body parts corresponding to some of the protocols.

[0089] Protocol Name Corresponding body parts Brain_XXX head Cardiac_XXX heart

[0090] Step 2: Plain images of the human body obtained through CT scans, such as Figure 3 As shown, the flat image reveals the outline of the human body, with information such as the bed frame contained in the background of the outline.

[0091] Plain film images, as standard medical imaging data, are grayscale data with values ​​ranging from -255 to 255. They also include the following data: the bed position corresponding to the image start alignment (Bed), the image pixel size (PX), the image width (Width), and the image height (Height).

[0092] Figure 3The anatomical radiograph shown consists of four scanned pieces of information: 1) the patient's body, 2) the bed on which the patient lies, 3) the air, and 4) the headrest on the bed. The data values ​​for these four pieces of information differ in the image. Here, the range of image data values ​​for the patient's body is defined as [patient_low, patient_max]. Because the scanning method for anatomical radiographs is generally fixed, [patient_low, patient_max] can have fixed values ​​on a specific device.

[0093] Step 3: Based on the value ranges of the four information values ​​in the flat-section image, the image data in the flat-section image is binarized, such as... Figure 4 As shown, all data within the range is marked in white with a value of 255, and all data outside the range is marked in black with a value of 0.

[0094] In other words, for Figure 4 The plain film data, [patient_low,patient_max] = [-50,255], is binarized to obtain... Figure 4 In the image shown, the air, bed frame, and headrest are no longer displayed. Here, [-50, 255] represents... Figure 3 The range of values ​​for patient data may vary depending on the equipment used in actual applications.

[0095] Step 4: Figure 4 The origin point is located at the top left corner of the image and marked as Origin, with coordinates (0,0). For example... Figure 5 As shown, the X-axis direction is from left to right, and the Y-axis direction is from top to bottom.

[0096] Step 5: Starting from the binarized flat image coordinates A(Width / 2, 0), extract the color of pixels along the positive Y-axis until the extracted color is no longer white. These coordinates represent the starting position of the human head. Label these coordinates as (hsx, hsy), where hsx = width / 2. Figure 6 and Figure 7 As shown.

[0097] That is, starting from pixel A (Width / 2, 0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate B (hsx, hsy) with a y-value greater than 0, then the pixel coordinate B with a y-value greater than 0 is taken as the starting position of the patient's head, hsx = Width / 2, hsy > 0.

[0098] Step 6: Starting from the binarized flat image coordinates C(Width*3 / 4,0), extract the color of the pixels along the positive Y-axis until the extracted color is no longer white. These coordinates represent the position of the human shoulder. Label these coordinates as (SHx,SHy). Figure 8 As shown.

[0099] That is, starting from pixel C(Width*3 / 4,0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate D(SHx,SHy) with a y-value greater than 0, then the pixel coordinate D with a y-value greater than 0 is taken as the starting position of the patient's shoulder, SHx = Width*3 / 4, SHy > 0.

[0100] Step 7: The position of the scanning bed corresponding to the starting position of the flat image is marked as Bed(start). The size of each pixel is marked as PX. The position of the scanning bed corresponding to the coordinate point (hsx, hsy) of the head can be calculated as Bed(head) = Bed(start) + PX*hsy.

[0101] The scanning range of a bed is marked as SR. The scanning start position of the head corresponding to the scanning bed can be calculated as Bed(HS) = Bed(head) and the scanning end position is Bed(HE) = Bed(head) + SR.

[0102] Therefore, when scanning a head-to-bed position in a PET system, the scanning range of the head relative to the scanning bed can be set to [Bed(HS),Bed(HE)].

[0103] When performing multi-bed scanning with a head-mounted protocol, the scanning range begins at the head position. Therefore, the starting point of the entire scanning range can be set to Bed(HS), and the ending position can be calculated based on the number of beds. Figure 9 As shown.

[0104] Step 8: The position of the scanning bed corresponding to the starting position of the flat image is marked as Bed(start). The size of each pixel is marked as PX. The position of the scanning bed corresponding to the coordinate point (SHx, SHy) of the shoulder can be calculated as Bed(SH) = Bed(start) + SHx*PX.

[0105] In the Y-axis direction, the distance between the heart position and the shoulder position is generally about 10 cm, marked as D(SC). The scanning start position of the heart on the scanning bed can be calculated as Bed(Car) = Bed(SH) + D(SC).

[0106] The scanning range of a bed is marked as SR. The scanning start position of the heart corresponding to the scanning bed can be calculated as Bed(CS) = Bed(Car) and the scanning end position as Bed(CE) = Bed(CS) + SR.

[0107] When performing a cardiac protocol single-bed scan, the scan range relative to the scan bed can be set to [Bed(CS), Bed(CE)], such as... Figure 10 As shown.

[0108] When performing multi-bed cardiac scans, most scans will not scan the head, only the body parts. The starting point of the second bed in the entire scan range can be set as Bed (CS), and then the start and end positions of the entire scan range can be calculated based on the number of beds. In this embodiment, the entire X-axis range needs to be covered, so information limiting the X-axis is not specifically explained.

[0109] The above methods can be used to automatically determine the scanning range for head and heart protocol types.

[0110] The above method can use the planar positioning image (also known as a plain film) of a CT scan to identify the starting position of the head and shoulders of the patient being examined. Then, based on the starting position of the head and shoulders, the specific scanning range relative to the scanning bed is determined. The PET system then performs intelligent scanning based on the determined specific scanning range, so as to effectively save the patient's scanning time.

[0111] Furthermore, this embodiment of the invention also provides an operating console, which includes a memory and a processor; the memory stores computer program instructions, and the processor executes the computer program instructions stored in the memory, specifically performing the aforementioned intelligent calculation method for the PET-CT scan range. During the scanning process, there is no need for the doctor to manually determine the bed position, and the scan area identified by the intelligent calculation method according to this embodiment of the invention can completely cover the location to be measured, ensuring scanning accuracy.

[0112] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0113] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0115] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for intelligently calculating the scanning range of a PET-CT scan, characterized in that, PET scans are performed on a bed-by-bed basis. The method described here involves intelligent identification of the area to be scanned within the PET system before scanning. The method includes: S10. Obtain a planar positioning image from a CT scan for localization, perform binarization processing on the planar positioning image, obtain a first image and the pixel value range of the patient's body parts in the first image, record the pixel value of the patient's body parts in the planar positioning image as 255, and record other pixel values ​​as 0. The planar positioning image includes: the position Bed(Start) of the scanning bed corresponding to the starting point of the planar positioning image and the scanning range Bed(Start)-Bed(end), the pixel size PX of the planar positioning image, the width Width of the planar positioning image, and the height Height of the planar positioning image; S20. Based on the first image and the pixel value range, a pixel traversal strategy is adopted to determine the position of the head range and the shoulder relative to the scanning bed. S20 includes: S21, based on pre-defined coordinate information, the top left corner of the first image is the origin (0,0), the X-axis direction is from the left to the right of the first image, and the Y-axis direction is from the top to the bottom of the first image; S22. Starting from pixel A (Width / 2, 0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate B (hsx, hsy) with a y-value greater than 0, then take the pixel coordinate B with a y-value greater than 0 as the starting position of the patient's head, hsx=Width / 2, hsy>0. S23. Starting from pixel C (Width*3 / 4, 0) of the first image, traverse along the positive Y-axis. If there is a first pixel coordinate D (SHx, SHy) with a y value greater than 0, then take the pixel coordinate D with a y value greater than 0 as the starting position of the patient's shoulder, SHx = Width*3 / 4, SHy>0. S24. Based on the position Bed(Start) of the scanning bed corresponding to the starting point of the planar positioning image and the pixel coordinates B and D, obtain the starting positions of the patient's head and shoulders relative to the scanning bed. S25. Based on the predefined scanning bed length, obtain the head range of the patient's head relative to the scanning bed; S30. Based on the patient's basic information and the position of the area to be scanned, the head area, and the shoulder area relative to the scanning bed, determine the bed range to which the patient's area to be scanned belongs in the PET scan, so that the PET system can perform fully automatic PET scanning of the area to be scanned based on the bed range.

2. The intelligent computing method according to claim 1, characterized in that, The planar localization images used for localization from the CT scan include: The position of the scanning bed corresponding to the initial alignment of the planar positioning image (Bed(Start)) and the scanning range (Bed(start) - Bed(end)) are defined by the following parameters: the pixel size (PX) of the planar positioning image, the width (Width) of the planar positioning image, and the height (Height) of the planar positioning image.

3. The intelligent computing method according to claim 2, characterized in that, S10 includes: The planar positioning image is binarized, and the pixel value of the patient's body parts in the planar positioning image is recorded as 255, and the other pixel values ​​are recorded as 0, to obtain the first image and the pixel value of the patient's body parts in the first image is 255.

4. The intelligent computing method according to claim 1, characterized in that, S24 includes: The pixel coordinates B (hsx, hsy) of the patient's head correspond to the position of the scanning bed Bed(head); Bed(head) = Bed(start) + PX*hsy; Bed(start) is the position of the scanning bed corresponding to the starting point of the planar positioning image, and PX is the size of the pixel in the planar positioning image; S25 includes: The predefined length of the scanning bed is SR, the starting position of the patient's head relative to the scanning bed is Bed(head), and the ending position of the scan is Bed(HE) = Bed(head) + SR; The scanning range of the patient's head relative to the scanning bed is [Bed(head), Bed(HE)].

5. The intelligent computing method according to claim 1, characterized in that, S24 includes: The pixel coordinates D(SHx, SHy) of the patient's shoulder correspond to the position Bed(SH) of the scanning bed; Bed(SH) = Bed(start) + SHy*PX; Bed(start) is the position of the scanning bed corresponding to the starting point of the planar positioning image, and PX is the size of the pixel in the planar positioning image.

6. The intelligent computing method according to claim 5, characterized in that, S30 includes: When the patient's area to be scanned is the heart region, the distance from the heart position to the shoulder position along the Y-axis is 10 ± 2 cm, marked as D(SC). The pixel coordinates D of the patient's shoulder correspond to the scan bed position Bed(SH), and the scan start position corresponding to the heart is Bed(Car). Bed(Car) = Bed(SH) + D(SC); If the predefined scanning bed length is SR, then the scanning start position of the scanning bed corresponding to the heart is Bed (Car), and the scanning end position is Bed (CE). Bed(CE) = Bed(Car) + SR The scanning range for the cardiac region is [Bed (Car), Bed (CE)].

7. The intelligent computing method according to claim 5, characterized in that, S30 includes: When the patient's area to be scanned is the lung region, the distance from the lung position to the shoulder position along the Y-axis is marked as P(SC). The pixel coordinate D of the patient's shoulder corresponds to the position of the scanning bed: Bed(SH), and the scan start position of the lungs corresponding to the scanning bed is: Bed(F). Bed(F) = Bed(SH) + P(SC); If the predefined scanning bed length is SR, then the scanning start position for the lungs is Bed(F), and the scanning end position is Bed(FS). Bed(FS) = Bed(F) + SR The scanning range for the lung region is [Bed(F), Bed(FS)].

8. An operating console, characterized in that, include: A memory and a processor; the memory stores computer program instructions, and the processor executes the computer program instructions stored in the memory, specifically performing the method described in any one of claims 1 to 7.

Images