Method and device for determining the number of angles of sparse angle CT scanning, equipment and medium

Abstract

The application relates to a method, device, equipment and medium for determining the number of angles of sparse-angle CT scanning, which comprises the following steps: acquiring physical parameters of a region of interest; acquiring scanning parameters of the region of interest; and determining the number of scanning angles of the region of interest based on a pre-established mapping relationship between the whole of the physical parameters and the scanning parameters and the number of scanning angles, the physical parameters and the scanning parameters. The method provided by the application estimates the strength of artifacts according to existing information, and then determines the number of angles required for sparse-angle CT scanning, so that the influence of artifacts is reduced, and the processing pressure of subsequent artifact removal is relieved.

Description

Technical Field

[0001] This application relates to the field of CT data acquisition technology, specifically to a method, apparatus, equipment, and medium for determining the angle number of sparse angle CT scans. Background Technology

[0002] Computed tomography (CT) combines a series of X-ray images of the human body taken from different angles with computer processing to obtain a cross-sectional image of the body. To make the reconstructed images clinically usable, most commercial systems currently use more than 2000 angles for scanning. Reducing the number of scanning angles can effectively reduce radiation dose; this method of reconstruction using data from fewer angles is called sparse-angle CT reconstruction.

[0003] However, due to insufficient scanning angle, sparse-angle CT reconstruction images produce a large number of artifacts, degrading image quality. The intensity of artifacts is related to scanning conditions, the location of the reconstructed image, the size of the field of view, and the structure of the scanned volume. In recent years, with technological advancements, it has become possible to remove artifacts caused by insufficient scanning angle to a certain extent.

[0004] However, the ability to remove artifacts in the later stages is limited. To reduce the processing burden of artifact removal in the later stages, it is necessary to estimate the strength of the artifacts based on the scanned information, and then determine the appropriate number of angles required for sparse angle scanning. Summary of the Invention

[0005] To address the aforementioned issues, embodiments of this application provide a method, apparatus, device, and medium for determining the number of scanning angles required to meet clinical diagnostic needs.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] Firstly, a method for determining the angle number in sparse angle CT scans is provided, the method comprising:

[0008] Obtain the physical parameters of the region of interest;

[0009] Obtain the scanning parameters of the region of interest;

[0010] Based on the pre-established mapping relationship between physical parameters, scanning parameters, and scanning angles, the scanning angles of the region of interest are determined.

[0011] Secondly, a device for determining the angle number in sparse angle CT scanning is provided, the device comprising:

[0012] The physical parameter acquisition unit is used to acquire the physical parameters of the region of interest.

[0013] The scanning parameter acquisition unit is used to acquire the scanning parameters of the region of interest.

[0014] The scanning angle number determination unit is used to determine the scanning angle number of the region of interest based on the pre-established mapping relationship between the physical parameters and scanning parameters as a whole and the scanning angle number, the physical parameters, and the scanning parameters.

[0015] Thirdly, embodiments of this application also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-described method for determining the angle number of sparse angle CT scans.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when instructed by a processor, implements the steps of the above-described method for determining the angle number of sparse angle CT scans.

[0017] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0018] The method for determining the angle number in sparse-angle CT scanning provided in this application obtains the physical parameters of the region of interest (ROI), the scanning parameters of the ROI, and, based on a pre-established mapping relationship between the physical parameters, the overall scanning parameters, and the scanning angle number, determines the scanning angle number of the ROI. This method for determining the angle number in sparse-angle CT scanning can reduce artifacts and their impact when the scanning angle is reduced, thereby alleviating the processing pressure of subsequent artifact removal. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A flowchart illustrating a method for determining the angle number in a sparse angle CT scan according to an embodiment of this application is shown.

[0021] Figure 2 A flowchart illustrating a method for determining the angle number in a sparse angle CT scan according to another embodiment of this application is shown.

[0022] Figure 3 A schematic diagram of a device for determining the angle number of a sparse angle CT scan according to an embodiment of this application is shown.

[0023] Figure 4A schematic diagram of the structure of a computer device according to an embodiment of this application is shown. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0026] The concept of this application is as follows: In sparse-angle CT image reconstruction, artifacts caused by insufficient scanning angle can be removed through various means. However, due to the limited ability to remove artifacts, it is desirable to determine an appropriate number of angles to reduce artifacts and their impact, thereby alleviating the processing pressure of subsequent artifact removal. This application estimates the intensity of artifacts based on existing information, and then determines the number of angles required for sparse-angle CT scanning.

[0027] Figure 1 This application illustrates a method for determining the angle number in sparse angle CT scans according to one embodiment.

[0028] according to Figure 1 As shown, the method includes steps S110 to S130:

[0029] Step S110: Obtain the physical parameters of the region of interest.

[0030] Parameters related to sparse-angle CT scans can include physical parameters of the plain radiographs. For example, physical parameters may include, but are not limited to, bone tissue content G extracted from the plain radiographs, attenuation information of the region of interest in the plain radiographs, and body position information T. Body position information T can refer to one of the following: prone, supine, lateral, head-forward, or feet-forward. The above are merely illustrative examples; any parameter that can be obtained from plain radiograph data can be used as a physical parameter, and the number of physical parameters must be at least one.

[0031] Step S120: Obtain the scanning parameters of the region of interest.

[0032] Parameters related to sparse angle CT scans may also include sparse angle scanning parameters set by the physician. For example, scanning parameters may include, but are not limited to, the scanning voltage and scanning current set by the physician, and at least one of the distances R from the farthest point in the imaging field of view to the scan center; or at least one of the radiation intensity I set by the physician and the distance R from the farthest point in the imaging field of view to the scan center. The radiation intensity I can also be calculated using the scanning voltage and scanning current set by the physician. The above are merely illustrative examples; any parameter relating to the region of interest that can be acquired can be used as a scanning parameter, and the number of scanning parameters must be at least one.

[0033] Step S130: Based on the pre-established mapping relationship between physical parameters and scanning parameters as a whole and the number of scanning angles, physical parameters, and scanning parameters, determine the number of scanning angles of the region of interest.

[0034] Physical parameters, scanning parameters, and the number of scanning angles all affect the intensity of artifacts in sparse-angle CT imaging. Generally, given certain physical and scanning parameters, more scanning angles reduce artifact intensity but result in a higher radiation dose to the scanned body; conversely, fewer scanning angles result in a lower radiation dose but increased artifact intensity. Therefore, this application pre-establishes a mapping relationship between the overall physical and scanning parameters and the number of scanning angles to determine the appropriate number of scanning angles for diagnostic purposes under certain physical and scanning parameter conditions. This number of scanning angles balances the effects of artifacts in the imaging image and the radiation dose to the scanned body, thereby determining the appropriate number of scanning angles for the region of interest. The mapping relationship between the overall physical and scanning parameters and the number of scanning angles can be obtained, but is not limited to, through training a fully connected neural network model. A fully connected convolutional neural network model can include multiple convolutional layers and activation layers following each convolutional layer, with the activation layers using ReLU functions.

[0035] The method for determining the angle number in sparse-angle CT scanning provided in this application involves obtaining the physical parameters of the region of interest (ROI); obtaining the scanning parameters of the ROI; and determining the scanning angle number of the ROI based on a pre-established mapping relationship between the physical parameters, scanning parameters, and the overall scanning angle number, along with the physical parameters and scanning parameters. This method for determining the angle number in sparse-angle CT scanning can reduce artifacts and their impact when the scanning angle is reduced, thereby alleviating the processing pressure of subsequent artifact removal.

[0036] In some embodiments of this application, the physical parameters of the region of interest in the above method include: acquiring pre-scan data of the region of interest; and acquiring the physical parameters of the region of interest based on the pre-scan data.

[0037] Pre-scan data may include plain film data or ultra-low dose pre-scan data; this application will use plain film data as an example for explanation. This application first acquires plain film data of the region of interest (ROI). This plain film data may be obtained, but is not limited to, based on a plain film scan, or retrieved from historical data stored in a database. In CT scanning applications, global CT imaging of the entire scan body is often not required; only images of certain regions of interest (ROIs) are needed. Especially in the field of clinical medical diagnosis, it is sufficient to establish images of suspicious lesions. Therefore, this application acquires plain film data of the ROI to reduce the amount of data and improve the accuracy of angle determination.

[0038] In some embodiments of this application, the physical parameters in the above method include at least one of the following: attenuation information of the region of interest, body position information, and bone density information.

[0039] Since modern commercial CT scans commonly use cone-beam scanning, the attenuation information S of the region of interest (ROI) is the sum of all pixel values ​​in the plain image, used as a reference factor for the dose level of the ROI. Body position information T has a certain impact on the intensity of artifacts. Bone density information G is the sum of the CT values ​​of pixels in the plain image that exceed a first preset threshold. This first preset threshold can be flexibly set according to needs and is not specifically limited here. Bone tissue produces a large number of artifacts; therefore, bone density information G is an important factor affecting the intensity of artifacts. The physical parameters of this application include at least one of S, T, and G to improve the suitability of the determined number of scanning angles.

[0040] In some embodiments of this application, the scanning parameters in the above method include at least one of scanning voltage, scanning current, and the distance from the farthest point from the imaging center in the imaging field of view to the scanning center; or, the scanning parameters include at least one of radiation intensity and the distance from the farthest point from the imaging center in the imaging field of view to the scanning center.

[0041] X-ray intensity I is an important reference factor affecting image quality, and it can be set by the physician. Alternatively, the physician can set the scanning voltage and scanning current instead of directly setting the X-ray intensity I, and then calculate and determine the X-ray intensity I using these parameters. Therefore, both scanning voltage and scanning current, or X-ray intensity, can be used as scanning parameters.

[0042] In sparse-angle CT scans, the imaging artifacts tend to increase in magnitude the further away from the scan center. Therefore, the distance R from the farthest point in the imaging field of view to the scan center is an important factor affecting the intensity of the artifacts.

[0043] In some embodiments of this application, the pre-established mapping relationship between the physical parameters and scanning parameters as a whole and the scanning angle number in the above method includes: a relationship established through a trained angle number model; the angle number model is represented by the following formula (1):

[0044] y = g(f1(x1), ... f n (x n )) Formula (1).

[0045] Where n represents the number of parameters, n≥2 and n includes at least one physical parameter and one scanning parameter, x represents the parameter, f represents the relationship between the parameter and the corresponding reconstructed image artifact, g represents the relationship between the reconstructed image artifact and the minimum number of angles, and y represents the minimum number of angles. Parameters can be either data values ​​or images.

[0046] In one scenario, when the physical parameters include the attenuation information S of the region of interest and the bone density information G, and the scanning parameters include the radiation intensity I and the distance R from the farthest point in the imaging field of view to the imaging center, the number of parameters is 4. The above formula (1) can be specifically expressed as the following formula (2):

[0047] y=g(f1(I), f2(S), f3(R), f4(G)) formula (2).

[0048] Where f1 represents the relationship between the ray intensity I and its corresponding reconstructed image artifacts, f2 represents the relationship between the attenuation information S of the region of interest and its corresponding reconstructed image artifacts, f3 represents the relationship between the distance R from the farthest point from the imaging center to the scanning center in the imaging field of view and its corresponding reconstructed image artifacts, f4 represents the relationship between the bone density information G and its corresponding reconstructed image artifacts, g represents the relationship between the reconstructed image artifacts and the minimum number of angles, and y represents the minimum number of angles required to meet diagnostic needs under the above parameters I, S, R, and G.

[0049] In some embodiments of this application, the angle number model is trained in the above method as follows: a training sample set is constructed, which includes multiple sets of corresponding training parameters and minimum angle numbers; the training sample set is input into the angle number model for training to obtain a trained angle number model. The training parameters include at least physical training parameters and scanning training parameters; each set of corresponding training parameters and minimum angle numbers are obtained by the following methods: obtaining training parameters; performing sparse angle scanning imaging with different training angle numbers according to the training parameters to obtain different scan images; analyzing the artifact intensity of different scan images to determine the angle value with the minimum training angle number in the scan image where the artifact intensity is lower than a preset artifact intensity threshold; using the training parameters and the corresponding angle value as a set of corresponding training parameters and minimum angle numbers; adjusting the training parameters to determine multiple sets of corresponding training parameters and minimum angle numbers.

[0050] First, a training sample set is constructed, which includes multiple sets of corresponding training parameters and the minimum number of angles.

[0051] Obtain first training parameters, which include at least physical training parameters and scanning training parameters. Physical training parameters may include, but are not limited to, bone tissue content G extracted from the plain film image for training, body position information T for training, and attenuation information S of the region of interest in the plain film image for training. Scanning parameters may include, but are not limited to, scanning voltage, scanning current, and the distance R from the farthest point in the imaging field of view to the imaging center for training, or the ray intensity I for scanning and the distance R from the farthest point in the imaging field of view to the imaging center for training. In the case of the angle number model represented by formula (2), the first training parameters include training I1, S1, R1, and G1.

[0052] Using the first training parameter, sparse angle scanning imaging is performed with different numbers of training angles to obtain different scanned images. Sparse angle scanning imaging with different numbers of training angles can be performed in a process from few to many training angles, or in a process from many to few training angles. Each adjustment of the training angle number yields one scanned image, meaning that the number of different scanned images corresponds one-to-one with the number of different training angles.

[0053] The artifact intensity of each scanned image is analyzed to determine the angle value with the fewest training angles among the scanned images where the artifact intensity is lower than the preset artifact intensity threshold. Taking the scanning process from the most training angles to the least training angles as an example, using the first training parameter, scanning with the most training angles usually yields scanned images without artifacts or with very low artifact intensity; then the training angles are gradually reduced, and as the training angles decrease, the artifact intensity of the obtained scanned images will increase; when the artifact intensity of the scanned image is higher than or equal to the preset artifact intensity threshold, the scanned image no longer meets the diagnostic requirements; therefore, the angle value with the fewest training angles among the scanned images where the artifact intensity is lower than the preset artifact intensity threshold is determined. The preset artifact intensity threshold can be flexibly set according to requirements, and is not specifically limited here. In the case of the angle number model represented by formula (2), the angle value is Y1. For example, if the artifact intensity of the scanned image obtained by scanning with a training angle of 101 using the first training parameter is lower than the preset artifact intensity threshold, and the artifact intensity of the scanned image obtained by scanning with a training angle of 100 is higher than the preset artifact intensity threshold, then the determined angle value is 101.

[0054] The first training parameter and the corresponding angle value are used as the first set of corresponding training parameters and minimum number of angles. In the case of the angle number model represented by formula (2), the first set of training samples is [Y1, I1, S1, R1, G1].

[0055] To obtain as many training samples as possible to form a training sample set, the data values ​​of the training parameters are adjusted. Each adjustment of the training parameters determines a corresponding set of training parameters and the minimum number of angles. For example, after determining a set of training samples [Y1, I1, S1, R1, G1] using the first training parameters and the corresponding angle values, the first training parameters are adjusted to obtain the second training parameters I2, S2, R2, G2. Based on the second training parameters, sparse angle scanning imaging is performed at different training angles to obtain different scan images. The artifact intensity of different scan images is analyzed, and the angle value Y2 with the fewest training angles in the scan images with artifact intensity below a preset artifact intensity threshold is determined. [Y2, I2, S2, R2, G2] is used as the second set of training samples. Subsequent adjustments of the training parameters follow the same pattern, which will not be elaborated here. Through the above adjustment process, multiple sets of corresponding training parameters and the minimum number of angles can be obtained as the training sample set.

[0056] Then, the training sample set is input into the angle number model for training, resulting in a trained angle number model.

[0057] In some embodiments of this application, after obtaining the physical parameters of the region of interest and before determining the scanning angle of the region of interest, the method further includes: if the physical parameters do not meet the requirements for using sparse CT scanning, then obtaining conventional scanning parameters; and performing conventional scanning imaging using the conventional scanning parameters.

[0058] In one example, the physical parameters include the weight information of the object to be scanned. If the weight exceeds a preset weight threshold, conventional scanning parameters are obtained, and conventional scanning and imaging are performed using these parameters. In other words, sparse angle scanning cannot be performed when the object to be scanned has a large weight.

[0059] In another example, based on the flat area data, all pixel values ​​of the flat area image are determined. If all pixel values ​​are greater than a second preset threshold, then conventional scanning parameters are obtained, and conventional scanning imaging is performed using these parameters. If all pixel values ​​are greater than the second preset threshold, it indicates the possible presence of metal within the region of interest. In the presence of metal, sparse angle scanning imaging is not recommended because it easily produces artifacts that are extremely difficult to remove. Of course, if the sparse reconstruction algorithm is sufficiently good, sparse angle scanning imaging can be used even when metal is present. Therefore, the method provided in this embodiment is a preferred method.

[0060] If the physical parameters meet the requirements for using sparse CT scanning, then proceed to steps S120 and S130.

[0061] In one example, based on the flat area data, all pixel values ​​of the flat area image are determined; if all pixel values ​​are lower than a second preset threshold, the physical parameters of the region of interest are obtained.

[0062] The presence of metal can be analyzed by examining whether the planar image contains regions with exceptionally high pixel values. Therefore, the planar image data is analyzed to determine all pixel values. If all pixel values ​​are below a second preset threshold (i.e., the planar image does not contain regions with exceptionally high pixel values), the physical parameters of the region of interest are obtained, and sparse angular scanning imaging is performed using the number of scanning angles. The second preset threshold can be flexibly set according to requirements and is not specifically limited here.

[0063] Figure 2 This application illustrates another embodiment of a method for determining the angle number in sparse angle CT scans. According to... Figure 2 As shown, the method for determining the angle number of sparse angle CT scans in this embodiment includes the following steps: S210 to S260:

[0064] Step S210: Obtain pre-scan data of the region of interest.

[0065] Step S220: Based on the pre-scan data, obtain the physical parameters of the region of interest. The physical parameters include at least one of the following: attenuation information of the region of interest, body position information, and bone density information.

[0066] Step S230: Determine whether there are any physical parameters that do not meet the requirements for using sparse CT scanning.

[0067] Step S240: If not, obtain the scanning parameters of the region of interest. The scanning parameters include at least one of the following: scanning voltage, scanning current, and distance from the farthest point from the imaging center in the imaging field of view to the scanning center; or the scanning parameters include at least one of the following: X-ray intensity and distance from the farthest point from the imaging center in the imaging field of view to the scanning center.

[0068] Step S250: Based on the relationships, physical parameters, and scanning parameters established through the trained angle number model, determine the scanning angle number of the region of interest. The angle number model is expressed by the following formula: y = g(f1(x1), ... f n (x n )); n represents the number of parameters, n≥2 and n includes at least one physical parameter and one scanning parameter, x represents the parameter, f represents the relationship between the parameter and the corresponding reconstructed image artifact, g represents the relationship between the reconstructed image artifact and the minimum number of angles, and y represents the minimum number of angles.

[0069] The angle number model in step S250 is trained through the following steps S251 to S257:

[0070] Step S251: Obtain training parameters, which include at least physical training parameters and scanning training parameters.

[0071] Step S252: Based on the training parameters, perform sparse angle scanning imaging with different training angle numbers to obtain different scan images.

[0072] Step S253: Analyze the artifact intensity of different scanned images and determine the angle value with the fewest training angles in the scanned images where the artifact intensity is lower than the preset artifact intensity threshold.

[0073] Step S254: Use the training parameters and the corresponding angle values ​​as a set of corresponding training parameters and minimum number of angles.

[0074] Step S255: Adjust the training parameters and determine multiple sets of corresponding training parameters and minimum number of angles.

[0075] Step S256: Construct a training sample set using multiple sets of corresponding training parameters and the minimum number of angles.

[0076] Step S257: Input the training sample set into the angle number model for training to obtain the trained angle number model.

[0077] Step S260: If yes, obtain the conventional scanning parameters and perform conventional scanning imaging using the conventional scanning parameters.

[0078] Figure 3 An angle number determination device for sparse angle CT scans according to an embodiment of this application is shown.

[0079] according to Figure 3 As shown, the device 300 includes:

[0080] The physical parameter acquisition unit 301 is used to acquire the physical parameters of the region of interest.

[0081] Parameters related to sparse-angle CT scans can include physical parameters of the plain radiographs. For example, physical parameters may include, but are not limited to, bone tissue content G extracted from the plain radiographs, attenuation information of the region of interest in the plain radiographs, and body position information T. Body position information T can refer to one of the following: prone, supine, lateral, head-forward, or feet-forward. The above are merely illustrative examples; any parameter that can be obtained from plain radiograph data can be used as a physical parameter, and the number of physical parameters must be at least one.

[0082] The scanning parameter acquisition unit 302 is used to acquire the scanning parameters of the region of interest.

[0083] Parameters related to sparse angle CT scans may also include sparse angle scanning parameters set by the physician. For example, scanning parameters may include, but are not limited to, the scanning voltage and scanning current set by the physician, and at least one of the distance R from the farthest point in the imaging field of view to the scan center; or at least one of the radiation intensity I set by the physician and the distance R from the farthest point in the imaging field of view to the scan center, where the radiation intensity I can also be calculated using the scanning voltage and scanning current set by the physician. The above are merely illustrative examples; any parameter relating to the region of interest that can be acquired can be used as a scanning parameter, and the number of scanning parameters must be at least one.

[0084] The scanning angle number determination unit 303 is used to determine the scanning angle number of the region of interest based on the pre-established mapping relationship between the physical parameters and scanning parameters as a whole and the scanning angle number, the physical parameters, and the scanning parameters.

[0085] Physical parameters, scanning parameters, and the number of scanning angles all affect the intensity of artifacts in sparse-angle CT imaging. Generally, given certain physical and scanning parameters, more scanning angles reduce artifact intensity but result in a higher radiation dose to the scanned body; conversely, fewer scanning angles result in a lower radiation dose but increased artifact intensity. Therefore, this application pre-establishes a mapping relationship between the overall physical and scanning parameters and the number of scanning angles to determine the appropriate number of scanning angles for diagnostic purposes under certain physical and scanning parameter conditions. This number of scanning angles balances the effects of artifacts in the imaging image and the radiation dose to the scanned body, thereby determining the appropriate number of scanning angles for the region of interest. The mapping relationship between the overall physical and scanning parameters and the number of scanning angles can be obtained, but is not limited to, through training a fully connected neural network model. A fully connected convolutional neural network model can include multiple convolutional layers and activation layers following each convolutional layer, with the activation layers using ReLU functions.

[0086] In some embodiments of this application, the physical parameter acquisition unit 301 in the above-described apparatus 300 is further configured to acquire pre-scan data of the region of interest; and acquire physical parameters of the region of interest based on the pre-scan data.

[0087] In some embodiments of this application, in the above-described device 300, the physical parameters of the region of interest acquired by the physical parameter acquisition unit 301 include at least one of the following: attenuation information of the region of interest, body position information, and bone density information.

[0088] In some embodiments of this application, in the above-described apparatus 300, the scanning parameters of the region of interest acquired by the scanning parameter acquisition unit 302 include at least one of the following: scanning voltage, scanning current, and distance from the farthest point from the imaging center in the imaging field of view to the scanning center; or, the scanning parameters include at least one of the following: radiation intensity and distance from the farthest point from the imaging center in the imaging field of view to the scanning center.

[0089] In some embodiments of this application, in the above-described apparatus 300, the scanning angle number determination unit 303 is further configured to determine the scanning angle number of the region of interest based on the relationship established through a trained angle number model, physical parameters, and scanning parameters. The angle number model is expressed by the following formula: y = g(f1(x1), ... f n (x n )); where n represents the number of parameters, n≥2 and n includes at least one physical parameter and one scanning parameter, x represents the parameter, f represents the relationship between the parameter and the corresponding reconstructed image artifact, g represents the relationship between the reconstructed image artifact and the minimum number of angles, and y represents the minimum number of angles.

[0090] In some embodiments of this application, the scanning angle number determination unit 303 in the above-described apparatus 300 further includes a training sample set construction unit for constructing a training sample set, which includes multiple sets of corresponding training parameters and minimum angle numbers; and a model training unit for inputting the training sample set into an angle number model for training to obtain a trained angle number model. The training parameters include at least physical training parameters and scanning training parameters. Each set of corresponding training parameters and minimum angle numbers is obtained through the following methods: acquiring training parameters; performing sparse angle scanning imaging with different training angle numbers based on the training parameters to obtain different scan images; analyzing the artifact intensity of different scan images to determine the angle value with the minimum training angle number in scan images where the artifact intensity is lower than a preset artifact intensity threshold; using the training parameters and corresponding angle values ​​as a set of corresponding training parameters and minimum angle numbers; and adjusting the training parameters to determine multiple sets of corresponding training parameters and minimum angle numbers.

[0091] In some embodiments of this application, the above-mentioned device 300 further includes: a judgment unit, used to judge whether there is a situation where the physical parameters do not meet the requirements for using sparse CT scanning; a conventional scanning parameter acquisition unit, used to acquire conventional scanning parameters when the judgment unit judges that there is a situation where the physical parameters do not meet the requirements for sparse scanning; and a conventional scanning unit, used to perform conventional scanning imaging with conventional scanning parameters.

[0092] It should be noted that the aforementioned sparse angle CT scan angle number determination device 300 can implement the aforementioned sparse angle CT scan angle number determination method, which will not be elaborated further.

[0093] Figure 4 This is a schematic diagram of the structure of a computer device according to an embodiment of this application. Figure 4 As shown, at the hardware level, the computer device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the computer device may also include other hardware required for its operations.

[0094] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0095] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0096] The processor reads the corresponding computer program from non-volatile memory into memory and then runs it, forming the angle number determination device 300 for sparse angle CT scans at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0097] Obtain the physical parameters of the region of interest;

[0098] Obtain the scanning parameters of the region of interest;

[0099] Based on the pre-established mapping relationship between physical parameters, scanning parameters, and scanning angles, the scanning angles of the region of interest are determined.

[0100] The above is as stated in this application. Figure 3The method executed by the sparse angle CT scan angle number determination device 300 disclosed in the embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0101] This computer device can also perform Figure 3 The method executed by the sparse angle CT scanning angle number determination device 300, and the realization of the sparse angle CT scanning angle number determination device 300 in Figure 3 The functions of the embodiments shown are not described in detail here.

[0102] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a computer device including multiple applications, enable the computer device to perform... Figure 3 The method executed by the angle number determination device 300 for sparse angle CT scanning in the illustrated embodiment is specifically used to perform:

[0103] Obtain the physical parameters of the region of interest;

[0104] Obtain the scanning parameters of the region of interest;

[0105] Based on the pre-established mapping relationship between physical parameters, scanning parameters, and scanning angles, the scanning angles of the region of interest are determined.

[0106] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0111] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0112] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0113] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0114] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for determining the angle number in sparse angle CT scanning, characterized in that, The method includes: Obtain the physical parameters of the region of interest; Obtain the scanning parameters of the region of interest; Based on the pre-established mapping relationship between physical parameters, scanning parameters, and scanning angles, the physical parameters and the scanning parameters are used to determine the scanning angles of the region of interest. The pre-established mapping relationship between the physical parameters and scanning parameters as a whole and the scanning angle number includes: the relationship established through a trained angle number model; The angle model is expressed by the following formula: ； in, Indicates the number of parameters. and It should include at least one physical parameter and one scan parameter. Indicates parameters, This indicates the relationship between the parameters and the corresponding artifacts in the reconstructed image. This represents the relationship between reconstructed image artifacts and the minimum number of angles. This represents the minimum number of angles.

2. The method for determining the angle number in sparse angle CT scanning according to claim 1, characterized in that, The acquisition of the physical parameters of the region of interest includes: Acquire pre-scan data of the region of interest; Based on the pre-scan data, the physical parameters of the region of interest are obtained.

3. The method for determining the angle number in sparse angle CT scanning according to claim 1, characterized in that, The physical parameters include at least one of the following: attenuation information of the region of interest, body position information, and bone density information.

4. The method for determining the angle number in sparse angle CT scanning according to claim 1, characterized in that, The scanning parameters include at least one of the following: scanning voltage, scanning current, and the distance from the farthest point from the imaging center in the imaging field of view to the scanning center; or, the scanning parameters include at least one of the following: radiation intensity and the distance from the farthest point from the imaging center in the imaging field of view to the scanning center.

5. The method for determining the angle number in sparse angle CT scanning according to claim 1, characterized in that, The angle number model is trained in the following way: Construct a training sample set, which includes multiple sets of corresponding training parameters and a minimum number of angles; The training sample set is input into the angle number model for training to obtain a trained angle number model; The training parameters include at least physical training parameters and scanning training parameters; The training parameters and minimum number of angles for each group are obtained using the following method: Obtain training parameters; Based on the training parameters, sparse angle scanning imaging is performed with different training angle numbers to obtain different scan images; Analyze the artifact intensity of different scanned images to determine the angle value with the fewest training angles among the scanned images with artifact intensity lower than a preset artifact intensity threshold; The training parameters and the corresponding angle values ​​are used as a set of corresponding training parameters and minimum number of angles; Adjust the training parameters to determine multiple sets of corresponding training parameters and minimum number of angles.

6. The angle determination method for sparse angle CT scanning according to claim 2, characterized in that, After obtaining the physical parameters of the region of interest and before determining the scanning angle of the region of interest, the method further includes: If the physical parameters do not meet the requirements for using sparse CT scanning, then obtain the conventional scanning parameters; Perform a routine scan and image formation using the aforementioned standard scanning parameters.

7. A device for determining the angle number in sparse angle CT scanning, characterized in that, The device includes: The physical parameter acquisition unit is used to acquire the physical parameters of the region of interest. A scanning parameter acquisition unit is used to acquire the scanning parameters of the region of interest; The scanning angle number determination unit is used to determine the scanning angle number of the region of interest based on a pre-established mapping relationship between physical parameters, scanning parameters and scanning angle number, the physical parameters and the scanning parameters; The pre-established mapping relationship between the physical parameters and scanning parameters as a whole and the scanning angle number includes: the relationship established through a trained angle number model; The angle model is expressed by the following formula: ； in, Indicates the number of parameters. and It should include at least one physical parameter and one scan parameter. Indicates parameters, This indicates the relationship between the parameters and the corresponding artifacts in the reconstructed image. This represents the relationship between reconstructed image artifacts and the minimum number of angles. This represents the minimum number of angles.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for determining the angle number of sparse angle CT scans as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is instructed by the processor, it implements the steps of the method for determining the angle number of sparse angle CT scans as described in any one of claims 1 to 6.

Images