CT imaging method and apparatus, and device and storage medium

Abstract

A CT imaging method and apparatus, and a device and a storage medium. The CT imaging method comprises: by means of a first-layer detector and a second-layer detector of a double-layer detector, respectively collecting first projection data and second projection data that correspond to a target object (S110); determining multiple types of sub-pixels on the basis of the first projection data and pixels of the first-layer detector (S120); determining a target signal strength of each type of sub-pixel on the basis of the first projection data and the second projection data, and on the basis of the target signal strength, obtaining a target projection signal corresponding to the double-layer detector (S130); and on the basis of a super-resolution network model, performing super-resolution processing on the target projection signal to obtain a super-resolution imaging signal, and obtaining a super-resolution imaging image on the basis of the super-resolution imaging signal (S140).

Description

CT imaging method, device, equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 17, 2023, with application number 202310869034.3. The entire contents of the above application are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of CT imaging technology, for example, to a CT imaging method, apparatus, device and storage medium. Background Art

[0003] Cone Beam Computed Tomography (CBCT) is a three-dimensional tomographic imaging technology based on flat-panel detectors and is widely used in the medical field. However, the resolution of CT imaging has always been limited.

[0004] Summary of the Invention

[0005] The present application provides a CT imaging method, apparatus, device and storage medium.

[0006] According to one aspect of the present application, a CT imaging method is provided, wherein the method comprises:

[0007] Collecting first projection data and second projection data corresponding to the target object through a first layer detector and a second layer detector in the double-layer detector respectively;

[0008] determining a plurality of types of sub-pixels based on the first projection data and pixels of the first layer of detectors;

[0009] determining a target signal intensity of each type of the sub-pixel based on the first projection data and the second projection data, and obtaining a target projection signal corresponding to the double-layer detector based on the target signal intensity;

[0010] The target projection signal is super-resolution processed based on a super-resolution network model to obtain a super-resolution imaging signal, and a super-resolution imaging image is obtained based on the super-resolution imaging signal.

[0011] According to another aspect of the present application, a CT imaging device is provided, wherein the device includes:

[0012] A projection data acquisition module is configured to respectively acquire first projection data and second projection data corresponding to the target object through a first layer detector and a second layer detector in the double-layer detector;

[0013] a sub-pixel determination module configured to determine multiple types of sub-pixels based on the first projection data and pixels of the first layer of detectors;

[0014] a signal strength determination module configured to determine a target signal strength of each type of the sub-pixel based on the first projection data and the second projection data, and obtain a target projection signal corresponding to the double-layer detector based on the target signal strength;

[0015] The image imaging module is configured to perform super-resolution processing on the target projection signal based on a super-resolution network model to obtain a super-resolution imaging signal, and obtain a super-resolution imaging image based on the super-resolution imaging signal.

[0016] According to another aspect of the present application, an electronic device is provided, comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the CT imaging method described in any embodiment of the present application.

[0020] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the CT imaging method described in any embodiment of the present application when executed.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] FIG1 is a flow chart of a CT imaging method provided according to Embodiment 1 of the present application;

[0023] FIG2 is a scene diagram of sub-pixel imaging of a double-layer detector provided according to an embodiment of the present application;

[0024] FIG3 is a structural diagram of an RNN network model provided according to an embodiment of the present application;

[0025] FIG4 is a flow chart of a CT imaging method provided according to Example 2 of the present application;

[0026] FIG5 is a schematic structural diagram of a CT imaging device provided according to Example 3 of the present application;

[0027] FIG6 is a schematic diagram of the structure of an electronic device for implementing the CT imaging method according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] Related technologies for improving the spatial resolution of CT imaging include X-ray source-based flying spot technology, detector sub-pixel shifting technology, and deep learning techniques. However, these technologies require improvements in hardware and post-processing algorithms, and suffer from high equipment costs, long acquisition times, strong data dependence, poor interpretability, and low generalization. Deep learning techniques require extensive data training, resulting in poor interpretability and generalization. Consequently, the spatial resolution of CT imaging in related technologies is relatively poor.

[0029] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Example 1

[0032] FIG1 is a flow chart of a CT imaging method according to a first embodiment of the present application. This embodiment can perform CT imaging. The method can be performed by a CT imaging device. The CT imaging device can be implemented in the form of hardware and / or software. The CT imaging device can be configured in computer software. As shown in FIG1 , the method includes:

[0033] S110 , respectively collecting first projection data and second projection data corresponding to the target object using a first layer detector and a second layer detector in a double-layer detector.

[0034] The dual-layer detector is a flat-panel detector comprising a first layer of detectors and a second layer of detectors. The target object can be understood as an object to be imaged by a computed tomography (CT) scan. In the embodiments of the present application, the target object can be preset based on scenario requirements and is not specifically limited herein. For example, the target object can be limestone.

[0035] The first projection data may be understood as projection data corresponding to the target object acquired by the first layer of detectors. The second projection data may be understood as projection data corresponding to the target object acquired by the second layer of detectors.

[0036] For example, before respectively collecting the first projection data and the second projection data corresponding to the target object through the first layer detector and the second layer detector of the double-layer detector, the method further includes:

[0037] Illuminating a target object with a target light source so that a light beam passing through the target object is projected onto the first layer of detectors and the second layer of detectors, and the width of the light beam projected onto the second layer of detectors in a single pass is equal to the width of a pixel of the second layer of detectors;

[0038] Scanning the light beam along the pixels of the second layer of detectors from a first direction to a second direction to obtain a first real-time light beam projected onto the first layer of detectors and a second real-time light beam projected onto the second layer of detectors, so as to obtain first projection data corresponding to the first real-time light beam and second projection data corresponding to the second real-time light beam;

[0039] The target light source can be understood as a light source that illuminates the target object. The first layer of detectors is located between the second layer of detectors and the target light source, the target object is located between the first layer of detectors and the target light source, and the target light source is located on the central axis of the double-layer detectors (see Figure 2).

[0040] The first direction can be understood as the starting direction of the light beam scanning along the second layer of detectors. The second direction can be understood as the ending direction of the light beam scanning along the second layer of detectors. In the embodiment of the present application, the first and second directions can be preset based on scenario requirements and are not specifically limited here. For example, the first direction can be to the left of the second layer of detectors, and the second direction can be to the right of the second layer of detectors.

[0041] The first real-time light beam may be understood as a real-time light beam projected onto the first layer of detectors. The second real-time light beam may be understood as a real-time light beam projected onto the second layer of detectors.

[0042] S120 . Determine multiple types of sub-pixels based on the first projection data and pixels of the first layer of detectors.

[0043] It can be understood that when the width of the light beam projected onto the second layer detector in a single time is equal to the width of the pixel of the second layer detector, and the light beam is scanned from the first direction to the second direction along the pixel of the second layer detector, the first real-time light beam projected onto the first layer detector will be cut into real-time light beams of different sizes by the boundary points of the pixels of the first layer detector. In this embodiment of the present application, the pixels corresponding to the real-time light beams of different sizes cut by the boundary points of the pixels of the first layer detector are determined as the sub-pixels (refer to Figure 2).

[0044] For example, the first projection data includes a first real-time boundary point and a second real-time boundary point of the first real-time light beam, and the determining of multiple types of sub-pixels based on the first projection data and pixels of the first layer of detectors includes:

[0045] Using pixels corresponding to the first real-time light beam as projection pixels, and determining the projection pixels surrounded by pixels of the first layer of detectors as sub-pixels of a first type;

[0046] Determining the projected pixel, whose first boundary is the first real-time boundary point and whose second boundary is a boundary point of a pixel of the first layer of detectors, as a second type of sub-pixel;

[0047] The projection pixel whose first boundary is a boundary point of the pixel of the first layer detector and whose second boundary is a second real-time boundary point is determined as a sub-pixel of the third type.

[0048] The projection pixel may be understood as a pixel corresponding to the first real-time light beam.

[0049] The first boundary and the second boundary can be understood as the two boundaries of the sub-pixel. In the embodiment of the present application, the first boundary and the second boundary can also be preset according to the scene requirements and are not specifically limited here. For example, the first boundary can be the left boundary of the sub-pixel, and the second boundary can be the right boundary.

[0050] The first real-time boundary point and the second real-time boundary point can be understood as the two real-time boundary points of the first real-time light beam. In the embodiment of the present application, the first real-time boundary point and the second real-time boundary point can also be preset according to the scene requirements, and are not specifically limited here. Exemplarily, the first real-time boundary point can be the left boundary point of the first real-time light beam, and the second real-time boundary point can be the right boundary point of the first real-time light beam.

[0051] The first type can be understood as the type of sub-pixels corresponding to sub-pixels enclosed by pixels of the first layer of detectors. The second type can be understood as the type of sub-pixels corresponding to sub-pixels whose first boundary is the first real-time boundary point and whose second boundary is a boundary point of pixels of the first layer of detectors. The third type can be understood as the type of sub-pixels corresponding to sub-pixels whose first boundary is a boundary point of pixels of the first layer of detectors and whose second boundary is a second real-time boundary point.

[0052] S130 : Determine a target signal intensity of each type of the sub-pixel based on the first projection data and the second projection data, and obtain a target projection signal corresponding to the double-layer detector based on the target signal intensity.

[0053] The target signal intensity can be understood as the signal intensity corresponding to the sub-pixel. In the embodiment of the present application, the target signal intensities corresponding to different types of sub-pixels can be the same or different. The target projection signal can be understood as the projection signal corresponding to the double-layer detector.

[0054] S140 , performing super-resolution processing on the target projection signal based on a super-resolution network model to obtain a super-resolution imaging signal, and obtaining a super-resolution imaging image based on the super-resolution imaging signal.

[0055] The super-resolution network model can be understood as a model that has the function of super-resolution processing of the target projection signal. In the embodiment of the present application, the super-resolution network model can be preset according to the scene requirements and is not specifically limited here. For example, the super-resolution network model can be a recurrent neural network (RNN) model.

[0056] The super-resolution imaging signal can be understood as an imaging signal obtained by super-resolution processing of the target projection signal. The super-resolution imaging image can be understood as an imaging image corresponding to the super-resolution imaging signal. For example, the super-resolution imaging image can be a super-resolution CT image.

[0057] For example, the first projection data further includes first energy information of the first real-time light beam, the second projection data further includes second energy information of the second real-time light beam, and the super-resolution processing of the target projection signal based on the super-resolution network model to obtain the super-resolution imaging signal includes:

[0058] Performing horizontal super-resolution and vertical super-resolution processing on the input target projection signal, the first energy information, and the second energy information through a super-resolution network model to obtain a super-resolution imaging signal.

[0059] The super-resolution network model includes a horizontal super-resolution model and a vertical super-resolution model.

[0060] The first energy information may be understood as the energy information of the first real-time light beam, and the second energy information may be understood as the energy information of the second real-time light beam.

[0061] The horizontal super-resolution model can be understood as a model that performs horizontal super-resolution on the target projection signal. The vertical super-resolution model can be understood as a model that performs vertical super-resolution on the target projection signal. In the embodiment of the present application, the horizontal super-resolution model and the vertical super-resolution model included in the super-resolution network model are simultaneously used to perform horizontal super-resolution and vertical super-resolution processing on the target projection signal, thereby improving the spatial resolution of the obtained super-resolution imaging signal and thus improving the spatial resolution of the determined super-resolution imaging image.

[0062] It is important to understand that the RNN network can decode the image corresponding to the target projection signal of the encoded double-layer detector, thereby obtaining a super-resolution imaging image corresponding to the higher-resolution super-resolution imaging signal. In addition, the RNN network's powerful nonlinear fitting ability can also well fit the energy spectrum differences between multi-layer detectors. Referring to Figure 3, taking the double-layer detector data as an example, when the front and back layer pixels between the double-layer detectors are asymmetric about the central axis, the image corresponding to the entire target projection signal needs to be input into the network for training; when the front and back layer pixels between the double-layer detectors are symmetric about the central axis, only the left half or right half of the image needs to be input into the network for training, which saves image training time and improves model training efficiency.

[0063] As shown in Figure 3, the RNN network contains six hidden layers, with 16, 32, 64, 64, 32, and 4 nodes in each layer, respectively. The activation function for each node in the layer is the Leaky Rectified Linear Unit (Leaky ReLU). The input and output image resolutions of the RNN network are M×N and M×2N, respectively. M is the number of pixels in the vertical direction of the image, and N is the number of pixels in the horizontal direction. The loss function of the RNN network is the Mean Squared Error (MSE) function.

[0064] As can be seen, horizontal super-resolution of the image corresponding to the target projection signal of the dual-layer detector is achieved. It can be understood that if the input data is changed from horizontal to vertical during network training, the network input and output image resolutions become M×N and 2M×N, respectively. This means that vertical super-resolution of the image corresponding to the target projection signal of the dual-layer detector can be achieved.

[0065] In an embodiment of the present application, two-dimensional image super-resolution is achieved using a double-layer flat-panel detector. For example, an RNN network is first used to super-resolution the image corresponding to the target projection signal in the horizontal or vertical direction, and then the RNN network is used to super-resolution the image in the other direction to achieve two-dimensional image super-resolution. This image super-resolution method requires training two different RNN networks using image data in the horizontal and vertical directions, respectively, to obtain a horizontal super-resolution model and a vertical super-resolution model. The horizontal super-resolution model and the vertical super-resolution model are then used to simultaneously perform horizontal super-resolution and vertical super-resolution processing on the image corresponding to the target projection signal with an input resolution of M×N, thereby obtaining an output image with a resolution of 2M×2N corresponding to the super-resolution imaging signal.

[0066] It should be understood that the above-mentioned image super-resolution processing method can also be used for multi-layer detectors with three or more layers. From the perspective of signal extraction, the number of signal sampling points and the degree of information aliasing collected by a multi-layer (≧3) detector are more and more complex than those of a double-layer detector, and also contain more object space information, which also makes it possible to reconstruct images with higher resolution. From the perspective of mathematical models, the difference between building a super-resolution mathematical model for a multi-layer (≧3) detector and building a mathematical model for a double-layer detector is that more inter-layer pixel combinations need to be considered. In the super-resolution task of a multi-layer (≧3) detector, the image input and output resolutions of the RNN network become M×N and LM×LN, where L is the number of detector layers.

[0067] In an embodiment of the present application, first projection data and second projection data corresponding to a target object are collected by the first layer detector and the second layer detector in a double-layer detector, respectively; multiple types of sub-pixels are determined based on the first projection data and the pixels of the first layer detector; the target signal intensity of each type of the sub-pixel is determined based on the first projection data and the second projection data, and the target projection signal corresponding to the double-layer detector is obtained based on the target signal intensity, thereby ensuring the accuracy and signal-to-noise ratio of the determined target projection signal; the target projection signal is super-resolution processed based on a super-resolution network model to obtain a super-resolution imaging signal, and a super-resolution imaging image is obtained based on the super-resolution imaging signal, thereby significantly improving the spatial resolution of CT imaging.

[0068] Example 2

[0069] FIG4 is a flow chart of a CT imaging method provided in Example 2 of the present application. This embodiment describes the determination of the target signal intensity of each type of sub-pixel based on the first projection data and the second projection data as described in the above embodiment. As shown in FIG4 , the method includes:

[0070] S210 , respectively collecting first projection data and second projection data corresponding to the target object using a first layer detector and a second layer detector in a double-layer detector.

[0071] S220: Determine multiple types of sub-pixels based on the first projection data and pixels of the first layer of detectors.

[0072] The first projection data further includes a first signal intensity of the first real-time light beam, and the second projection data includes a second signal intensity of the second real-time light beam.

[0073] The first signal strength may be understood as the signal strength of the first real-time light beam, and the second signal strength may be understood as the signal strength of the second real-time light beam.

[0074] S230: Obtain the pixel width of the double-layer detector, the first distance between the target light source and the first layer detector, the second distance between the target light source and the second layer detector, and the second real-time coordinates of the second real-time boundary point, and determine the magnification ratio according to the first distance and the second distance.

[0075] The pixel width can be understood as the width of a pixel in the dual-layer detector. The first distance can be understood as the distance between the target light source and the first layer of detectors. The second distance can be understood as the distance between the target light source and the second layer of detectors. The second real-time coordinates can be understood as the real-time coordinates of the second real-time boundary point of the first real-time light beam. The magnification ratio can be understood as the ratio between the first distance and the second distance.

[0076] S240 : For the first type of sub-pixel, determine second subscript information according to the magnification ratio, the pixel width, and the second real-time coordinate.

[0077] The second subscript information is the subscript of the pixel of the light beam corresponding to the current sub-pixel in the second layer of detectors.

[0078] In one example, the subscript of a pixel can be understood as the index of the detector pixel in the detector array.

[0079] S250: Determine the target signal strength according to the second subscript information and the second signal strength.

[0080] In one embodiment, determining the target signal intensity of each type of sub-pixel based on the first projection data and the second projection data further includes:

[0081] Acquire first real-time coordinates of the first real-time boundary point;

[0082] For the second type of sub-pixel, determining the first subscript information according to the magnification ratio, the first real-time coordinate, and the pixel width, wherein the first subscript information is the subscript of the current sub-pixel in the pixel of the first layer of detectors;

[0083] The second subscript information is determined according to the second real-time coordinate and the pixel width, and the target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

[0084] The first real-time coordinates may be understood as the real-time coordinates of the first real-time boundary point of the first real-time light beam.

[0085] In one embodiment, determining the target signal intensity of each type of sub-pixel based on the first projection data and the second projection data further includes:

[0086] For the sub-pixel of the third type, determining the first subscript information according to the second real-time coordinate and the pixel width;

[0087] determining second subscript information according to the magnification ratio, the second real-time coordinate, and the pixel width;

[0088] The target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

[0089] For example, as shown in FIG2 , determining the target signal intensity of each type of sub-pixel based on the first projection data and the second projection data may be:

[0090] Wherein, s1 represents the sub-pixel whose first subscript information is 1, s2 represents the sub-pixel whose first subscript information is 2, s3 represents the sub-pixel whose first subscript information is 3, s4 represents the sub-pixel whose first subscript information is 4, and s5 represents the sub-pixel whose first subscript information is 5. Indicates the second signal strength with the second subscript information being 1, Indicates the first signal strength with the first subscript information being 1, Indicates the second signal strength with the second subscript information being 2, Indicates the first signal strength with the first subscript information being 2, Indicates the second signal strength with the second subscript information being 3.

[0091] For example, the calculation formula for the current sub-pixel width is:

[0092] in, Indicates the width of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, Indicates the first real-time coordinate of the current sub-pixel.

[0093] For example, the calculation formula for the amplification ratio of the first layer detector to the second layer detector is:

[0094] Where γ represents the amplification ratio, represents the second distance, Indicates the first distance.

[0095] For example, the calculation formulas for the first real-time coordinate and the second real-time coordinate of the current sub-pixel are:

[0096] in, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ k Indicates the current sub-pixel width.

[0097] For the first type of sub-pixels:

[0098] Where γ represents the amplification ratio, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0099] Among them, i0 represents the second subscript information, γ represents the magnification ratio, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0100] For the second type of sub-pixels:

[0101] Where γ represents the amplification ratio, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0102] Wherein, i0 represents the second subscript information, j0 represents the first subscript information, γ represents the magnification ratio, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0103] For the third type of sub-pixels:

[0104] Where γ represents the amplification ratio, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0105] Wherein, i0 represents the second subscript information, j0 represents the first subscript information, γ represents the magnification ratio, Indicates the first real-time coordinate of the current sub-pixel, Indicates the second real-time coordinate of the current sub-pixel, δ del Indicates the pixel width of the double-layer detector.

[0106] In summary, the calculation formula for determining the target signal intensity of each type of sub-pixel based on the first projection data and the second projection data is:

[0107] in, Indicates the target signal strength of the current sub-pixel, i0 indicates the second subscript information of the current type of sub-pixel, j0 indicates the first subscript information of the current type of sub-pixel, Indicates the second signal strength corresponding to the current sub-pixel, Indicates the first signal strength corresponding to the first subscript information, Indicates the second signal strength corresponding to the second subscript information.

[0108] S260: Obtain a target projection signal corresponding to the double-layer detector based on the target signal intensity.

[0109] In an embodiment of the present application, multiple types of sub-pixels are determined directly based on the inter-layer pixel offset phenomenon existing in existing multi-layer (≧2) detectors, and CT imaging is performed based on the target signal intensities of the multiple types of sub-pixels. There is no need to make major system improvements to the existing CT imaging equipment. Only the existing single-layer flat-panel detector needs to be replaced to greatly improve the spatial resolution of the imaging equipment, and high-efficiency and low-cost CT imaging can be achieved.

[0110] S270 , performing super-resolution processing on the target projection signal based on a super-resolution network model to obtain a super-resolution imaging signal, and obtaining a super-resolution imaging image based on the super-resolution imaging signal.

[0111] In this embodiment of the present application, the pixel width of the dual-layer detector, the first distance between the target light source and the first-layer detector, the second distance between the target light source and the second-layer detector, and the second real-time coordinates of the second real-time boundary point are obtained, and the amplification ratio is determined based on the first and second distances. For the first type of sub-pixel, second subscript information is determined based on the amplification ratio, the pixel width, and the second real-time coordinates, where the second subscript information is the subscript of the pixel of the second-layer detector corresponding to the light beam of the current sub-pixel. The target signal intensity is determined based on the second subscript information and the second signal intensity. This ensures the accuracy of the target signal intensity corresponding to each type of sub-pixel determined.

[0112] In one embodiment, the CT imaging method provided in the embodiment of the present application can be implemented by a CT imaging device. In one example, the CT imaging device can include the above-mentioned double-layer detector.

[0113] Example 3

[0114] FIG5 is a schematic diagram of the structure of a CT imaging device provided in Example 3 of the present application. As shown in FIG5 , the device includes: a projection data acquisition module 310, a sub-pixel determination module 320, a signal intensity determination module 330, and an image imaging module 340; wherein,

[0115] The projection data acquisition module 310 is configured to respectively collect first projection data and second projection data corresponding to the target object through the first layer detector and the second layer detector in the double-layer detector; the sub-pixel determination module 320 is configured to determine multiple types of sub-pixels based on the first projection data and the pixels of the first layer detector; the signal intensity determination module 330 is configured to determine the target signal intensity of each type of the sub-pixel based on the first projection data and the second projection data, and obtain the target projection signal corresponding to the double-layer detector based on the target signal intensity; the image imaging module 340 is configured to perform super-resolution processing on the target projection signal based on a super-resolution network model to obtain a super-resolution imaging signal, and obtain a super-resolution imaging image based on the super-resolution imaging signal.

[0116] In an embodiment of the present application, first projection data and second projection data corresponding to a target object are collected by the first layer detector and the second layer detector in a double-layer detector, respectively; multiple types of sub-pixels are determined based on the first projection data and the pixels of the first layer detector; the target signal intensity of each type of the sub-pixel is determined based on the first projection data and the second projection data, and the target projection signal corresponding to the double-layer detector is obtained based on the target signal intensity, thereby ensuring the accuracy and signal-to-noise ratio of the determined target projection signal; the target projection signal is super-resolution processed based on a super-resolution network model to obtain a super-resolution imaging signal, and a super-resolution imaging image is obtained based on the super-resolution imaging signal, thereby significantly improving the spatial resolution of CT imaging.

[0117] In one embodiment, the CT imaging device further includes: a beam projection module and a beam scanning module; wherein,

[0118] The light beam projection module is configured to illuminate the target object through a target light source before the light beam passes through the first layer detector and the second layer detector of the double-layer detector to respectively collect the first projection data and the second projection data corresponding to the target object, so that the light beam passing through the target object is projected onto the first layer detector and the second layer detector, and the width of the light beam projected on the second layer detector in a single time is equal to the width of the pixel of the second layer detector;

[0119] The beam scanning module is configured to scan the light beam along the pixels of the second layer of detectors from a first direction to a second direction, to obtain a first real-time light beam projected onto the first layer of detectors and a second real-time light beam projected onto the second layer of detectors, so as to obtain first projection data corresponding to the first real-time light beam and second projection data corresponding to the second real-time light beam;

[0120] The first layer of detectors is located between the second layer of detectors and the target light source, the target object is located between the first layer of detectors and the target light source, and the target light source is located on the central axis of the double-layer detectors.

[0121] In one embodiment, the first projection data includes a first real-time boundary point and a second real-time boundary point of the first real-time light beam, and the sub-pixel determination module 320 is configured as follows:

[0122] Using pixels corresponding to the first real-time light beam as projection pixels, and determining the projection pixels surrounded by pixels of the first layer of detectors as sub-pixels of a first type;

[0123] Determining the projected pixel, whose first boundary is the first real-time boundary point and whose second boundary is a boundary point of a pixel of the first layer of detectors, as a second type of sub-pixel;

[0124] The projection pixel whose first boundary is a boundary point of the pixel of the first layer detector and whose second boundary is a second real-time boundary point is determined as a sub-pixel of the third type.

[0125] In one embodiment, the first projection data further includes a first signal intensity of the first real-time light beam, and the second projection data includes a second signal intensity of the second real-time light beam. The signal intensity determination module 330 is configured as follows:

[0126] Obtaining a pixel width of the double-layer detector, a first distance between the target light source and the first-layer detector, a second distance between the target light source and the second-layer detector, and a second real-time coordinate of the second real-time boundary point, and determining a magnification ratio according to the first distance and the second distance;

[0127] For the first type of sub-pixel, determining second subscript information based on the magnification ratio, the pixel width, and the second real-time coordinate, wherein the second subscript information is the subscript of the pixel of the light beam corresponding to the current sub-pixel on the second layer of detectors;

[0128] The target signal strength is determined according to the second subscript information and the second signal strength.

[0129] In one embodiment, the signal strength determination module 330 is further configured to:

[0130] Acquire first real-time coordinates of the first real-time boundary point;

[0131] For the second type of sub-pixel, determining the first subscript information according to the magnification ratio, the first real-time coordinate, and the pixel width, wherein the first subscript information is the subscript of the current sub-pixel in the pixel of the first layer of detectors;

[0132] The second subscript information is determined according to the second real-time coordinate and the pixel width, and the target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

[0133] In one embodiment, the signal strength determination module 330 is further configured to:

[0134] For the sub-pixel of the third type, determining the first subscript information according to the second real-time coordinate and the pixel width;

[0135] determining second subscript information according to the magnification ratio, the second real-time coordinate, and the pixel width;

[0136] The target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

[0137] In one embodiment, the first projection data further includes first energy information of the first real-time light beam, and the second projection data further includes second energy information of the second real-time light beam. The imaging module 340 is configured as follows:

[0138] Performing horizontal super-resolution and vertical super-resolution processing on the input target projection signal, the first energy information, and the second energy information through a super-resolution network model to obtain a super-resolution imaging signal.

[0139] The super-resolution network model includes a horizontal super-resolution model and a vertical super-resolution model.

[0140] The CT imaging device provided in the embodiments of the present application can execute the CT imaging method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0141] Example 4

[0142] FIG6 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0143] As shown in FIG6 , the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, that is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the ROM 12 or the computer program loaded from the storage unit 18 into the RAM 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0144] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0145] The processor 11 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the CT imaging method.

[0146] In some embodiments, the CT imaging method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the CT imaging method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the CT imaging method in any other suitable manner (e.g., via firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementation in one or more computer programs that can be executed and / or interpreted on a programmable system comprising at least one programmable processor, which can be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a dedicated computer, or other programmable data processing device so that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0148] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. Examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs) or flash memories, optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and virtual private server (VPS) services.

[0152] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0153] The above specific embodiments do not constitute a limitation on the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors.

Claims

1. A CT imaging method, comprising: The first layer detector and the second layer detector of the double-layer detector respectively collect the first projection data and the second projection data corresponding to the target object; Determining a plurality of types of sub-pixels based on the first projection data and pixels of the first layer of detectors; Determine the target signal intensity of each type of the sub-pixel based on the first projection data and the second projection data, and obtain the target projection signal corresponding to the double-layer detector based on the target signal intensity; The target projection signal is super-resolution processed based on a super-resolution network model to obtain a super-resolution imaging signal, and a super-resolution imaging image is obtained based on the super-resolution imaging signal.

2. The method according to claim 1, before respectively collecting the first projection data and the second projection data corresponding to the target object by the first layer detector and the second layer detector in the double layer detector, further comprising: Irradiating a target object through a target light source so that a light beam passing through the target object is projected onto the first layer of detectors and the second layer of detectors, and a width of the light beam projected once onto the second layer of detectors is equal to a width of a pixel of the second layer of detectors; Scanning the light beam along the pixels of the second layer of detectors from the first direction to the second direction to obtain a first real-time light beam projected on the first layer of detectors and a second real-time light beam projected on the second layer of detectors, so as to obtain the first projection data corresponding to the first real-time light beam and the second projection data corresponding to the second real-time light beam; The first layer of detectors is located between the second layer of detectors and the target light source, the target object is located between the first layer of detectors and the target light source, and the target light source is located on the central axis of the double-layer detectors.

3. The method according to claim 2, wherein: The first projection data includes a first real-time boundary point and a second real-time boundary point of the first real-time light beam, and the determining of multiple types of sub-pixels based on the first projection data and pixels of the first layer of detectors includes: Using pixels corresponding to the first real-time light beam as projection pixels, and determining the projection pixels wrapped by the pixels of the first layer of detectors as sub-pixels of the first type; Determine the projected pixel whose first boundary is the first real-time boundary point and whose second boundary is a boundary point of the pixel of the first layer of detectors as a sub-pixel of the second type; The projection pixel whose first boundary is a boundary point of the pixel of the first layer detector and whose second boundary is a second real-time boundary point is determined as a sub-pixel of the third type.

4. The method according to claim 3, wherein: The first projection data further includes a first signal intensity of the first real-time light beam, the second projection data includes a second signal intensity of the second real-time light beam, and determining the target signal intensity of each type of the sub-pixel based on the first projection data and the second projection data includes: Acquire the pixel width of the double-layer detector, the first distance between the target light source and the first-layer detector, the second distance between the target light source and the second-layer detector, and the second real-time coordinates of the second real-time boundary point, and determine the magnification ratio according to the first distance and the second distance; For the first type of sub-pixel, second subscript information is determined according to the magnification ratio, the pixel width, and the second real-time coordinate, wherein the second subscript information is the subscript of the pixel of the light beam corresponding to the current sub-pixel in the second layer of the detector; The target signal strength is determined according to the second index information and the second signal strength.

5. The method according to claim 4, further comprising: Acquire the first real-time coordinates of the first real-time boundary point; For the second type of sub-pixel, determining first subscript information according to the magnification ratio, the first real-time coordinate, and the pixel width, wherein the first subscript information is the subscript of the current sub-pixel in the pixel of the first layer of detectors; The second subscript information is determined according to the second real-time coordinate and the pixel width, and the target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

6. The method according to claim 4, further comprising: For the third type of sub-pixel, determining the first subscript information according to the second real-time coordinate and the pixel width; Determine second subscript information according to the magnification ratio, the second real-time coordinate, and the pixel width; The target signal strength is determined according to the first subscript information, the second subscript information, the first signal strength, and the second signal strength.

7. The method according to claim 1, wherein: The first projection data further includes first energy information of the first real-time light beam, the second projection data further includes second energy information of the second real-time light beam, and the super-resolution processing of the target projection signal based on the super-resolution network model to obtain the super-resolution imaging signal includes: The super-resolution network model performs horizontal super-resolution and vertical super-resolution processing on the input target projection signal, the first energy information and the second energy information to obtain a super-resolution imaging signal. Wherein, the super-resolution network model includes a horizontal super-resolution model and a vertical super-resolution model.

8. A CT imaging device, comprising: A projection data acquisition module, configured to respectively acquire first projection data and second projection data corresponding to the target object through a first layer detector and a second layer detector in the double-layer detector; a sub-pixel determination module, configured to determine a plurality of types of sub-pixels based on the first projection data and pixels of the first layer of detectors; a signal strength determination module, configured to determine a target signal strength of each type of the sub-pixel based on the first projection data and the second projection data, and obtain a target projection signal corresponding to the double-layer detector based on the target signal strength; The image imaging module is configured to perform super-resolution processing on the target projection signal based on a super-resolution network model to obtain a super-resolution imaging signal, and obtain a super-resolution imaging image based on the super-resolution imaging signal.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the CT imaging method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the CT imaging method according to any one of claims 1 to 7 when executed.

Images