Three-dimensional CT imaging method and device, electronic equipment and storage medium

Abstract

The invention provides a three-dimensional CT imaging method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring two DR images with a vertical relation for a to-be-imaged object, and acquiring three-dimensional coordinate information of the to-be-imaged object; inputting the two DR images with the vertical relation and the three-dimensional coordinate information into a preset three-dimensional volume reconstruction model, and obtaining three-dimensional volume data of the to-be-imaged object; and slicing the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged. According to the method, the three-dimensional volume reconstruction speed can be improved on the basis of ensuring the imaging quality, so that the high-quality three-dimensional CT image can be quickly obtained.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a three-dimensional CT imaging method, device, electronic device, and storage medium. Background Art

[0002] To obtain 3D computed tomography (CT) images, the 3D volume reconstruction problem is usually solved first. The 3D volume reconstruction methods in related technologies, such as 3D volume reconstruction using algorithms such as FDK, and single-projection 3D volume reconstruction methods based on deep learning, etc.

[0003] Although the 3D volume reconstruction using algorithms such as FDK can ensure the imaging quality, the large number of DR images collected in the circumferential direction leads to high data acquisition cost and slow imaging speed.

[0004] When using a single-projection 3D volume reconstruction method based on deep learning, the detailed structure of the reconstruction results of devices with rich internal information is not well restored, that is, the imaging quality cannot be guaranteed.

[0005] Therefore, the related art has not yet provided a technical solution that can both ensure imaging quality and improve the speed of three-dimensional volume reconstruction, and thus cannot quickly obtain high-quality three-dimensional CT images. Summary of the invention

[0006] In view of this, the present application provides a three-dimensional CT imaging method, device, electronic device and storage medium, which can improve the three-dimensional volume reconstruction speed while ensuring the imaging quality, thereby quickly obtaining high-quality three-dimensional CT images.

[0007] To solve the above technical problems, the technical solution of this application is implemented as follows:

[0008] In one embodiment, a three-dimensional CT imaging method is provided, the method comprising:

[0009] Capturing two DR images with a vertical relationship for the object to be imaged, and obtaining three-dimensional coordinate information of the object to be imaged;

[0010] Inputting the two DR images having a vertical relationship and the three-dimensional coordinate information into a preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged;

[0011] Slicing the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged;

[0012] Among them, the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on the three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on the two DR images with a vertical relationship; the fusion model is used to obtain the three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data.

[0013] The generation of the preset three-dimensional volume reconstruction model includes:

[0014] Establishing an initial three-dimensional volume reconstruction model;

[0015] Acquire a training data set; wherein the training data set includes three-dimensional coordinate information of a reference object, two DR images with a vertical relationship, and three-dimensional volume data;

[0016] Using the training data set to train the initial three-dimensional volume reconstruction model; and calculating the loss value of the set loss function according to the calculated value and the reference value; wherein the calculated value is the three-dimensional volume data obtained by the three-dimensional volume reconstruction model during the training process, and the reference value is the three-dimensional volume data in the training data set;

[0017] In response to the loss function being less than a preset loss threshold, the preset three-dimensional volume reconstruction model is obtained.

[0018] Wherein, the loss function is a weighted sum of the first loss, the second loss and the third loss;

[0019] Among them, the first loss is the 2D projection loss of the calculated value and the reference value, the second loss is the structural similarity loss of the calculated value and the reference value; and the third loss is the 3D reconstruction loss of the calculated value and the reference value.

[0020] The weights of the first loss and the third loss are set to be the same and greater than the weight of the second loss.

[0021] The first volume model is used to obtain first volume data based on the three-dimensional coordinate information, including:

[0022] The first volume model encodes the three-dimensional coordinate information through Fourier feature mapping, inputs the encoded three-dimensional coordinate information into a perceptual neural network, performs implicit neural representation learning, and obtains the first volume data.

[0023] The second volume model is used to obtain second volume data based on the two DR images having a vertical relationship, including:

[0024] The second volume model splices the two DR images having a vertical relationship in the width dimension, and inputs the splicing result into the encoding and decoding network to obtain the second volume data.

[0025] The fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data, including:

[0026] The fusion model splices the first volume data and the second volume data in the channel dimension, and obtains the three-dimensional volume data of the object to be imaged through a three-dimensional convolution.

[0027] In another embodiment, a three-dimensional CT imaging device is provided, the device comprising:

[0028] A storage unit, used to store a preset three-dimensional volume reconstruction model; wherein the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on two DR images with a vertical relationship; the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data;

[0029] An acquisition unit, used for acquiring two DR images having a vertical relationship with respect to an object to be imaged, and acquiring three-dimensional coordinate information of the object to be imaged;

[0030] A processing unit, configured to input the two DR images having a vertical relationship and the three-dimensional coordinate information into the preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged;

[0031] A slicing unit is used to slice the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged.

[0032] In another embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a three-dimensional CT imaging method when executing the program.

[0033] In another embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, a three-dimensional CT imaging method is implemented.

[0034] It can be seen from the above technical scheme that the above embodiment does not require full-view projection, and only needs two orthogonal projection images of the object to be imaged, and its three-dimensional coordinate information, which are input into the preset three-dimensional volume reconstruction model to obtain the three-dimensional volume data of the object to be imaged, and then obtain the three-dimensional CT image of the object; wherein the preset three-dimensional volume reconstruction model first obtains the first volume data corresponding to the three-dimensional coordinate information and the second volume data corresponding to the two orthogonal projection images, and then fuses the first volume data and the second volume data to obtain the three-dimensional volume of the object to be imaged. This scheme reduces the scale of training data and the data collected for the object to be imaged through the implementation of two orthogonal projection images; by introducing the three-dimensional coordinate information of the object to be imaged, the generalization of the model is improved, and the speed of three-dimensional volume reconstruction can be improved on the basis of ensuring the imaging quality, thereby quickly obtaining high-quality three-dimensional CT images. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 A schematic diagram of a process for establishing a preset three-dimensional volume reconstruction model in an embodiment of the present application;

[0037] Figure 2 This is a schematic diagram of the structure of the three-dimensional volume reconstruction model in an embodiment of the present application;

[0038] Figure 3 This is a schematic diagram of the MLP network architecture used in the embodiments of the present application;

[0039] Figure 4 This is a schematic diagram of a second volume data structure model in an embodiment of the present application;

[0040] Figure 5 This is a schematic diagram of the three-dimensional CT imaging process in the embodiment of the present application;

[0041] Figure 6 This is a schematic diagram of the structure of a three-dimensional CT imaging device in an embodiment of the present application;

[0042] Figure 7 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe the order or precedence of the objects. It should be understood that the data used in this way can be interchangeable where appropriate, so that the implementation of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0045] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0046] X-ray-based imaging methods, including DR and CT, obtain internal information by attenuating the object through the rays. DR technology is very efficient, but the results observed from a 2D perspective are usually not enough to represent the 3D structure. To accurately describe the internal information of the object being measured, the most direct and accurate method is to construct a complete 3D volume. Compared with DR, CT technology can accurately reconstruct the complete 3D structure of the object being measured.

[0047] Traditional CT reconstruction uses specific reconstruction algorithms such as analytical reconstruction and iterative reconstruction, but these require a lot of calculations. At the same time, due to the limitations of Shannon-Nyquist sampling theorem, the key to high-quality reconstruction is to obtain complete projections. These conditions largely limit the reconstruction speed. The key measure to improve the reconstruction speed is to reduce the projection images and calculations required for reconstruction. Researchers introduced compressed sensing into CT reconstruction and developed a regularization method based on compressed sensing. This type of method uses the prior information of the image to reduce the required projections while ensuring the quality of reconstruction. Recent studies have introduced deep learning technology into sparse view CT reconstruction. By using artificially designed neural networks, the network is allowed to directly learn the mapping function from 2D X-ray projections to 3D CT volumes. Compared with traditional regularization-based methods, deep learning methods extract prior information for predicting CT through data-driven end-to-end networks, which can more feasibly achieve CT reconstruction. At present, this method has also achieved very good results.

[0048] However, deep learning methods also face common limitations in their applications. First, it is difficult to obtain large-scale training data sets, which may constitute a significant bottleneck in certain specific application scenarios because collecting sufficient amounts of data is often accompanied by high costs. In addition, deep learning-based CT reconstruction technology performs poorly in generalization ability and is difficult to adapt to a variety of imaging objects, thus limiting its wide applicability. Furthermore, most of the current deep learning-driven CT reconstruction methods not only have large model parameters, but also complex architectural designs, which not only increases the consumption of computing resources, but also places higher requirements on memory.

[0049] Therefore, the related art has not yet provided a technical solution that can both ensure imaging quality and improve the speed of three-dimensional volume reconstruction, and thus cannot quickly obtain high-quality three-dimensional CT images.

[0050] Based on the above problems, a three-dimensional CT imaging method is provided in the embodiment of the present application. It does not require full-view projection, but only requires two orthogonal projection images of the object to be imaged, and its three-dimensional coordinate information, and inputs a preset three-dimensional volume reconstruction model to obtain the three-dimensional volume data of the object to be imaged, and then obtain a three-dimensional CT image of the object; wherein the preset three-dimensional volume reconstruction model first obtains the first volume data corresponding to the three-dimensional coordinate information and the second volume data corresponding to the two orthogonal projection images, and then fuses the first volume data and the second volume data to obtain the three-dimensional volume of the object to be imaged. This solution reduces the scale of training data and the data collected for the object to be imaged by implementing two orthogonal projection images; by introducing the three-dimensional coordinate information of the object to be imaged, the generalization of the model is improved, and the speed of three-dimensional volume reconstruction can be improved on the basis of ensuring the imaging quality, thereby quickly obtaining a high-quality three-dimensional CT image.

[0051] In the embodiment of the present application, before performing three-dimensional CT imaging, a preset three-dimensional volume reconstruction model needs to be established. Figure 1 , Figure 1 This is a schematic diagram of the process of establishing a preset three-dimensional volume reconstruction model in the embodiment of this application. The specific steps are:

[0052] Step 101: Establish an initial three-dimensional volume reconstruction model.

[0053] In the embodiment of the present application, the initial three-dimensional volume reconstruction model established has the same structure as the preset three-dimensional volume reconstruction model obtained through training, and both include three models, namely: a first volume model, a second volume model and a fusion model;

[0054] Among them, the first volume model is used to obtain the first volume data based on the three-dimensional coordinate information, and the second volume model is used to obtain the second volume data based on two DR images with a vertical relationship; the fusion model is used to obtain the three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data.

[0055] Step 102, obtaining a training data set; wherein the training data set includes three-dimensional coordinate information of a reference object, two DR images with a vertical relationship, and three-dimensional volume data.

[0056] The training data set obtained can be a pre-stored data set or a collected data set.

[0057] The implementation for acquiring the training data set is as follows:

[0058] The circumferential DR images of the reference object are collected; the DR images collected for the reference object are 360 ​​DR images in different directions;

[0059] During the acquisition process, relevant parameters such as tube voltage, tube current, exposure time, and position during the measurement period are guaranteed to remain unchanged.

[0060] The acquired DR images can be preprocessed first, and the preprocessing includes:

[0061] The acquired DR images are cropped, logarithmized, and normalized based on the chip parameters and mechanical parameters.

[0062] Then, the FDK algorithm is used to reconstruct the 3D volume of each reference object, obtaining one-to-one corresponding 3D volume data and 360 DR images in different directions;

[0063] Then, the three-dimensional position coordinate information is obtained for each reference object. The three-dimensional position coordinate information is generated according to the volume size of the reference object. The number of coordinates is the volume size. If the volume size is 128×128×128, then the number of coordinates is 128 cubed.

[0064] In this way, there is a set of corresponding data for each reference object: 3D volume data, 3D position coordinate information and 360 DR images in different directions;

[0065] Select multiple groups of two DR images with a vertical relationship from the 360 ​​DR images in different directions; each group of two DR images with a vertical relationship is combined with the corresponding three-dimensional volume data and three-dimensional position coordinate information as a training sample;

[0066] Two DR images with a vertical relationship for different reference objects can generate a training sample, which in turn constitutes a training data set.

[0067] There is no particular order in which to establish the initial three-dimensional volume reconstruction model and to obtain the training data set, and they can be performed simultaneously or one after the other, and there is no particular order in which to perform step 101 and step 102.

[0068] Step 103: Use the training data set to train the initial three-dimensional volume reconstruction model; and calculate the loss value of the set loss function according to the calculated value and the reference value.

[0069] The calculated value is the three-dimensional volume data obtained by the three-dimensional volume reconstruction model during the training process, and the reference value is the three-dimensional volume data in the training data set.

[0070] The loss function in this embodiment is the weighted sum of the first loss, the second loss and the third loss; wherein the first loss is the 2D projection loss (Projection Loss) of the calculated value and the reference value, the second loss is the structural similarity loss (SSIM Loss) of the calculated value and the reference value; the third loss is the 3D reconstruction loss (Reconstruction Loss) of the calculated value and the reference value.

[0071] The 3D reconstruction loss measures the geometric difference between the predicted 3D structure and the real structure. This loss ensures that the model reconstructs the 3D model as accurately as possible in space; the structural similarity loss focuses on the visual quality and structural consistency of the image. It usually evaluates the similarity between the predicted image and the real image, and can better capture the sensitivity of the human eye to image quality. The 2D projection loss can further improve the training efficiency. Combining the three losses together and weighting them appropriately can comprehensively optimize the model performance from different aspects. This method can effectively improve the robustness and reconstruction accuracy of the model. The specific loss calculation formula is given below:

[0072] L(Y truth ,Y pred )=λ3L re +λ1L pl +λ2LSSIM

[0073] Among them, Y truth Indicates the reference value, Y pred Indicates a calculated value;

[0074] 3D reconstruction loss representing the calculated value and the reference value;

[0075]

[0076] L pl 2D projection loss representing the calculated value and the reference value; P1(Y truth )、P2(Y truth ) and P3(Y truth ) represent the projection reference values ​​in the three directions of depth, width and height, respectively. pred )、P2(Y pred ) and P3(Y pred ) represent the projection calculation values ​​in the three directions of depth, width and height respectively;

[0077] L SSIM (Ypred,Ytruth)=1-SSIM(Ypred,Ytruth)

[0078] L SSIM (Ypred, Ytruth) represents the structural similarity loss of the calculated value and the reference value. Usually, the larger the SSIM value, the better, and the maximum value is 1. Since it is calculated together with the other two losses, 1-SSIM is used here to represent the structural similarity loss.

[0079] Among them, λ1, λ2 and λ3 control the relative importance of different loss terms. In the dual-view CT reconstruction task, global shape consistency is given priority. Based on this, in specific use, the weights of the first loss and the third loss can be set to be the same and greater than the weight of the second loss. For example, λ1=λ3=1, λ2=0.1 are set, but in specific implementation, it is not limited to this.

[0080] Through the above loss function, a loss value can be calculated for each 3D volume reconstruction model in training.

[0081] Step 104 : In response to the calculated loss value being less than a preset loss threshold, a preset three-dimensional volume reconstruction model is obtained.

[0082] In response to a calculated loss value being not less than a preset loss threshold, the three-dimensional volume reconstruction model in training is trained again; before the model training, an initial learning rate and a learning decay rate are set; when training again, the learning rate obtained from the last training is decayed according to the set decay rate, and the three-dimensional volume reconstruction model is trained again.

[0083] The specific structural implementation of the preset three-dimensional volume reconstruction model and the initial three-dimensional volume reconstruction model is given below in conjunction with the accompanying drawings.

[0084] See also Figure 2 , Figure 2 Schematic diagram of the structure of the three-dimensional volume reconstruction model in the embodiment of the present application. Figure 2 The three-dimensional volume reconstruction model in the method includes a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on three-dimensional coordinate information, that is, it is used to process the input three-dimensional coordinate information and output the first volume data; the second volume model is used to obtain second volume data based on two DR images with a vertical relationship, that is, it is used to process the input two DR images with a vertical relationship and output the second volume data; the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data; that is, it is used to fuse the first volume data output by the first model and the second volume data output by the second model, and output the three-dimensional volume data of the object to be imaged.

[0085] The first volume model receives the input three-dimensional coordinate information, encodes the three-dimensional coordinate information through Fourier feature mapping, inputs the encoded three-dimensional coordinate information into the perceptual neural network, performs implicit neural representation learning, and obtains the first volume data.

[0086] Since Fourier features are effective for the network to learn high-frequency functions, we use Fourier feature mapping to encode the spatial coordinates. The specific calculation formula is as follows:

[0087] γ(c)=[cos(2πBc),sin(2πBc)] T

[0088] Among them, B represents the coefficient of Fourier characteristic transform, and B is obtained from Gaussian distribution N(0,σ 2 ), σ is a hyperparameter representing the standard deviation of the prior distribution. In the specific implementation, σ can be 4, but is not limited to this. c is the coordinate information before position encoding, that is, the input three-dimensional coordinate information. γ(c) is the coordinate information after Fourier feature embedding, that is, the encoded three-dimensional coordinate information;

[0089] The encoded three-dimensional coordinate information is used as the input of the perceptual neural network, and implicit neural representation learning is performed through the perceptual neural network to obtain the first volume data.

[0090] The perceptual neural network can be implemented by a multi-layer perceptron (MLP), see Figure 3 , Figure 3 Schematic diagram of the MLP network architecture used in the embodiments of the present application. Figure 3 The MLP depth in is 8, which is implemented by 8 linear networks. The input of the MLP is the encoded three-dimensional coordinate information, and the output is the first volume data. When the MLP is implemented with a depth of 8, a network with a width of 256 neural points is constructed for implicit neural representation learning. Such an implementation requires the size of Fourier feature embedding to be 256. The MLP implementation here is an example implementation, and the specific implementation is not limited to this.

[0091] The second volume model splices two DR images with a vertical relationship in the width dimension, and inputs the splicing result into the encoding and decoding network to obtain the second volume data.

[0092] See also Figure 4 , Figure 4 The schematic diagram of the second volume data structure model in the embodiment of the present application is as follows. The two DR images (the first DR image and the second DR image) with a vertical relationship are spliced ​​in the width dimension through the connector C, and then input into the encoder (Encoder) - reshape (Reshape) module - decoder (Decoder) - output the second volume data.

[0093] The encoder-decoder convolutional neural network is used to extract features from 2D images and align the features of the input image with the voxels in the 3D geometric structure. The encoder is 2D and the decoder is 3D. The modified ResNet can be used as a 2D encoder to extract local and global information from the projected image; then the extracted features are reshaped into 3D volume features through the Reshape operation; then the decoder is used to perform upsampling in sequence, and the decoder restores the reshaped 3D volume features to a 3D feature map aligned with the true value volume.

[0094] The decoder includes 4 upsampling modules and one bilinear interpolation module. Each upsampling module includes a 3D transposed convolution layer, a 3D convolution layer, a 3D BN layer, and a 3D activation (ReLU) layer.

[0095] The first volume data output by the first volume model and the second volume data output by the second volume model both have the same shape as the target result (the three-dimensional volume data of the object to be imaged).

[0096] The fusion model concatenates the first volume data and the second volume data in the channel dimension, and obtains the three-dimensional volume data of the object to be imaged through a three-dimensional convolution.

[0097] So far, the architecture of the preset 3D volume reconstruction model and the detailed implementation process of the training process are given. The preset 3D volume reconstruction model is stored and can be directly obtained and used when 3D volume reconstruction and 3D CT imaging are needed.

[0098] The following is a detailed description of the three-dimensional CT imaging process implemented in the embodiment of the present application in conjunction with the accompanying drawings.

[0099] See also Figure 5 , Figure 5 This is a schematic diagram of the three-dimensional CT imaging process in the embodiment of this application. The specific steps are:

[0100] Step 501 : acquiring two DR images with a vertical relationship for an object to be imaged, and obtaining three-dimensional coordinate information of the object to be imaged.

[0101] In the embodiment of the present application, when acquiring DR images of the object to be imaged, it is sufficient to acquire two DR images having a vertical relationship, and there is no need to acquire 360 ​​DR images in a 360-degree circumferential direction.

[0102] In the process of acquiring two DR images with a vertical relationship, it is ensured that the tube voltage, tube current, exposure time, position during the test and other related parameters remain unchanged and are the same as the parameters of the data acquisition when the data set is acquired.

[0103] Whether to process the acquired DR images and how to process them can be the same as the processing method of the DR images in the training data set, so as to ensure that the expected output can be obtained after being input into the preset three-dimensional volume reconstruction model.

[0104] If the DR images in the sample data set during model training have been preprocessed as follows, the collected DR images are also preprocessed as follows in this step:

[0105] The acquired DR images are cropped, logarithmized, and normalized based on the chip parameters and mechanical parameters.

[0106] The three-dimensional position coordinate information of the object to be imaged is obtained. The three-dimensional position coordinate information is generated according to the volume size of the object to be imaged. The number of coordinates is the volume size. If the volume size is 128×128×128, then the number of coordinates is 128 cubed.

[0107] Step 502: input two DR images having a vertical relationship and three-dimensional coordinate information into a preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged.

[0108] Step 503: Slice the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged.

[0109] The embodiment of the present application does not limit how to slice a three-dimensional volume to obtain a three-dimensional CT image.

[0110] In specific implementation, if the purpose is only to obtain a three-dimensional CT image of the object to be imaged, the implementation of step 503 can also be encapsulated in a preset three-dimensional volume reconstruction model as a three-dimensional CT imaging model; if it is desired to obtain the three-dimensional CT image of the object to be imaged and the three-dimensional volume data of the object to be imaged at the same time, it can be implemented according to the above method disclosed in the embodiments of the present application.

[0111] In the embodiment of the present application, full-view projection is not required. Only two orthogonal projection images of the object to be imaged and its three-dimensional coordinate information are needed to be input into a preset three-dimensional volume reconstruction model to obtain the three-dimensional volume data of the object to be imaged, and then obtain the three-dimensional CT image of the object. This solution reduces the scale of training data and the data collected for the object to be imaged by implementing two orthogonal projection images; by introducing the three-dimensional coordinate information of the object to be imaged, the generalization of the model is improved, and the speed of three-dimensional volume reconstruction can be increased while ensuring the imaging quality, thereby quickly obtaining high-quality three-dimensional CT images.

[0112] Based on the same inventive concept, the present application also provides a three-dimensional CT imaging device. Figure 6 , Figure 6 This is a schematic diagram of the structure of a three-dimensional CT imaging device in an embodiment of the present application. The device includes:

[0113] The storage unit 601 is used to store a preset three-dimensional volume reconstruction model; wherein the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on two DR images with a vertical relationship; the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data;

[0114] An acquisition unit 602 is used to acquire two DR images having a vertical relationship with respect to the object to be imaged, and acquire three-dimensional coordinate information of the object to be imaged;

[0115] The processing unit 603 is used to input the two DR images having a vertical relationship and the three-dimensional coordinate information into a preset three-dimensional volume reconstruction model to obtain the three-dimensional volume data of the object to be imaged;

[0116] The slicing unit 604 slices the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged.

[0117] In another example, the generation of a preset three-dimensional volume reconstruction model includes:

[0118] Establishing an initial three-dimensional volume reconstruction model;

[0119] Acquire a training data set; wherein the training data set includes three-dimensional coordinate information of a reference object, two DR images with a vertical relationship, and three-dimensional volume data;

[0120] Using the training data set to train an initial three-dimensional volume reconstruction model; and calculating a loss value of a set loss function according to a calculated value and a reference value; wherein the calculated value is three-dimensional volume data obtained by the three-dimensional volume reconstruction model during the training process, and the reference value is three-dimensional volume data in the training data set;

[0121] In response to the loss function being less than a preset loss threshold, a preset three-dimensional volume reconstruction model is obtained.

[0122] In another example, the loss function is a weighted sum of the first loss, the second loss, and the third loss;

[0123] Among them, the first loss is the 2D projection loss of the calculated value and the reference value, the second loss is the structural similarity loss of the calculated value and the reference value; the third loss is the 3D reconstruction loss of the calculated value and the reference value.

[0124] In another example, the weights of the first loss and the third loss are set to be the same and greater than the weight of the second loss.

[0125] In another example, the first volume model is used to obtain first volume data based on three-dimensional coordinate information, including:

[0126] The first volume model encodes the three-dimensional coordinate information through Fourier feature mapping, and inputs the encoded three-dimensional coordinate information into the perceptual neural network to perform implicit neural representation learning to obtain the first volume data.

[0127] In another example, the second volume model is used to obtain second volume data based on two DR images having a perpendicular relationship, including:

[0128] The second volume model splices two DR images with a vertical relationship in the width dimension, and inputs the splicing result into the encoding and decoding network to obtain the second volume data.

[0129] In another example, the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data, including:

[0130] The fusion model concatenates the first volume data and the second volume data in the channel dimension, and obtains the three-dimensional volume data of the object to be imaged through a three-dimensional convolution.

[0131] The units in the above-mentioned embodiments may be integrated into one body or deployed separately; they may be combined into one unit or further divided into multiple sub-units.

[0132] In another embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the three-dimensional CT imaging method when executing the program.

[0133] In another embodiment, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, a three-dimensional CT imaging method is implemented.

[0134] Figure 7 Schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, the electronic device may include: a processor (Processor) 710, a communication interface (Communications Interface) 720, a memory (Memory) 730 and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the following method:

[0135] For the object to be imaged, two DR images with a vertical relationship are collected, and the three-dimensional coordinate information of the object to be imaged is obtained;

[0136] Input two DR images with a vertical relationship and three-dimensional coordinate information into a preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged;

[0137] Slicing the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged;

[0138] Among them, the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on two DR images with a vertical relationship; the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data.

[0139] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0140] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0142] The flow chart and block diagram in the accompanying drawings of the present application show the possible architecture, function and operation of the system, method and computer program product according to the various embodiments disclosed in the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in the order of the standards in different figures. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims disclosed in this application may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments and / or claims of this application may be combined and / or combined in a variety of ways, and all of these combinations and / or combinations fall within the scope disclosed in this application.

[0144] Specific embodiments are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas, and is not used to limit the present application. For those skilled in the art, changes can be made in the specific implementation methods and application scopes according to the ideas, spirits and principles of the present invention, and any modifications, equivalent substitutions, improvements, etc. made therein should be included in the scope of protection of this application.

Claims

1. A three-dimensional CT imaging method, characterized in that: The method comprises: Capturing two DR images with a vertical relationship for the object to be imaged, and obtaining three-dimensional coordinate information of the object to be imaged; Inputting the two DR images having a vertical relationship and the three-dimensional coordinate information into a preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged; Slicing the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged; Among them, the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on the three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on the two DR images with a vertical relationship; the fusion model is used to obtain the three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data.

2. The method according to claim 1, characterized in that The generation of the preset three-dimensional volume reconstruction model includes: Establishing an initial three-dimensional volume reconstruction model; Acquire a training data set; wherein the training data set includes three-dimensional coordinate information of a reference object, two DR images with a vertical relationship, and three-dimensional volume data; Using the training data set to train the initial three-dimensional volume reconstruction model; and calculating the loss value of the set loss function according to the calculated value and the reference value; wherein the calculated value is the three-dimensional volume data obtained by the three-dimensional volume reconstruction model during the training process, and the reference value is the three-dimensional volume data in the training data set; In response to the loss function being less than a preset loss threshold, the preset three-dimensional volume reconstruction model is obtained.

3. The method according to claim 2, characterized in that The loss function is a weighted sum of the first loss, the second loss and the third loss; Among them, the first loss is the 2D projection loss of the calculated value and the reference value, the second loss is the structural similarity loss of the calculated value and the reference value; and the third loss is the 3D reconstruction loss of the calculated value and the reference value.

4. The method according to claim 3, characterized in that The weights of the first loss and the third loss are set to be the same and greater than the weight of the second loss.

5. The method according to claim 1, characterized in that The first volume model is used to obtain first volume data based on the three-dimensional coordinate information, including: The first volume model encodes the three-dimensional coordinate information through Fourier feature mapping, inputs the encoded three-dimensional coordinate information into a perceptual neural network, performs implicit neural representation learning, and obtains the first volume data.

6. The method according to claim 1, characterized in that The second volume model is used to obtain second volume data based on the two DR images having a vertical relationship, and includes: The second volume model splices the two DR images having a vertical relationship in the width dimension, and inputs the splicing result into the encoding and decoding network to obtain the second volume data.

7. The method according to claim 1, characterized in that The fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data, including: The fusion model splices the first volume data and the second volume data in the channel dimension, and obtains the three-dimensional volume data of the object to be imaged through a three-dimensional convolution.

8. A three-dimensional CT imaging device, characterized in that: The device comprises: A storage unit, used to store a preset three-dimensional volume reconstruction model; wherein the preset three-dimensional volume reconstruction model includes: a first volume model, a second volume model and a fusion model; the first volume model is used to obtain first volume data based on three-dimensional coordinate information, and the second volume model is used to obtain second volume data based on two DR images with a vertical relationship; the fusion model is used to obtain three-dimensional volume data of the object to be imaged based on the first volume data and the second volume data; An acquisition unit, used for acquiring two DR images having a vertical relationship with respect to an object to be imaged, and acquiring three-dimensional coordinate information of the object to be imaged; A processing unit, configured to input the two DR images having a vertical relationship and the three-dimensional coordinate information into the preset three-dimensional volume reconstruction model to obtain three-dimensional volume data of the object to be imaged; A slicing unit is used to slice the three-dimensional volume data to obtain a three-dimensional CT image of the object to be imaged.

9. An electronic 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 program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

Images