Method and apparatus for constructing an extended image sequence, and device

Abstract

The application discloses a method and device for constructing an extended image sequence, and relates to the technical field of image sequence reconstruction, and mainly aims to improve the low authenticity of the simulated object extended image sequence constructed at present, so that the difference between the simulated object and the real projected object is large, and the authenticity of the forward projection is poor. The method comprises the following steps: obtaining tomography data of a target projected object; performing tomography image reconstruction processing on the tomography data to generate a tomography reconstruction image sequence of the target projected object, the tomography reconstruction image sequence of the target projected object being used for representing the maximum image sequence reconstructed under the current reconstruction condition; and constructing an extended image sequence of a simulated projected object matched with the target projected object based on the tomography reconstruction image sequence of the target projected object, the extended image sequence being used for representing the extended image sequence of the simulated projected object which is not reconstructed and needs to be virtually constructed under the current reconstruction condition.

Description

Technical Field

[0001] This application relates to the field of image sequence reconstruction technology, and in particular to a method, apparatus, and device for constructing extended image sequences. Background Technology

[0002] In modern medical diagnostics, CT (Computed Tomography) is widely used in disease examinations and health checkups due to its short scan time and clear images. In CT iterative reconstruction algorithms, simulated forward projection data is crucial, directly determining the quality of the CT image. Therefore, the simulated object data used for forward projection directly affects the projection result. To obtain simulated object data that closely approximates the real projected object, it is necessary to construct such data. The model for the simulated object data comes from CT reconstructed images; however, sometimes CT reconstructed images cannot completely reconstruct the simulated object data, leading to significant differences between the simulated object and the real projected object, thus affecting the realism of the forward projection. Summary of the Invention

[0003] In view of this, this application provides a method, apparatus, and device for constructing extended image sequences, the main purpose of which is to improve the problem that the existing constructed extended image sequences of simulated objects have low realism, resulting in large differences between simulated objects and real projected objects, leading to poor realism of forward projection.

[0004] According to one aspect of this application, a method for constructing an extended image sequence is provided, comprising:

[0005] Acquire tomographic scan data of the target projected object;

[0006] The tomographic scan data is subjected to tomographic scan image reconstruction processing to generate a tomographic scan reconstructed image sequence of the target projection object. The tomographic scan reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions.

[0007] Based on the tomographic reconstruction image sequence of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed.

[0008] Preferably, before acquiring the tomographic scan data of the target projected object, the method further includes:

[0009] Acquire the planar image data of the target projection object;

[0010] The construction of an extended image sequence of a simulated projection object matching the target projection object based on the tomographic reconstructed image sequence of the target projection object specifically includes:

[0011] Based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed.

[0012] Preferably, the step of constructing an extended image sequence of a simulated projection object matching the target projection object based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object specifically includes:

[0013] A compression mapping model is established based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object;

[0014] Based on the compression mapping model and the planar image data of the target projected object, reconstruction processing is performed to obtain an extended image sequence.

[0015] Preferred options also include:

[0016] The expanded image sequence is corrected based on the tomographic reconstructed image sequence of the target projected object to obtain a corrected expanded image sequence, wherein the correction includes size and / or sharpness adjustment.

[0017] Preferably, the step of constructing an extended image sequence of a simulated projection object matching the target projection object based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object includes:

[0018] Obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence;

[0019] The tomographic reconstruction image sequence of the target projection object and the planar image data of the target projection object are processed by multinomial fitting or neural network model to obtain the complete sequence of the equivalent phantom.

[0020] The extended image sequence is extracted from the complete sequence of the equivalent phantom.

[0021] Preferably, constructing an extended image sequence of a simulated projected object that matches the target projected object based on the tomographic reconstructed image sequence of the target projected object includes:

[0022] Obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence;

[0023] Based on the tomographic reconstruction image sequence of the target projected object, obtain the equivalent radius of the position in the equivalent phantom corresponding to the tomographic reconstruction image sequence;

[0024] Based on the equivalent phantom and the equivalent radius, the expansion radius corresponding to the simulated projected object in each image of the expanded image sequence is determined.

[0025] The extended image sequence is generated by performing polynomial fitting or neural network model processing on the tomographic reconstructed image sequence of the extended radius and the target projected object.

[0026] Preferably, after constructing an extended image sequence of a simulated projected object that matches the target projected object based on the tomographic reconstructed image sequence of the target projected object, the method further includes:

[0027] By combining the extended image sequence and the tomographic reconstruction image sequence of the target projection object, a complete image sequence simulating the projection object is generated.

[0028] According to another aspect of this application, an apparatus for constructing an extended image sequence is provided, comprising:

[0029] The first acquisition module is used to acquire the tomographic scan data of the target projected object;

[0030] The reconstruction module is used to perform tomographic image reconstruction processing on the tomographic scan data to generate a tomographic reconstructed image sequence of the target projection object. The tomographic reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions.

[0031] The construction module is used to construct an extended image sequence of a simulated projection object that matches the target projection object based on the tomographic reconstruction image sequence of the target projection object. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed.

[0032] Preferably, before the first acquisition module, the device further includes:

[0033] The second acquisition module is used to acquire the planar image data of the target projection object;

[0034] The construction module is specifically used for:

[0035] Based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed.

[0036] Preferably, the construction module specifically includes:

[0037] The establishment unit is used to establish a compression mapping model based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object;

[0038] The first reconstruction unit is used to perform reconstruction processing based on the compression mapping model and the planar image data of the target projected object to obtain an extended image sequence.

[0039] Preferred options also include:

[0040] The trimming unit is used to correct the extended image sequence based on the tomographic reconstruction image sequence of the target projected object, so as to obtain a corrected extended image sequence, wherein the correction includes size and / or sharpness adjustment.

[0041] Preferably, the construction module includes:

[0042] An acquisition unit is used to acquire an equivalent phantom of the target projected object, wherein the equivalent phantom includes the positions corresponding to the tomographic scan sequence and the extended sequence;

[0043] The fitting unit is used to process the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object through multinomial fitting or neural network model to obtain the complete sequence of the equivalent phantom.

[0044] An extraction unit is used to extract the extended image sequence from the complete sequence of the equivalent phantom.

[0045] Preferably, the construction module includes:

[0046] The acquisition unit is used to acquire the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence;

[0047] The reconstruction unit is used to obtain the equivalent radius of the position corresponding to the tomographic reconstruction image sequence in the equivalent phantom based on the tomographic reconstruction image sequence of the target projected object.

[0048] The determining unit is used to determine the expansion radius corresponding to the simulated projection object of each image in the expanded image sequence based on the equivalent phantom and the equivalent radius;

[0049] The fitting unit is also used to perform polynomial fitting or neural network model processing on the extended radius and the tomographic reconstruction image sequence of the target projected object to generate an extended image sequence.

[0050] Preferably, after the construction module, the device further includes:

[0051] The generation module is used to combine the extended image sequence and the tomographic reconstruction image sequence of the target projection object to generate a complete image sequence simulating the projection object.

[0052] According to another aspect of this application, a storage medium is provided that stores at least one executable instruction that causes a processor to perform operations corresponding to the above-described method for constructing extended image sequences.

[0053] According to another aspect of this application, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0054] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described method for constructing the extended image sequence.

[0055] By employing the above technical solutions, the technical solutions provided in the embodiments of this application have at least the following advantages:

[0056] This application provides a method, apparatus, and device for constructing extended image sequences. First, tomographic scan data of a target projection object is acquired. Second, tomographic scan image reconstruction processing is performed on the tomographic scan data to generate a tomographic scan reconstructed image sequence of the target projection object. This tomographic scan reconstructed image sequence of the target projection object represents the maximum image sequence reconstructed under the current reconstruction conditions. Finally, based on the tomographic scan reconstructed image sequence of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed. This extended image sequence represents the extended image sequence of simulated projection objects that were not reconstructed under the current reconstruction conditions and need to be virtually constructed. Compared with existing technologies, this application's embodiment, by reconstructing the maximum image sequence reconstructed under the current reconstruction conditions and constructing an extended image sequence of simulated projection objects that were not reconstructed under the current reconstruction conditions and need to be virtually constructed based on this maximum image sequence, further generates an image sequence of the simulated projection object. This reduces the error between the simulated object and the real projection object, improves the realism of the extended image sequence of the simulated object, and thus ensures the realism of the forward projection.

[0057] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0058] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0059] Figure 1 A flowchart illustrating a method for constructing an extended image sequence according to an embodiment of this application is shown;

[0060] Figure 2 This diagram illustrates the relationship between the distance data of the transmission wave covering the rotation center provided in this embodiment and the maximum image sequence reconstructed by the target projected object under the current reconstruction conditions.

[0061] Figure 3 A schematic diagram of a tomographic scan provided in an embodiment of this application is shown;

[0062] Figure 4 This illustration shows a schematic diagram of a flat film image provided in an embodiment of this application;

[0063] Figure 5 This paper illustrates the mapping relationship between the flat image and the reconstructed image provided in an embodiment of this application.

[0064] Figure 6 A flowchart illustrating the 2D to 3D conversion process provided in an embodiment of this application is shown.

[0065] Figure 7 A flowchart illustrating the flat-plane-based correction process provided in an embodiment of this application is shown.

[0066] Figure 8 This illustrates incomplete planar image data provided in an embodiment of this application;

[0067] Figure 9 The image data of the cross section provided in the embodiment of this application are shown;

[0068] Figure 10 A flowchart illustrating the construction process of the extended image sequence provided in an embodiment of this application is shown;

[0069] Figure 11 This illustration shows a block diagram of an apparatus for constructing an extended image sequence according to an embodiment of this application;

[0070] Figure 12 A schematic diagram of the structure of a terminal provided in an embodiment of this application is shown. Detailed Implementation

[0071] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0072] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0073] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.

[0074] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0075] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0076] The embodiments of this application can be applied to computer systems / servers that can operate with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems, etc.

[0077] Computer systems / servers can be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0078] This application provides a method for constructing extended image sequences, such as... Figure 1 As shown, the method includes:

[0079] 101. Obtain the tomographic scan data of the target projected object.

[0080] In this embodiment, tomography is a slice imaging technique that uses any kind of penetrating wave. It can be used in scientific fields such as radiology, archaeology, biology, atmospheric science, geophysics, oceanography, plasma physics, materials science, astrophysics, and quantum information. After tomographic scanning of the target projection object using penetrating waves such as X-rays, the analog signal r received by the detector is converted into a digital signal. The attenuation coefficient of each pixel is calculated by a computer to obtain tomographic scan data. The target projection object can be any object to be to be tomographic scanned or a patient. This embodiment does not make any specific limitation.

[0081] 102. Perform tomographic image reconstruction processing on the tomographic scan data to generate a sequence of tomographic reconstructed images of the target projected object.

[0082] The tomographic reconstructed image sequence of the target projected object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions, that is, the image sequence of the part of the target projected object contained in the tomographic data. In this embodiment, the tomographic data of the target projected object obtained in step 101 is subjected to tomographic image reconstruction processing to generate the maximum image sequence reconstructed by the target projected object under the current reconstruction conditions.

[0083] It should be noted that when performing tomographic image reconstruction processing on tomographic scan data, back projection method, iterative reconstruction algorithm, and analytical methods including filtered back projection method and Fourier transform method can all be used. The embodiments of this application do not make specific limitations.

[0084] 103. Based on the tomographic reconstruction image sequence of the target projection object, construct an extended image sequence of the simulated projection object that matches the target projection object.

[0085] The extended image sequence is used to represent the extended image sequence of the simulated projected object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed. In this embodiment of the application, an extended image sequence of the simulated projected object that matches the target projected object is constructed based on the maximum image sequence reconstructed under the current reconstruction conditions in step 102, that is, an extended image sequence virtually constructed under the current reconstruction conditions.

[0086] It should be noted that when constructing an extended image sequence of a simulated projected object that matches the target projected object, a polynomial fitting can be directly performed based on the maximum image sequence reconstructed under the current reconstruction conditions to obtain the extended function, thereby constructing the extended image sequence; alternatively, a polynomial fitting can be performed based on the maximum image sequence reconstructed under the current reconstruction conditions and on the planar image data obtained before the tomographic scan to obtain the extended function, thereby constructing the extended image sequence. No specific limitation is made in the embodiments of this application.

[0087] In existing technologies, when constructing an extended image sequence of a simulated projected object that matches the target projected object, it is usually done as follows: Figure 2 As shown, firstly, the distance data ConeBeamZCover covering the rotation center in the tomographic scan, and the image interval distance data in the image sequence are obtained. The quotient of the distance data ConeBeamZCover covering the rotation center and the image interval distance data is calculated to obtain the number of images covering the rotation center. Secondly, the difference between the number of images covering the rotation center and the number of images in the maximum image sequence reconstructed under the current reconstruction conditions is calculated to obtain the number of images in the virtually constructed extended image sequence. The relationship between the distance data covering the rotation center and the maximum image sequence reconstructed under the current reconstruction conditions is as follows: Figure 3 As shown; finally, based on the following formula, the extended image sequence of the simulated projected object matching the target projected object is calculated.

[0088]

[0089]

[0090] Wherein, Pad Im g(x,y,z) pad Image(x,y,z) represents a virtual extended image sequence under the current reconstruction conditions, where x,y,z represent the z-th image, the y-th row, and the x-th column. img () represents the maximum image sequence reconstructed under the current reconstruction conditions, where x, y, z represent the z-th image, the y-th row, and the x-th column; Let Image(x,y,z) represent the complete image sequence of the simulated projected object, where x,y,z represent the z-th image, the y-th row, and the x-th column. img In the expression, z is the longest of N images, and PadImg(x,y,z) is the longest of N images. pad M images are needed, in Image(x,y,z) img There are M / 2 images before and after the first image. The first M / 2 images are Image(x,y,z1), and the second M / 2 images are Image(x,y,z1). NCopy M / 2 Image(x,y,z) directly from the beginning. img The first image in the image(x,y,z) is used as the first expanded image, and M / 2 images are copied from the end. img The last image in the sequence is used as the tail extension image, thus obtaining the complete image sequence of the simulated projected object:

[0091]

[0092] However, while the above construction method is simple, its accuracy is low.

[0093] Compared with the prior art, the embodiments of this application reconstruct the maximum image sequence reconstructed under the current reconstruction conditions, and construct an extended image sequence of the simulated projected object that was not reconstructed under the current reconstruction conditions and needs to be virtually constructed based on the maximum image sequence, and further generate an image sequence of the simulated projected object, thereby reducing the error between the simulated object and the real projected object, improving the realism of the extended image sequence of the simulated object, and thus ensuring the realism of the forward projection.

[0094] For further explanation and limitation, in the embodiments of this application, before acquiring the tomographic scan data of the target projected object, the method further includes: acquiring the planar image data of the target projected object; constructing an extended image sequence of a simulated projected object that matches the target projected object based on the tomographic scan reconstructed image sequence of the target projected object, specifically including: constructing an extended image sequence of a simulated projected object that matches the target projected object based on the tomographic scan reconstructed image sequence of the target projected object and the planar image data of the target projected object.

[0095] Among them, planar image data is image data created by a penetrating wave through a projected target object, forming image data with no thickness and overlapping images within the aperture range; that is, planar image data, such as... Figure 4 As shown. It should be noted that in the early stage of the tomographic scan, a planar image scan is performed to obtain the two-dimensional information of the target projection object, which is used to locate the area to be scanned. Subsequent planar images will not be used again. The planar images contain information of the real scanned object, which can be used to enhance the realism of the extended phantom and improve the realism of the simulated forward projection. In order to obtain a complete image sequence of the simulated projection object that is closer to the target projection object, in this embodiment, the maximum image sequence reconstructed under the current reconstruction conditions is combined with the planar image data obtained before the tomographic scan to perform polynomial fitting to obtain the extended function, and then the extended image sequence is constructed. This can effectively reduce the error between the simulated object and the real projection object, improve the realism of the extended image sequence of the simulated object, and thus ensure the realism of the forward projection.

[0096] To improve the realism of the extended image sequence, in this embodiment, based on the tomographic reconstructed image sequence of the target projected object and the planar image data of the target projected object, an extended image sequence of a simulated projected object matching the target projected object is constructed. Specifically, this includes: establishing a compression mapping model based on the tomographic reconstructed image sequence of the target projected object and the planar image data of the target projected object; and performing reconstruction processing based on the compression mapping model and the planar image data of the target projected object to obtain the extended image sequence.

[0097] It should be noted that the flat-panel image data Polit Im g(x,z) polit Proj(x,y,z) can be viewed as the target projected object. cover An image where all or part of the data is compressed from three dimensions into a two-dimensional image can be likened to the shadow of a three-dimensional object. In the embodiments of this application, Polit Im g(x,z) is used. polit ) is all from Proj(x,y,z) cover ) in this situation. Specifically, such as Figure 5 As shown, the right figure can be seen as the largest image sequence Image(x,y,z) reconstructed under the current reconstruction conditions. img Mapping to the flat image data in the left image: Polit Im g(x,z) polit In the dashed arrow section, firstly, through Image(x,y,z)... img ) and PolitIm g(x,z polit Establish a compression mapping function Then through The function `PolitImg(x,z)` extracts data from a flat-panel image. polit The extended image sequence PadImg(x,y,z) is derived from the current reconstruction conditions. pad ).

[0098] For example, in via The function `PolitImg(x,z)` extracts data from a flat-panel image. polit The extended image sequence PadImg(x,y,z) is derived from the current reconstruction conditions. pad When performing image processing, two-dimensional point cloud data of the image and two-dimensional point cloud data of the image contour can be obtained; then, the two-dimensional point cloud data of the image can be reconstructed using the two-dimensional point cloud data of the image. The processing flow is as follows: Figure 6 As shown

[0099] Optionally, in the embodiments of this application, the method further includes: correcting and extending the image sequence based on the tomographic reconstruction image sequence of the target projected object to obtain the corrected extended image sequence.

[0100] The corrections include size and / or sharpness adjustments. Specifically, this is based on the largest image sequence Image(x,y,z) reconstructed under the current reconstruction conditions. img The extended image sequence PadImg(x,y,z) is derived under the current reconstruction conditions. pad The process involves adjustments, including size and sharpness adjustments, ultimately resulting in the corrected extended image sequence PadImg(x,y,z) generated under the current reconstruction conditions. pad For example, this can be achieved using Image(x,y,z). img Modify the image content and numerical values ​​in PadImg(x,y,z) pad The expanded content and size can be achieved using image fusion technology, adaptive filtering, and other techniques.

[0101] As a feasible method, the trimming process is as follows: Figure 7 As shown, by using Polit Im g(x,z) polit ) and Image(x,y,z) img Using these as training data, a neural training network is built, and Polit Im g(x,z) is achieved through artificial intelligence neural training methods. polit ) and Image(x,y,z) img They can be converted into each other. The neural training network can employ any machine learning method, and this application does not impose specific limitations on this method.

[0102] In another embodiment of this application, based on the tomographic reconstruction image sequence of the target projected object and the planar image data of the target projected object, an extended image sequence of a simulated projected object matching the target projected object is constructed, including: obtaining an equivalent phantom of the target projected object; processing the tomographic reconstruction image sequence of the target projected object and the planar image data of the target projected object through a polynomial fitting or neural network model to obtain a complete sequence of the equivalent phantom; and extracting the extended image sequence from the complete sequence of the equivalent phantom.

[0103] The equivalent phantom includes the positions corresponding to the tomographic scan sequence and the extended sequence.

[0104] It should be noted that, as one possible scenario, the embodiments of this application are used to construct an extended image sequence for the portion of the target projection object not included in the planar image data of the target projection object, i.e., Polit Im g(x,z) polit This does not fully cover Pad Im g(x,y,z) pad In cases like this, multinomial fitting or neural network models, along with flat-panel image construction, can be combined to generate extended image sequences. Specifically, for example... Figure 8 As shown, a complete image sequence simulating a projected object. It is a complete head, but the top of the head is missing in the flat-panel image data. Understandably, Pad Im g(x,y,z) pad The extended image sequence Pad Im g1(x,y,z) is the portion of the target projected object contained in the planar image data of the target projected object. pad 1) and the extended image sequence Pad Im g2(x,y,z) of the portion of the target projected object not included in the planar image data of the target projected object. pad2 The extended image sequence PadIm g1(x,y,z) is composed of a portion of the planar image data of the target projected object. pad1 Polit Im g(x,z) can be derived from flat image data. polit The reconstructed extended image sequence PadIm g2(x,y,z) is the portion of the planar image data not included in the target projected object. pad2 ) is for Polit Im g(x,z) data that exceeds the flat image data polit The range of () can be calculated using the following formula:

[0105]

[0106] Pad Im g2(x,y,z pad2 )=g{Polit Im g(x,z polit Image(x,y,z) img )}

[0107] Pad Im g(x,y,z pad = Pad Im g1(x,y,z) pad1 )+Pad Im g2(x,y,z pad2 )

[0108] Here, g() represents a polynomial fitting function, which can be configured differently according to the actual situation. For example, if the missing part is the top of the head, g() can be configured as an elliptic function g()={(x^2 / a+y ^ 2 / b=c),Image(x,y,z)},

[0109] Where a represents the distance between the focus and the upper endpoint of the y-axis; b represents half the distance between the two intersection points of the ellipse and the y-axis; and c represents half the distance between the two foci.

[0110] The shape information of the missing location is obtained by fitting an elliptic function, and the corresponding CT value of the image is calculated using Image(x,y,z).

[0111] In another embodiment of this application, constructing an extended image sequence of a simulated projected object matching the target projected object based on a tomographic reconstructed image sequence of the target projected object includes: obtaining an equivalent phantom of the target projected object; obtaining the equivalent radius of the position in the equivalent phantom corresponding to the tomographic reconstructed image sequence based on the tomographic reconstructed image sequence of the target projected object; determining the extended radius corresponding to the simulated projected object of each image in the extended image sequence based on the equivalent phantom and the equivalent radius; and performing polynomial fitting or neural network model processing on the extended radius and the tomographic reconstructed image sequence of the target projected object to generate the extended image sequence.

[0112] The equivalent phantom includes the positions corresponding to the tomographic scan sequence and the extended sequence. It should be noted that since the tomographic scan of an object ultimately yields a transmitted wave attenuation value, any projected target object, regardless of its shape, can be equivalently represented as a cylindrical water phantom with the same attenuation as the projected target object. Specifically, it is based on the largest reconstructed image sequence Image(x,y,z) under the current reconstruction conditions. img Obtain the equivalent water model radius WaterR(z) img ), where f water Image(x,y,z) img ))=WaterR(z img Since the flat-panel image data is mainly stored as data of the transmitted wave at a fixed angle, the radius is estimated by measuring the attenuation of the flat-panel image data. When recommending the scanning current using the ACS, the equivalent attenuation area is first calculated, such as... Figure 9 As shown, the equivalent attenuation area is:

[0113]

[0114]

[0115] Here, α represents the water coefficient of the tomographic scan. By statistically analyzing the area of ​​the flat-section image data and proportionally converting it to a radius, i.e., calculating the area s from the flat-section image, and then deriving R. Further, based on the equivalent water model radius WaterR(z)... pad Determine the virtual extended image sequence Pad Im g(x,y,z) under the current reconstruction conditions. pad The corresponding WaterR(Pad Im g(z)) pad Finally, combine WaterR(Pad Im g(z)) pad Image(x,y,z) and Image(x,y,z) img Polynomial fitting is performed to generate an extended image sequence PadImg(x,y,z). padThe formula is as follows:

[0116] Pad Im g(x,y,z pad )=g(WaterR(Pad Im g(z pad Image(x,y,z) img ))

[0117] Here, g() represents the constructor.

[0118] In addition, if a parameter adjustment instruction for the constructor required for polynomial fitting is detected, polynomial fitting is performed again on the tomographic reconstructed image sequence of the target projected object and the planar image data of the target projected object according to the parameter-adjusted constructor, so as to update the extended image sequence.

[0119] It should be noted that if the difference between the constructed extended image sequence and the target projected object is greater than a preset threshold, the extended image sequence can be updated by adjusting the parameters of the constructor.

[0120] For further explanation and limitation, in the embodiments of this application, after constructing an extended image sequence of a simulated projected object that matches the target projected object based on the tomographic reconstruction image sequence of the target projected object, the method of the embodiments further includes: combining the extended image sequence and the tomographic reconstruction image sequence of the target projected object to generate a complete image sequence of the simulated projected object.

[0121] Specifically, based on the above embodiments, an extended image sequence PadImg(x,y,z) of the target projected object can be obtained. img Furthermore, through the formula This yields a complete image sequence of the simulated projected object, which can be used for forward projection.

[0122] In specific application scenarios, such as Figure 10 As shown, when constructing an extended image sequence of a simulated projected object that matches the target projected object, a polynomial fitting can be directly performed based on the maximum image sequence reconstructed under the current reconstruction conditions to obtain the construction extension function, thereby constructing the extended image sequence; alternatively, a polynomial fitting can be performed based on the maximum image sequence reconstructed under the current reconstruction conditions and on the flat image data obtained before the tomographic scan to obtain the construction extension function, thereby constructing the extended image sequence.

[0123] This application provides a method for constructing an extended image sequence. First, tomographic scan data of a target projection object is acquired. Second, tomographic scan image reconstruction processing is performed on the tomographic scan data to generate a tomographic scan reconstructed image sequence of the target projection object. This tomographic scan reconstructed image sequence of the target projection object is used to represent the maximum image sequence reconstructed under the current reconstruction conditions. Finally, based on the tomographic scan reconstructed image sequence of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed. This extended image sequence is used to represent the extended image sequence of simulated projection objects that are not reconstructed under the current reconstruction conditions and need to be virtually constructed. Compared with existing technologies, this application's embodiment, by reconstructing the maximum image sequence reconstructed under the current reconstruction conditions and constructing an extended image sequence of simulated projection objects that are not reconstructed under the current reconstruction conditions and need to be virtually constructed based on this maximum image sequence, further generates an image sequence of simulated projection objects. This reduces the error between the simulated object and the real projection object, improves the realism of the extended image sequence of the simulated object, and thus ensures the realism of the forward projection.

[0124] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this application provides an apparatus for constructing extended image sequences, such as... Figure 11 As shown, the device includes:

[0125] First, the acquisition module 21, the reconstruction module 22, and the construction module 23.

[0126] The first acquisition module 21 is used to acquire the tomographic scan data of the target projected object;

[0127] Reconstruction module 22 is used to perform tomographic image reconstruction processing on the tomographic scan data to generate a tomographic reconstructed image sequence of the target projection object. The tomographic reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions.

[0128] The construction module 23 is used to construct an extended image sequence of a simulated projection object that matches the target projection object based on the tomographic reconstruction image sequence of the target projection object. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed.

[0129] In specific application scenarios, before the first acquisition module, the device further includes:

[0130] The second acquisition module is used to acquire the planar image data of the target projection object;

[0131] The construction module is specifically used for:

[0132] Based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed.

[0133] In specific application scenarios, the construction module specifically includes:

[0134] A unit is established to build a compression mapping model based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object.

[0135] The first reconstruction unit is used to perform reconstruction processing based on the compression mapping model and the planar image data of the target projected object to obtain an extended image sequence.

[0136] In specific application scenarios, it also includes:

[0137] The trimming unit is used to correct the extended image sequence based on the tomographic reconstruction image sequence of the target projected object, so as to obtain a corrected extended image sequence, wherein the correction includes size and / or sharpness adjustment.

[0138] In specific application scenarios, the construction module includes:

[0139] An acquisition unit is used to acquire an equivalent phantom of the target projected object, wherein the equivalent phantom includes the positions corresponding to the tomographic scan sequence and the extended sequence;

[0140] The fitting unit is used to process the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object through multinomial fitting or neural network model to obtain the complete sequence of the equivalent phantom.

[0141] An extraction unit is used to extract the extended image sequence from the complete sequence of the equivalent phantom.

[0142] In specific application scenarios, the construction module includes:

[0143] The acquisition unit is used to acquire the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence;

[0144] The reconstruction unit is used to obtain the equivalent radius of the position corresponding to the tomographic reconstruction image sequence in the equivalent phantom based on the tomographic reconstruction image sequence of the target projected object.

[0145] The determining unit is used to determine the expansion radius corresponding to the simulated projection object of each image in the expanded image sequence based on the equivalent phantom and the equivalent radius;

[0146] The fitting unit is also used to perform polynomial fitting or neural network model processing on the extended radius and the tomographic reconstruction image sequence of the target projected object to generate an extended image sequence.

[0147] In specific application scenarios, after the construction module, the device further includes:

[0148] The generation module is used to combine the extended image sequence and the tomographic reconstruction image sequence of the target projection object to generate a complete image sequence simulating the projection object.

[0149] This application provides an apparatus for constructing extended image sequences. First, tomographic scan data of a target projection object is acquired. Second, tomographic scan image reconstruction processing is performed on the tomographic scan data to generate a tomographic scan reconstructed image sequence of the target projection object. This tomographic scan reconstructed image sequence of the target projection object is used to represent the maximum image sequence reconstructed under the current reconstruction conditions. Finally, based on the tomographic scan reconstructed image sequence of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed. This extended image sequence is used to represent the extended image sequence of simulated projection objects that are not reconstructed under the current reconstruction conditions and need to be virtually constructed. Compared with the prior art, this application's embodiment, by reconstructing the maximum image sequence reconstructed under the current reconstruction conditions and constructing an extended image sequence of simulated projection objects that are not reconstructed under the current reconstruction conditions and need to be virtually constructed based on this maximum image sequence, and further generating an image sequence of simulated projection objects, reduces the error between the simulated object and the real projection object, improves the realism of the extended image sequence of the simulated object, and thus ensures the realism of the forward projection.

[0150] According to one embodiment of this application, a storage medium is provided, the storage medium storing at least one executable instruction that can execute the method for constructing extended image sequences in any of the above method embodiments.

[0151] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0152] Figure 12 The diagram shows a structural schematic of a terminal according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the terminal.

[0153] like Figure 12As shown, the terminal may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0154] The processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308.

[0155] Communication interface 304 is used to communicate with other network elements such as clients or other servers.

[0156] The processor 302 is used to execute program 310, specifically to execute the relevant steps in the embodiment of the method for constructing extended image sequences of the above-mentioned interface.

[0157] Specifically, program 310 may include program code that includes computer operation instructions.

[0158] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The terminal includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0159] Memory 306 is used to store program 310. Memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0160] Specifically, program 310 can be used to cause processor 302 to perform the following operations:

[0161] Acquire tomographic scan data of the target projected object;

[0162] The tomographic scan data is subjected to tomographic scan image reconstruction processing to generate a tomographic scan reconstructed image sequence of the target projection object. The tomographic scan reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions.

[0163] Based on the tomographic reconstruction image sequence of the target projection object, an extended image sequence of a simulated projection object matching the target projection object is constructed. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed.

[0164] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device constructing the extended image sequence, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0165] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0166] The methods and systems of this application may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this application are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this application may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this application. Thus, this application also covers recording media storing programs for performing the methods according to this application.

[0167] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0168] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for constructing an extended image sequence, characterized in that, include: Acquire tomographic scan data of the target projected object; The tomographic scan data is subjected to tomographic scan image reconstruction processing to generate a tomographic scan reconstructed image sequence of the target projection object. The tomographic scan reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions. Based on the tomographic reconstruction image sequence of the target projection object, an extended image sequence of the simulated projection object matching the target projection object is constructed. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed. Wherein, the construction of an extended image sequence of a simulated projected object matching the target projected object based on the tomographic reconstructed image sequence of the target projected object includes any of the following methods: Method 1: Obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence; based on the tomographic scan reconstructed image sequence of the target projected object, obtain the equivalent radius of the position in the equivalent phantom corresponding to the tomographic scan reconstructed image sequence; based on the equivalent phantom and the equivalent radius, determine the extended radius corresponding to the simulated projected object of each image in the extended image sequence; perform polynomial fitting or neural network model processing on the extended radius and the tomographic scan reconstructed image sequence of the target projected object to generate the extended image sequence; Method 2: Obtain the planar image data of the target projection object; establish a compression mapping model based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object; perform reconstruction processing based on the compression mapping model and the planar image data of the target projection object to obtain an extended image sequence; Method 3: Obtain the planar image data of the target projected object; obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence; process the tomographic scan reconstructed image sequence of the target projected object and the planar image data of the target projected object through polynomial fitting or neural network model to obtain the complete sequence of the equivalent phantom; extract the extended image sequence from the complete sequence of the equivalent phantom.

2. The method according to claim 1, characterized in that, Also includes: The extended image sequence is corrected based on the tomographic reconstruction image sequence of the target projected object to obtain a corrected extended image sequence, wherein the correction includes size and / or sharpness adjustment.

3. The method according to claim 1, characterized in that, After constructing an extended image sequence of a simulated projection object that matches the target projection object from the tomographic reconstructed image sequence based on the target projection object, the method further includes: By combining the extended image sequence and the tomographic reconstruction image sequence of the target projection object, a complete image sequence simulating the projection object is generated.

4. A device for constructing extended image sequences, characterized in that, include: The first acquisition module is used to acquire the tomographic scan data of the target projected object; The reconstruction module is used to perform tomographic image reconstruction processing on the tomographic scan data to generate a tomographic reconstructed image sequence of the target projection object. The tomographic reconstructed image sequence of the target projection object is used to characterize the maximum image sequence reconstructed under the current reconstruction conditions. The construction module is used to construct an extended image sequence of a simulated projection object that matches the target projection object based on the tomographic reconstruction image sequence of the target projection object. The extended image sequence is used to characterize the extended image sequence of the simulated projection object that has not been reconstructed under the current reconstruction conditions and needs to be virtually constructed. Wherein, the construction of an extended image sequence of a simulated projected object matching the target projected object based on the tomographic reconstructed image sequence of the target projected object includes any of the following methods: Method 1: Obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence; based on the tomographic scan reconstructed image sequence of the target projected object, obtain the equivalent radius of the position in the equivalent phantom corresponding to the tomographic scan reconstructed image sequence; based on the equivalent phantom and the equivalent radius, determine the extended radius corresponding to the simulated projected object of each image in the extended image sequence; perform polynomial fitting or neural network model processing on the extended radius and the tomographic scan reconstructed image sequence of the target projected object to generate the extended image sequence; Method 2: Obtain the planar image data of the target projection object; establish a compression mapping model based on the tomographic reconstructed image sequence of the target projection object and the planar image data of the target projection object; perform reconstruction processing based on the compression mapping model and the planar image data of the target projection object to obtain an extended image sequence; Method 3: Obtain the planar image data of the target projected object; obtain the equivalent phantom of the target projected object, the equivalent phantom including the positions corresponding to the tomographic scan sequence and the extended sequence; process the tomographic scan reconstructed image sequence of the target projected object and the planar image data of the target projected object through polynomial fitting or neural network model to obtain the complete sequence of the equivalent phantom; extract the extended image sequence from the complete sequence of the equivalent phantom.

5. A storage medium storing at least one executable instruction, characterized in that, The executable instructions cause the processor to perform the operations corresponding to the method for constructing the extended image sequence as described in any one of claims 1-3.

6. An electronic device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, characterized in that the executable instruction causes the processor to perform the operation corresponding to the method for constructing the extended image sequence as described in any one of claims 1-3.

Images