Lamination reconstruction imaging phase recovery method and device based on object function implicit representation

Abstract

The invention relates to a lamination reconstruction imaging phase recovery method and device based on object function implicit representation, and the method comprises the steps: generating the implicit representation of an object function through employing a preset deep neural network; carrying out random sampling on each pixel volume between adjacent slice layers, and calculating a corresponding projection potential function value according to coordinates of sampling points; performing forward simulation of multi-sheet layer lamination imaging on the projection potential function value; defining a corresponding loss function according to the difference between the simulation data and the experiment data; judging whether the loss function meets a preset convergence condition or not; and if the loss function meets a preset convergence condition, sampling and phase recovery of the three-dimensional object function are carried out in a three-dimensional space position by using implicit representation, and object function information meeting a preset optimal condition is obtained. According to the embodiment of the invention, the representation capability of the neural network and the function continuity of the neural network in the solution space are utilized, the defect of local optimization traps in a traditional method is avoided, and the accuracy of phase recovery is improved.

Description

Technical Field

[0001] The present application relates to the field of optical imaging technology, and in particular to a stacked reconstruction imaging phase recovery method and device based on implicit representation of physical functions. Background Art

[0002] In multi-layer stacking imaging technology, the object function is usually represented by various functions on a two-dimensional surface at a specific spatial position to represent the projection potential function, such as a pixel matrix, a two-dimensional function, etc.

[0003] In the related art, the regularization factor can be used to constrain the solution space characteristics or inter-layer correlation to obtain the phase information reconstruction result.

[0004] However, related technologies are prone to local optimal solution problems; at the same time, since the spatial position of the projection potential function needs to be preset and cannot be changed, this hyperparameter has an unignorable impact on the algorithm. Summary of the invention

[0005] The present application provides a stacked reconstruction imaging phase recovery method and device based on implicit representation of a material function, so as to solve the problem that the related art reduces the accuracy of stacked imaging phase recovery.

[0006] The first aspect of the present application provides a phase recovery method for stacked reconstruction imaging based on implicit representation of material function, comprising the following steps: generating an implicit representation of material function using a preset deep neural network; performing random sampling on each pixel volume between adjacent slices to obtain sampling points of each pixel volume, and calculating corresponding projection potential function values ​​according to the coordinates of the sampling points; performing forward simulation of multi-layer stacked imaging on the projection potential function values ​​to obtain forward simulation results, and obtaining simulation data of a series of convergent beam diffractions according to the forward simulation results; defining a corresponding loss function according to the difference between the simulation data and experimental data, and making the loss function meet preset conditions according to neural network parameters; when the loss function meets the preset conditions, determining whether the loss function meets preset convergence conditions; if the loss function meets the preset convergence conditions, performing sampling and phase recovery of three-dimensional material function at a three-dimensional spatial position using the implicit representation to obtain material function information that meets preset optimal conditions.

[0007] Optionally, in one embodiment of the present application, after determining whether the loss function satisfies a preset convergence condition, it further includes: if the loss function does not satisfy the preset convergence condition, randomly or regularly sampling the slice thickness of the material function until the loss function satisfies the preset convergence condition, and stopping sampling.

[0008] Optionally, in one embodiment of the present application, the generating an implicit representation of a material function using a deep neural network includes: inputting the spatial coordinates or spatial coordinate encoding of the material function into the deep neural network to obtain a material function value corresponding to the spatial coordinate position according to the deep neural network.

[0009] Optionally, in one embodiment of the present application, the spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

[0010] Optionally, in one embodiment of the present application, calculating the corresponding projection potential function value according to the coordinates of the sampling point includes: calculating the volume fraction of the sampling point according to the coordinates of the sampling point; multiplying the volume fraction and the potential function value of the sampling point to obtain the product result of the sampling point; accumulating the product result to obtain the projection potential of the next layer of pixels, and iteratively applying the projection potential to a preset layer to obtain the projection potential function value of the preset layer.

[0011] The second aspect of the present application provides a stacked reconstruction imaging phase recovery device based on implicit representation of material function, including: a generation module, used to generate an implicit representation of material function using a preset deep neural network; a calculation module, used to randomly sample each pixel volume between adjacent slices to obtain sampling points of each pixel volume, and calculate the corresponding projection potential function value according to the coordinates of the sampling points; a simulation module, used to perform forward simulation of multi-layer stacked imaging on the projection potential function value to obtain forward simulation results, and obtain simulation data of a series of convergent beam diffractions according to the forward simulation results; a definition module, used to define a corresponding loss function according to the difference between the simulation data and the experimental data, and make the loss function meet preset conditions according to neural network parameters; a judgment module, used to judge whether the loss function meets preset convergence conditions when the loss function meets the preset conditions; a phase recovery module, used to use the implicit representation to perform sampling and phase recovery of the three-dimensional material function at a three-dimensional spatial position when the loss function meets the preset convergence conditions, to obtain material function information that meets preset optimal conditions.

[0012] Optionally, in one embodiment of the present application, it also includes: a sampling module, which is used to randomly or regularly sample the slice thickness of the material function after determining whether the loss function satisfies a preset convergence condition, if the loss function does not satisfy the preset convergence condition, until the loss function satisfies the preset convergence condition, and stop sampling.

[0013] Optionally, in one embodiment of the present application, the generation module includes: a generation unit, used to input the spatial coordinates or spatial coordinate encoding of the material function into the deep neural network, so as to obtain the material function value corresponding to the spatial coordinate position according to the deep neural network.

[0014] Optionally, in one embodiment of the present application, the spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

[0015] Optionally, in one embodiment of the present application, the calculation module includes: a first calculation unit, used to calculate the volume fraction of the sampling point according to the coordinates of the sampling point; a second calculation unit, used to multiply the volume fraction and the potential function value of the sampling point to obtain the product result of the sampling point; an accumulation unit, used to accumulate the product result to obtain the projection potential of the next layer of pixels, and iteratively apply the preset layer according to the projection potential to obtain the projection potential function value of the preset layer.

[0016] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the stacked reconstruction imaging phase recovery method based on implicit representation of material functions as described in the above embodiments.

[0017] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned stacked reconstruction imaging phase recovery method based on implicit representation of material function.

[0018] The fifth aspect of the present application provides a computer program product, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned stacked reconstruction imaging phase recovery method based on implicit representation of material function.

[0019] The embodiment of the present application utilizes the representation capability of the neural network and its functional continuity in the solution space, avoiding the shortcomings of the local optimization trap of the traditional method and improving the accuracy of phase recovery. Thus, the problem of the related technology reducing the accuracy and efficiency of stack imaging phase recovery is solved.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A flowchart of a stacked reconstruction imaging phase recovery method based on implicit representation of a material function provided according to an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the input and output structure of a fully connected network of a phase recovery method for stacked reconstruction imaging based on implicit representation of physical functions according to an embodiment of the present application;

[0024] Figure 3 A schematic diagram of an algorithm flow of a stacked reconstruction imaging phase recovery method based on implicit representation of a material function according to an embodiment of the present application;

[0025] Figure 4 A schematic structural diagram of a stacked reconstruction imaging phase recovery device based on implicit representation of a physical function according to an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0028] The following describes the stacked reconstruction imaging phase recovery method and device based on the implicit representation of the material function in the embodiment of the present application with reference to the accompanying drawings. In order to solve the problem mentioned in the above background technology that the related technology reduces the accuracy and efficiency of the stacked imaging phase recovery, the present application provides a stacked reconstruction imaging phase recovery method based on the implicit representation of the material function. In this method, the representation ability of the neural network and its function continuity in the solution space are utilized to avoid the shortcomings of the local optimization trap of the traditional method and improve the accuracy of phase recovery. As a result, the problem of the related technology reducing the accuracy and efficiency of the stacked imaging phase recovery is solved.

[0029] Specifically, Figure 1 A schematic flow chart of a stacked reconstruction imaging phase recovery method based on implicit representation of material function provided in an embodiment of the present application.

[0030] like Figure 1 As shown, the stacked reconstruction imaging phase recovery method based on implicit representation of the material function includes the following steps:

[0031] In step S101, a preset deep neural network is used to generate an implicit representation of the function.

[0032] In the actual implementation process, the embodiment of the present application can use a preset deep neural network to generate an implicit representation of the physical function, that is, to build a neural network model for implicitly representing the physical function in multiple layers.

[0033] The embodiment of the present application avoids the limitations brought by the traditional regularization factor through the implicit representation of the neural network, ensures the global optimal solution in the multi-layer stacking reconstruction process, effectively overcomes the local optimization problem, improves the quality of the imaging results, and improves the accuracy of phase recovery.

[0034] It should be noted that the neural network model includes but is not limited to a fully connected neural network, and needs to be selected and optimized according to specific imaging requirements.

[0035] Optionally, in one embodiment of the present application, a deep neural network is used to generate an implicit representation of a material function, including: inputting the spatial coordinates of the material function or the spatial coordinate encoding into the deep neural network to obtain the material function value corresponding to the spatial coordinate position according to the deep neural network.

[0036] As a possible implementation method, the embodiment of the present application can be constructed as follows Figure 2 The fully connected neural network model F shown in the figure takes as input the spatial coordinates (X, Y, Z) of a point in the physical function. The second layer of the neural network encodes the dimension expansion of the three values. The output of the neural network is the predicted value of the physical function corresponding to the spatial coordinate position, which includes the real part A and the imaginary part B.

[0037] Optionally, in one embodiment of the present application, the spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

[0038] Among them, the spatial coordinate encoding in the embodiment of the present application is a dimension expansion encoding, including but not limited to trigonometric function encoding and hash encoding.

[0039] In step S102, each pixel volume between adjacent slices is randomly sampled to obtain sampling points of each pixel volume, and the corresponding projection potential function value is calculated according to the coordinates of the sampling points.

[0040] It can be understood that the calculation of the projection potential function involves a weighted accumulation operation of random or regular sampling and its product with the volume fraction.

[0041] In the actual implementation process, the embodiment of the present application can perform n random or regular samplings within the volume at the same pixel position between each pair of adjacent slices, perform calculations based on the coordinates of the sampling points, and finally obtain the corresponding projection potential function value.

[0042] The embodiments of the present application utilize an innovative inter-pixel sampling mechanism to improve algorithm sampling efficiency, thereby improving computational efficiency and imaging quality.

[0043] Optionally, in one embodiment of the present application, the corresponding projection potential function value is calculated according to the coordinates of the sampling point, including: calculating the volume fraction of the sampling point according to the coordinates of the sampling point; multiplying the volume fraction and the potential function value of the sampling point to obtain the product result of the sampling point; accumulating the product result to obtain the projection potential of the next layer of pixels, and iteratively applying the preset layer according to the projection potential to obtain the projection potential function value of the preset layer.

[0044] It can be understood that the pixel size and number in the embodiment of the present application can be adjusted and optimized as needed during the iteration process; the preset slices in the embodiment of the present application can be all slices; the embodiment of the present application can perform multi-layer slicing on the three-dimensional object function, and the thickness of each slice in the embodiment of the present application is randomly sampled to obtain the Z direction coordinates {Z0, Z1, ..., Z n}.

[0045] Specifically, the embodiment of the present application can be used to divide adjacent slices Z i and Z i+1 , the thickness between the layers is d i , set the pixel size, and traverse all pixels. Sampling the position between the layers of a certain pixel [m,n], that is, sampling the set {x,y,z|m <x<m+1,n<y<n+1,Z i <z<Z i+1} sampling. In the embodiment of the present application, the sampling frequency is set to randomly divide the z direction into 4 parts, the z direction division length is {z1, z2, z3, z4}, and randomly sample {x, y, z} in each divided area and calculate F(x, y, z) to obtain the potential function set {F1, F2, F3, F4}. The potential function values ​​at these sampling points are multiplied by the corresponding volume fraction to obtain the product result of the sampling point, and the product results are accumulated to obtain the projection potential function value of the corresponding pixel in the next layer, that is, P[m,n]=∑z i F i The above mechanism is applied iteratively to process all the slices, and the projection potential functions of all the slices required for multi-layer simulation are obtained, and finally the projection potential function value is obtained.

[0046] The embodiment of the present application utilizes an innovative multi-layer thickness random sampling mechanism to further improve the algorithm sampling efficiency, thereby improving the computing efficiency and imaging quality.

[0047] In step S103, a forward simulation of multi-layer stacking imaging is performed on the projection potential function value to obtain a forward simulation result, and a series of convergent beam diffraction simulation data is obtained according to the forward simulation result.

[0048] It can be understood that the interlaminar spacing in the multi-layer simulation process in the embodiment of the present application can be adjusted and optimized as needed during the iterative process.

[0049] In the actual implementation process, the embodiments of the present application can refer to the experimental conditions to complete the forward simulation process of multi-layer stacking imaging, and obtain 4D simulation data of a series of converging beam diffractions, thereby providing support for subsequent improvement of the quality of imaging results.

[0050] In step S104, a corresponding loss function is defined according to the difference between the simulation data and the experimental data, and the loss function is made to meet preset conditions according to the neural network parameters.

[0051] It can be understood that in the embodiment of the present application, making the loss function meet the preset conditions may be designing and minimizing the loss function.

[0052] In the embodiment of the present application, a loss function can be defined to measure the difference between the simulation data and the experimental data, wherein the defined loss function is the mean square error (MSE), and the neural network model parameters are optimized through the back propagation algorithm to minimize the loss function and match the experimental data. Through a flexible and efficient imaging algorithm framework, it can be widely used in a variety of optical imaging fields, such as biomedicine, materials science, etc.

[0053] The embodiment of the present application can use a gradient descent algorithm to adjust the neural network parameters to reduce the loss, and use a back-propagation optimization strategy to further improve the algorithm sampling efficiency, improve computing efficiency and imaging quality.

[0054] It should be noted that the preset conditions can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0055] In step S105, when the loss function satisfies the preset condition, it is determined whether the loss function satisfies the preset convergence condition.

[0056] In the actual execution process, the embodiment of the present application can determine whether the loss function has converged when the loss function is minimized, so as to take targeted measures according to different convergence results.

[0057] It should be noted that the preset conditions and the preset convergence conditions can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0058] Optionally, in one embodiment of the present application, after determining whether the loss function satisfies the preset convergence condition, it also includes: if the loss function does not meet the preset convergence condition, randomly or regularly sampling the slice thickness of the physical function until the loss function meets the preset convergence condition, and stopping sampling.

[0059] Specifically, the embodiment of the present application can randomly or regularly sample the slice thickness of the material function when the loss function does not converge, repeat the above steps of slicing the three-dimensional material function into multiple layers to define the loss function, until the loss function converges, and stop sampling.

[0060] It should be noted that the preset convergence condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0061] In step S106, if the loss function meets the preset convergence condition, sampling and phase recovery of the three-dimensional physical function are performed at the three-dimensional spatial position using implicit representation to obtain physical function information that meets the preset optimal condition.

[0062] It can be understood that the physical function information that meets the preset optimal conditions in the embodiment of the present application may be physical function information that meets high-precision and global optimal solutions.

[0063] In an embodiment of the present application, when the loss function converges, it indicates that the implicit expression of the physical function has reached the optimal state. At this time, the implicit representation can be used to perform sampling and phase recovery of the three-dimensional physical function at the three-dimensional spatial position to obtain high-precision, globally optimal solution physical function information.

[0064] The embodiment of the present application can perform post-processing on the parameters of the neural network, such as full-space sampling to obtain an explicit expression of the physical function.

[0065] It should be noted that the preset optimal conditions can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0066] Specifically, it can be combined Figure 3 In the embodiment of the present application, the working principle of the stacked reconstruction imaging phase recovery method based on implicit representation of the material function in the embodiment of the present application is described in detail with a specific embodiment.

[0067] like Figure 3 The embodiment of the present application may include the following steps:

[0068] Step S301: Setting a neural network model.

[0069] Step S302: sampling the slice thickness.

[0070] Step S303: Calculate the projection potential of each slice.

[0071] Step S304: multi-slice forward simulation.

[0072] Step S305: Optimize the loss function.

[0073] Step S306: Determine whether the loss function converges.

[0074] Step S307: End iteration and post-processing.

[0075] According to the stacked reconstruction imaging phase recovery method based on implicit representation of physical functions proposed in the embodiment of the present application, the representation ability of the neural network and its functional continuity in the solution space can be utilized to avoid the shortcomings of the local optimization trap of the traditional method and improve the accuracy and efficiency of the stacked imaging phase recovery. Therefore, the problem that the related technology reduces the accuracy and efficiency of the stacked imaging phase recovery is solved.

[0076] Next, a stacked reconstruction imaging phase recovery device based on implicit representation of material functions proposed in an embodiment of the present application is described with reference to the accompanying drawings.

[0077] Figure 4 It is a structural schematic diagram of a stacked reconstruction imaging phase recovery device based on implicit representation of a physical function according to an embodiment of the present application.

[0078] like Figure 4 As shown, the stacked reconstruction imaging phase recovery device 10 based on implicit representation of physical function includes: a generation module 100, a calculation module 200, a simulation module 300, a definition module 400, a judgment module 500 and a phase recovery module 600.

[0079] Specifically, the generation module 100 is used to generate an implicit representation of a function using a preset deep neural network.

[0080] The calculation module 200 is used to randomly sample each pixel volume between adjacent slices to obtain sampling points of each pixel volume, and calculate corresponding projection potential function values ​​according to the coordinates of the sampling points.

[0081] The simulation module 300 is used to perform a forward simulation of multi-layer stacking imaging on the projection potential function value to obtain a forward simulation result, and to obtain simulation data of a series of convergent beam diffractions according to the forward simulation result.

[0082] The definition module 400 is used to define a corresponding loss function according to the difference between the simulation data and the experimental data, and make the loss function meet the preset conditions according to the neural network parameters.

[0083] The judgment module 500 is used to judge whether the loss function meets a preset convergence condition when the loss function meets the preset condition.

[0084] The phase recovery module 600 is used to obtain the physical function information that meets the preset optimal conditions by sampling and phase recovery of the three-dimensional physical function at the three-dimensional space position using implicit representation when the loss function meets the preset convergence conditions.

[0085] Optionally, in one embodiment of the present application, the stacked reconstruction imaging phase recovery device 10 based on implicit representation of material function further includes: a sampling module.

[0086] Among them, the sampling module is used to randomly or regularly sample the slice thickness of the physical function after determining whether the loss function meets the preset convergence conditions. If the loss function does not meet the preset convergence conditions, the sampling is stopped until the loss function meets the preset convergence conditions.

[0087] Optionally, in one embodiment of the present application, the generation module 100 includes: a generation unit.

[0088] Among them, the generation unit is used to input the spatial coordinates of the material function or the spatial coordinate encoding into the deep neural network, so as to obtain the material function value corresponding to the spatial coordinate position according to the deep neural network.

[0089] Optionally, in one embodiment of the present application, the spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

[0090] Optionally, in one embodiment of the present application, the calculation module 200 includes: a first calculation unit, a second calculation unit and an accumulation unit.

[0091] Wherein, the first calculation unit is used to calculate the volume fraction of the sampling point according to the coordinates of the sampling point.

[0092] The second calculation unit is used to multiply the volume fraction and the potential function value of the sampling point to obtain a product result of the sampling point.

[0093] The accumulation unit is used to accumulate the product results to obtain the projection potential of the next layer of pixels, and iteratively apply the preset slice layer according to the projection potential to obtain the projection potential function value of the preset slice layer.

[0094] It should be noted that the aforementioned explanation of the embodiment of the stacked reconstruction imaging phase recovery method based on implicit representation of the material function is also applicable to the stacked reconstruction imaging phase recovery device based on implicit representation of the material function in this embodiment, and will not be repeated here.

[0095] According to the stacked reconstruction imaging phase recovery device based on the implicit representation of the physical function proposed in the embodiment of the present application, the representation ability of the neural network and its function continuity in the solution space can be utilized to avoid the shortcomings of the local optimization trap of the traditional method and improve the accuracy of phase recovery. Therefore, the problem of the related technology reducing the accuracy and efficiency of stacked imaging phase recovery is solved.

[0096] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0097] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0098] When the processor 502 executes the program, the stacked reconstruction imaging phase recovery method based on implicit representation of the material function provided in the above embodiment is implemented.

[0099] Furthermore, the electronic device further comprises:

[0100] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0101] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0102] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0103] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0104] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0105] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0106] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the stacked reconstruction imaging phase recovery method based on implicit representation of a material function is implemented as described above.

[0107] The embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed by a processor, the stacked reconstruction imaging phase recovery method based on implicit representation of the material function as described above is implemented.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0109] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0112] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0115] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A stacked reconstruction imaging phase recovery method based on implicit representation of physical function, characterized in that: The following steps are involved: Using a preset deep neural network to generate implicit representation of the function; Randomly sampling each pixel volume between adjacent slices to obtain sampling points of each pixel volume, and calculating corresponding projection potential function values ​​according to the coordinates of the sampling points; Performing a forward simulation of multi-layer stacking imaging on the projection potential function value to obtain a forward simulation result, and acquiring simulation data of a series of converging beam diffractions according to the forward simulation result; Defining a corresponding loss function according to the difference between the simulation data and the experimental data, and making the loss function meet a preset condition according to the neural network parameters; When the loss function satisfies the preset condition, determining whether the loss function satisfies the preset convergence condition; If the loss function satisfies the preset convergence condition, the implicit representation is used to perform sampling and phase recovery of the three-dimensional physical function at the three-dimensional spatial position to obtain physical function information that meets the preset optimal condition.

2. The method according to claim 1, characterized in that: After determining whether the loss function satisfies a preset convergence condition, the method further includes: If the loss function does not satisfy the preset convergence condition, the slice thickness of the material function is randomly or regularly sampled until the loss function satisfies the preset convergence condition, and the sampling is stopped.

3. The method according to claim 1, characterized in that The implicit representation of the generator function using a deep neural network includes: The spatial coordinates or spatial coordinate encoding of the material function is input into the deep neural network to obtain the material function value corresponding to the spatial coordinate position according to the deep neural network.

4. The method according to claim 3, characterized in that: The spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

5. The method according to claim 1, characterized in that The calculating the corresponding projection potential function value according to the coordinates of the sampling point includes: Calculate the volume fraction of the sampling point according to the coordinates of the sampling point; Multiplying the volume fraction and the potential function value of the sampling point to obtain a product result of the sampling point; The product results are accumulated to obtain the projection potential of the next layer of pixels, and the preset slice is iteratively applied according to the projection potential to obtain the projection potential function value of the preset slice.

6. A stacked reconstruction imaging phase recovery device based on implicit representation of physical function, characterized in that: include: A generation module for generating an implicit representation of a function using a preset deep neural network; A calculation module, used for randomly sampling each pixel volume between adjacent slices to obtain sampling points of each pixel volume, and calculating corresponding projection potential function values ​​according to the coordinates of the sampling points; A simulation module, used for performing a forward simulation of multi-layer stacking imaging on the projection potential function value to obtain a forward simulation result, and obtaining simulation data of a series of convergent beam diffractions according to the forward simulation result; A definition module, used to define a corresponding loss function according to the difference between the simulation data and the experimental data, and make the loss function meet a preset condition according to the neural network parameters; A judgment module, used for judging whether the loss function satisfies a preset convergence condition when the loss function satisfies the preset condition; The phase recovery module is used to use the implicit representation to perform sampling and phase recovery of the three-dimensional physical function at the three-dimensional spatial position when the loss function meets the preset convergence condition, so as to obtain physical function information that meets the preset optimal condition.

7. The device according to claim 6, characterized in that Also includes: The sampling module is used to randomly or regularly sample the slice thickness of the material function after determining whether the loss function meets the preset convergence condition, if the loss function does not meet the preset convergence condition, until the loss function meets the preset convergence condition, and then stop sampling.

8. The device according to claim 6, characterized in that The generation module comprises: A generating unit is used to input the spatial coordinates or the spatial coordinate encoding of the physical function into the deep neural network, so as to obtain the physical function value corresponding to the spatial coordinate position according to the deep neural network.

9. The device according to claim 8, characterized in that The spatial coordinate encoding includes at least one dimension expansion encoding of trigonometric function encoding and hash encoding.

10. The device according to claim 6, characterized in that The calculation module comprises: A first calculation unit, configured to calculate a volume fraction of the sampling point according to the coordinates of the sampling point; A second calculation unit, configured to multiply the volume fraction and the potential function value of the sampling point to obtain a product result of the sampling point; The accumulation unit is used to accumulate the multiplication results to obtain the projection potential of the next layer of pixels, and iteratively apply the projection potential to the preset layer to obtain the projection potential function value of the preset layer.

11. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the stacked reconstruction imaging phase recovery method based on implicit representation of a material function as described in any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the stacked reconstruction imaging phase recovery method based on implicit representation of material function as described in any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the stacked reconstruction imaging phase recovery method based on implicit representation of material function as described in any one of claims 1 to 5.

Images