WO2021031069A1 - 一种图像重建方法及装置 - Google Patents

一种图像重建方法及装置 Download PDF

Info

Publication number
WO2021031069A1
WO2021031069A1 PCT/CN2019/101371 CN2019101371W WO2021031069A1 WO 2021031069 A1 WO2021031069 A1 WO 2021031069A1 CN 2019101371 W CN2019101371 W CN 2019101371W WO 2021031069 A1 WO2021031069 A1 WO 2021031069A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
sample
processing result
projection
resolution
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/101371
Other languages
English (en)
French (fr)
Inventor
胡战利
汪影
杨永峰
梁栋
刘新
郑海荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to PCT/CN2019/101371 priority Critical patent/WO2021031069A1/zh
Publication of WO2021031069A1 publication Critical patent/WO2021031069A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks

Definitions

  • This application belongs to the field of computer application technology, and in particular relates to an image reconstruction method and device.
  • PET Positron Emission Computed Tomography
  • FBP Filtered Back-projection
  • the iterative reconstruction algorithm also includes algebraic reconstruction and statistical reconstruction. At present, the maximum likelihood expectation maximization in statistical reconstruction is widely used in clinical and practice because of its better performance. However, when there is relatively serious statistical noise in the projected image, the image quality will produce checkerboard artifacts as the number of iterations increase. This method will amplify the noise accordingly, and the quality of the reconstructed image will be lower.
  • the embodiments of the present application provide an image reconstruction method and device, which can solve the problem that image noise is amplified during image reconstruction in the prior art and the quality of the reconstructed image obtained is low.
  • an image reconstruction method including:
  • mapping matrix super-resolution processing is performed on the first image to obtain a second image; the mapping matrix is obtained by training the acquired sample images and projection images through the decision tree method, and is used to convert low The resolution image is mapped to a high-resolution image; the projection image is obtained by performing affine transformation on the sample image.
  • the method before performing super-resolution processing on the first image according to a preset mapping matrix to obtain a second image, the method further includes:
  • the mapping relationship is the mapping relationship between the sample processing result and the projection image .
  • performing decision tree training on the sample image and the projection image to obtain a sample processing result includes:
  • the calculating the loss function between the sample processing result and the projection image, and adjusting a preset mapping relationship according to the loss function to obtain the mapping matrix includes:
  • the relationship matrix between the target result and the projected image is determined as the mapping matrix.
  • said performing iterative processing on said sample image to obtain said sample processing result according to a preset decision tree method includes:
  • the calculation of the square loss function value between each of the sample processing results and the projection image includes:
  • N represents the total number of sample images
  • x n denotes the n-th sample image
  • y n represents the n-th sample image corresponding to the projected image
  • X represents the sample image
  • Y represents the projected image
  • represents a preset regularization parameter
  • I represents a unit matrix
  • the iterative super-resolution processing on the fused image to obtain the sample processing result includes:
  • W represents the mapping matrix
  • an embodiment of the present application provides an image reconstruction device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor executes the The following steps are implemented when computer-readable instructions:
  • mapping matrix super-resolution processing is performed on the first image to obtain a second image; the mapping matrix is obtained by training the acquired sample images and projection images through the decision tree method, and is used to convert low The resolution image is mapped to a high-resolution image; the projection image is obtained by performing affine transformation on the sample image.
  • an image reconstruction device including:
  • the reconstruction unit is configured to perform super-resolution processing on the first image according to a preset mapping matrix to obtain a second image; the mapping matrix is obtained by training the acquired sample images and projection images through a decision tree method , Used to map a low-resolution image to a high-resolution image; the projection image is obtained by performing affine transformation on the sample image.
  • an embodiment of the present application provides a computer-readable storage medium that stores computer-readable instructions, the computer-readable instructions include program instructions, and the program instructions when executed by a processor The processor is caused to execute the method of the first aspect described above.
  • the embodiments of the present application provide a computer-readable instruction product, which when the computer-readable instruction product runs on a terminal device, causes the terminal device to execute the image reconstruction method described in any one of the above-mentioned first aspects.
  • the embodiment of the present application has the following beneficial effects: obtaining the first image to be processed; performing super-resolution processing on the first image according to a preset mapping matrix to obtain the second image.
  • the obtained sample image and the projection image are passed through a decision tree method in advance to fit the mapping relationship from the low-resolution image to the high-resolution image, so as to convert the low-resolution positron emission computer
  • the tomographic PET mapping is a high-resolution projection image, which improves the quality of the PET image reconstructed in each iteration, so that the reconstruction reaches convergence in advance, and improves the quality of the PET reconstructed image while reducing the number of iterations.
  • FIG. 1 is a flowchart of an image reconstruction method provided in Embodiment 1 of the present application.
  • FIG. 2 is a flowchart of an image reconstruction method provided by Embodiment 2 of the present application.
  • Fig. 3 is an experimental result of image reconstruction provided in the second embodiment of the present application.
  • FIG. 4 is a schematic diagram of an image reconstruction device provided in Embodiment 3 of the present application.
  • FIG. 5 is a schematic diagram of an image reconstruction device provided in Embodiment 4 of the present application.
  • the term “if” can be construed as “when” or “once” or “in response to determination” or “in response to detecting “.
  • the phrase “if determined” or “if detected [described condition or event]” can be interpreted as meaning “once determined” or “response to determination” or “once detected [described condition or event]” depending on the context ]” or “in response to detection of [condition or event described]”.
  • FIG. 1 is a flowchart of an image reconstruction method provided in Embodiment 1 of the present application.
  • the execution subject of the image reconstruction method in this embodiment is a device with an image reconstruction function, including but not limited to devices such as computers, servers, tablets, or terminals.
  • the image reconstruction method shown in the figure may include the following steps:
  • S101 Acquire a first image to be processed.
  • This embodiment proposes a PET positron emission computer tomography image reconstruction algorithm based on a decision tree.
  • the super-resolution technology based on the decision tree is added to the PET image reconstruction algorithm based on the stain, and the decision tree is used to fit The model that maps the resolution image to the high resolution image, and super-resolution is performed on the image reconstructed in each iteration. It is possible to reduce the number of iterations to achieve convergence earlier, and at the same time reduce the time to adjust parameters, achieve better reconstruction results under relatively poor parameter settings, and improve the quality of PET reconstructed images.
  • Positron emission computed tomography is a relatively advanced clinical examination imaging technology in the field of nuclear medicine, and high-quality PET can improve the diagnosis accuracy of doctors, so improving the PET image reconstruction algorithm has always been the subject of research.
  • the existing PET image reconstruction algorithms are mainly divided into two categories: analytical reconstruction algorithms and iterative reconstruction algorithms.
  • Analytical reconstruction algorithms mainly include back projection, filtered back projection and Fourier reconstruction.
  • One of the most widely used algorithms is filtered back projection.
  • Iterative reconstruction algorithms also include algebraic reconstruction and statistical reconstruction.
  • maximum likelihood-expectation maximization in statistical reconstruction is widely used in clinical and practice because of its better performance.
  • the image quality will produce checkerboard artifacts as the number of iterations increases, but worse. Therefore, there is a penalized likelihood PET image reconstruction algorithm based on color spots that introduces regularization terms.
  • the first image in this embodiment is used to represent a PET image with a lower resolution or a reconstructed image.
  • the acquisition method can be directly acquired through PET scanning equipment.
  • S102 Perform super-resolution processing on the first image according to a preset mapping matrix to obtain a second image; the mapping matrix is obtained by training the acquired sample image and projection image through a decision tree method, and is used for The low-resolution image is mapped to a high-resolution image; the projection image is obtained by performing affine transformation on the sample image.
  • the first image in this embodiment is used to represent an acquired low-resolution PET image or a reconstructed image
  • the second image is used to represent a high-resolution projection image obtained by performing PET image reconstruction on the first image.
  • a machine learning algorithm is added in the process of reconstructing the PET image.
  • a decision tree is used to train the low-resolution image block and the corresponding high-resolution image block to fit the low-resolution image
  • the mapping relationship that is mapped to the high-resolution image that is, the mapping matrix, is used to perform super-resolution processing on the first image through the mapping matrix to obtain the second image, which improves the quality of the PET image after each iteration and makes the reconstruction reach convergence in advance. It reduces the number of iterations while improving the quality of PET reconstructed images.
  • the first image to be processed is acquired; the super-resolution processing is performed on the first image according to the preset mapping matrix to obtain the second image.
  • the obtained sample image and the projection image are passed through a decision tree method in advance to fit the mapping relationship from the low-resolution image to the high-resolution image, so as to convert the low-resolution positron emission computer
  • the tomographic PET mapping is a high-resolution projection image, which improves the quality of the PET image reconstructed in each iteration, so that the reconstruction reaches convergence in advance, and improves the quality of the PET reconstructed image while reducing the number of iterations.
  • FIG. 2 is a flowchart of an image reconstruction method provided by an embodiment of the present application.
  • the image reconstruction method as shown in the figure may include the following steps before step S101:
  • the sample image in this embodiment may be a reconstructed image, where the reconstructed image x is a PET image of a hospital patient, and the projection image y is obtained by performing affine transformation on x.
  • the data obtained in this embodiment is not a projection image collected in real time, so the projection image y is obtained by projecting the reconstructed PET image x, and the super-resolution process is added during the reconstruction of the projection image y into a PET image, and finally the reconstructed PET image is obtained.
  • the reconstructed image x is obtained by affine transformation: Among them, P represents the system matrix, which represents the probability that the detector detects a coincidence event for the pixel i in the sample image; r represents a random background event, and s represents a scattering event.
  • S203 Perform decision tree training on the sample image and the projection image to obtain a sample processing result.
  • Step S203 includes: performing iterative processing on the sample image to obtain the sample processing result according to a preset decision tree method.
  • x)- ⁇ U(x); among them, the regularization parameter ⁇ can be set to ⁇ 2 -7 during initialization, we choose Q L (x; x n ), As the likelihood proxy function L(y
  • the step of iteratively processing the sample image to obtain the sample processing result according to a preset decision tree method includes S2031 to S2033:
  • S2031 According to a preset decision tree method, perform image smoothing iterative processing on the sample image to obtain a smooth image.
  • x n represents the nth iteration image
  • N j represents the total pixel value of the jth image block
  • w jk represents the weight related to the neighborhood block, which is adaptively determined by the penalty function and the current estimated image of each iteration .
  • S2032 Perform pixel image fusion iterative processing on the pixels in the smooth image to obtain a fused image.
  • the EM image is obtained by updating the sinogram ⁇ y i ⁇ Then get through image smoothing Finally, it is fused pixel by pixel, and the iterative image of each penalty likelihood reconstruction is obtained through the KKT condition: among them,
  • the regularization parameter ⁇ is a constant, used to control the weight of the prior and balance the log-likelihood term and the penalty term.
  • iterative super-resolution processing is performed on the fused image according to the following formula to obtain the sample processing result:
  • W represents the mapping matrix
  • Re represents the pixel value of the fused image in the n+1th iteration
  • the sample processing result corresponding to the pixel value of the fused image in the n+1th iteration.
  • the decision tree is used to perform super-resolution processing.
  • the model from low-resolution image to high-resolution image fitted through multiple decision tree training is used to reconstruct the image in each iteration on: among them, It is the mapping matrix fitted by the decision tree training.
  • the image x and the high-resolution reference image y reconstructed in each iteration of the low resolution training sample are used to fit the closest mapping from x to y using the decision tree clustering Model, namely W.
  • S204 Calculate the loss function between the sample processing result and the projection image, and adjust a preset mapping relationship according to the loss function to obtain the mapping matrix; the mapping relationship is between the sample processing result and the projection image Mapping relations.
  • step S204 includes:
  • S2041 Calculate the square loss function value between each of the sample processing results and the projection image, and identify the sample processing result when the square loss function value is the smallest as the target result.
  • the square loss function value between the processing result of each sample and the projected image is calculated by the following formula: Where N represents the total number of sample images, x n represents the nth sample image, and y n represents the projection image corresponding to the nth sample image;
  • mapping matrix fitted by the decision tree training.
  • the training sample that is, the image x and the high-resolution reference image y reconstructed in each iteration of the sample image, are mapped from x to y using the decision tree clustering
  • the closest model is W.
  • W depends on the low-resolution image block x. Then this mapping relationship can be written as,
  • S2042 Determine the relationship matrix between the target result and the projection image as the mapping matrix.
  • W T (X T X + ⁇ I) -1 X T ⁇ Y can be calculated; where X and Y respectively represent low resolution
  • ⁇ I represents the regular term added; I represents the unit matrix; ⁇ represents the regularization parameter, and ⁇ can be set to 0.01.
  • T decision trees to obtain T models and the final prediction result is the average of the predicted values of T trees.
  • How to train a decision tree is to split and cluster each group of corresponding high- and low-resolution image blocks ⁇ x H , x L ⁇ to the left and right sub-nodes recursively and disjointly, like a binary tree. Until the node sample size is less than 2 and cannot be split or reaches the maximum depth, it stops splitting to form leaf nodes.
  • the leaf node model is the model we need to train and fit.
  • the principle of splitting is to calculate the response function according to the characteristics of the image block.
  • each split will traverse all the features of the image block to select the optimal feature.
  • the reference quantity of the optimal feature is defined as:
  • (X H c , X L c ) represents the corresponding high and low resolution image blocks split into the left child node and the right child node.
  • W(x L n )x L n represents the predicted value of the sample x L n
  • represents the number of samples split to the child node, that is, the image block
  • k represents the set hyperparameter;
  • the decision tree model is not only applied to the image reconstructed in each iteration, but also to the projection image ⁇ y i ⁇ at the beginning of the loop. It only replaces the training set with the projection image calculated by the iterative reconstruction of each back projection and the corresponding original Reference projection.
  • the decision tree of this embodiment is to cluster the samples into the last few leaf nodes, that is, several categories through the above-described splitting process, and then find the mapping matrix W through the above-described principle of minimizing the square loss function, that is, to find the mapping model.
  • Figure a in Figure 3 is a reference PET image
  • Figure b is a PET image reconstructed based on the patch regularization iterative reconstruction algorithm
  • Figure c is a PET image reconstructed by the algorithm of this embodiment. It can be seen from the figure that the resolution of the PET image reconstructed in this embodiment is better than the PET image reconstructed based on the patch regularization iterative reconstruction algorithm, and it is also closer to the reference PET image, which fully illustrates the feasibility of the algorithm. It can also be seen from the evaluation parameter table that the image reconstructed by this algorithm is better than patch-based reconstruction on PNSR and SSIM, which further proves the effectiveness of this algorithm.
  • the above solution is to obtain the sample image to be trained; perform affine transformation on the sample image to obtain the projection image; perform decision tree training on the sample image and the projection image to obtain the sample processing result; calculate the sample
  • the preset mapping relationship is adjusted according to the loss function to obtain the mapping matrix
  • the mapping relationship is the mapping relationship between the sample processing result and the projection image.
  • FIG. 4 is a schematic diagram of an image reconstruction device provided in Embodiment 3 of the present application.
  • the image reconstruction device 400 may be a mobile terminal such as a smart phone or a tablet computer.
  • the units included in the image reconstruction apparatus 400 of this embodiment are used to execute the steps in the embodiment corresponding to FIG. 1.
  • the image reconstruction device 400 of this embodiment includes:
  • the acquiring unit 401 is configured to acquire the first image to be processed
  • the reconstruction unit 402 is configured to perform super-resolution processing on the first image according to a preset mapping matrix to obtain a second image; the mapping matrix is used to train the acquired sample images and projection images through a decision tree method Obtained, used to map a low-resolution image to a high-resolution image; the projection image is obtained by performing affine transformation on the sample image.
  • the image reconstruction device 400 further includes:
  • the first acquiring unit is used to acquire the sample image to be trained
  • a transformation unit configured to perform affine transformation on the sample image to obtain the projection image
  • a training unit configured to train the sample image and the projection image on a decision tree to obtain a sample processing result
  • the calculation unit is configured to calculate a loss function between the sample processing result and the projection image, and adjust a preset mapping relationship according to the loss function to obtain the mapping matrix; the mapping relationship is the sample processing result and the projection The mapping relationship between images.
  • the training unit includes:
  • An iterative processing unit configured to iteratively process the sample image according to a preset decision tree method to obtain the sample processing result
  • calculation unit includes:
  • the first calculation unit is configured to calculate the square loss function value between each of the sample processing results and the projection image, and identify the sample processing result when the square loss function value is the smallest as the target result;
  • the matrix determination unit is used to determine the relationship matrix between the target result and the projection image as the mapping matrix.
  • the iterative processing unit includes:
  • a smoothing unit configured to perform image smoothing iterative processing on the sample image according to a preset decision tree method to obtain a smooth image
  • a fusion unit configured to perform pixel image fusion iterative processing on the pixels in the smooth image to obtain a fused image
  • the super-resolution processing unit is configured to perform iterative super-resolution processing on the fused image to obtain the sample processing result.
  • the calculating the square loss function value between each of the sample processing results and the projection image includes:
  • N represents the total number of sample images
  • x n denotes the n-th sample image
  • y n represents the n-th sample image corresponding to the projected image
  • X represents the sample image
  • Y represents the projected image
  • represents a preset regularization parameter
  • I represents a unit matrix
  • the super-resolution processing unit is used for:
  • W represents the mapping matrix
  • the first image to be processed is acquired; the super-resolution processing is performed on the first image according to the preset mapping matrix to obtain the second image.
  • the obtained sample image and the projection image are passed through a decision tree method in advance to fit the mapping relationship from the low-resolution image to the high-resolution image, so as to convert the low-resolution positron emission computer
  • the tomographic PET mapping is a high-resolution projection image, which improves the quality of the PET image after each iteration, so that the reconstruction reaches convergence in advance, and improves the quality of the PET reconstruction image while reducing the number of iterations.
  • FIG. 5 is a schematic diagram of an image reconstruction apparatus provided in Embodiment 4 of the present application.
  • the image reconstruction apparatus 500 in this embodiment as shown in FIG. 5 may include: a processor 501, a memory 502, and computer-readable instructions 503 stored in the memory 502 and running on the processor 501.
  • the processor 501 executes the computer-readable instruction 503, the steps in the foregoing image reconstruction method embodiments are implemented.
  • the memory 502 is configured to store computer-readable instructions, and the computer-readable instructions include program instructions.
  • the processor 501 is configured to execute program instructions stored in the memory 502. Wherein, the processor 501 is configured to call the program instructions to perform the following operations:
  • the processor 501 is used for:
  • the mapping relationship is the mapping relationship between the sample processing result and the projection image .
  • processor 501 is specifically configured to:
  • the calculating the loss function between the sample processing result and the projection image, and adjusting a preset mapping relationship according to the loss function to obtain the mapping matrix includes:
  • the relationship matrix between the target result and the projected image is determined as the mapping matrix.
  • processor 501 is specifically configured to:
  • the calculating the square loss function value between each of the sample processing results and the projection image includes:
  • N represents the total number of sample images
  • x n denotes the n-th sample image
  • y n represents the n-th sample image corresponding to the projected image
  • X represents the sample image
  • Y represents the projected image
  • represents a preset regularization parameter
  • I represents a unit matrix
  • processor 501 is specifically configured to:
  • W represents the mapping matrix
  • the first image to be processed is acquired; the super-resolution processing is performed on the first image according to the preset mapping matrix to obtain the second image.
  • the obtained sample image and the projection image are passed through a decision tree method in advance to fit the mapping relationship from the low-resolution image to the high-resolution image, so as to convert the low-resolution positron emission computer
  • the tomographic PET mapping is a high-resolution projection image, which improves the quality of the PET image after each iteration, so that the reconstruction reaches convergence in advance, and improves the quality of the PET reconstructed image while reducing the number of iterations.
  • the processor 501 may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors or digital signal processors (DSP). , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory 502 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501.
  • a part of the memory 502 may also include a non-volatile random access memory.
  • the memory 502 may also store device type information.
  • the processor 501, memory 502, and computer-readable instructions 503 described in the embodiments of this application can execute the implementations described in the first embodiment and the second embodiment of the image reconstruction method provided in the embodiments of this application.
  • the way, the implementation way of the terminal described in the embodiment of this application can also be implemented, which will not be repeated here.
  • a computer-readable storage medium stores computer-readable instructions, the computer-readable instructions include program instructions, and the program instructions are executed by a processor When realized:
  • the mapping relationship is the mapping relationship between the sample processing result and the projection image .
  • the calculating the loss function between the sample processing result and the projection image, and adjusting a preset mapping relationship according to the loss function to obtain the mapping matrix includes:
  • the relationship matrix between the target result and the projected image is determined as the mapping matrix.
  • N represents the total number of sample images
  • x n denotes the n-th sample image
  • y n represents the n-th sample image corresponding to the projected image
  • X represents the sample image
  • Y represents the projected image
  • represents a preset regularization parameter
  • I represents a unit matrix
  • W represents the mapping matrix
  • the first image to be processed is acquired; the super-resolution processing is performed on the first image according to the preset mapping matrix to obtain the second image.
  • the obtained sample image and the projection image are passed through a decision tree method in advance to fit the mapping relationship from the low-resolution image to the high-resolution image, so as to convert the low-resolution positron emission computer
  • the tomographic PET mapping is a high-resolution projection image, which improves the quality of the PET image reconstructed in each iteration, so that the reconstruction reaches convergence in advance, and improves the quality of the PET reconstructed image while reducing the number of iterations.
  • the computer-readable storage medium may be the internal storage unit of the terminal described in any of the foregoing embodiments, such as the hard disk or memory of the terminal.
  • the computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a smart memory card (Smart Media Card, SMC), or a Secure Digital (SD) card , Flash Card, etc.
  • the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.
  • the computer-readable storage medium is used to store the computer-readable instructions and other programs and data required by the terminal.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
  • the disclosed terminal and method can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present application.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium It includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)

Abstract

适用于计算机应用技术领域的一种图像重建方法及装置,包括:获取待处理的第一图像(S101);根据预设的映射矩阵,对第一图像进行超分辨处理,得到第二图像(S102)。通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。

Description

一种图像重建方法及装置 技术领域
本申请属于计算机应用技术领域,尤其涉及一种图像重建方法及装置。
背景技术
正电子发射型计算机断层显像(Positron Emission Computed Tomography,PET)是核医学领域比较先进的临床检查影像技术,而高质量的PET可以提高医生的诊断精确度,因此改进PET图像重建算法一直是人们在研究的主题。现有的PET图像重建算法主要分为解析重建算法和迭代重建算法两类。解析重建算法主要包括反投影,滤波反投影以及傅里叶重建。其中最广泛应用的算法是滤波反投影(Filtered Back-projection,FBP)。迭代重建算法又包括代数重建和统计重建,目前统计重建中极大似然期望最大化,因其更好的性能在临床和实践中被广泛应用。但其因投影图像中存在相对严重的统计噪声时,随迭代次数的增加图像质量会产生棋盘格伪影,这种方式会把噪声也相应放大,由此得到的重建图像的质量较低。
技术问题
本申请实施例提供了图像重建方法及装置,可以解决现有技术中在进行图像重建时会放大图像噪声,得到的重建图像质量较低的问题。
技术解决方案
第一方面,本申请实施例提供了一种图像重建方法,包括:
获取待处理的第一图像;
根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
其中,所述根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像之前,还包括:
获取待训练的样本图像;
对所述样本图像进行仿射变换得到所述投影图像;
对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
其中,所述对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果,包括:
根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
其中,所述根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果,包括:
根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
其中,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
Figure PCTCN2019101371-appb-000001
其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
其中,所述计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,包括:
通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
Figure PCTCN2019101371-appb-000002
其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
其中,所述对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果,包括:
根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
Figure PCTCN2019101371-appb-000003
其中,W表示所述映射矩阵;
Figure PCTCN2019101371-appb-000004
表示第n+1次迭代的所述融合图像的像素值;
Figure PCTCN2019101371-appb-000005
所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
第二方面,本申请实施例提供了一种图像重建装置,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现以下步骤:
获取待处理的第一图像;
根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图 像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
第三方面,本申请实施例提供了一种图像重建装置,包括:
获取单元,用于获取待处理的第一图像;
重建单元,用于根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
第四方面,本申请实施例提供了一种计算机可读存储介质,所述计算机存储介质存储有计算机可读指令,所述计算机可读指令包括程序指令,所述程序指令当被处理器执行时使所述处理器执行上述第一方面的方法。
第五方面,本申请实施例提供了一种计算机可读指令产品,当计算机可读指令产品在终端设备上运行时,使得终端设备执行上述第一方面中任一项所述的图像重建方法。
可以理解的是,上述第二方面至第五方面的有益效果可以参见上述第一方面中的相关描述,在此不再赘述。
有益效果
本申请实施例与现有技术相比存在的有益效果是:通过获取待处理的第一图像;根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像。本实施例中通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本申请实施例一提供的图像重建方法的流程图;
图2是本申请实施例二提供的图像重建方法的流程图;
图3是本申请实施例二提供的图像重建的实验结果;
图4是本申请实施例三提供的图像重建装置的示意图;
图5是本申请实施例四提供的图像重建装置的示意图。
本发明的实施方式
以下描述中,为了说明而不是为了限定,提出了诸如特定系统结构、技术之类的具体细节,以便透彻理解本申请实施例。然而,本领域的技术人员应当清楚,在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中,省略对众所周知的系统、装置、电路以及方法的详细说明,以免不必要的细节妨碍本申请的描述。
应当理解,当在本申请说明书和所附权利要求书中使用时,术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在,但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解,在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合,并且包括这些组合。
如在本申请说明书和所附权利要求书中所使用的那样,术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地,短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。
另外,在本申请说明书和所附权利要求书的描述中,术语“第一”、“第二”、“第三”等仅用于区分描述,而不能理解为指示或暗示相对重要性。
在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此,在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例,而是意味着“一个或多个但不是所有的实施例”,除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”,除非是以其他方式另外特别强调。
参见图1,图1是本申请实施例一提供的一种图像重建方法的流程图。本实施例中图像重建方法的执行主体为具有图像重建功能的装置,包括但不限于计算机、服务器、平板电脑或者终端等装置。如图所示的图像重建方法可以包括以下步骤:
S101:获取待处理的第一图像。
本实施例提出一种基于决策树的PET正电子发射型计算机断层显像图像重建算法,在基于色斑的PET图像重建算法中加入基于决策树的超分辨技术,利用决策树拟合出从低分辨率图像映射到高分辨率图像的模型,对每次迭代重建出来的图像进行超分辨。可以减少迭代次数以提早达到收敛,同时减少调整参数的时间,在相对较差的参数设置下实现更好的重建结果,提高PET重建图像的质量。
正电子发射型计算机断层显像是核医学领域比较先进的临床检查影像技术,而高质量的PET可以提高医生的诊断精确度,因此改进PET图像重建算法一直是人们在研究的主题。现有的PET图像重建算法主要分为解析重建算法和迭代重建算法两类。解析重建算法主要包括反投影,滤波反投影以及傅里叶重建。其中最广泛应用的算法是滤波反投影。迭代重 建算法又包括代数重建和统计重建,目前统计重建中极大似然-期望最大化,因其更好的性能在临床和实践中被广泛应用。但其因投影图像中存在相对严重的统计噪声时,随迭代次数的增加图像质量会产生棋盘格伪影反而更差。因而有了引入正则化项的基于色斑的惩罚似然PET图像重建算法。
本实施例的第一图像用于表示分辨率较低的PET图像或者重建图像。其获取方式可以是通过PET扫描设备直接获取。
S102:根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
现有的PET图像重建算法,常用的有解析重建中的滤波反投影和迭代重建中的极大似然期望最大化(Maximum likelihood-expectation maximization,MLEM)算法。重建算法虽然计算简单快速,但其重建结果具有较差的分辨率和噪声特性,需要完整的投影图像和较大的计数值。MLEM算法的实际使用中存在的问题是,当投影图像中存在相对严重的统计噪声时,随着迭代的进行,重建图像的质量不是完全更好,会把噪声也相应放大。在此基础上改进的基于色斑patch的正则化迭代重建算法,在图像迭代更新过程中引入正则化项,但它对算法参数的值敏感,需要花费大量时间调整参数以实现最佳重建效果。本实施例在保留边缘和细节,实现较好的重建图像的同时,也减少了调整参数的设置的时间,在较差的参数设置下,不需要较高的计数水平也可以实现较好的重建。
本实施例的第一图像用于表示获取到的低分辨率的PET图像或者重建图像,第二图像用于表示对第一图像进行PET图像重建得到的高分辨率的投影图像。本实施例在对PET图像重建的过程中,加入了机器学习算法,在每一次迭代重建图像,利用决策树训练低分辨率图像块和对应高分辨率图像块,拟合出从低分辨率图像映射到高分辨率图像的映射关系,即映射矩阵,以通过映射矩阵,对第一图像进行超分辨处理得到第二图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,减少了迭代次数的同时提高PET重建图像的质量。
上述方案,通过获取待处理的第一图像;根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像。本实施例中通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。
参见图2,图2是本申请实施例提供的一种图像重建方法的流程图。如图所示的图像重建方法在步骤S101之前可以包括以下步骤:
S201:获取待训练的样本图像。
本实施例中的样本图像可以为重建图像,其中,重建图像x是医院病人的PET图像,以对x进行仿射变换得到投影图像y。
S202:对所述样本图像进行仿射变换得到所述投影图像。
本实施例中得到的数据不是实时采集的投影图像,所以是由重建PET图像x投影得到投影图像y,投影图像y重建为PET图像过程中加入超分辨过程,最后得到重建后的PET图像。
本实施例的投影图像
Figure PCTCN2019101371-appb-000006
由重建图像x通过仿射变换得到:
Figure PCTCN2019101371-appb-000007
其中,P表示系统矩阵,表示探测器对样本图像中的像素点i检测到符合事件的概率;r表示随机背景事件,s表示散射事件。
S203:对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果。
步骤S203包括:根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果。
本实施例中对样本图像进行迭代处理得到样本处理结果为:
Figure PCTCN2019101371-appb-000008
其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示样本图像的像素值;y表示投影图像的像素值。
具体的,由于衰变的正电子发射本身满足泊松分布,我们假设PET投影图像y可以被认为是独立泊松随机变量的分布。惩罚似然重建通过最大化惩罚似然函数来估计重建图像x:
Figure PCTCN2019101371-appb-000009
其中,Φ(x)=L(y|x)-βU(x);其中,正则化参数β在初始化时可以设定为β=2 -7,我们选择Q L(x;x n),
Figure PCTCN2019101371-appb-000010
分别作为似然代理函数L(y|x)和惩罚代理函数U(x):
Figure PCTCN2019101371-appb-000011
其中,
Figure PCTCN2019101371-appb-000012
其中,n j表示图像的像素总数,j和k分别表示两个图像块;系统矩阵P={p ij},p ij表示探测器对i在像素点j检测到符合事件的概率;y i表示第i对对探测器采集的投影数据;
Figure PCTCN2019101371-appb-000013
表示第n次迭代的预测投影数据;x n表示第n次迭代图像;
Figure PCTCN2019101371-appb-000014
表示第n次迭代的第j个图像块;
Figure PCTCN2019101371-appb-000015
表示第n次迭代的第k个图像块;N j表示第j个图像块的总像素值;
Figure PCTCN2019101371-appb-000016
是与邻域块有关的权重,由惩罚函数和每次迭代的当前估计图像自适应决定;
Figure PCTCN2019101371-appb-000017
表示第n次迭代的按像素分配的权重。
进一步的,步骤根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果,包括S2031~S2033:
S2031:根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像。
本实施例根据如下公式实现图像平滑:
Figure PCTCN2019101371-appb-000018
其中,x n表示第n次迭代图像;
Figure PCTCN2019101371-appb-000019
表示第n次迭代的第j个图像块;
Figure PCTCN2019101371-appb-000020
表示第n次迭代的第k个图像块;N j表示第j个图像块的总像素值;w jk表示与邻域块有关的权重,由惩罚函数和每次迭代的当前估计图像自适应决定。
S2032:对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像。
本实施例通过正弦图sinogram{y i}来更新EM图像得到
Figure PCTCN2019101371-appb-000021
然后通过图像平滑得到
Figure PCTCN2019101371-appb-000022
最后就是逐个像素融合,通过KKT条件得到每次惩罚似然重建的迭代图像:
Figure PCTCN2019101371-appb-000023
其中,
Figure PCTCN2019101371-appb-000024
正则化参数β是一个常数,用于控制先验的权重,平衡对数似然项和惩罚项。
S2033:对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
本实施例根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
Figure PCTCN2019101371-appb-000025
其中,W表示所述映射矩阵;
Figure PCTCN2019101371-appb-000026
表示第n+1次迭代的所述融合图像的像素值;
Figure PCTCN2019101371-appb-000027
所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
具体的,在得到每次迭代重建图像后,运用决策树进行超分辨处理。通过多棵决策树训练拟合出的从低分辨率图像到高分辨率图像的模型,作用在每次迭代重建图像
Figure PCTCN2019101371-appb-000028
上:
Figure PCTCN2019101371-appb-000029
其中,
Figure PCTCN2019101371-appb-000030
是决策树训练拟合出来的映射矩阵,将训练样本的低分辨每次迭代重建出来的图像x和高分辨率参考图像y,用决策树聚类拟合出从x映射到y的最接近的模型,即W。
需要说明的是,本实施例中的W和
Figure PCTCN2019101371-appb-000031
相同,都是用于表示映射矩阵,此处只是为表述简洁没有带括号里的自变量。
S204:计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
进一步的,步骤S204包括:
S2041:计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果。
本实施例通过如下公式计算每个样本处理结果与投影图像之间的平方损失函数值:
Figure PCTCN2019101371-appb-000032
其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示第n个样本图像对应的投影图像;
具体的,
Figure PCTCN2019101371-appb-000033
是决策树训练拟合出来的映射矩阵,将训练样本,即样本图像的低分辨每次迭代重建出来的图像x和高分辨率参考图像y,用决策树聚类拟合出从x映射到y的最接近的模型,即W。且W依赖于低分辩图像块x。则这种映射关系可以写成,
Figure PCTCN2019101371-appb-000034
通过决策树训练,根据最小化平方损失函数的原则:
Figure PCTCN2019101371-appb-000035
找到最拟合的模型W,其中,N表示训练样本大小,x n表示第n个训练样本的低分辩图像块,y n表示对应高分辩图像块。
S2042:确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
本实施例的映射矩阵为:W=[(X TX+λI) -1X T·Y] T;其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
本实施例中为了解决岭回归,即正则化最小二乘回归问题,则可计算出W:W T=(X TX+λI) -1X T·Y;其中,X,Y分别表示低分辩图像和对应高分辩图像,λI表示加入的正则项;I表示单位矩阵;λ表示正则化参数,可以把λ设为0.01。
训练T棵决策树得到T个模型,最终预测结果即T棵树的预测值的平均值。如何训练决策树,即是把每组对应高低分辨率图像块{x H,x L}递归且不相交地分裂聚类到左右子节点,形如二叉树。一直到节点样本大小小于2不能分裂或达到最大深度则停止分裂形成叶子节点,叶子节点模型即我们需要训练拟合的模型。分裂的原则即根据图像块特征计算响应函数,响应函数为:r θ(x L)=x L[θ]-θ th;其中,θ表示图像块x L的特征,x L[·]表示图像块x L的数据矩阵的一维向量,θ th表示阈值。当r θ(x L)<0时,图像块对{x H,x L}分裂到左子节点;反之,则分裂到右子节点。
至于计算响应函数的特征,每次分裂都会遍历图像块的所有特征选择其中的最优特征,最优特征的参考量定义为:
Q(σ,θ,X H,X L)=∑ c∈{Le,Ri}|X c|·E(X H c,X L c);
Figure PCTCN2019101371-appb-000036
其中,(X H c,X L c)表示分裂到左子节点和右子节点的对应高低分辨率图像块。
Figure PCTCN2019101371-appb-000037
表示样本x L n的均值,W(x L n)x L n表示样本x L n的预测值,|N|表示分裂到子节点的样本数即图像块,k表示设置的超参数;σ表示左右子节点定义的值分裂到左子节点时σ=0,反之σ=1。
本实施例的伪代码图见算法1:
Figure PCTCN2019101371-appb-000038
决策树的模型不仅作用在每次迭代重建出来的图像上,还作用在循环最开始的投影图像{y i},只是把训练集换成迭代重建每次反投影计算出来的投影图像和对应原始参考投影。本实施例的决策树就是把样本通过以上描述的分裂过程聚类分成最后若干叶子节点即若干类,然后通过上述描述的最小化平方损失函数的原则找到映射矩阵W即找到映射模型。
本实施例的实验结果请一并参阅图3和表1所示:
表1.PET图像分辨率评估参数表
评估参数 峰值信噪比PNSR 结构相似形SSIM
基于patch的重建图像 29.67 0.87
本实施例的重建图像 34.51 0.88
图3中图a是参考的PET图像,图b是基于patch正则化迭代重建算法重建出来的PET图像,图c由本实施例算法重建出来的PET图像。由图可知,本实施例重建出来的PET图像分辨率比基于patch正则化迭代重建算法重建出来的PET图像要好,与参考PET图像也更接近,充分说明了本算法的可行性。而从评估参数表也可看出,经过本算法重建出来的图像在PNSR、SSIM上都比基于patch重建结果更好,进一步证明了本算法的有效。
上述方案,通过获取待训练的样本图像;对所述样本图像进行仿射变换得到所述投影图像;对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得 到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。通过利用决策树拟合出从低分辨率图像映射到高分辨率图像的模型,对每次迭代重建出来的图像进行超分辨。可以减少迭代次数以提早达到收敛,同时减少调整参数的时间,在相对较差的参数设置下实现更好的重建结果,提高PET重建图像的质量。
参见图4,图4是本申请实施例三提供的一种图像重建装置的示意图。图像重建装置400可以为智能手机、平板电脑等移动终端。本实施例的图像重建装置400包括的各单元用于执行图1对应的实施例中的各步骤,具体请参阅图1及图1对应的实施例中的相关描述,此处不赘述。本实施例的图像重建装置400包括:
获取单元401,用于获取待处理的第一图像;
重建单元402,用于根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
进一步的,所述图像重建装置400还包括:
第一获取单元,用于获取待训练的样本图像;
变换单元,用于对所述样本图像进行仿射变换得到所述投影图像;
训练单元,用于对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
计算单元,用于计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
进一步的,所述训练单元包括:
迭代处理单元,用于迭代根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
进一步的,所述计算单元包括:
第一计算单元,用于计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
矩阵确定单元,用于确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
进一步的,所述迭代处理单元包括:
平滑单元,用于根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
融合单元,用于对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
超分辨处理单元,用于对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
其中,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
Figure PCTCN2019101371-appb-000039
其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
所述计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,包括:
通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
Figure PCTCN2019101371-appb-000040
其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
进一步的,所述超分辨处理单元用于:
根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
Figure PCTCN2019101371-appb-000041
其中,W表示所述映射矩阵;
Figure PCTCN2019101371-appb-000042
表示第n+1次迭代的所述融合图像的像素值;
Figure PCTCN2019101371-appb-000043
所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
上述方案,通过获取待处理的第一图像;根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像。本实施例中通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
参见图5,图5是本申请实施例四提供的一种图像重建装置的示意图。如图5所示的本实施例中的图像重建装置500可以包括:处理器501、存储器502以及存储在存储器502中并可在处理器501上运行的计算机可读指令503。处理器501执行计算机可读指令503时实现上述各个图像重建方法实施例中的步骤。存储器502用于存储计算机可读指令,所述计算机可读指令包括程序指令。处理器501用于执行存储器502存储的程序指令。其中,处理器501被配置用于调用所述程序指令执行以下操作:
处理器501用于:
获取待训练的样本图像;
对所述样本图像进行仿射变换得到所述投影图像;
对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
进一步的,处理器501具体用于:
根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
进一步的,处理器501具体用于:
根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
其中,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
Figure PCTCN2019101371-appb-000044
其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
所述计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,包括:
通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
Figure PCTCN2019101371-appb-000045
其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
进一步的,处理器501具体用于:
根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
Figure PCTCN2019101371-appb-000046
其中,W表示所述映射矩阵;
Figure PCTCN2019101371-appb-000047
表示第n+1次迭代的所述融合图像的像素值;
Figure PCTCN2019101371-appb-000048
所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
上述方案,通过获取待处理的第一图像;根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像。本实施例中通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET 图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。
应当理解,在本申请实施例中,所称处理器501可以是中央处理单元(Central Processing Unit,CPU),该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
该存储器502可以包括只读存储器和随机存取存储器,并向处理器501提供指令和数据。存储器502的一部分还可以包括非易失性随机存取存储器。例如,存储器502还可以存储设备类型的信息。
具体实现中,本申请实施例中所描述的处理器501、存储器502、计算机可读指令503可执行本申请实施例提供的图像重建方法的第一实施例和第二实施例中所描述的实现方式,也可执行本申请实施例所描述的终端的实现方式,在此不再赘述。
在本申请的另一实施例中提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,所述计算机可读指令包括程序指令,所述程序指令被处理器执行时实现:
获取待训练的样本图像;
对所述样本图像进行仿射变换得到所述投影图像;
对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
进一步的,所述计算机可读指令被处理器执行时还实现:
根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
进一步的,所述计算机可读指令被处理器执行时还实现:
根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
其中,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
Figure PCTCN2019101371-appb-000049
其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
进一步的,所述计算机可读指令被处理器执行时还实现:
通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
Figure PCTCN2019101371-appb-000050
其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
进一步的,所述计算机可读指令被处理器执行时还实现:
根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
Figure PCTCN2019101371-appb-000051
其中,W表示所述映射矩阵;
Figure PCTCN2019101371-appb-000052
表示第n+1次迭代的所述融合图像的像素值;
Figure PCTCN2019101371-appb-000053
所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
上述方案,通过获取待处理的第一图像;根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像。本实施例中通过预先对获取到的样本图像和投影图像通过决策树的方法,拟合出从低分辨率图像映射到高分辨率图像的映射关系,以将低分辨率的正电子发射型计算机断层显像PET映射为高分辨率的投影图像,提高每次迭代重建后的PET图像的质量,使重建提前达到收敛,在减少迭代次数的同时提高了PET重建图像的质量。
所述计算机可读存储介质可以是前述任一实施例所述的终端的内部存储单元,例如终端的硬盘或内存。所述计算机可读存储介质也可以是所述终端的外部存储设备,例如所述终端上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述计算机可读存储介质还可以既包括所述终端的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机可读指令及所述终端所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,上述描述的终端和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的终端和方法,可以通过其它 的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另外,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接,也可以是电的,机械的或其它的形式连接。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本申请实施例方案的目的。另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分,或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到各种等效的修改或替换,这些修改或替换都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以权利要求的保护范围为准。

Claims (20)

  1. 一种图像重建方法,其特征在于,包括:
    获取待处理的第一图像;
    根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
  2. 如权利要求1所述的图像重建方法,其特征在于,所述根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像之前,还包括:
    获取待训练的样本图像;
    对所述样本图像进行仿射变换得到所述投影图像;
    对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
    计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
  3. 如权利要求2所述的图像重建方法,其特征在于,所述对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果,包括:
    根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
    所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
    计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
    确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
  4. 如权利要求3所述的图像重建方法,其特征在于,所述根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果,包括:
    根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
    对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
    对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
  5. 如权利要求3所述的图像重建方法,其特征在于,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
    Figure PCTCN2019101371-appb-100001
    其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
  6. 如权利要求3所述的图像重建方法,其特征在于,所述计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,包括:
    通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
    Figure PCTCN2019101371-appb-100002
    其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
    所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
    其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
  7. 如权利要求4所述的图像重建方法,其特征在于,所述对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果,包括:
    根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
    Figure PCTCN2019101371-appb-100003
    其中,W表示所述映射矩阵;
    Figure PCTCN2019101371-appb-100004
    表示第n+1次迭代的所述融合图像的像素值;
    Figure PCTCN2019101371-appb-100005
    所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
  8. 一种图像重建装置,其特征在于,包括:
    获取单元,用于获取待处理的第一图像;
    重建单元,用于根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
  9. 如权利要求8所述的图像重建装置,其特征在于,所述图像重建装置还包括:
    第一获取单元,用于获取待训练的样本图像;
    变换单元,用于对所述样本图像进行仿射变换得到所述投影图像;
    训练单元,用于对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
    计算单元,用于计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
  10. 如权利要求9所述的图像重建装置,其特征在于,所述训练单元包括:
    迭代处理单元,用于迭代根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
    所述计算单元包括:
    第一计算单元,用于计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
    矩阵确定单元,用于确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
  11. 一种图像重建装置,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,其特征在于,所述处理器执行所述计算机可读指令时实现 如下步骤:
    获取待处理的第一图像;
    根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
  12. 如权利要求11所述的图像重建装置,其特征在于,所述根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像之前,还包括:
    获取待训练的样本图像;
    对所述样本图像进行仿射变换得到所述投影图像;
    对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
    计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
  13. 如权利要求12所述的图像重建装置,其特征在于,所述对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果,包括:
    根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
    所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
    计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
    确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
  14. 如权利要求13所述的图像重建装置,其特征在于,所述根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果,包括:
    根据预设的决策树方法,对所述样本图像进行图像平滑迭代处理得到平滑图像;
    对所述平滑图像中的像素点进行像素图像融合迭代处理,得到融合图像;
    对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果。
  15. 如权利要求13所述的图像重建装置,其特征在于,所述对所述样本图像进行迭代处理得到所述样本处理结果为:
    Figure PCTCN2019101371-appb-100006
    其中,Φ(x)=L(y|x)-βU(x);L(y|x)表示似然代理函数;U(x)表示惩罚代理函数;β表示正则化参数,x表示所述样本图像的像素值;y表示所述投影图像的像素值。
  16. 如权利要求13所述的图像重建装置,其特征在于,所述计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,包括:
    通过如下公式计算每个所述样本处理结果与所述投影图像之间的平方损失函数值:
    Figure PCTCN2019101371-appb-100007
    其中,N表示样本图像的总数目,x n表示第n个样本图像,y n表示所述第n个样本图像对应的投影图像;
    所述映射矩阵为:W=[(X TX+λI) -1X T·Y] T
    其中,X表示所述样本图像,Y表示所述投影图像,λ表示预设的正则化参数,I表示单位矩阵。
  17. 如权利要求14所述的图像重建装置,其特征在于,所述对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果,包括:
    根据如下公式对所述融合图像进行迭代的超分辨处理,得到所述样本处理结果:
    Figure PCTCN2019101371-appb-100008
    其中,W表示所述映射矩阵;
    Figure PCTCN2019101371-appb-100009
    表示第n+1次迭代的所述融合图像的像素值;
    Figure PCTCN2019101371-appb-100010
    所述第n+1次迭代的所述融合图像的像素值对应的样本处理结果。
  18. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,其特征在于,所述计算机可读指令被处理器执行时实现如下步骤:
    获取待处理的第一图像;
    根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像;所述映射矩阵为对获取到的样本图像和投影图像通过决策树的方法进行训练得到,用于将低分辨率图像映射为高分辨率图像;所述投影图像为对所述样本图像进行仿射变换得到。
  19. 如权利要求18所述的计算机可读存储介质,其特征在于,所述根据预设的映射矩阵,对所述第一图像进行超分辨处理,得到第二图像之前,还包括:
    获取待训练的样本图像;
    对所述样本图像进行仿射变换得到所述投影图像;
    对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果;
    计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵;所述映射关系为样本处理结果和投影图像之间映射关系。
  20. 如权利要求19所述的计算机可读存储介质,其特征在于,所述对所述样本图像和所述投影图像进行决策树训练,得到样本处理结果,包括:
    根据预设的决策树方法,对所述样本图像进行迭代处理得到所述样本处理结果;
    所述计算所述样本处理结果和所述投影图像之间的损失函数,根据所述损失函数调整预设的映射关系,得到所述映射矩阵,包括:
    计算每个所述样本处理结果与所述投影图像之间的平方损失函数值,识别所述平方损失函数值最小时的样本处理结果为目标结果;
    确定所述目标结果和所述投影图像之间的关系矩阵,作为所述映射矩阵。
PCT/CN2019/101371 2019-08-19 2019-08-19 一种图像重建方法及装置 Ceased WO2021031069A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/101371 WO2021031069A1 (zh) 2019-08-19 2019-08-19 一种图像重建方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/101371 WO2021031069A1 (zh) 2019-08-19 2019-08-19 一种图像重建方法及装置

Publications (1)

Publication Number Publication Date
WO2021031069A1 true WO2021031069A1 (zh) 2021-02-25

Family

ID=74660142

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/101371 Ceased WO2021031069A1 (zh) 2019-08-19 2019-08-19 一种图像重建方法及装置

Country Status (1)

Country Link
WO (1) WO2021031069A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115700785A (zh) * 2021-07-16 2023-02-07 顺丰科技有限公司 图像特征提取方法、装置、电子设备及存储介质
CN115830362A (zh) * 2022-11-02 2023-03-21 抖音视界有限公司 图像处理方法、装置、设备、介质及产品
CN116403114A (zh) * 2023-04-18 2023-07-07 中科开采夫(海南)空天信息研究院有限公司 一种基于深度学习的遥感影像目标识别方法及系统
CN117726656A (zh) * 2024-02-08 2024-03-19 开拓导航控制技术股份有限公司 基于超分辨率图像的目标跟踪方法、装置、系统和介质
CN120147132A (zh) * 2025-02-28 2025-06-13 西安邮电大学 一种基于图像超分辨的激光焦点动态跟踪方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130156297A1 (en) * 2011-12-15 2013-06-20 Microsoft Corporation Learning Image Processing Tasks from Scene Reconstructions
US20190090826A1 (en) * 2017-09-26 2019-03-28 General Electric Company Systems and methods for improved diagnostics for nuclear medicine imaging
CN109564677A (zh) * 2018-11-09 2019-04-02 香港应用科技研究院有限公司 基于随机森林分类器加权结果的超分辨率合成系统和方法
CN109598676A (zh) * 2018-11-15 2019-04-09 华南理工大学 一种基于哈达玛变换的单幅图像超分辨率方法
CN109961834A (zh) * 2019-03-22 2019-07-02 上海联影医疗科技有限公司 影像诊断报告的生成方法及设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130156297A1 (en) * 2011-12-15 2013-06-20 Microsoft Corporation Learning Image Processing Tasks from Scene Reconstructions
US20190090826A1 (en) * 2017-09-26 2019-03-28 General Electric Company Systems and methods for improved diagnostics for nuclear medicine imaging
CN109564677A (zh) * 2018-11-09 2019-04-02 香港应用科技研究院有限公司 基于随机森林分类器加权结果的超分辨率合成系统和方法
CN109598676A (zh) * 2018-11-15 2019-04-09 华南理工大学 一种基于哈达玛变换的单幅图像超分辨率方法
CN109961834A (zh) * 2019-03-22 2019-07-02 上海联影医疗科技有限公司 影像诊断报告的生成方法及设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HU ZHANLI, WANG YING, ZHANG XUEZHU, ZHANG MENGXI, YANG YONGFENG, LIU XIN, ZHENG HAIRONG, LIANG DONG: "Super-resolution of PET image based on dictionary learning and random forests", NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH. SECTION A, ELSEVIER BV * NORTH-HOLLAND, NL, vol. 927, 1 May 2019 (2019-05-01), NL, pages 320 - 329, XP055783319, ISSN: 0168-9002, DOI: 10.1016/j.nima.2019.02.042 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115700785A (zh) * 2021-07-16 2023-02-07 顺丰科技有限公司 图像特征提取方法、装置、电子设备及存储介质
CN115830362A (zh) * 2022-11-02 2023-03-21 抖音视界有限公司 图像处理方法、装置、设备、介质及产品
CN116403114A (zh) * 2023-04-18 2023-07-07 中科开采夫(海南)空天信息研究院有限公司 一种基于深度学习的遥感影像目标识别方法及系统
CN117726656A (zh) * 2024-02-08 2024-03-19 开拓导航控制技术股份有限公司 基于超分辨率图像的目标跟踪方法、装置、系统和介质
CN117726656B (zh) * 2024-02-08 2024-06-04 开拓导航控制技术股份有限公司 基于超分辨率图像的目标跟踪方法、装置、系统和介质
CN120147132A (zh) * 2025-02-28 2025-06-13 西安邮电大学 一种基于图像超分辨的激光焦点动态跟踪方法及系统

Similar Documents

Publication Publication Date Title
WO2021031069A1 (zh) 一种图像重建方法及装置
CN109712209B (zh) Pet图像的重建方法、计算机存储介质、计算机设备
CN107123095B (zh) 一种pet图像重建方法、成像系统
CN107133996B (zh) 产生用于pet数据重建的衰减图的方法及pet/ct系统
CN107481297B (zh) 一种基于卷积神经网络的ct图像重建方法
WO2021159948A1 (zh) 一种基于深度学习的低剂量pet三维重建方法
CN109961491A (zh) 多模态图像截断补偿方法、装置、计算机设备和介质
CN107527359A (zh) 一种pet图像重建方法及pet成像设备
CN111709897B (zh) 一种基于域变换的正电子发射断层图像的重建方法
CN111325695B (zh) 基于多剂量等级的低剂量图像增强方法、系统及存储介质
CN103186882B (zh) Pet系统中图像的衰减校正方法及装置
WO2020118829A1 (zh) 基于决策树的pet图像超分辨重建方法、装置、设备及介质
US12597189B2 (en) Methods and apparatus for synthetic computed tomography image generation
WO2020118830A1 (zh) 字典训练及图像超分辨重建方法、系统、设备及存储介质
CN108038840A (zh) 一种图像处理方法、装置、图像处理设备及存储介质
CN110580689A (zh) 一种图像重建方法及装置
CN109961435B (zh) 脑图像获取方法、装置、设备及存储介质
CN110874855A (zh) 一种协同成像方法、装置、存储介质和协同成像设备
CN108537755B (zh) 一种基于几何结构约束的pet图像增强的方法及系统
CN116228753A (zh) 肿瘤预后评估方法、装置、计算机设备和存储介质
WO2021184350A1 (zh) 一种基于神经网络的网格化磁共振图像重建方法和装置
CN114862980A (zh) 散射校正方法、pet成像方法、装置、设备及存储介质
CN114549594A (zh) 图像配准方法、装置和电子设备
CN113469915A (zh) 一种基于去噪打分匹配网络的pet重建方法
WO2025067508A1 (zh) 用于处理扫描数据的方法、装置、计算机设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19942309

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19942309

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19942309

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16.02.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 19942309

Country of ref document: EP

Kind code of ref document: A1