WO2022109928A1 - Procédé de reconstruction d'image et application - Google Patents

Procédé de reconstruction d'image et application Download PDF

Info

Publication number
WO2022109928A1
WO2022109928A1 PCT/CN2020/131792 CN2020131792W WO2022109928A1 WO 2022109928 A1 WO2022109928 A1 WO 2022109928A1 CN 2020131792 W CN2020131792 W CN 2020131792W WO 2022109928 A1 WO2022109928 A1 WO 2022109928A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
reconstructed
reconstruction method
image reconstruction
pixel
Prior art date
Application number
PCT/CN2020/131792
Other languages
English (en)
Chinese (zh)
Inventor
郑海荣
梁栋
胡战利
刘新
黄英
Original Assignee
深圳先进技术研究院
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 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Priority to PCT/CN2020/131792 priority Critical patent/WO2022109928A1/fr
Publication of WO2022109928A1 publication Critical patent/WO2022109928A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation

Definitions

  • the present application belongs to the technical field of computed tomography, and in particular relates to an image reconstruction method and application.
  • Computed tomography is to use x-rays to scan the human body, and then the analog signal r received by the detector is converted into a digital signal, and the attenuation of each pixel is calculated by an electronic computer. It is a device that can display the tomographic structure of various parts of the human body by reconstructing the image.
  • Image fusion refers to the image data collected by multi-source channels about the same target through image processing and computer technology, etc., to maximize the extraction of favorable information in the respective channels, and finally to synthesize high-quality images. Improve the utilization rate of image information, improve the accuracy and reliability of computer interpretation, improve the spatial resolution and spectral resolution of the original image, and facilitate monitoring.
  • the images to be fused have been registered and have the same pixel bit width.
  • CT computed tomography
  • Low-dose CT imaging can be achieved by reducing the number of projections per revolution of the human body by reducing the milliamp-second scanning scheme.
  • the present application provides an image reconstruction method and application.
  • the present application provides an image reconstruction method, which includes the following steps: Step 1: reconstruct the corrected projection data; obtain reconstructed data; Step 2: regularize the reconstructed data , obtain a regularized image; Step 3: Reconstruct the regularized image to obtain a reconstructed image; Step 4: Use the reconstructed image as prior information, and conduct a guided kernel under the guidance of the reconstructed image Filter (Guided Kernel Filter) to get the restored image.
  • Step 1 reconstruct the corrected projection data
  • Step 2 regularize the reconstructed data , obtain a regularized image
  • Step 3 Reconstruct the regularized image to obtain a reconstructed image
  • Step 4 Use the reconstructed image as prior information, and conduct a guided kernel under the guidance of the reconstructed image Filter (Guided Kernel Filter) to get the restored image.
  • step 1 the corrected projection data is reconstructed by a penalized weighted least squares algorithm to obtain an ideal projection vector to be estimated.
  • the step 1 uses a sinogram recovery method based on a penalized weighted least squares algorithm to recover sinogram data using a combination of low milliampere seconds and sparse view protocols.
  • step 2 the total variation method based on penalized weighted least squares is used to reconstruct the image using the recovered sinogram data, and then the total variation method based on penalized weighted least squares is used to reconstruct the image.
  • the non-quadratic penalty function performs neighborhood patches instead of single-pixel regularization.
  • step 3 uses a regularization algorithm to reconstruct the regularized image.
  • step 4 a sparse matrix is constructed, and the matrix is normalized to obtain a normalized kernel matrix; then guided kernel filtering is performed under the guidance of the reconstructed image to obtain Restore the image.
  • the matrix is constructed by using the k-nearest neighbor algorithm.
  • Another embodiment provided by the present application is: when calculating the image roughness between adjacent pixels in the penalized weighted least squares total variation method, a patch related to each pixel is used.
  • U( ⁇ ) is the patch-based roughness function
  • f j ( ⁇ ), f k ( ⁇ ) are feature vectors consisting of the intensity values of all pixels in the center of the patch at pixel j and pixel k, respectively
  • h is A positive weighting factor equal to the normalized inverse spatial distance between pixel j and pixel k
  • h ) is a non-quadratic penalty function.
  • the present application also provides an application of the image reconstruction method, where the image reconstruction method is applied to image noise reduction and artifact removal or image fusion.
  • the image reconstruction method provided in this application is an image reconstruction method of sparse viewing angle and image fusion.
  • the image reconstruction method provided in this application solves the problem of improving the quality of low-millisecond or sparse reconstructed images.
  • the image reconstruction method provided in this application is a promising option for obtaining high-quality images under low-dose scanning. Therefore, research and development of new low-dose CT reconstruction methods can not only ensure CT imaging quality but also reduce harmful radiation doses, which has important scientific significance and application prospects in the field of medical diagnosis.
  • the finally obtained restored image not only suppresses noise, but also retains image details.
  • the image reconstruction method provided in this application includes complete reconstruction and restoration of CT images.
  • the reconstructed image of PWLS-TV has good structural information.
  • the image reconstruction method provided in this application is based on image update regularized by a non-quadratic penalty function of patches.
  • the method utilizes spatial regularization to penalize image intensity differences between adjacent pixels, thereby improving image quality.
  • Non-quadratic penalty functions can preserve edges.
  • FIG. 1 is a schematic diagram of the overall framework of the image reconstruction method of the present application.
  • FIG. 2 is a schematic diagram of an image reconstruction result of the present application.
  • noise measurements at each i are generated from a statistical model of the pre-log projection data after computing the noise-free line integral y i in the model-based direct projection operation
  • I0 is the incident X-ray intensity
  • y i is the sinogram data
  • yi is the sinogram data
  • yi is the variance of the background electronic noise, set to 0.1.
  • the existing method Due to the large dose in the CT scanning process, the existing method has potential harm to the human body due to radiation exposure; due to the large amount of data collected, the image reconstruction speed is slow; (3) due to the long scanning time, it leads to the occurrence of patient movement problems. induced artifacts.
  • Regularization means that in linear algebra theory, an ill-posed problem is usually defined by a set of linear algebraic equations, and this set of equations is usually derived from an ill-posed inverse problem with a large condition number.
  • a large condition number means that rounding errors or other errors can seriously affect the outcome of the problem.
  • the present application provides an image reconstruction method, the method includes the following steps:
  • Step 1 reconstruct the corrected projection data; obtain reconstructed data;
  • Step 2 perform regularization on the reconstructed data to obtain a regularized image;
  • Step 3 reconstruct the regularized image to obtain a reconstructed image ;
  • Step 4 take the reconstructed image as prior information, and carry out guided kernel filtering (Guided Kernel Filter) under the guidance of the reconstructed image to obtain a restored image.
  • guided kernel filtering Guided Kernel Filter
  • the corrected projection data is reconstructed by penalized weighted least squares (PWLS) algorithm to obtain the ideal projection vector to be estimated.
  • PWLS penalized weighted least squares
  • the step 1 uses a sinogram recovery method based on a penalized weighted least squares algorithm to recover sinogram data using a combination of low milliamps and sparse view protocols.
  • the corrected projection data is reconstructed by the following PWLS algorithm to obtain P.
  • the PWLS method updates the image from the sinogram y
  • step 2 uses the total variation (PWLS-TV) method based on penalized weighted least squares to use the recovered sinogram data for reconstructing the image, and then the non-two-dimensional variation of the penalized weighted least squares total variation method
  • a secondary penalty function performs neighborhood patches instead of single-pixel regularization (PWLS-PR).
  • Patch-based regularization is performed on the non-quadratic penalty function of the reconstructed data through PWLS-TV.
  • ⁇ jk ( ⁇ n ) is a weighting factor related to the distance between pixel j and pixel k in the neighborhood N j
  • ⁇ n is the current objective function
  • step 3 uses a regularization algorithm to reconstruct the regularized image.
  • step 4 a sparse matrix is constructed, and the matrix is normalized to obtain a normalized kernel matrix; then guided kernel filtering is performed under the guidance of the reconstructed image to obtain a restored image.
  • smoothing can effectively remove noise, it also loses some details, resulting in the loss of details in the reconstructed image. Therefore, the guided kernel filtering method is used to restore the lost structural information, so that the denoised image retains the image details well and the structure is clearer.
  • the matrix is constructed using the k-nearest neighbor algorithm.
  • the k-nearest neighbor algorithm which is widely used in machine learning, is used to construct sparse matrices.
  • the kNN side finds k similar neighbors for each pixel, and normalizes the matrix to get the normalized kernel matrix K.
  • GK filtering guided kernel filtering
  • ⁇ TV is the PWLS- TV method image update from P
  • U( ⁇ ) is the patch-based roughness function
  • f j ( ⁇ ), f k ( ⁇ ) are feature vectors consisting of the intensity values of all pixels in the center of the patch at pixel j and pixel k, respectively
  • h is A positive weighting factor equal to the normalized inverse spatial distance between pixel j and pixel k
  • h ) is a non-quadratic penalty function.
  • the present application also provides an application of the image reconstruction method, where the image reconstruction method is applied to image noise reduction and artifact removal or image fusion.
  • a PWLS (penalized weighted least squares) based sinogram recovery method is used to recover sinogram data using a combination of low milliamps and sparse view protocols.
  • the recovered sinogram data is then used to reconstruct the image using a (penalized weighted least squares-based total variation) PWLS-TV method.
  • PWLS sinogram restoration as a preprocessing step is effective for image reconstruction with a combination of low mas and sparse views.
  • a patch-based regularization method for iterative image reconstruction that uses neighborhood patches instead of individual pixels when computing its non-quadratic penalty function. Compared with traditional pixel-based regularization methods, this regularization method is more robust in distinguishing between random fluctuations and sharp edges caused by noise.
  • Figure 2 shows the XCAT Phantom reconstructed by different algorithms; it can be seen from Figure 2 that the method of the present application can well denoise and remove artifacts and preserve the detailed structure of the image, which can effectively improve the peak signal-to-noise ratio and structural similarity of the image At the same time, the image detail information can be recovered to a certain extent.

Abstract

La présente invention se rapporte au domaine technique de la tomodensitométrie et concerne, en particulier, un procédé de reconstruction d'image et son application. Dans une image reconstruite de rétroprojection filtrée classique, le procédé peut entraîner un bruit excessif et des artéfacts de stries, ce qui conduit en outre à des erreurs de diagnostic et quantitatives. L'invention concerne un procédé de reconstruction d'image. Le procédé comprend les étapes suivantes : étape 1 : réalisation d'une reconstruction sur des données de projection corrigées, de façon à obtenir des données reconstruites ; étape 2 : réalisation d'une régularisation sur les données reconstruites, de manière à obtenir une image régularisée ; étape 3 : réalisation d'une reconstruction sur l'image régularisée, de façon à obtenir une image reconstruite ; et étape 4 : prise de l'image reconstruite à titre d'informations a priori, réalisation d'un filtre de noyau guidé sous le guidage de l'image reconstruite, de façon à obtenir une image récupérée. L'image récupérée présente de bonnes informations de structure.
PCT/CN2020/131792 2020-11-26 2020-11-26 Procédé de reconstruction d'image et application WO2022109928A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/131792 WO2022109928A1 (fr) 2020-11-26 2020-11-26 Procédé de reconstruction d'image et application

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/131792 WO2022109928A1 (fr) 2020-11-26 2020-11-26 Procédé de reconstruction d'image et application

Publications (1)

Publication Number Publication Date
WO2022109928A1 true WO2022109928A1 (fr) 2022-06-02

Family

ID=81755085

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/131792 WO2022109928A1 (fr) 2020-11-26 2020-11-26 Procédé de reconstruction d'image et application

Country Status (1)

Country Link
WO (1) WO2022109928A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102737392A (zh) * 2012-06-07 2012-10-17 南方医科大学 一种低剂量x线ct图像的非局部正则化先验重建方法
US20160151035A1 (en) * 2014-12-01 2016-06-02 Canon Kabushiki Kaisha Image processing apparatus, radiation imaging system, control method, and storage medium
CN106127825A (zh) * 2016-06-15 2016-11-16 赣南师范学院 一种基于广义惩罚加权最小二乘的x射线ct图像重建方法
CN106462985A (zh) * 2014-09-15 2017-02-22 皇家飞利浦有限公司 利用锐度驱动的正则化参数的迭代图像重建
US20180260980A1 (en) * 2017-03-13 2018-09-13 General Electric Company System and method for reconstructing an object via tomography
CN111968192A (zh) * 2020-06-29 2020-11-20 深圳先进技术研究院 一种ct图像的构建方法、ct设备以及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102737392A (zh) * 2012-06-07 2012-10-17 南方医科大学 一种低剂量x线ct图像的非局部正则化先验重建方法
CN106462985A (zh) * 2014-09-15 2017-02-22 皇家飞利浦有限公司 利用锐度驱动的正则化参数的迭代图像重建
US20160151035A1 (en) * 2014-12-01 2016-06-02 Canon Kabushiki Kaisha Image processing apparatus, radiation imaging system, control method, and storage medium
CN106127825A (zh) * 2016-06-15 2016-11-16 赣南师范学院 一种基于广义惩罚加权最小二乘的x射线ct图像重建方法
US20180260980A1 (en) * 2017-03-13 2018-09-13 General Electric Company System and method for reconstructing an object via tomography
CN111968192A (zh) * 2020-06-29 2020-11-20 深圳先进技术研究院 一种ct图像的构建方法、ct设备以及存储介质

Similar Documents

Publication Publication Date Title
JP6855223B2 (ja) 医用画像処理装置、ｘ線コンピュータ断層撮像装置及び医用画像処理方法
Xu et al. Limited-angle X-ray CT reconstruction using image gradient ℓ₀-norm with dictionary learning
WO2021159948A1 (fr) Procédé de reconstruction 3d de tep à faible dose reposant sur l'apprentissage profond
CN107481297B (zh) 一种基于卷积神经网络的ct图像重建方法
JP2024054204A (ja) ニューラルネットワークの学習方法、プログラム、医用画像処理方法及び医用装置
CN103810733B (zh) 一种稀疏角度x射线ct图像的统计迭代重建方法
CN103810734B (zh) 一种低剂量x射线ct投影数据恢复方法
WO2022110530A1 (fr) Procédé de reconstruction d'image tomographique, basé sur un échantillonnage de données spect et des caractéristiques de bruit
CN103679706B (zh) 一种基于图像各向异性边缘检测的ct稀疏角度重建方法
CN101980302A (zh) 投影数据恢复导引的非局部平均低剂量ct重建方法
Huang et al. Data extrapolation from learned prior images for truncation correction in computed tomography
WO2022000192A1 (fr) Procédé de construction d'image tdm, dispositif de tdm et support de stockage
CN103810735A (zh) 一种低剂量x射线ct图像统计迭代重建方法
Fang et al. Removing ring artefacts for photon-counting detectors using neural networks in different domains
Huang et al. Field of view extension in computed tomography using deep learning prior
CN103793890A (zh) 一种能谱ct图像的恢复处理方法
Feng et al. Dual residual convolutional neural network (DRCNN) for low-dose CT imaging
CN112070856B (zh) 基于非下采样轮廓波变换的有限角c型臂ct图像重建方法
WO2022011690A1 (fr) Procédé d'apprentissage auto-supervisé et application
Zhang et al. Euler’s elastica strategy for limited-angle computed tomography image reconstruction
JP7187131B2 (ja) 画像生成装置、ｘ線コンピュータ断層撮影装置及び画像生成方法
CN111968192A (zh) 一种ct图像的构建方法、ct设备以及存储介质
WO2022109928A1 (fr) Procédé de reconstruction d'image et application
WO2022257959A1 (fr) Agrégation de caractéristiques multi-modalité et multi-échelle pour synthétiser une image par tomographie d'émission monophotonique (temp) à partir d'un balayage temp rapide et d'une image de tomodensitométrie
CN112656438B (zh) 一种基于曲面全变差的低剂量ct投影域去噪及重建方法

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: 20962819

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: 20962819

Country of ref document: EP

Kind code of ref document: A1