CN109171792B - Imaging method and CT imaging system using same - Google Patents
Imaging method and CT imaging system using same Download PDFInfo
- Publication number
- CN109171792B CN109171792B CN201811227526.8A CN201811227526A CN109171792B CN 109171792 B CN109171792 B CN 109171792B CN 201811227526 A CN201811227526 A CN 201811227526A CN 109171792 B CN109171792 B CN 109171792B
- Authority
- CN
- China
- Prior art keywords
- projection data
- image
- dynamic
- scanned
- static
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computerised tomographs
- A61B6/032—Transmission computed tomography [CT]
- A61B6/035—Mechanical aspects of CT
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5258—Devices using data or image processing specially adapted for radiation diagnosis involving detection or reduction of artifacts or noise
- A61B6/5264—Devices using data or image processing specially adapted for radiation diagnosis involving detection or reduction of artifacts or noise due to motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/008—Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
Abstract
The invention provides an imaging method and a CT imaging system using the same, which respectively obtain dynamic projection data and static projection data of an object to be scanned; after the stable image reconstruction neural network is obtained by using the dynamic projection data training, the input of the static projection data is realized, and the CT image with higher image quality and time resolution can be obtained. The CT imaging system comprises a plurality of groups of ray sources and detectors which are annularly arranged on the peripheral side of the object to be scanned, and the object to be scanned can relatively rotate relative to the ray sources and the detectors which are arranged in groups. By the imaging method, the CT image with higher image quality and time resolution can be obtained.
Description
Technical Field
The present invention relates to the field of computed tomography imaging technology, and more particularly, to an imaging method and a CT imaging system using the same.
Background
In the conventional CT imaging method, projection data of each angle of a scanned object is acquired by adopting a method of rotating the scanned object or rotating a ray source and a detector, and then a CT image is calculated by a reconstruction algorithm. Conventional CT can be considered as slow CT and therefore the object cannot move any further during the rotation, which would lead to severe motion artifacts in the reconstructed image.
For imaging of moving objects, such as cardiac imaging, the use of slow CT imaging methods tends to produce more motion artifacts. In order to solve the problem of CT imaging of a moving object, the scanning speed is generally increased, and the current fastest CT scanning speed can reach 3Hz, namely three scanning circles are scanned in one second. Although the CT scanning speed is improved a lot, the motion artifact can not be eliminated fundamentally, and the quality requirement of CT imaging of a moving object can not be met.
In view of the above, there is a need to design an improved imaging method and a CT imaging system using the same to solve the above problems.
Disclosure of Invention
The invention aims to provide an imaging method which can be applied to moving objects and objects which can generate deformation and improve the imaging quality and a CT imaging system using the imaging method.
In order to achieve the above object, the present invention provides an imaging method, comprising the steps of:
s1, carrying out intensive projection on the object to be scanned to obtain a series of dynamic projection data, and carrying out image reconstruction by using the dynamic projection data to obtain a dynamic CT image;
s2, sampling a plurality of dynamic projection data in the series of dynamic projection data to carry out image reconstruction so as to obtain a dynamic initial image;
s3, establishing an image reconstruction neural network, taking the plurality of dynamic projection data as input projection data, taking the dynamic initial image as an input image, and taking the dynamic CT image as an output image to train the image reconstruction neural network, so as to obtain a trained image reconstruction neural network;
s4, carrying out static projection on the object to be scanned to obtain a series of static projection data, and carrying out image reconstruction by using the static projection data to obtain a static initial image;
and S5, inputting the static projection data and the static initial image into the trained image reconstruction neural network, and outputting a CT image.
As a further improvement of the present invention, the structure of the object to be scanned in the step S1 is the same as or similar to that in the step S4.
As a further improvement of the present invention, in particular, in step S2, 20 to 30 projection data are sampled for image reconstruction to obtain the dynamic initial image.
As a further improvement of the present invention, the static projection data includes 20-30 angle projection data of the object to be scanned.
As a further improvement of the invention, the image reconstruction neural network comprises a data input layer, a plurality of convolution calculation layers, a full connection layer, and an excitation layer and a pooling layer which are sandwiched between the continuous convolution calculation layers; the convolution calculation layer is used for extracting the characteristics of the data or the image transmitted by the data input layer through convolution calculation.
In order to achieve the above object, the present invention further provides a CT imaging system using the imaging method according to any one of the above technical solutions, wherein the CT imaging system includes an object to be scanned, a plurality of sets of radiation sources and detectors arranged around the object to be scanned, and the object to be scanned and the plurality of sets of radiation sources and detectors can rotate relatively.
As a further improvement of the present invention, the static projection data is obtained by performing exposure and data acquisition simultaneously by the plurality of groups of radiation sources and detectors when the plurality of groups of radiation sources and detectors and the object to be scanned are in a relatively static state.
As a further improvement of the present invention, the dynamic projection data is obtained when the object to be scanned and the plurality of sets of ray sources and detectors rotate relatively for one circle.
As a further improvement of the present invention, the object to be scanned is disposed on an object placing table, the object placing table is rotatable, the plurality of groups of radiation sources and the detector are stationary, and the object placing table is rotated to drive the object to be scanned to rotate for a circle relative to the plurality of groups of radiation sources and the detector to obtain the dynamic projection data.
As a further improvement of the present invention, the plurality of groups of radiation sources and detectors are disposed on a guide rail, the object to be scanned is stationary, and the plurality of groups of radiation sources and detectors rotate around the object to be scanned along the guide rail for one revolution to obtain the dynamic projection data.
As a further improvement of the present invention, the series of static projection data obtained in step S4 corresponds to the number of groups of the radiation sources and the detectors.
The invention has the beneficial effects that: the imaging method of the invention obtains dynamic projection data, dynamic CT images and dynamic initial images through dynamic CT imaging, so as to train the neural network and obtain a stable image reconstruction neural network; a neural network is reconstructed based on the image, static projection data and a static initial image are input, and a CT image with high image quality and high time resolution can be obtained.
Drawings
FIG. 1 is a schematic flow chart of an imaging method of the present invention.
FIG. 2 is a schematic structural diagram of a CT imaging system according to an embodiment of the present invention.
Fig. 3 is a schematic structural view of fig. 2 from another angle.
FIG. 4 is a schematic structural diagram of another embodiment of a CT imaging system according to the present invention.
Fig. 5 is a schematic diagram of a training process of the image reconstruction neural network according to the present invention.
Fig. 6 is a schematic diagram of the using process of the image reconstruction neural network of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures and/or processing steps closely related to the aspects of the present invention are shown in the drawings, and other details not closely related to the present invention are omitted.
In addition, it is also to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1 to 6, an imaging method includes the following steps:
s1, carrying out intensive projection on the object to be scanned to obtain a series of dynamic projection data, and carrying out image reconstruction by using the dynamic projection data to obtain a dynamic CT image;
s2, sampling a plurality of dynamic projection data in a series of dynamic projection data to carry out image reconstruction to obtain a dynamic initial image;
s3, establishing an image reconstruction neural network, taking a plurality of dynamic projection data as input projection data, taking a dynamic initial image as an input image, taking a dynamic CT image as an output image, and training the image reconstruction neural network to obtain a trained image reconstruction neural network;
s4, carrying out static projection on the object to be scanned to obtain a series of static projection data, and carrying out image reconstruction by using the static projection data to obtain a static initial image;
and S5, inputting the static projection data and the static initial image into the trained image reconstruction neural network, and outputting a CT image.
The structure of the object to be scanned used in step S1 and step S4 is the same or similar to each other. The structure of the scanned object used in the training process of the image reconstruction neural network is the same as or similar to that used in the using process, so that the training effect of the image reconstruction neural network and the quality of the finally reconstructed image can be improved.
Referring to fig. 5 to 6 in combination with fig. 1, in step S3, the image reconstruction neural network includes a data input layer, a plurality of convolution calculation layers, a full connection layer, and an excitation layer and a pooling layer sandwiched between successive convolution calculation layers. The data input layer is mainly used for carrying out mean value removal, normalization, PCA (principal Component analysis) and other processing on input data of the input image reconstruction neural network, and then transmitting the data to the convolution calculation layer. The convolution calculation layer is used for extracting the characteristics of the data or the image transmitted by the data input layer through convolution calculation and outputting the result. The excitation layer is mainly used for carrying out nonlinear mapping on the output result of the convolution calculation layer. The pooling layer is used to compress the data and the amount of parameters in the data to reduce overfitting. The full-connection layer is arranged at the tail part of the image reconstruction neural network, each neuron in the full-connection layer is in full connection with all neurons in the previous layer, and all neurons between any two layers in the image reconstruction neural network are in weighted connection so as to integrate the extracted features.
Referring to fig. 2 to 4, the present invention further provides a CT imaging system 100 using the imaging method, which includes an object placing table 1 for placing an object to be scanned, a plurality of groups of annular radiation sources 2 and detectors 3 annularly disposed around the object placing table 1, wherein the detectors 3 are disposed inside the radiation sources 2, and gaps 31 for the radiation of the radiation sources 2 to pass through are formed between the adjacent detectors 3.
Preferably, the CT imaging system 100 includes 20-30 sets of detectors 3 and radiation sources 2. Each group of the ray sources 2 and the detectors 3 are respectively arranged on two opposite sides of the object placing table 1, the relative positions of the ray sources 2 and the detectors 3 are fixed, the connecting lines of all the ray sources 2 and the detectors 3 are intersected at a position point, and the object placing table 1 is arranged at the position point, so that rays emitted by the ray sources 2 pass through an object to be scanned and then reach the detectors 3.
The object placing table 1 and the plurality of groups of the ray sources 2 and the detectors 3 can rotate relatively. With such an arrangement, in step S1, the radiation source 2 and the detector 3 rotate for a circle relative to the object to be scanned on the object placing table 1, perform intensive projection to acquire a series of dynamic projection data including projection data of hundreds of angles of the object to be scanned, and then perform image reconstruction using the dynamic projection data to obtain a dynamic CT image. It should be noted that the dynamic CT image has a high image quality and a poor time resolution.
In one embodiment, a rotating table 11 is provided below the placing table 1. In step S1, when the plurality of sets of radiation sources 2 and the detector 3 are stationary, the rotating platform 11 rotates to drive the object placing table 1 and the object to be scanned placed on the object placing table 1 to rotate for one circle to obtain dynamic projection data.
In another embodiment, a guide rail 21 is disposed around the object placing table 1 below the detector 3 and the radiation source 2, and the detector 3 and the radiation source 2 arranged in a group can rotate around the object placing table 1 along the guide rail 21. In step S1, the object placing table 1 is stationary, and the group of detectors 3 and the radiation source 2 rotate around the object to be scanned along the guide rail 21 to obtain dynamic projection data. Of course, the rotary table 11 may be provided below the placement table 1 and the guide rail 21 may be provided below the detector 3 and the radiation source 2.
It should be noted that, other embodiments may also be adopted to realize the relative rotation between the object placing table 1 and the plurality of sets of the radiation sources 2 and the detectors 3, and the invention is not limited herein.
Preferably, in step S2, 20-30 dynamic projection data are sampled for image reconstruction to obtain a dynamic initial image; in step S3, the 20-30 dynamic projection data are used as input projection data of the training image reconstruction neural network, and the dynamic initial image obtained in the previous step is used as an input image of the training image reconstruction neural network for training the image reconstruction neural network. In step S4, the static projection data is a series of static projection data obtained by simultaneously performing exposure and data acquisition on the sets of the source 2 and the detector 3 while the sets of the source 2 and the detector 3 are in a relatively static state with respect to the object to be scanned, and includes 20-30 angle projection data of the object to be scanned. The series of static projection data obtained in step S4 corresponds to the number of sets of the radiation source 2 and the detector 3. The data volume of the static projection data is much smaller than the data volume of the dynamic projection data. Therefore, the ray source 2, the detector 3 and the object placing table 1 are kept relatively still, and motion artifacts in the traditional scanning mode are avoided. In step S5, the CT image obtained by reconstructing the neural network based on the static projection data, the static initial image, and the trained image has a higher image quality and a higher temporal resolution.
Note that, in step S1 and step S4, the same CT imaging system 100 is used. Therefore, the geometric parameters of the CT imaging system 100 are the same when dynamic projection data and static projection data are acquired in the training process and the using process of the image reconstruction neural network, and the applicability of the trained image reconstruction neural network is ensured.
In summary, the CT imaging system 100 of the present invention includes a plurality of sets of the radiation source 2 and the detector 3 disposed around the object placing table 1, and the object placing table 1 can rotate relatively to the radiation source 2 and the detector 3 disposed in pairs; training a neural network by using the CT imaging system 100, establishing a relation between input projection data and a dynamic initial image and a dynamic CT image, and obtaining a trained image reconstruction neural network; the imaging method of the invention based on the image reconstruction neural network and the CT imaging system 100 can rapidly image moving objects and objects which can generate deformation by using a small amount of static projection data and static initial images, and obtain CT images with higher image quality and time resolution, thereby accelerating the imaging efficiency of the CT imaging system 100 and overcoming the defect that more motion artifacts exist in the imaging of the moving objects and the objects which can generate deformation. The imaging method and the CT imaging system 100 can be applied to CT imaging of moving objects and objects that may generate deformation, such as: cardiac imaging. That is, the imaging method and the CT imaging system 100 of the present invention realize fast CT imaging with high image quality and time resolution on moving objects and objects that may generate deformation.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (11)
1. An imaging method comprising the steps of:
s1, carrying out intensive projection on the object to be scanned to obtain a series of dynamic projection data, and carrying out image reconstruction by using the dynamic projection data to obtain a dynamic CT image;
s2, sampling a plurality of dynamic projection data in the series of dynamic projection data to carry out image reconstruction so as to obtain a dynamic initial image;
s3, establishing an image reconstruction neural network, taking the plurality of dynamic projection data as input projection data, taking the dynamic initial image as an input image, and taking the dynamic CT image as an output image to train the image reconstruction neural network, so as to obtain a trained image reconstruction neural network;
s4, carrying out static projection on the object to be scanned to obtain a series of static projection data, and carrying out image reconstruction by using the static projection data to obtain a static initial image;
and S5, inputting the static projection data and the static initial image into the trained image reconstruction neural network, and outputting a CT image.
2. The imaging method according to claim 1, characterized in that: the structure of the object to be scanned in the step S1 is the same as or similar to that in the step S4.
3. The imaging method according to claim 1, characterized in that: specifically, in step S2, 20 to 30 projection data are sampled for image reconstruction to obtain the dynamic initial image.
4. The imaging method according to claim 1, characterized in that: the static projection data includes 20-30 angular projection data of the object to be scanned.
5. The imaging method according to claim 1, characterized in that: the image reconstruction neural network comprises a data input layer, a plurality of convolution calculation layers, a full connection layer, and an excitation layer and a pooling layer which are sandwiched between the continuous convolution calculation layers; the convolution calculation layer is used for extracting the characteristics of the data or the image transmitted by the data input layer through convolution calculation.
6. A CT imaging system using the imaging method of any of claims 1-5, characterized by: CT imaging system including waiting scan thing, ring locate wait to scan thing week side a plurality of groups ray source and detector, wait to scan the thing with but relative rotation between a plurality of groups ray source and the detector.
7. The CT imaging system of claim 6, wherein: and the static projection data are obtained by simultaneously carrying out exposure and data acquisition on the plurality of groups of ray sources and detectors in a relatively static state with the object to be scanned.
8. The CT imaging system of claim 6, wherein: the dynamic projection data is obtained when the object to be scanned and the plurality of groups of ray sources and detectors rotate relatively for one circle.
9. The CT imaging system of claim 8, wherein: treat that the scanner sets up on putting the thing platform, it is rotatable to put the thing platform, a plurality of groups ray sources and detector motionless, it is rotatory in order to drive to treat the scanner for a plurality of groups ray sources and detector rotate a week in order to obtain dynamic projection data to put the thing platform.
10. The CT imaging system of claim 8, wherein: the plurality of groups of the ray sources and the detectors are arranged on the guide rail, the object to be scanned is not moved, and the plurality of groups of the ray sources and the detectors rotate around the object to be scanned for a circle along the guide rail so as to obtain the dynamic projection data.
11. The CT imaging system of claim 6, wherein: the series of static projection data obtained in step S4 corresponds to the number of sets of the source and the detector.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821597030 | 2018-09-29 | ||
| CN2018215970305 | 2018-09-29 | ||
| CN2018111451309 | 2018-09-29 | ||
| CN201811145130 | 2018-09-29 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109171792A CN109171792A (en) | 2019-01-11 |
| CN109171792B true CN109171792B (en) | 2022-06-07 |
Family
ID=64946021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811227526.8A Active CN109171792B (en) | 2018-09-29 | 2018-10-22 | Imaging method and CT imaging system using same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109171792B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111657979A (en) * | 2019-03-08 | 2020-09-15 | 江苏一影医疗设备有限公司 | CT imaging system and imaging method thereof |
| CN110051378B (en) * | 2019-04-30 | 2023-07-25 | 上海联影医疗科技股份有限公司 | CT imaging method, CT data acquisition method, system, equipment and storage medium |
| CN110428370B (en) * | 2019-07-01 | 2021-11-23 | 北京理工大学 | Method for improving conical beam SPECT imaging resolution by utilizing eccentric rotation |
| CN113812971B (en) * | 2021-08-27 | 2023-10-13 | 浙江大学 | Multi-degree-of-freedom four-dimensional dual-energy cone beam CT imaging system and method |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102379716A (en) * | 2011-08-24 | 2012-03-21 | 苏州生物医学工程技术研究所 | Static CT (computed tomography) scanner system and scanning method thereof |
| CN105447866A (en) * | 2015-11-22 | 2016-03-30 | 南方医科大学 | X-ray chest radiograph bone marrow suppression processing method based on convolution neural network |
| CN106204449B (en) * | 2016-07-06 | 2019-09-10 | 安徽工业大学 | A kind of single image super resolution ratio reconstruction method based on symmetrical depth network |
| US20180018757A1 (en) * | 2016-07-13 | 2018-01-18 | Kenji Suzuki | Transforming projection data in tomography by means of machine learning |
| CN106651766A (en) * | 2016-12-30 | 2017-05-10 | 深圳市唯特视科技有限公司 | Image style migration method based on deep convolutional neural network |
| JP7217847B2 (en) * | 2017-02-27 | 2023-02-06 | 北京納米維景科技有限公司 | Static real-time CT imaging system suitable for wide-field needs and its imaging method |
| CN106952228B (en) * | 2017-03-10 | 2020-05-22 | 北京工业大学 | Super-resolution reconstruction method of single image based on image non-local self-similarity |
| CN107330949B (en) * | 2017-06-28 | 2020-11-03 | 上海联影医疗科技有限公司 | Artifact correction method and system |
| CN107374658B (en) * | 2017-07-01 | 2023-10-03 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Shooting system and shooting method for positive side dual-energy image |
| CN107507148B (en) * | 2017-08-30 | 2018-12-18 | 南方医科大学 | Method based on the convolutional neural networks removal down-sampled artifact of magnetic resonance image |
| CN107481297B (en) * | 2017-08-31 | 2021-06-15 | 南方医科大学 | CT image reconstruction method based on convolutional neural network |
| CN107945132B (en) * | 2017-11-29 | 2022-10-04 | 深圳安科高技术股份有限公司 | Neural network-based CT image artifact correction method and device |
| CN108416821B (en) * | 2018-03-08 | 2019-08-02 | 山东财经大学 | A kind of CT Image Super-resolution Reconstruction method of deep neural network |
-
2018
- 2018-10-22 CN CN201811227526.8A patent/CN109171792B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109171792A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109171792B (en) | Imaging method and CT imaging system using same | |
| CN109863512B (en) | System and method for automatic transformation by manifold approximation | |
| US8731269B2 (en) | Method and system for substantially reducing artifacts in circular cone beam computer tomography (CT) | |
| CN1217625C (en) | Weight used for partially scanning for quantum segmental multi-sectional CT imaging | |
| EP0492896A2 (en) | Reconstructing a 3-D image | |
| WO2007098284B1 (en) | Method and apparatus for cone beam ct dynamic imaging | |
| AU2006315013A1 (en) | System and method for reconstructing an image by rectilinear trajectory scanning | |
| JPH0728862B2 (en) | CT device | |
| KR20060135560A (en) | X-ray ct apparatus | |
| JP2007089674A (en) | Shape of appearance measuring apparatus and x-ray ct apparatus | |
| JPH08263638A (en) | System and method for creation of tomographic image of object | |
| CN110276813B (en) | CT image reconstruction method, device, storage medium and computer equipment | |
| CN108876730A (en) | The method, device and equipment and storage medium of correction of movement artifact | |
| CN110916708A (en) | CT scanning projection data artifact correction method and CT image reconstruction method | |
| CN112102428A (en) | CT cone beam scanning image reconstruction method, scanning system and storage medium | |
| EP4071720A1 (en) | System and method for utilizing a deep learning network to correct for a bad pixel in a computed tomography detector | |
| JP7206073B2 (en) | MEDICAL IMAGE PROCESSING APPARATUS, MEDICAL IMAGE GENERATING APPARATUS, MEDICAL IMAGE PROCESSING METHOD, AND PROGRAM | |
| CN109816747A (en) | A kind of metal artifacts reduction method of Cranial Computed Tomography image | |
| CN102062740B (en) | Cone-beam CT (Computed Tomography) scanning imaging method and system | |
| KR20060043586A (en) | Ct image producing method and x-ray ct apparatus | |
| CN114359126A (en) | Geometric correction method and device for three-dimensional image, electronic device and storage medium | |
| CN106097411B (en) | CT machine image rebuilding method and high resolution ct scanning machine | |
| CN111657979A (en) | CT imaging system and imaging method thereof | |
| JPH05168620A (en) | Ct scanner | |
| JP2023078074A (en) | Sparse Projection Reconstruction Method Based on Graph Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |