CN114255296B - CT image reconstruction method and device based on single X-ray image - Google Patents
CT image reconstruction method and device based on single X-ray image Download PDFInfo
- Publication number
- CN114255296B CN114255296B CN202111587397.5A CN202111587397A CN114255296B CN 114255296 B CN114255296 B CN 114255296B CN 202111587397 A CN202111587397 A CN 202111587397A CN 114255296 B CN114255296 B CN 114255296B
- Authority
- CN
- China
- Prior art keywords
- image
- reconstructed
- reconstruction
- ray
- digital
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000000241 respiratory effect Effects 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 13
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 2
- 210000003484 anatomy Anatomy 0.000 abstract description 5
- 238000013507 mapping Methods 0.000 abstract description 2
- 238000002591 computed tomography Methods 0.000 description 100
- 230000006870 function Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 210000000038 chest Anatomy 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a CT image reconstruction method and device based on a single X-ray image, wherein the method comprises the following steps: training data preprocessing, namely acquiring 4D CT images of N patients, constructing a respiratory model for each patient, and generating 3D CT images under M respiratory phases for each respiratory model; generating digital reconstructed images under K angles for the 3D CT image; model training, namely taking a digital reconstructed image as input, taking a 3D CT image as a learning target, and sending the digital reconstructed image into a deep learning neural network for training to obtain a CT image reconstructed network; and (3) reconstructing the CT image, namely sending the single X-ray image into a CT image reconstruction network, and acquiring a 3D CT image reconstructed according to the single X-ray image. According to the technical scheme provided by the invention, according to the characteristic that the human anatomy structure is strictly limited, a deep learning-based method is introduced to learn the mapping from a single X-ray image to a 3D CT image, so that the technical problem that the 3D CT image cannot be acquired in real time in an operation is solved.
Description
Technical Field
The invention relates to the technical field of digital image processing, in particular to a CT image reconstruction method and device based on a single X-ray image.
Background
During the operation of a patient, based on the 2D image of X-ray imaging, the change of the anatomical structure inside the human body can be observed in real time and noninvasively. In a single view 2D image, the 3D anatomy of the patient is projected onto the 2D plane, resulting in overlapping human tissue structures with each other, reducing the visibility of the in vivo structures. The 3D CT (Computed Tomography ) image can obtain a patient image with high spatial resolution, and generate a three-dimensional image of the internal anatomy of the human body, which can solve the problem of overlapping human body tissues in the X-ray projection.
A 3D CT image is reconstructed clinically using a set of X-ray projection data acquired with X-rays rotated completely around the patient by a reconstruction algorithm. In order to obtain a reconstructed image free of artifacts, such algorithms require more sampling angles, bringing more radiation dose to the patient. Furthermore, during surgery, it is very difficult to perform rotational X-ray projections around the patient.
In view of the foregoing, there is a need for a CT image reconstruction method based on a single X-ray image to alleviate the problems of the prior art.
Disclosure of Invention
The invention provides a CT image reconstruction method based on a single X-ray image, which introduces a deep learning neural network and can be used for rapidly reconstructing a 3D CT image through the single X-ray image so as to alleviate the defects of the prior art.
In a first aspect, the present invention provides a CT image reconstruction method based on a single X-ray image, including: training data preprocessing, namely acquiring 4D CT images of N patients, constructing a respiratory model for each patient, and generating 3D CT images under M respiratory phases for each respiratory model; generating digital reconstructed images under K angles for the 3D CT image; model training, namely taking a digital reconstructed image as input, taking a 3D CT image as a learning target, and sending the digital reconstructed image into a deep learning neural network for training to obtain a CT image reconstructed network; and (3) reconstructing the CT image, namely sending the single X-ray image into a CT image reconstruction network, and acquiring a 3D CT image reconstructed according to the single X-ray image.
Optionally, the breathing model is built from a patient breathing cycle, which is fitted from displacements of points on the patient's chest.
Optionally, the step of generating a digitally reconstructed image under K angles for the 3D CT image comprises: setting the distance between the 3D CT image and the virtual point light source and the radial cone angle of the virtual point light source; in the radial cone angle, T rays are led out from the virtual point light source, the projection of the T rays on the virtual panel after passing through the 3D CT image is a digital reconstruction image, the rays simulate X rays, and when passing through the 3D CT image, the simulated X rays attenuate when passing through human tissues represented by the 3D CT image; and changing the positions of the K virtual point light sources and the virtual panel to generate digital reconstructed images under K angles.
Optionally, before generating the digitally reconstructed image under K angles for the 3D CT image, comprising: the 3D CT image is cropped to a cuboid region.
Optionally, before generating the digitally reconstructed image under K angles for the 3D CT image, further comprises: resampling the 3D CT image to the same resolution.
Optionally, the CT image reconstruction network includes: a pooling component and a transpose convolution component.
In a second aspect, the present invention provides a CT image reconstruction apparatus based on a single X-ray image, including: the preprocessing module is used for acquiring 4D CT images of N patients, constructing a breathing model for each patient, and generating 3D CT images under M breathing phases for each breathing model; generating digital reconstructed images under K angles for the 3D CT image; the model training module is used for taking the digital reconstructed image as input, taking the 3D CT image as a learning target, and sending the digital reconstructed image into the deep learning neural network for training to obtain a CT image reconstruction network; the CT image reconstruction module is used for sending the single X-ray image into a CT image reconstruction network to acquire a 3D CT image reconstructed according to the single X-ray image.
In a third aspect, the present invention provides a computing device comprising: a processor, and a memory storing a program, the processor implementing the method of the first aspect when executing the program.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a program which when executed implements the method of the first aspect.
The beneficial effects of the invention are as follows:
the technical scheme provided by the invention can comprise the following beneficial effects: according to the characteristic that the human anatomy structure is strictly limited, a deep learning-based method is introduced to learn the mapping from a single X-ray image to a 3D CT image, so that the technical problem that the 3D CT image cannot be acquired in real time in an operation is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the following description are one embodiment of the present invention, and other drawings may be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a CT image reconstruction method based on a single X-ray image according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a CT image reconstruction device based on a single X-ray image according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computing device according to a third embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, wherein the described embodiments are some embodiments of the present invention, but not all embodiments.
Embodiment one:
Fig. 1 is a flowchart of a CT image reconstruction method based on a single X-ray image according to a first embodiment of the present invention, as shown in fig. 1, the method includes the following three steps.
Step S101: data for training is preprocessed. Specifically, training data preprocessing is performed to obtain 4D CT images of N patients, a respiratory model is constructed for each patient, 3D CT images under M respiratory phases are generated for each respiratory model, and digital reconstructed images under K angles are generated for the 3D CT images.
It should be noted that, the 4D CT image refers to a concept of adding time to the 3D CT image, and may dynamically show a state of a patient body structure changing with time. Illustratively, the relief of the chest cavity changes as the patient breathes, and portions of the patient's organs in the 3D CT image change position or morphology as the patient breathes. The patient's breath exhibits a periodic variation and the breathing pattern describes alternating patient inspiration and expiration, with M breathing phases selectable at different points in time within a breathing cycle. Illustratively, the digital reconstructed image under K angles may be a digital reconstructed image projected at 4 angles of 0 degrees, 30 degrees, 60 degrees, 90 degrees from the 3D CT image.
In some embodiments, the breathing model is built from a patient breathing cycle that is fitted from displacements of points on the patient's chest. Illustratively, the displacement of points on the patient's chest cavity varies in a sine or cosine curve over time during patient breathing. And extracting the displacement of each point on the chest of the patient from the 4D CT image, so as to fit a sine or cosine curve and obtain the respiratory cycle of the patient.
In some embodiments, the step of generating a digitally reconstructed image at K angles for a 3D CT image comprises: setting the distance between the 3D CT image and the virtual point light source and the radial cone angle of the virtual point light source; in the radial cone angle, T rays are led out from the virtual point light source, the projection of the T rays on the virtual panel after passing through the 3D CT image is a digital reconstruction image, the rays simulate X rays, and when passing through the 3D CT image, the simulated X rays attenuate when passing through human tissues represented by the 3D CT image; and changing the positions of the K virtual point light sources and the virtual panel to generate digital reconstructed images under K angles.
It should be noted that, according to the human tissue represented by the 3D CT image, the T rays attenuate during the process of passing through the 3D CT image. Illustratively, the attenuation is calculated from T rays from the pixel CT values in the 3D CT image traversed by the rays.
In some embodiments, before generating a digitally reconstructed image at K angles for a 3D CT image, comprising: the 3D CT image is cropped to a cuboid region. Clipping the 3D CT image in a cuboid region reduces the learning target of the deep learning neural network and reduces the learning difficulty. Illustratively, a cuboid is set according to a human tissue envelope of a region of interest in the 3D CT image, thereby focusing the learning object on the region of interest.
In some embodiments, before generating the digitally reconstructed image at K angles for the 3D CT image, further comprising: resampling the 3D CT image to the same resolution. Illustratively, the 3D CT image is resampled to a 1x 1mm 3 resolution, thereby reducing the learning difficulty caused by the difference of resolution ratios of the data samples.
Step S102: training the CT image reconstruction network. Specifically, model training takes a digital reconstructed image as input, takes a 3D CT image as a learning target, and sends the digital reconstructed image into a deep learning neural network for training to obtain a CT image reconstruction network.
In some embodiments, the CT image reconstruction network includes: a pooling component and a transpose convolution component. It should be noted that the pooling component may be used for downsampling, and the transpose convolution component, i.e. the deconvolution component, may be used for upsampling.
Illustratively, 80% of the data generated in the step S101 is input as a training set into a deep learning neural network, data features are extracted through operations such as convolution pooling, a reconstructed 3D CT image is generated after transposed convolution, and a loss function of a prediction result and an actual 3D CT image is calculated; back propagation, updating network parameters. And using the rest data generated in the step S101 as a verification set, and verifying the classification accuracy under the current network. The loss function is reduced and converged through repeated iteration.
Step S103: CT image reconstruction is performed using a single X-ray image. Specifically, the CT image reconstruction is carried out, a single X-ray image is sent into a CT image reconstruction network, and a 3D CT image reconstructed according to the single X-ray image is obtained.
Embodiment two:
The embodiment of the invention provides a CT image reconstruction device based on a single X-ray image, which is mainly used for executing the CT image reconstruction method based on the single X-ray image provided by the embodiment of the invention, and the CT image reconstruction device provided by the embodiment of the invention is specifically introduced below.
Fig. 2 is a schematic structural diagram of a CT image reconstruction device according to a second embodiment of the present invention. As shown in fig. 2, the CT image reconstruction device 200 includes the following modules:
A preprocessing module 201, configured to acquire 4D CT images of N patients, construct a respiratory model for each patient, and generate 3D CT images under M respiratory phases for each respiratory model; digitally reconstructed images at K angles are generated for the 3D CT images.
The model training module 202 is configured to send the digital reconstructed image as input, the 3D CT image as a learning target, and the model training module to the deep learning neural network for training to obtain a CT image reconstruction network.
The CT image reconstruction module 203 is configured to send the single X-ray image to a CT image reconstruction network, and obtain a 3D CT image reconstructed from the single X-ray image.
Embodiment III:
The embodiment of the invention also provides a computing device. As shown in fig. 3, the computing device 300 of this embodiment includes: a processor 301, a memory 302, and a program stored in the memory 302 and executable on the processor 301. The processor 301 executes a program to implement the steps of the above embodiments of the CT image reconstruction method based on a single X-ray image, for example, steps S101 to S103 shown in fig. 1. Or the processor 301 performs the functions of the modules in the above embodiments of the apparatus, for example, the modules in fig. 3, to implement a CT image reconstruction apparatus.
Illustratively, the program may be split into one or more modules that are stored in the memory 302 and executed by the processor 301 to perform the present invention. The one or more modules may be a series of program instruction segments capable of performing specific functions to describe the execution of the program in a computing device. For example, the program may be partitioned into a model training module and a target recognition module.
The specific functions of each module are as follows: a preprocessing module 201, configured to acquire 4D CT images of N patients, construct a respiratory model for each patient, and generate 3D CT images under M respiratory phases for each respiratory model; digitally reconstructed images at K angles are generated for the 3D CT images. The model training module 202 is configured to send the digital reconstructed image as input, the 3D CT image as a learning target, and the model training module to the deep learning neural network for training to obtain a CT image reconstruction network. The CT image reconstruction module 203 is configured to send the single X-ray image to a CT image reconstruction network, and obtain a 3D CT image reconstructed from the single X-ray image. .
The computing device can be a single chip system, a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The computing device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example and does not constitute a limitation of the computing device, and may include more or fewer components than illustrated, or may combine certain components, or different components, e.g., the computing device may also include an input-output device, etc.
The Processor may be a micro control unit (Microcontroller Unit, MCU), a central processing unit (Central Processing Unit, CPU), or other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is a control center for the computing device, connecting various parts of the overall computing device using various interfaces and lines.
The memory may be used to store the program and/or module, and the processor may implement various functions of the single X-ray image based CT image reconstruction method and apparatus by running or executing the program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Embodiment four:
The modules integrated in the CT image reconstruction device based on a single X-ray image may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A CT image reconstruction method based on a single X-ray image, comprising:
the pre-processing of the training data is performed,
Acquiring 4D CT images of N patients, constructing a respiratory model for each patient, and generating 3D CT images under M respiratory phases for each respiratory model;
Resampling the 3D CT image to the same resolution;
cutting the 3D CT image into a cuboid region;
setting the distance between the 3D CT image and the virtual point light source and the radial cone angle of the virtual point light source;
In the radiation cone angle, T rays are led out from the virtual point light source, the projection of the T rays on the virtual panel after passing through the 3D CT image is a digital reconstruction image, the rays simulate X rays, and when passing through the 3D CT image, the X rays simulate attenuation when passing through human tissues represented by the 3D CT image;
changing the positions of the virtual point light sources and the virtual panel K times to generate digital reconstruction images under K angles;
the model is trained in such a way that,
Taking the digital reconstructed image as input, taking the 3D CT image as a learning target, and sending the digital reconstructed image into a deep learning neural network for training to obtain a CT image reconstruction network;
The CT image is reconstructed and the image is reconstructed,
And sending the single X-ray image into a CT image reconstruction network to obtain a 3D CT image reconstructed according to the single X-ray image.
2. The method of claim 1, wherein the breathing model is constructed from a patient breathing cycle that is fitted from displacements of points on the patient's chest.
3. The method of claim 1, wherein the CT image reconstruction network comprises: a pooling component and a transpose convolution component.
4. A single X-ray image-based CT image reconstruction apparatus for performing the single X-ray image-based CT image reconstruction method of claim 1, comprising:
A preprocessing module for
Acquiring 4D CT images of N patients, constructing a respiratory model for each patient, and generating 3D CT images under M respiratory phases for each respiratory model;
Generating digital reconstruction images under K angles for the 3D CT image;
Model training module for
Taking the digital reconstructed image as input, taking the 3D CT image as a learning target, and sending the digital reconstructed image into a deep learning neural network for training to obtain a CT image reconstruction network;
CT image reconstruction module for
And sending the single X-ray image into a CT image reconstruction network to obtain a 3D CT image reconstructed according to the single X-ray image.
5. A computing device, comprising: a processor and a memory storing a program, wherein the processor implements the method of any one of claims 1 to 3 when executing the program.
6. A computer-readable storage medium, on which a program is stored, characterized in that the program, when executed, implements the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111587397.5A CN114255296B (en) | 2021-12-23 | 2021-12-23 | CT image reconstruction method and device based on single X-ray image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111587397.5A CN114255296B (en) | 2021-12-23 | 2021-12-23 | CT image reconstruction method and device based on single X-ray image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114255296A CN114255296A (en) | 2022-03-29 |
| CN114255296B true CN114255296B (en) | 2024-04-26 |
Family
ID=80797109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111587397.5A Active CN114255296B (en) | 2021-12-23 | 2021-12-23 | CT image reconstruction method and device based on single X-ray image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255296B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146842A (en) * | 2018-07-09 | 2019-01-04 | 南方医科大学 | A kind of breath Motion Estimation method in chest digit synthesis X-ray Tomography |
| CN111260748A (en) * | 2020-02-14 | 2020-06-09 | 南京安科医疗科技有限公司 | Digital synthesis X-ray tomography method based on neural network |
| WO2020237873A1 (en) * | 2019-05-27 | 2020-12-03 | 清华大学 | Neural network-based spiral ct image reconstruction method and device, and storage medium |
| CN113052935A (en) * | 2021-03-23 | 2021-06-29 | 大连理工大学 | Single-view CT reconstruction method for progressive learning |
| CN113052936A (en) * | 2021-03-30 | 2021-06-29 | 大连理工大学 | Single-view CT reconstruction method integrating FDK and deep learning |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10709394B2 (en) * | 2018-01-15 | 2020-07-14 | Siemens Healthcare Gmbh | Method and system for 3D reconstruction of X-ray CT volume and segmentation mask from a few X-ray radiographs |
| US11090017B2 (en) * | 2018-09-13 | 2021-08-17 | Hologic, Inc. | Generating synthesized projection images for 3D breast tomosynthesis or multi-mode x-ray breast imaging |
| US20200294288A1 (en) * | 2019-03-13 | 2020-09-17 | The Uab Research Foundation | Systems and methods of computed tomography image reconstruction |
| US11026642B2 (en) * | 2019-03-29 | 2021-06-08 | Canon Medical Systems Corporation | Apparatuses and a method for artifact reduction in medical images using a neural network |
| US10867436B2 (en) * | 2019-04-18 | 2020-12-15 | Zebra Medical Vision Ltd. | Systems and methods for reconstruction of 3D anatomical images from 2D anatomical images |
-
2021
- 2021-12-23 CN CN202111587397.5A patent/CN114255296B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146842A (en) * | 2018-07-09 | 2019-01-04 | 南方医科大学 | A kind of breath Motion Estimation method in chest digit synthesis X-ray Tomography |
| WO2020237873A1 (en) * | 2019-05-27 | 2020-12-03 | 清华大学 | Neural network-based spiral ct image reconstruction method and device, and storage medium |
| CN111260748A (en) * | 2020-02-14 | 2020-06-09 | 南京安科医疗科技有限公司 | Digital synthesis X-ray tomography method based on neural network |
| CN113052935A (en) * | 2021-03-23 | 2021-06-29 | 大连理工大学 | Single-view CT reconstruction method for progressive learning |
| CN113052936A (en) * | 2021-03-30 | 2021-06-29 | 大连理工大学 | Single-view CT reconstruction method integrating FDK and deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114255296A (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3503038A1 (en) | Automated 3d root shape prediction using deep learning methods | |
| RU2556428C2 (en) | Method for weakening of bone x-ray images | |
| JP2020093083A (en) | Medical image reconstruction method and device thereof | |
| CN111388125B (en) | Method and device for calculating tooth movement amount before and after orthodontic treatment | |
| JP2006015136A (en) | Method and apparatus for direct reconstruction in tomosynthesis imaging | |
| WO2020087257A1 (en) | Image guidance method and device, and medical equipment and computer readable storage medium | |
| CN113822923A (en) | Method, apparatus and medium for acquiring target sectional image of blood vessel | |
| WO2022198553A1 (en) | Three-dimensional image-guided positioning method and system, and storage medium | |
| KR102346199B1 (en) | Method for generating panoramic image and image processing apparatus therefor | |
| CN114255296B (en) | CT image reconstruction method and device based on single X-ray image | |
| EP3725227B1 (en) | Method of calibrating x-ray projection geometry in x-ray cone beam computed tomography | |
| KR20210137281A (en) | 3D convolutional neural network based cone-beam artifact correction system and method | |
| CN116309909A (en) | Oral cavity scanning image processing method and device | |
| CN114565623A (en) | Pulmonary vessel segmentation method, device, storage medium and electronic equipment | |
| CN114596225A (en) | Motion artifact simulation method and system | |
| CN113888566A (en) | Target contour curve determining method and device, electronic equipment and storage medium | |
| JPS59149555A (en) | Picture reprocessing device | |
| WO2019212016A1 (en) | Image processing device, image processing method, and image processing program | |
| CN110428483B (en) | Image processing method and computing device | |
| Nakao | Medical Image Synthesis and Statistical Reconstruction Methods | |
| US20220392149A1 (en) | Methods for generating three-dimensional image data of human bones | |
| KR102383753B1 (en) | Medical image registration method and apparatus | |
| US11816768B1 (en) | System and method for medical imaging | |
| CN113855288B (en) | Image generation method, device, electronic equipment and storage medium | |
| US20240185487A1 (en) | System and method for medical imaging |
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 |