CN113034636A - Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label - Google Patents
Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label Download PDFInfo
- Publication number
- CN113034636A CN113034636A CN202110256654.0A CN202110256654A CN113034636A CN 113034636 A CN113034636 A CN 113034636A CN 202110256654 A CN202110256654 A CN 202110256654A CN 113034636 A CN113034636 A CN 113034636A
- Authority
- CN
- China
- Prior art keywords
- scattering
- projection data
- cross
- energy spectrum
- cone beam
- 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.)
- Granted
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
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/008—Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method and a device for improving the quality of a cone beam CT image based on a cross-scale multi-energy spectrum CT label, which comprises the following steps: constructing a sample data set which takes scattering pollution projection data and scattering signals as a sample pair based on the cross-scale multi-energy spectrum diagnosis CT image, optimizing parameters of a generative countermeasure network comprising a generator for estimating the scattering signals and a discriminator for distinguishing the scattering signals by utilizing the sample data set, and extracting the generator with optimized parameters as a cross-scale multi-energy spectrum scattering estimation model; and performing scattering estimation on the measured cone beam CT projection data by using a cross-scale multi-energy spectrum scattering estimation model, and realizing the scattering correction of the cone beam CT according to the estimated scattering signal and the cone beam CT projection data. Accurate scattering distribution is estimated in cone beam CT projection obtained from various imaging parts and x-ray energy spectrums, the image quality of cross-scale multi-energy spectrum cone beam CT is improved, and clinical requirements are met.
Description
Technical Field
The invention belongs to the technical field of medical engineering, and particularly relates to a cone beam CT image quality improvement method and device based on a cross-scale multi-energy spectrum CT label.
Background
Cone-beam CT dominates radiation therapy and surgical image guidance. The cone beam CT inherits the characteristic of high-definition structural imaging function of the traditional diagnosis CT based on a multi-layer detector, reserves the undistorted imaging characteristic of the conventional multi-row diagnosis CT anatomical structure, and can truly reflect the form and the position of a focus. Compared with the diagnosis CT, the cone beam CT equipment has simple structure and small key part volume; and the linearity of the imaging unit of the detector is small, the spatial resolution of the imaging system is high; and meanwhile, the total radiation dose is lower, which is beneficial to reducing the radiation damage risk of a patient. It also provides onboard and intraoperative imaging capabilities that accurately provide the location and morphology of a target region of interest (ROI) during treatment. Cone-beam CT is therefore commonly used in routine clinical applications such as intraoperative patient positioning, daily or weekly patient target verification, therapy monitoring, tumor localization, etc. Cone-beam CT has further been applied in advanced clinical applications including on-line target delineation, dose accumulation, on-board treatment planning, and diagnostic decision-making. Cone-beam CT can effectively obtain three-dimensional (3D) volumetric information at low x-ray exposure doses. However, due to scatter contamination during large cone angle illumination, the image quality of cone beam CT may be degraded by shadowing and/or streak artifacts. When a human body with a complex structure needs to be imaged, according to a signal and processing theory, the structures superpose and complex modulate scattering signals, if corresponding compensation and correction are not carried out, the direct reconstruction result is seriously polluted by artifacts, and the quality of a CT image is greatly reduced. The obvious shadow artifact exists in the abdominal cavity cone beam CT image obtained by the cone beam CT system loaded on the radiotherapy equipment, the soft tissue region resolution in the CT image is influenced, even the boundary region of the skin cannot be accurately identified, and the clinical application of the cone beam CT system such as patient positioning is influenced and limited. It is noted that now the radiotherapy apparatus has been loaded with auxiliary scatter suppression hardware including a butterfly filter and an anti-scatter grid, but still there are significant artifact problems. These problems limit the clinical use of cone-beam CT imaging.
The influence of the size of an imaging object and the imaging energy spectrum on the scattering distribution is not considered in the currently proposed scattering correction methods. The main influencing factors of scatter distribution in cone beam CT projections are the volume of the scanned object and the energy spectrum of the scanned x-rays. It was found that the scattered signal intensity increased monotonically with increasing x-ray irradiation volume. On clinical cone-beam CT systems (e.g., Varian Trilogy system) with cone angles in excess of 11 degrees in the axial (i.e., z-direction), the mean scatter signal ratio (SPR) for medium-sized human organs is about 2-3, resulting in CT number errors as high as 350Hounsfield Units (HU). In the Alexander Malusek et al study, for head size objects, the x-ray scatter signal at 30keV was 2.42 times higher than at 60keV and 3.24 times higher than at 90 keV. For a human-sized object, the SPR is 2 times at 30keV and 2.65 times at 90 keV. The difference in cross-scale object volume and the difference in ray energy spectrum become unavoidable problems with current scatter correction.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for improving the quality of cone-beam CT images based on a cross-scale multi-energy spectrum CT label, which are used for obtaining accurate scattering distribution in cone-beam CT projections from various imaging positions and x-ray energy spectra, thereby improving the image quality of the cross-scale multi-energy spectrum cone-beam CT and meeting clinical requirements.
In order to achieve the purpose, the invention provides the following technical scheme:
in a first aspect, a method for improving quality of a cone beam CT image based on a cross-scale multi-energy spectrum CT label includes the following steps:
constructing a sample data set which takes scattering pollution projection data and scattering signals as a sample pair based on the cross-scale multi-energy spectrum diagnosis CT image, optimizing parameters of a generative countermeasure network comprising a generator for estimating the scattering signals and a discriminator for distinguishing the scattering signals by utilizing the sample data set, and extracting the generator with optimized parameters as a cross-scale multi-energy spectrum scattering estimation model;
and performing scattering estimation on the measured cone beam CT projection data by using a cross-scale multi-energy spectrum scattering estimation model, and realizing the scattering correction of the cone beam CT according to the estimated scattering signal and the cone beam CT projection data.
In a second aspect, an apparatus for improving quality of cone-beam CT images based on cross-scale multi-energy spectrum CT tags includes a computer memory, a computer processor, and a computer program stored in the computer memory and executable on the computer processor, wherein the computer processor implements the above-mentioned method for improving quality of cone-beam CT images based on cross-scale multi-energy spectrum CT tags when executing the computer program.
Compared with the prior art, the invention has the beneficial effects that at least:
the invention provides a method and a device for improving the quality of a cone beam CT image based on a cross-scale multi-energy spectrum CT label. The method comprises the steps of constructing a sample pair containing scattering pollution projection data and scattering signals according to a cross-scale multi-energy spectrum diagnosis CT image, optimizing parameters of a generative countermeasure network by using the sample pair to construct a cross-scale multi-energy spectrum scattering estimation model, and when the method is applied, after scattering estimation is carried out on measured cone beam CT projection data by using the cross-scale multi-energy spectrum scattering estimation model, realizing cone beam CT scattering correction according to the estimated scattering signals and the cone beam CT projection data, so that the image quality of the cross-scale multi-energy spectrum cone beam CT can be greatly improved. The method can be used for improving the quality of cone beam CT images of different parts and different energies.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method for improving the quality of a cone-beam CT image based on a cross-scale multi-energy spectrum CT label according to an embodiment of the present invention;
FIG. 2 is a corrected image of a head phantom provided in accordance with an embodiment of the present invention, wherein (a) the uncorrected 75kVp image, (b) the corrected 75kVp image, (c) the corrected 100kVp image, (d) the corrected 125kVp image, (e) the gold standard 75kVp image;
fig. 3 is a modified image of an abdominal patient, wherein (a) the image is not modified, (b) the image is modified, and (c) the image is a gold standard, according to an embodiment 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 further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a method for improving quality of a cone-beam CT image based on a cross-scale multi-energy spectrum CT label according to an embodiment of the present invention. Referring to fig. 1, the method for improving the quality of cone beam CT images for an embodiment includes the steps of:
step 1, constructing a sample data set which takes scattering pollution projection data and scattering signals as a sample pair based on a cross-scale multi-energy spectrum diagnosis CT image.
In an embodiment, the cross-scale multi-energy spectrum diagnostic CT images can be abdominal patient diagnostic CT images obtained from a Philips Brilliance Big Bore CT device and dual-energy diagnostic CT images obtained from a Siemens SOMATOM Force X-ray computed tomography device, and the images can be used for constructing a sample pair as raw data.
Wherein, the construction of the cross-scale multi-energy spectrum diagnosis CT image with the scattering pollution projection data and the scattering signals as a sample pair comprises the following steps:
respectively carrying out forward projection processing and Monte Carlo simulation processing on the cross-scale multi-energy spectrum diagnosis CT image to obtain non-scattering projection data and a scattering signal;
adding the scattering signal into the non-scattering projection data to obtain a scatter signal ratio close to the measured cone-beam CT projection;
and adding the scattering signal into the non-scattering projection data according to the scattering original signal ratio to obtain scattering pollution projection data, wherein the scattering pollution projection data and the scattering signal form a sample pair.
In an embodiment, when the scatter signal is added to the non-scatter projection data, a ratio of the scatter signal to the original non-scatter projection data, referred to as a scatter signal ratio, is obtained, and the scatter signal ratio is generally relatively close to a scatter signal ratio existing in the measured cone-beam CT data, where the close is understood as: the difference between the ratio of the scattered signals and the ratio of the scattered signals in the measured cone-beam CT data is not more than 10%. And after a scatter signal ratio is obtained, adding a scattering signal into the non-scattering projection data according to the proportion of the scatter signal ratio to obtain scattering pollution projection data, wherein the scattering pollution projection data is used as a sample and the added scattering signal is used as a label to form a sample pair for optimizing network parameters of a generator and a discriminator.
And 2, optimizing parameters of a generative countermeasure network comprising a generator for estimating a scattering signal and a discriminator for distinguishing the scattering signal by utilizing the sample data set, and extracting the generator with optimized parameters as a cross-scale multi-energy spectrum scattering estimation model.
In an embodiment where the generator is used for scatter signal estimation, a symmetric encoder-decoder framework with a residual block may be employed, with inputs being scatter contamination projection data or measured cone-beam CT projection data and outputs being the estimated scatter signal, i.e. transforming the scatter contamination projection data into the estimated scatter signal to approximate the original scatter signal used as a label.
The discriminator is used as a two-classifier to distinguish the authenticity of the input scattering signal, namely to distinguish whether the output scattering model is the original scattering signal in the sample or the estimated scattering signal generated by the generator. Specifically, the discriminator adopts a Markov discriminator, the input of which is an estimated scattering signal and an original scattering signal in a sample pair, and the result of true and false discrimination of input data is output. The identified results are combined with the generator to optimize its parameters by a loss function through the network.
Loss function G used in optimizing parameters of generative countermeasure network*Comprises the following steps:
where λ is the coefficient of the LI regular term, the L1 regular termTo aboutThe beam estimates the difference between the scatter signal and the original scatter signal while maintaining the boundary:
‖·‖1the norm of L1 is shown,representing the loss function of a least squares generating countermeasure network,is defined as:
where j is the index of the sample pair, M is the total number of sample pairs of the sample data set, D (-) represents the discrimination result of the output of the discriminator, G (-) represents the estimated scatter signal output by the generator,andrepresenting scatter contamination projection data and scatter signals in the j-th sample pair.
In optimizing parameters of the generative countermeasure network, parameters in the generator and discriminator are optimized using an adaptive moment estimation algorithm (Adam).
And 3, performing scattering estimation on the measured cone beam CT projection data by using the cross-scale multi-energy spectrum scattering estimation model, and realizing cone beam CT scattering correction according to the estimated scattering signal and the cone beam CT projection data.
In an embodiment, implementing cone-beam CT scatter correction based on the estimated scatter signals and cone-beam CT projection data includes:
and obtaining the estimated scattering signal from the cone beam CT projection data to obtain corrected cone beam CT projection data, and performing noise reduction and reconstruction on the corrected cone beam CT projection data to obtain a corrected CT image.
After the corrected CT image is obtained, the effect of cone beam CT scattering correction is evaluated by taking the root mean square error, the Pearson correlation coefficient, the average structure similarity index and the spatial heterogeneity as quantitative evaluation indexes of the image.
FIG. 2 is a corrected image of a head phantom provided in accordance with an embodiment of the present invention, wherein (a) the uncorrected 75kVp image, (b) the corrected 75kVp image, (c) the corrected 100kVp image, (d) the corrected 125kVp image, (e) the gold standard 75kVp image;
fig. 3 is a modified image of an abdominal patient, wherein (a) the image is not modified, (b) the image is modified, and (c) the image is a gold standard, according to an embodiment of the present invention.
By analyzing the images in fig. 2 and 3, compared with a gold standard image, the corrected image CT number error is about 10HU, so that the scattering artifact in cone beam CT is corrected well, and the quality of the cone beam CT image is improved.
Embodiments also provide a cross-scale multi-energy spectrum CT tag-based cone beam CT image quality improving apparatus, comprising a computer memory, a computer processor, and a computer program stored in the computer memory and executable on the computer processor, wherein the computer processor when executing the computer program implements the above cross-scale multi-energy spectrum CT tag-based cone beam CT image quality improving method.
In practical applications, the computer memory may be volatile memory at the near end, such as RAM, or may be non-volatile memory, such as ROM, FLASH, floppy disk, mechanical hard disk, etc., or may be a remote storage cloud. The computer processor can be a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), or a Field Programmable Gate Array (FPGA), i.e. the steps of the cross-scale multi-energy spectrum CT tag-based cone beam CT image quality improvement method can be implemented by these processors.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. A cone beam CT image quality improvement method based on a cross-scale multi-energy spectrum CT label is characterized by comprising the following steps:
constructing a sample data set which takes scattering pollution projection data and scattering signals as a sample pair based on the cross-scale multi-energy spectrum diagnosis CT image, optimizing parameters of a generative countermeasure network comprising a generator for estimating the scattering signals and a discriminator for distinguishing the scattering signals by utilizing the sample data set, and extracting the generator with optimized parameters as a cross-scale multi-energy spectrum scattering estimation model;
and performing scattering estimation on the measured cone beam CT projection data by using a cross-scale multi-energy spectrum scattering estimation model, and realizing the scattering correction of the cone beam CT according to the estimated scattering signal and the cone beam CT projection data.
2. The method of claim 1, wherein constructing the cross-scale multi-energy spectrum-based diagnostic CT image with scatter contamination projection data and scatter signals as a sample pair comprises:
respectively carrying out forward projection processing and Monte Carlo simulation processing on the cross-scale multi-energy spectrum diagnosis CT image to obtain non-scattering projection data and a scattering signal;
adding the scattering signal into the non-scattering projection data to obtain a scatter signal ratio close to the measured cone-beam CT projection;
and adding the scattering signal into the non-scattering projection data according to the scattering original signal ratio to obtain scattering pollution projection data, wherein the scattering pollution projection data and the scattering signal form a sample pair.
3. The method of claim 1, wherein the generator employs a symmetric encoder-decoder framework with residual blocks, whose inputs are scatter contaminated projection data or measured cone-beam CT projection data and outputs are estimated scatter signals.
4. The method as claimed in claim 1, wherein the discriminator is a markov discriminator, and the input of the discriminator is the estimated scattering signal and the original scattering signal in the sample pair, and the output of the discriminator is true or false of the input data.
5. The method of claim 1, wherein the loss function G is used for optimizing parameters of the generative countermeasure network*Comprises the following steps:
where λ is the coefficient of the LI regular term, the L1 regular termThe difference between the scatter signal and the original scatter signal is estimated with constraints, while maintaining the boundary:
‖·‖1the norm of L1 is shown,representing the loss function of a least squares generating countermeasure network,is defined as:
where j is the index of the sample pair, M is the total number of sample pairs of the sample data set, D (-) represents the discrimination result of the output of the discriminator, G (-) represents the estimated scatter signal output by the generator,andrepresenting scatter contamination projection data and scatter signals in the j-th sample pair.
6. The method as claimed in claim 1 or 5, wherein the parameters in the generator and discriminator are optimized by using adaptive moment estimation algorithm when optimizing the parameters of the generative countermeasure network.
7. The method of claim 1, wherein the performing cone-beam CT scatter correction based on the estimated scatter signals and cone-beam CT projection data comprises:
and obtaining the estimated scattering signal from the cone beam CT projection data to obtain corrected cone beam CT projection data, and performing noise reduction and reconstruction on the corrected cone beam CT projection data to obtain a corrected CT image.
8. The method according to claim 1, wherein after the corrected CT image is obtained, the effect of cone beam CT scatter correction is evaluated by using a root mean square error, a Pearson correlation coefficient, an average structural similarity index, and spatial non-uniformity as quantitative evaluation indexes of the image.
9. An apparatus for improving quality of cone beam CT image based on cross-scale multi-energy spectrum CT label, comprising a computer memory, a computer processor and a computer program stored in the computer memory and executable on the computer processor, wherein the computer processor when executing the computer program realizes the method for improving quality of cone beam CT image based on cross-scale multi-energy spectrum CT label according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110256654.0A CN113034636B (en) | 2021-03-09 | 2021-03-09 | Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110256654.0A CN113034636B (en) | 2021-03-09 | 2021-03-09 | Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113034636A true CN113034636A (en) | 2021-06-25 |
CN113034636B CN113034636B (en) | 2022-04-29 |
Family
ID=76467395
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110256654.0A Active CN113034636B (en) | 2021-03-09 | 2021-03-09 | Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113034636B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578082A (en) * | 2012-08-09 | 2014-02-12 | 江苏超惟科技发展有限公司 | Cone beam CT scatter correction method and system |
CN104408753A (en) * | 2014-10-27 | 2015-03-11 | 浙江大学 | Self-adaptive iteration scattering correction method of cone beam CT |
CN109870471A (en) * | 2019-02-27 | 2019-06-11 | 西北工业大学 | A kind of Cone-Beam CT angle sequence scattering acquisition methods of monochromatic light grid detecting |
CN109919868A (en) * | 2019-02-27 | 2019-06-21 | 西北工业大学 | A kind of detecting of cone-beam CT beam hardening curve and projection weighted correction method |
US20200279410A1 (en) * | 2017-11-24 | 2020-09-03 | Sang Chul Lee | Scatter Correction Method and Apparatus for Dental Cone-Beam CT |
CN112204620A (en) * | 2018-04-26 | 2021-01-08 | 医科达有限公司 | Image enhancement using generative countermeasure networks |
CN112435307A (en) * | 2020-11-26 | 2021-03-02 | 浙江大学 | Deep neural network assisted four-dimensional cone beam CT image reconstruction method |
-
2021
- 2021-03-09 CN CN202110256654.0A patent/CN113034636B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578082A (en) * | 2012-08-09 | 2014-02-12 | 江苏超惟科技发展有限公司 | Cone beam CT scatter correction method and system |
CN104408753A (en) * | 2014-10-27 | 2015-03-11 | 浙江大学 | Self-adaptive iteration scattering correction method of cone beam CT |
US20200279410A1 (en) * | 2017-11-24 | 2020-09-03 | Sang Chul Lee | Scatter Correction Method and Apparatus for Dental Cone-Beam CT |
CN112204620A (en) * | 2018-04-26 | 2021-01-08 | 医科达有限公司 | Image enhancement using generative countermeasure networks |
CN109870471A (en) * | 2019-02-27 | 2019-06-11 | 西北工业大学 | A kind of Cone-Beam CT angle sequence scattering acquisition methods of monochromatic light grid detecting |
CN109919868A (en) * | 2019-02-27 | 2019-06-21 | 西北工业大学 | A kind of detecting of cone-beam CT beam hardening curve and projection weighted correction method |
CN112435307A (en) * | 2020-11-26 | 2021-03-02 | 浙江大学 | Deep neural network assisted four-dimensional cone beam CT image reconstruction method |
Non-Patent Citations (1)
Title |
---|
XIANGYANG TANG: "《Paired cycle-GAN-based image correction for quantitative cone-beam》", 《MEDICAL PHYSICS》 * |
Also Published As
Publication number | Publication date |
---|---|
CN113034636B (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Thummerer et al. | Comparison of CBCT based synthetic CT methods suitable for proton dose calculations in adaptive proton therapy | |
US7627079B2 (en) | Method for computing patient radiation dose in computed tomography | |
CN109146994B (en) | Metal artifact correction method for multi-energy spectrum X-ray CT imaging | |
US8835858B2 (en) | Systems and methods for attenuation compensation in nuclear medicine imaging based on emission data | |
US20220207791A1 (en) | Method and system for generating attenuation map from spect emission data | |
US10593070B2 (en) | Model-based scatter correction for computed tomography | |
US11419566B2 (en) | Systems and methods for improving image quality with three-dimensional scout | |
CN110811660B (en) | Method for correcting CT ray beam hardening artifact | |
Puvanasunthararajah et al. | The application of metal artifact reduction methods on computed tomography scans for radiotherapy applications: A literature review | |
CN110084864A (en) | A kind of electron density image method for reconstructing based on power spectrum CT | |
Li et al. | Implementation of dual‐energy technique for virtual monochromatic and linearly mixed CBCTs | |
Shi et al. | X‐ray scatter correction for dedicated cone beam breast CT using a forward‐projection model | |
Jiang et al. | A generalized image quality improvement strategy of cone-beam CT using multiple spectral CT labels in Pix2pix GAN | |
Trapp et al. | Empirical scatter correction: CBCT scatter artifact reduction without prior information | |
CN113034636B (en) | Cone beam CT image quality improvement method and device based on cross-scale multi-energy spectrum CT label | |
Chen et al. | Low dose cone-beam computed tomography reconstruction via hybrid prior contour based total variation regularization (hybrid-PCTV) | |
Liugang et al. | Metal artifact reduction method based on noncoplanar scanning in CBCT imaging | |
CN111134709B (en) | Multi-energy CT-based material decomposition method | |
Bayat et al. | A quantitative CBCT pipeline based on 2D antiscatter grid and grid‐based scatter sampling for image‐guided radiation therapy | |
Gomi et al. | Development of a denoising convolutional neural network-based algorithm for metal artifact reduction in digital tomosynthesis for arthroplasty: A phantom study | |
Park et al. | Unpaired-paired learning for shading correction in cone-beam computed tomography | |
Guleng | Radiation dose and image quality in CT-evaluation of how slice thickness, tube current modulation and reconstruction algorithms affect radiation dose and image noise | |
Zhao et al. | Multi-materials beam hardening artifacts correction for computed tomography (CT) based on X-ray spectrum estimation | |
Sathishkumar et al. | Advances in Modelling and Analysis B | |
Liu | Optimization and Clinical Evaluation of a Prior Knowledge-based 4D Cone Beam CT Estimation Technique for Lung Radiotherapy |
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 |