CN111627081A - CT image reconstruction method, device, equipment and medium - Google Patents
CT image reconstruction method, device, equipment and medium Download PDFInfo
- Publication number
- CN111627081A CN111627081A CN202010429907.5A CN202010429907A CN111627081A CN 111627081 A CN111627081 A CN 111627081A CN 202010429907 A CN202010429907 A CN 202010429907A CN 111627081 A CN111627081 A CN 111627081A
- Authority
- CN
- China
- Prior art keywords
- image
- projection images
- projection
- processing model
- image processing
- 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
- G06T11/006—Inverse problem, transformation from projection-space into object-space, e.g. transform methods, back-projection, algebraic methods
-
- 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
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2211/00—Image generation
- G06T2211/40—Computed tomography
- G06T2211/416—Exact reconstruction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2211/00—Image generation
- G06T2211/40—Computed tomography
- G06T2211/424—Iterative
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the invention discloses a CT image reconstruction method, a device, equipment and a medium. The method comprises the following steps: acquiring a plurality of projection images of an inspection object, wherein the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in different frame angles; inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images; reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, a CT image of the examination object is reconstructed from the plurality of new projection images and the plurality of projection images. According to the embodiment of the invention, the CT image is reconstructed according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images, so that the information content of the reconstructed CT image is increased, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis based on the reconstructed CT image.
Description
Technical Field
The embodiment of the invention relates to the technical field of computed tomography, in particular to a CT image reconstruction method, a device, equipment and a medium.
Background
A Computed Tomography (CT) technique is a technique for imaging internal information of an object under examination (human body) by using the principle of interaction between X-rays and a substance. During a CT scan, the X-ray source and the detector are rotated with the gantry around the object under examination to scan the object under examination at a plurality of gantry angles, resulting in scan data for the object under examination at a plurality of gantry angles. Projection images corresponding to the respective gantry angles are generated from scan data at the plurality of gantry angles. Then, a CT image is reconstructed from the generated projection images to provide conditions for a subsequent medical diagnosis.
The CT image is reconstructed from the projection images, often in several ways: the method comprises the steps that firstly, a sinogram with an artifact is obtained based on a plurality of projection images with the artifact; the sinogram with the artifact is processed by a deep learning network model, and a clear CT image is output, as shown in FIG. 1 (a). In the second method, a CT image is obtained by processing a projection image with artifacts by a deep learning network model, as shown in fig. 1 (b). However, the CT image reconstructed based on the projection image in the above-mentioned several ways is different from the real CT image, so that when the medical diagnosis is performed based on the reconstructed CT image, the treatment accuracy and timeliness are easily affected by misdiagnosis.
Disclosure of Invention
The embodiment of the invention provides a CT image reconstruction method, a device, equipment and a medium, which improve the accuracy of reconstructing a CT image.
In a first aspect, an embodiment of the present invention provides a CT image reconstruction method, where the method includes:
acquiring a plurality of projection images of an inspection object, wherein the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
reconstructing a CT image of the examination object from the plurality of new projection images and the plurality of projection images.
In a second aspect, an embodiment of the present invention further provides a CT image reconstruction apparatus, where the apparatus includes:
the system comprises an image acquisition module, a data acquisition module and a data acquisition module, wherein the image acquisition module is used for acquiring a plurality of projection images of an inspection object, the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
the image processing module is used for inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
an image reconstruction module for reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
and the image reconstruction module is also used for reconstructing a CT image of the checked object according to the plurality of new projection images and the plurality of projection images.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the CT image reconstruction method according to any of the embodiments of the present invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the CT image reconstruction method according to any one of the embodiments of the present invention.
The technical scheme disclosed by the embodiment of the invention has the following beneficial effects:
the method comprises the steps of obtaining a plurality of projection images of a CT scanner under different stand angles, inputting the projection images into an image processing model respectively to obtain a plurality of new projection images, and reconstructing a CT image of an inspection object according to the new projection images or reconstructing the CT image of the inspection object according to the new projection images and the projection images. Therefore, the CT image is reconstructed according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images, the information content of the reconstructed CT image is increased, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis based on the reconstructed CT image.
Drawings
FIG. 1(a) is a schematic diagram of a CT image output by processing a sinogram with an artifact through a deep learning network model in the related art;
FIG. 1(b) is a schematic diagram of a CT image obtained by processing a projection image with artifacts through a deep learning network model in the related art;
FIG. 2 is a schematic flow chart of a CT image reconstruction method according to an embodiment of the present invention;
FIG. 3 is a flow chart of another CT image reconstruction method according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of a CT image reconstruction method according to another embodiment of the present invention;
FIG. 4(a) is a schematic diagram of a plurality of projection images of a chlorella cell being processed to generate a plurality of new chlorella cell projection images according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of an embodiment of the present invention for generating an image processing model;
FIG. 6 is a schematic flow chart of another embodiment of the present invention for generating an image processing model;
FIG. 7 is a schematic flow chart illustrating the testing of an image processing model according to an embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a CT image reconstruction apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad invention. It should be further noted that, for convenience of description, only some structures, not all structures, relating to the embodiments of the present invention are shown in the drawings.
In order to facilitate understanding of the method, the apparatus, the device and the medium for reconstructing a CT image according to the embodiments of the present invention, a structure and an operation principle of a CT scanner (computer Tomography, chinese name: computer Tomography) will be described first. In this embodiment, the CT scanner is preferably a spiral CT.
Specifically, the CT scanner includes: the CT scanner comprises a radiation source, a detector, a rack and a scanning bed, so that when the CT scanner detects an inspection object, the inspection object can be placed on the scanning bed and moved into a detection channel, then the radiation source is controlled to emit X rays to irradiate the inspection object, and the detector is controlled to receive ray irradiation data passing through the inspection object, so that scanning data can be obtained. Projection images are then generated from the acquired scan data. Specifically, during scanning of the examination object, the radiation source and the detector are rotated with the gantry around the examination object to scan the examination object at a plurality of gantry angles, resulting in scan data of the examination object at a plurality of gantry angles. Projection images corresponding to the respective gantry angles are generated from scan data at the plurality of gantry angles. In the embodiment of the present invention, the object to be examined may be a living body, a non-living body, or the like, and is not particularly limited herein. Among these, the organism may be, but is not limited to: patients, animals, organs, cells, tissues, etc.; the non-living organism may be, but is not limited to: mannequins and water films, etc.
The CT image reconstruction method, apparatus, device, and medium according to the embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of a CT image reconstruction method according to an embodiment of the present invention, which may be applied to a scene of a CT image reconstructed based on an acquired projection image, and the method may be executed by a CT image reconstruction apparatus, which may be composed of hardware and/or software, and may be generally integrated in an electronic device, which may be a CT scanner. As shown in fig. 2, the method specifically includes the following steps:
s201, a plurality of projection images of an inspection object are acquired.
Wherein the plurality of projection images are generated from scan data acquired by the CT scanner at different gantry angles, wherein each projection image corresponds to one of the different gantry angles.
In an embodiment of the invention, each acquired projection image comprises parameter information between the object under examination and the CT scanner. Wherein the parameter information includes: the distance between the source and the detector in a CT scanner and the position of the center of rotation of the CT scanner.
Illustratively, the present embodiment acquires a plurality of projection images of an inspection object, and can be implemented as follows:
in a first mode
A plurality of projection images are generated from scan data acquired by the CT scanner at different gantry angles.
Mode two
By acquiring a plurality of projection images of the examination object from a pre-stored projection image storage device or unit.
Specifically, in the present embodiment, a plurality of projection images generated by scanning data under different gantry angles may be stored in the storage device or the storage unit in advance, so that when the plurality of projection images are acquired, the plurality of projection images of the inspection object may be acquired from the storage device or the storage unit, so as to improve the acquisition convenience of the projection images. The storage device may be any device having a data storage function, and is not particularly limited herein.
The above two modes are only exemplary illustrations of the embodiments of the present invention, and do not specifically limit the embodiments of the present invention.
S202, inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images.
The image processing model is a three-dimensional image processing model, and the three-dimensional image processing model is a three-dimensional deep learning network model. In this embodiment, the deep learning network may be, but is not limited to: convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adaptive Networks (GAN), CNN-based image segmentation Networks (U-Net), and the like.
In an embodiment of the present invention, the new projection image is a projection image corresponding to a middle rack angle of adjacent rack angles in the different rack angles, or a projection image corresponding to an omnidirectional rack angle, where the omnidirectional rack angle is a 360-degree (full-angle) rack angle. For example, if the different frame angles are [0 ° -180 ° ] and adjacent frame angles are evenly spaced by 5 °, the corresponding frame angle (middle frame angle) for the new projected image may be: 2.5-182.5 with an angle of 5 evenly spaced between adjacent intermediate frame angles. For another example, if the different frame angles are [0 ° -180 ° ], and the adjacent frame angles are uniformly spaced by 5 °, the frame angle corresponding to the new projected image may be: [0 ° -360 ° ] (full-angle frame angle), and the adjacent frame angles can be uniformly spaced by 5 °.
Illustratively, the acquired plurality of projection images are input into an image processing model, so that the input plurality of projection images are processed by the image processing model to obtain a plurality of new projection images. Thus, a foundation is laid for the subsequent reconstruction of CT images of the examination object based on the obtained plurality of new projection images.
As an alternative implementation, the image processing model used in this embodiment may be an image processing model trained on a certain CT scanner. That is, when an image processing model is generated by training a CT scanner, each training projection image in the training set used needs to include the same parameter information, so that the image processing model generated by training is ensured to be applicable only to the CT scanner.
Accordingly, when the plurality of projection images of the inspection object are obtained by processing the plurality of projection images of the inspection object using the image processing model for a certain CT scanner, in the embodiment of the present invention, each projection image needs to include a projection image having the same parameter information as the training projection image used by the image processing model, so that a plurality of new projection images belonging to the CT scanner can be obtained.
It should be noted that, for the process of generating the image processing model in the embodiment of the present invention, details will be described in the following embodiment, and redundant description thereof is not repeated here.
S203, reconstructing a CT image of the inspection object according to the plurality of new projection images.
S204, reconstructing a CT image of the inspection object according to the plurality of new projection images and the plurality of projection images.
It should be noted that, in this embodiment, the new projection image is: and the projection images corresponding to the middle frame angle of the adjacent frame angles in different frame angles or the projection images corresponding to the omnidirectional frame angle. Therefore, the present embodiment may reconstruct a CT image of an examination object from a plurality of new projection images and a plurality of projection images, or from a plurality of new projection images.
That is, if the new projection image is a projection image corresponding to a middle gantry angle of adjacent gantry angles among different gantry angles, reconstructing a CT image of the inspection object from the plurality of new projection images and the plurality of projection images; and if the new projection image is the projection image corresponding to the omnidirectional gantry angle, reconstructing and checking the corresponding CT image according to the plurality of new projection images.
As an alternative implementation manner, when reconstructing a CT image of an inspection object according to a plurality of new projection images and a plurality of projection images, or reconstructing a CT image of an inspection object according to a plurality of new projection images, the embodiment of the invention may be implemented by using an existing CT image reconstruction method, which is not specifically limited herein. Specifically, the conventional CT image reconstruction method includes: algebraic reconstruction methods (iterative methods), backprojection methods, convolution-backprojection methods, and the like.
According to the CT image reconstruction method provided by the embodiment of the invention, a plurality of projection images of a CT scanner under different frame angles are obtained, and are respectively input into an image processing model to obtain a plurality of new projection images, and then the CT image of an inspection object is reconstructed according to the plurality of new projection images, or the CT image of the inspection object is reconstructed according to the plurality of new projection images and the plurality of projection images. Therefore, the CT image is reconstructed according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images, the information content of the reconstructed CT image is increased, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis based on the reconstructed CT image.
As can be seen from the above analysis, the embodiment of the present invention processes the plurality of projection images of the inspection object by using the image processing model to obtain a plurality of new projection images, so as to reconstruct a CT image of the inspection object according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images.
In an embodiment of the invention, the reconstruction of a CT image of an examination object from a plurality of new projection images is further explained below with reference to fig. 3. Fig. 3 is a flowchart illustrating another CT image reconstruction method according to an embodiment of the present invention. As shown in fig. 3, the method specifically includes the following steps:
s301, a plurality of projection images of the inspection object are acquired.
Wherein the plurality of projection images are generated from scan data acquired by the CT scanner at different gantry angles, wherein each projection image corresponds to one of the different gantry angles.
S302, inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images.
And S303, if the plurality of new projection images are projection images corresponding to the omnidirectional gantry angle, reconstructing the CT image of the inspection object according to the plurality of new projection images by using a preset reconstruction algorithm.
For example, if the image processing model is a projection image model corresponding to a full-azimuth gantry angle, and the gantry angles corresponding to a plurality of projection images are [0 ° -180 ° ] and are uniformly spaced by 5 °, 360 new projection images having a gantry angle of [0 ° -360 ° ] can be obtained through the image processing model, wherein the gantry angles corresponding to each of the adjacent new projection images are uniformly spaced by 1 °. Then, from the 360 new projection images, a CT image of the examination object is reconstructed using an existing CT image reconstruction method.
According to the technical scheme provided by the embodiment of the invention, the plurality of projection images of the inspection object are acquired and input into the projection image model corresponding to the generated omnidirectional gantry angle to obtain the projection images corresponding to the omnidirectional gantry angle, and the projection images corresponding to the omnidirectional gantry angle are used as a plurality of new projection images to reconstruct the CT image of the inspection object according to the new projection images. Therefore, the information quantity of the reconstructed CT image is increased based on the new projection image, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis of the subsequent reconstructed CT image.
As can be seen from the above analysis, the embodiment of the present invention processes the plurality of projection images of the inspection object by using the image processing model to obtain a plurality of new projection images, so as to reconstruct a CT image of the inspection object according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images.
In the following, with reference to fig. 4, a description will be given of the reconstruction of a CT image of an examination object from a plurality of new projection images and a plurality of projection images according to an embodiment of the present invention. Fig. 4 is a flowchart illustrating a CT image reconstruction method according to another embodiment of the present invention. As shown in fig. 4, the method specifically includes the following steps:
s401, a plurality of projection images of the inspection object are acquired.
Wherein the plurality of projection images are generated from scan data acquired by the CT scanner at different gantry angles, wherein each projection image corresponds to one of the different gantry angles.
S402, inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images.
For example, as shown in fig. 4(a), when the test object is a chlorella cell, the plurality of obtained chlorella cell projection images (41 in the figure) are input to an image processing model, and the plurality of chlorella cell projection images are processed by the image processing model to generate a plurality of new chlorella cell projection images (42 in the figure).
And S403, if the new projection images are projection images corresponding to the middle frame angle of the adjacent frame angles in the different frame angles, reconstructing a CT image of the inspection object according to the new projection images and the projection images by using the preset reconstruction algorithm.
For example, if the image processing model is a projection image model corresponding to a middle frame angle that generates adjacent frame angles, and the frame angles corresponding to a plurality of projection images are [0 ° -180 ° ] evenly spaced by 5 °, then 37 new projection images having frame angles of [2.5 ° -182.5 ° ] can be obtained by the image processing model, where the frame angles corresponding to adjacent new projection images are evenly spaced by 5 °. Then, a CT image of the examination object is reconstructed from the 37 new projection images and the 37 projection images by using an existing CT image reconstruction method.
According to the technical scheme provided by the embodiment of the invention, a plurality of projection images of the inspection object are acquired and input into the projection image model corresponding to the middle frame angle for generating the adjacent frame angles, so as to obtain the projection images corresponding to the middle frame angles of the adjacent frame angles in different frame angles, and the projection images corresponding to the middle frame angles are used as new projection images, so as to reconstruct the CT image of the inspection object according to the new projection images and the projection images. Therefore, the information quantity of the reconstructed CT image is increased based on the new projection image, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis of the subsequent reconstructed CT image.
The following describes, with reference to fig. 5 and fig. 6, a generation process of an image processing model in the CT image reconstruction method according to the embodiment of the present invention in detail. First, as shown in fig. 5, an image processing model according to an embodiment of the present application may be generated by training in the following manner:
s501, acquiring a projection image set.
Wherein the set of projection images comprises: the projection images corresponding to a plurality of adjacent gantry angles, the projection image corresponding to the middle gantry angle of each adjacent gantry angle, or the projection image corresponding to the omnidirectional gantry angle, wherein each projection image includes an inspection object and parameter information between the CT scanners.
In the embodiment of the present invention, the parameter information includes: the distance between the source and the detector in a CT scanner and the position of the center of rotation of the CT scanner.
Optionally, the present embodiment may obtain the projection image set by the following method:
in a first mode
And generating projection images corresponding to a plurality of stand angles by using simulated scanning data through projection image simulation software, and forming a projection image set by the plurality of projection images. Wherein the projected image is a simulated projected image.
In this embodiment, in addition to the projection images corresponding to the plurality of frame angles, the projection image corresponding to the middle frame angle of each adjacent frame angle or the projection image corresponding to the omnidirectional corner cube is generated by using the simulated scan data.
For example, if the plurality of gantry angles are 2 °, 6 °, and 10 °, the projection image set includes projection images corresponding to a gantry angle of 2 °, projection images corresponding to a gantry angle of 6 °, projection images corresponding to a gantry angle of 10 °, and projection images corresponding to gantry angles of 4 ° and 8 °, respectively.
For another example, if the plurality of gantry angles are 120 °, 160 °, and 210 °, the projection image set has projection images corresponding to 120 ° gantry angles, and projection images corresponding to 160 ° gantry angles and projection images corresponding to 210 ° gantry angles, and also has projection images corresponding to each of other gantry angles ([0 ° -119 ° ], [121 ° -159 ° ] and [161 ° -360 ° ] in a full angle of 360 degrees other than 120 °, 160 °, and 210 °. Of course, in this example, the interval angles of other frame angles in the 360-degree full angle may also be set according to actual needs, and the interval angles are not specifically limited herein.
Mode two
The projection image set is acquired from a public projection image database provided by any hospital through a tool such as a web crawler.
The two acquisition manners are only exemplary illustrations of the embodiments of the present invention, and are not specific limitations of the embodiments of the present invention.
Further, in this embodiment, after the projection image set is acquired, the projection images that do not meet the requirements in the projection image set may be removed. The unsatisfactory projection image refers to a projection image in which any projection image does not have any correlation with most other projection images, for example, 200 projection images of the abdomen and 3 projection images of the chest are included in the projection image set, and then it can be determined that the 3 projection images of the chest are unsatisfactory projection images. That is to say, when it is determined that any projection image in the projection image set does not have any correlation with most other projection images, the projection image is considered as an invalid projection image, and the projection image is removed, so that interference factors are reduced, and the generation accuracy and speed of the image processing model are improved.
S502, training a preset initial image processing model by taking the projection images corresponding to the adjacent frame angles as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle as a training result to generate the image processing model.
The preset image processing model may be an existing general image processing model.
For example, the projection images corresponding to the plurality of adjacent frame angles are input to a preset initial image processing model as input data, the projection image corresponding to the middle frame angle of each adjacent frame angle is used as a training result, the preset initial image processing model is trained for a plurality of times, and the weight value corresponding to each calculation layer in the preset initial image processing model is continuously adjusted, so that the trained initial image processing model can accurately output the projection image corresponding to the middle frame angle of each adjacent frame angle until the projection image corresponding to the middle frame angle of each adjacent frame angle is input. Thus, the trained preset initial image processing model is used as an image processing model, namely a final image processing model.
And the projection image corresponding to the middle frame angle of each adjacent frame angle as the training result has the same characteristic point with the projection image corresponding to the adjacent frame angle. The same characteristic point refers to the same micro area which is stably existed in the projection image corresponding to the adjacent frame angle and the projection image corresponding to the middle frame angle and is similar to the point. For example, if the adjacent gantry angles are 2 ° and 6 °, and the feature point a exists in the projection image corresponding to 2 °, and the feature point a also exists in the projection image corresponding to 6 °, the feature point a also exists in the projection image corresponding to the intermediate gantry angle of 2 ° and 6 °.
And S503, training a preset initial image processing model by using the projected images corresponding to the plurality of adjacent stand angles as training data and the projected images corresponding to the omnidirectional stand angles as training results to generate the image processing model.
It should be noted that, in this embodiment, the new projection image is: and the projection images corresponding to the middle frame angle of the adjacent frame angles in different frame angles or the projection images corresponding to the omnidirectional frame angle. Therefore, in this embodiment, training is performed based on a preset initial image processing model, and the generated image processing model specifically includes: and generating an image processing model of the projection image corresponding to the middle frame angle of each adjacent frame angle or the image processing model of the projection image corresponding to the all-directional frame angle.
The image processing method comprises the steps of training a preset initial image processing model, generating the image processing model, and when the model is a model of a projection image corresponding to an all-position machine frame angle, inputting the projection image corresponding to a plurality of adjacent machine frame angles into the preset initial image processing model by taking the projection image corresponding to the all-position machine frame angle as input data, taking the projection image corresponding to the all-position machine frame angle as a training result, training the preset initial image processing model for multiple times, continuously adjusting the weight value corresponding to each calculation layer in the preset initial image processing model, and outputting the projection image corresponding to the all-position machine frame angle accurately until the projection image corresponding to the all-position machine frame angle is input into the trained initial image processing model. Thus, the trained preset initial image processing model is used as an image processing model, namely a final image processing model.
The projection images corresponding to the omnidirectional adjacent frame angles as the training result have the same characteristic points with the projection images of the plurality of adjacent frame angles. In this embodiment, the same feature point is explained with reference to S502 specifically, and redundant description thereof is not repeated here.
As an alternative implementation, the image processing model in this embodiment may be a specific image processing model for a certain CT scanner. Therefore, in order to generate the specific image processing model, in this embodiment, when the projection image set is acquired, parameter information included in each projection image in the projection image set that needs to be acquired is the same, so that the image processing model generated based on the training of the projection image set can only be applied to a certain CT scanner, and therefore, based on the specific image processing model, the processing of the projection images is more targeted, and the use requirement of a user for reconstructing and constructing a CT image for a plurality of projection images acquired by a specific CT scanner is met.
Next, as shown in fig. 6, the image processing model according to the embodiment of the present invention can be generated by training in the following manner:
s601, acquiring a projection image set.
Wherein the set of projection images comprises: the projection images corresponding to a plurality of adjacent gantry angles, the projection image corresponding to the middle gantry angle of each adjacent gantry angle, or the projection image corresponding to the omnidirectional gantry angle, wherein each projection image includes an inspection object and parameter information between the CT scanners.
S602, the projection image set is divided into a training set and a check set.
S603, training a preset initial image processing model by taking the projection images corresponding to a plurality of adjacent frame angles in the training set and the checking set as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle in the training set and the checking set as a training result to generate the image processing model.
S604, training a preset initial image processing model by using the projection images corresponding to a plurality of adjacent frame angles in the training set and the calibration set as training data and the projection images corresponding to all-directional frame angles in the training set and the calibration set as training results, so as to generate the image processing model.
Based on the multiple modes, the generated image processing model can realize the customization of the image processing model, and the personalized requirements of users are met.
Further, after generating the image processing model, the embodiment of the present invention may also test the accuracy of the image processing model, as shown in fig. 7. The method comprises the following steps:
s701, obtaining a test set corresponding to the projection image set.
S702, testing the image processing model by using the test set to determine the accuracy of the image processing model.
In this embodiment, the generated image processing model is tested by the test set to verify the accuracy and reliability of the image processing model, and whether the accuracy and reliability meet expectations is determined. If not, the image processing model is adjusted based on the acquired projection image set until the adjusted image processing model meets the expectation.
That is, the image processing model is tested by using the test set to ensure that the generated image processing model can meet the actual use requirements of the user, so that favorable conditions are provided for generating a new projection image.
In order to achieve the above object, an embodiment of the present invention further provides a CT image reconstruction apparatus. Fig. 8 is a schematic structural diagram of a CT image reconstruction apparatus according to an embodiment of the present invention. As shown in fig. 8, a CT image reconstruction apparatus 800 according to an embodiment of the present invention includes: an image acquisition module 810, an image processing module 820, and an image reconstruction module 830.
The image acquiring module 810 is configured to acquire a plurality of projection images of an inspection object, where the plurality of projection images are generated according to scan data acquired by a CT scanner under different gantry angles, and each projection image corresponds to one of the different gantry angles;
an image processing module 820, configured to input the plurality of projection images into an image processing model, so as to obtain a plurality of new projection images;
an image reconstruction module 830 for reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
an image reconstruction module 830 further configured to reconstruct a CT image of the examination object from the plurality of new projection images and the plurality of projection images.
As an optional implementation manner of the embodiment of the present invention, the new projection image is a projection image corresponding to an omnidirectional gantry angle, or a projection image corresponding to a middle gantry angle of adjacent gantry angles in different gantry angles;
accordingly, the image reconstruction module 830 is specifically configured to:
if the plurality of new projection images are projection images corresponding to the omnidirectional gantry angles, reconstructing a CT image of the inspection object according to the plurality of new projection images by using a preset reconstruction algorithm; alternatively, the first and second electrodes may be,
accordingly, the image reconstruction module 830 is specifically configured to:
and if the new projection images are projection images corresponding to the middle frame angle of the adjacent frame angles in the different frame angles, reconstructing the CT image of the inspection object according to the new projection images and the projection images by using the preset reconstruction algorithm.
As an optional implementation manner of the embodiment of the present invention, the apparatus 800 further includes: the system comprises a first acquisition module and a model generation module;
wherein the first obtaining module is configured to obtain a projection image set, and the projection image set includes: a plurality of projection images corresponding to adjacent gantry angles, a projection image corresponding to a middle gantry angle of each adjacent gantry angle, or a projection image corresponding to an omnidirectional gantry angle, wherein each projection image includes parameter information between an inspection object and the CT scanner;
the model generating module is used for training a preset initial image processing model by taking the projection images corresponding to the adjacent frame angles as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle as a training result so as to generate the image processing model; alternatively, the first and second electrodes may be,
and the model generation module is used for training a preset initial image processing model by using the projection images corresponding to the adjacent stand angles as training data and the projection images corresponding to the omnidirectional stand angles as training results so as to generate the image processing model.
As an optional implementation manner of the embodiment of the present invention, the apparatus 800 further includes: a dividing processing module;
the system comprises a projection image set, a dividing processing module, a verification processing module and a processing module, wherein the dividing processing module is used for dividing the projection image set so as to divide the projection image set into a training set and a verification set;
accordingly, the model generation module is specifically configured to:
training a preset initial image processing model by taking the projection images corresponding to a plurality of adjacent frame angles in the training set and the checking set as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle in the training set and the checking set as a training result to generate the image processing model; alternatively, the first and second electrodes may be,
and training a preset initial image processing model by using the projection images corresponding to a plurality of adjacent frame angles in the training set and the calibration set as training data and the projection images corresponding to all-directional frame angles in the training set and the calibration set as training results to generate the image processing model.
As an optional implementation manner of the embodiment of the present invention, the apparatus 800 further includes: a second acquisition module and a test module;
the second acquisition module is used for acquiring a test set corresponding to the projection image set;
and the testing module is used for testing the image processing model by utilizing the test set so as to determine the accuracy of the image processing model.
As an optional implementation manner of the embodiment of the present invention, the parameter information includes: the distance between the source and the detector in a CT scanner and the position of the center of rotation of the CT scanner.
As an optional implementation manner of the embodiment of the present invention, the image processing model is a three-dimensional image processing model, and the three-dimensional image processing model is a three-dimensional deep learning network model.
It should be noted that the foregoing explanation of the embodiment of the CT image reconstruction method is also applicable to the CT image reconstruction apparatus of the embodiment, and the implementation principle thereof is similar, and is not repeated here.
According to the technical scheme provided by the embodiment of the invention, a plurality of projection images of the CT scanner under different frame angles are obtained, and are respectively input into the image processing model to obtain a plurality of new projection images, and then the CT image of the inspection object is reconstructed according to the plurality of new projection images, or the CT image of the inspection object is reconstructed according to the plurality of new projection images and the plurality of projection images. Therefore, the CT image is reconstructed according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images, the information content of the reconstructed CT image is increased, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis based on the reconstructed CT image.
Referring to fig. 9, the present embodiment provides an electronic apparatus 900, which includes: one or more processors 920; the storage device 910 is configured to store one or more programs, and when the one or more programs are executed by the one or more processors 920, the one or more processors 920 implement the CT image reconstruction method provided in the embodiment of the present invention, including:
acquiring a plurality of projection images of an inspection object, wherein the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
reconstructing a CT image of the examination object from the plurality of new projection images and the plurality of projection images.
Of course, those skilled in the art will understand that the processor 920 may also implement the technical solution of the CT image reconstruction method provided in any embodiment of the present invention.
The electronic device 900 shown in fig. 9 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention. The electronic device in the embodiment of the present invention may be a device having a graphics Processing Unit (GPU for short) or a Tensor Processing Unit (TPU for short).
As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: one or more processors 920, a storage device 910, and a bus 950 that couples the various system components (including the storage device 910 and the processors 920).
The storage 910 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)911 and/or cache memory 912. The electronic device 900 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 913 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 9, and commonly referred to as a "hard disk drive"). Although not shown in FIG. 9, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 950 by one or more data media interfaces. Storage 910 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 914 having a set (at least one) of program modules 915 may be stored, for instance, in the storage device 910, such program modules 915 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment. Program modules 915 generally perform the functions and/or methods of any of the embodiments described herein.
The electronic device 900 may also communicate with one or more external devices 960 (e.g., keyboard, pointing device, display 970, etc.), with one or more devices that enable a user to interact with the electronic device 900, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 930. Also, the electronic device 900 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 940. As shown in FIG. 9, the network adapter 940 communicates with the other modules of the electronic device 900 via the bus 950. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 920 executes various functional applications and data processing by executing programs stored in the storage device 910, for example, to implement a CT image reconstruction method provided by an embodiment of the present invention.
It should be noted that the foregoing explanation of the embodiment of the CT image reconstruction method is also applicable to the electronic device of the embodiment, and the implementation principle thereof is similar and will not be described herein again.
According to the electronic device provided by the embodiment of the invention, a plurality of projection images of the CT scanner under different frame angles are acquired, the plurality of projection images are respectively input into the image processing model to obtain a plurality of new projection images, and then the CT image of the inspection object is reconstructed according to the plurality of new projection images, or the CT image of the inspection object is reconstructed according to the plurality of new projection images and the plurality of projection images. Therefore, the CT image is reconstructed according to the plurality of new projection images or the plurality of new projection images and the plurality of projection images, the information content of the reconstructed CT image is increased, the accuracy of the reconstructed CT image is improved, and a reliable basis is provided for medical diagnosis based on the reconstructed CT image.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the CT image reconstruction method provided in any embodiment of the present invention, where the method includes:
acquiring a plurality of projection images of an inspection object, wherein the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
reconstructing a CT image of the examination object from the plurality of new projection images and the plurality of projection images.
Of course, the embodiments of the present invention provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor, and the computer program is not limited to the method operations described above, but may also perform related operations in the CT image reconstruction method provided in any embodiment of the present invention.
The computer-readable storage media of embodiments of the invention may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A CT image reconstruction method, comprising:
acquiring a plurality of projection images of an inspection object, wherein the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
reconstructing a CT image of the examination object from the plurality of new projection images and the plurality of projection images.
2. The method of claim 1, wherein the new projection image is a projection image corresponding to an omnidirectional gantry angle or a projection image corresponding to a middle gantry angle of adjacent ones of the different gantry angles;
accordingly, reconstructing a CT image of the examination object from the plurality of new projection images comprises:
if the plurality of new projection images are projection images corresponding to the omnidirectional gantry angles, reconstructing a CT image of the inspection object according to the plurality of new projection images by using a preset reconstruction algorithm; alternatively, the first and second electrodes may be,
correspondingly, the reconstructing a CT image of the examination object from the plurality of new projection images and the plurality of projection images comprises:
and if the new projection images are projection images corresponding to the middle frame angle of the adjacent frame angles in the different frame angles, reconstructing the CT image of the inspection object according to the new projection images and the projection images by using the preset reconstruction algorithm.
3. The method of claim 1, wherein prior to inputting the projection image into an image processing model to obtain a new projection image, further comprising:
acquiring a projection image set, the projection image set comprising: a plurality of projection images corresponding to adjacent gantry angles, a projection image corresponding to a middle gantry angle of each adjacent gantry angle, or a projection image corresponding to an omnidirectional gantry angle, wherein each projection image includes parameter information between an inspection object and the CT scanner;
training a preset initial image processing model by taking the projection images corresponding to the plurality of adjacent frame angles as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle as a training result to generate the image processing model; alternatively, the first and second electrodes may be,
and training a preset initial image processing model by using the projected images corresponding to the plurality of adjacent frame angles as training data and the projected images corresponding to the omnidirectional frame angles as training results so as to generate the image processing model.
4. The method of claim 3, wherein after acquiring the set of projection images, further comprising:
dividing the projection image set to divide the projection image set into a training set and a check set;
correspondingly, the training a preset initial image processing model to generate the image processing model includes:
training a preset initial image processing model by taking the projection images corresponding to a plurality of adjacent frame angles in the training set and the checking set as training data and the projection image corresponding to the middle frame angle of each adjacent frame angle in the training set and the checking set as a training result to generate the image processing model; alternatively, the first and second electrodes may be,
and training a preset initial image processing model by using the projection images corresponding to a plurality of adjacent frame angles in the training set and the calibration set as training data and the projection images corresponding to all-directional frame angles in the training set and the calibration set as training results to generate the image processing model.
5. The method of claim 4, wherein after the dividing the set of projection images, further comprising:
acquiring a test set corresponding to the projection image set;
and testing the image processing model by using the test set to determine the accuracy of the image processing model.
6. The method of claim 3, wherein the parameter information comprises: the distance between the source and the detector in a CT scanner and the position of the center of rotation of the CT scanner.
7. The method of any of claims 1 or 3-5, wherein the image processing model is a three-dimensional image processing model and the three-dimensional image processing model is a three-dimensional deep learning network model.
8. A CT image reconstruction apparatus, comprising:
the system comprises an image acquisition module, a data acquisition module and a data acquisition module, wherein the image acquisition module is used for acquiring a plurality of projection images of an inspection object, the plurality of projection images are generated according to scanning data acquired by a CT scanner under different frame angles, and each projection image corresponds to one frame angle in the different frame angles;
the image processing module is used for inputting the plurality of projection images into an image processing model to obtain a plurality of new projection images;
an image reconstruction module for reconstructing a CT image of the examination object from the plurality of new projection images; alternatively, the first and second electrodes may be,
and the image reconstruction module is also used for reconstructing a CT image of the checked object according to the plurality of new projection images and the plurality of projection images.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the CT image reconstruction method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a CT image reconstruction method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010429907.5A CN111627081B (en) | 2020-05-20 | 2020-05-20 | CT image reconstruction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010429907.5A CN111627081B (en) | 2020-05-20 | 2020-05-20 | CT image reconstruction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111627081A true CN111627081A (en) | 2020-09-04 |
| CN111627081B CN111627081B (en) | 2023-06-20 |
Family
ID=72259097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010429907.5A Active CN111627081B (en) | 2020-05-20 | 2020-05-20 | CT image reconstruction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111627081B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509091A (en) * | 2020-12-10 | 2021-03-16 | 上海联影医疗科技股份有限公司 | Medical image reconstruction method, apparatus, device and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180293762A1 (en) * | 2017-04-05 | 2018-10-11 | General Electric Company | Tomographic reconstruction based on deep learning |
| CN109157239A (en) * | 2018-10-31 | 2019-01-08 | 上海联影医疗科技有限公司 | Position scan method, CT scanning method, device, equipment and the medium of image |
| US20200020140A1 (en) * | 2018-07-10 | 2020-01-16 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for computed tomography image reconstruction |
-
2020
- 2020-05-20 CN CN202010429907.5A patent/CN111627081B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180293762A1 (en) * | 2017-04-05 | 2018-10-11 | General Electric Company | Tomographic reconstruction based on deep learning |
| US20200020140A1 (en) * | 2018-07-10 | 2020-01-16 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for computed tomography image reconstruction |
| CN109157239A (en) * | 2018-10-31 | 2019-01-08 | 上海联影医疗科技有限公司 | Position scan method, CT scanning method, device, equipment and the medium of image |
Non-Patent Citations (2)
| Title |
|---|
| 吴清江等: "基于卷积神经网络的有限视角CT重建", 《电脑知识与技术》 * |
| 王小强等: "前门控大螺距扫描在双源CT冠状动脉成像中的应用", 《济宁医学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509091A (en) * | 2020-12-10 | 2021-03-16 | 上海联影医疗科技股份有限公司 | Medical image reconstruction method, apparatus, device and medium |
| CN112509091B (en) * | 2020-12-10 | 2023-11-14 | 上海联影医疗科技股份有限公司 | Medical image reconstruction method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111627081B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697741B (en) | PET image reconstruction method, device, equipment and medium | |
| CN106491151B (en) | PET image acquisition method and system | |
| US9775582B2 (en) | Medical image photographing apparatus and method of processing medical image | |
| CN109754447A (en) | Image generating method, device, equipment and storage medium | |
| US11670017B2 (en) | Systems and methods for reprojection and backprojection via homographic resampling transform | |
| CN108601572B (en) | X-ray imaging system and method for constructing two-dimensional X-ray image | |
| US11941786B2 (en) | Image noise reduction method and device | |
| US8655040B2 (en) | Integrated image registration and motion estimation for medical imaging applications | |
| CN111080584A (en) | Quality control method for medical image, computer device and readable storage medium | |
| KR20240013724A (en) | Artificial Intelligence Training Using a Multipulse X-ray Source Moving Tomosynthesis Imaging System | |
| Shi et al. | Review of CT image reconstruction open source toolkits | |
| CN108742679B (en) | Nodule detection apparatus and method | |
| US10896503B2 (en) | Identification of areas of interest in imaging applications | |
| Montoya et al. | Reconstruction of three‐dimensional tomographic patient models for radiation dose modulation in CT from two scout views using deep learning | |
| CN111627081B (en) | CT image reconstruction method, device, equipment and medium | |
| CN113989231A (en) | Method and device for determining kinetic parameters, computer equipment and storage medium | |
| CN111583354B (en) | Training method of medical image processing unit and medical image motion estimation method | |
| WO2022026661A1 (en) | Systems and methods for image denoising via adversarial learning | |
| JP7267000B2 (en) | Medical image processing device, nuclear medicine diagnosis device, medical image processing method, and learning device | |
| Shamul et al. | Change detection in sparse repeat CT scans with non-rigid deformations | |
| US20240046534A1 (en) | Systems and methods for imaging | |
| CN112561972B (en) | Medical image registration method | |
| US20240090863A1 (en) | Medical image processing method, apparatus, and system | |
| CN113520426B (en) | Coaxiality measuring method, medical equipment rack adjusting method, equipment and medium | |
| Li et al. | A novel method of micro-tomography geometric angle calibration with random phantom |
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 |