CN113870178A - Plaque artifact correction and component analysis method and device based on artificial intelligence - Google Patents
Plaque artifact correction and component analysis method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN113870178A CN113870178A CN202110930360.1A CN202110930360A CN113870178A CN 113870178 A CN113870178 A CN 113870178A CN 202110930360 A CN202110930360 A CN 202110930360A CN 113870178 A CN113870178 A CN 113870178A
- Authority
- CN
- China
- Prior art keywords
- image
- artifact
- model
- plaque
- trained
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention discloses a plaque artifact correction and component analysis method and device based on artificial intelligence, and relates to the technical field of medical images. One embodiment of the method comprises: acquiring an artifact image of a target area; restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a plaque component discrimination result in the target area. This embodiment can improve the accuracy of plaque component detection.
Description
Technical Field
The invention relates to the technical field of medical imaging, in particular to a plaque artifact correction and component analysis method and device based on artificial intelligence.
Background
The analysis aiming at the cost of the vascular plaque has important significance for judging whether the patient is subsequently embolized. In the prior art, an original image with an artifact is generally used for directly judging the plaque component, and the judgment method has low accuracy due to the adverse effect of the artifact.
Disclosure of Invention
In view of this, embodiments of the present invention provide a plaque artifact correction and component analysis method and apparatus based on artificial intelligence, which improve the accuracy of detecting a plaque component by correcting an artifact image and performing a plaque component determination based on the corrected image and the artifact image together.
To achieve the above object, according to one aspect of the present invention, an artificial intelligence based plaque artifact correction and composition analysis method is provided.
The plaque artifact correction and component analysis method based on artificial intelligence comprises the following steps: acquiring an artifact image of a target area; restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a plaque component discrimination result in the target area.
Optionally, the artifact correction model is trained by the following steps for generating an antagonistic network: acquiring a normal image of the target region without artifacts and without lesions; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact; inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus; inputting the first image into the focus simulation model to obtain a third image with artifacts and focuses; and training the artifact correction model by taking the third image as a training sample and the second image as a label of the training sample.
Optionally, the artifact simulation model and the lesion simulation model are both generation confrontation networks; the artifact simulation model is formed by using an artifact sample as a training sample and using an artifact removal sample corresponding to the artifact sample as a label confrontation training; the focus simulation model is formed by training a focus sample as a training sample and a focus-free sample corresponding to the focus sample as a label.
Optionally, the artifact correction model is trained by the following steps for generating an antagonistic network: acquiring a systolic image of a target area and a diastolic image corresponding to the systolic image; and training the artifact correction model by using the systolic image as a training sample and the diastolic image as a label of the training sample.
Optionally, the detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a component discrimination result of the plaque in the target region includes: and inputting the corrected image and the artifact image into the plaque component discrimination model to obtain a plaque component discrimination result in the target region.
Optionally, the detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a component discrimination result of the plaque in the target region includes: and inputting the corrected image, the artifact image and a focus image detected from the artifact image in advance into the plaque component judgment model to obtain a plaque component judgment result in the target region.
In order to achieve the above object, according to another aspect of the present invention, an artificial intelligence based plaque artifact correction and composition analysis apparatus is provided.
The plaque artifact correction and component analysis device based on artificial intelligence of the embodiment of the invention can comprise: the artifact acquisition unit is used for acquiring an artifact image of the target area; the artifact correction unit is used for restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and the detection unit is used for detecting the corrected image and the artifact image according to a pre-trained plaque component distinguishing model to obtain a plaque component distinguishing result in the target area.
Optionally, the detection unit may be further configured to: inputting the corrected image and the artifact image into the plaque component discrimination model to obtain a plaque component discrimination result in the target region; alternatively, the corrected image, the artifact image, and a lesion image detected in advance from the artifact image are input to the plaque component determination model, and a result of determining the components of the plaque in the target region is obtained.
To achieve the above object, according to still another aspect of the present invention, there is provided an electronic apparatus.
An electronic device of the present invention includes: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the artificial intelligence-based plaque artifact correction and component analysis method provided by the invention.
To achieve the above object, according to still another aspect of the present invention, there is provided a computer-readable storage medium.
The invention relates to a computer readable storage medium, on which a computer program is stored, wherein the program is executed by a processor to implement the artificial intelligence-based plaque artifact correction and composition analysis method provided by the invention.
According to the technical scheme of the invention, the embodiment of the invention has the following advantages or beneficial effects:
after acquiring the artifact image of the target area, firstly, restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model so as to obtain a plaque component discrimination result in the target area. With the above steps, the accuracy of the detection of the plaque component can be improved by the corrected image from which the artifact is removed. Further, the corrected image, the artifact image, and the lesion image detected in advance from the artifact image can be input to the plaque component determination model together, which contributes to obtaining a more accurate plaque component determination result. In addition, the invention also provides an effective plaque component discrimination model training method, and specifically, firstly, a normal image without an artifact and a focus of the target region is obtained; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact, inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus, and inputting the first image into the focus simulation model to obtain a third image with the artifact and the focus; and finally, taking the third image as a training sample and the second image as a label training artifact correction model of the training sample. The training method can generate partial images required by training through a machine learning model, so that fewer original images are required, and the training effect of the model is better.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram illustrating the main steps of a plaque artifact correction and component analysis method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the training and using steps of an artifact correction model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a component of an artificial intelligence-based plaque artifact correction and composition analysis apparatus according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic structural diagram of an electronic device for implementing the artificial intelligence-based plaque artifact correction and composition analysis method according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments of the present invention and the technical features of the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic diagram illustrating main steps of a plaque artifact correction and composition analysis method based on artificial intelligence according to an embodiment of the present invention.
As shown in fig. 1, the plaque artifact correction and component analysis method based on artificial intelligence according to the embodiment of the present invention can be specifically executed according to the following steps:
step S101: acquiring an artifact image of the target area.
In the embodiment of the present invention, the target region may be any region to be determined of a human body, such as a coronary artery region or a cerebral artery region, and the target region is taken as a coronary artery region as an example for description. The artifact image refers to an original image acquired by a medical detection device such as CT (Computed Tomography), and it is understood that the original image generally has Artifacts (Artifacts), and the Artifacts refer to various forms of images appearing on the image without the existence of an original scanned object.
Step S102: and restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image.
In this step, the artifact correction model is a machine learning model for removing artifacts in the artifact image and repairing the artifact image, and preferably, the artifact correction model may be a generation countermeasure network gan (generic adaptive networks).
Fig. 2 is a schematic diagram of a training step and a using step of an artifact correction model in an embodiment of the present invention, and as shown in fig. 2, the training step of the artifact correction model is as follows: firstly, acquiring a normal image without artifacts and without focuses of the target area; then, inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact; inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus; inputting the first image into the focus simulation model to obtain a third image with artifacts and focuses; and finally, training the artifact correction model by taking the third image as a training sample and the second image as a label of the training sample. The training method can generate partial images required by training through the machine learning model, so that fewer original images are required, and the training effect of the model is better.
Preferably, the artifact simulation model and the lesion simulation model are both generated as an antagonistic network. Specifically, the artifact simulation model may be formed by using an artifact sample as a training sample and an artifact removal sample corresponding to the artifact sample as a label confrontation training; the focus simulation model can be formed by training by taking a focus sample as a training sample and taking a focus-free sample corresponding to the focus sample as a label.
In an optional technical solution, the artifact correction model may be further trained by the following steps: acquiring a systolic image of a target area and a diastolic image corresponding to the systolic image; and training the artifact correction model by using the systolic image as a training sample and the diastolic image as a label of the training sample. It can be understood that, for the systolic image and the diastolic image corresponding to each other, the artifact of the systolic image at the same position is often removed by the diastolic image, so that the two images can be used as training data of the artifact correction model.
After the artifact correction model is trained, the artifact image in step S101 may be input into the artifact correction model, so that a corrected image corresponding to the artifact image may be obtained.
Step S103: and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a plaque component discrimination result in the target area.
In this step, the plaque component discrimination model is a machine learning model for detecting blood vessel plaque components, and may generally include a convolutional Neural network cnn (convolutional Neural network) for extracting image features and a classification network for performing plaque component detection based on image features.
In practice, two ways of obtaining the components of the plaque may be used. In the first aspect, the corrected image and the artifact image are input to the plaque component determination model, and a result of determining the components of the plaque in the target region is obtained. Illustratively, the patch component discrimination result may be: whether or not it contains a calcified component, a lipid component, a fiber component and the ratio of each component. In a second aspect, the patch component discrimination model is input with the corrected image, the artifact image, and a lesion image (i.e., an image containing a lesion such as a patch) detected in advance from the artifact image, and a patch component discrimination result in the target region is obtained. Wherein, the focus image can be obtained by the following steps: firstly, a region where a focus is located is determined from an artifact image by using a predetermined focus detection algorithm, and then, an image of the region where the focus is located is extracted from the artifact image to obtain a focus image. It can be understood that the plaque component detection accuracy of the second method is higher because the lesion image focused on the plaque is detected by adding the plaque component discrimination model.
According to the technical scheme of the embodiment of the invention, after the artifact image of the target area is obtained, firstly, the artifact image is repaired by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model so as to obtain a plaque component discrimination result in the target area. With the above steps, the accuracy of the detection of the plaque component can be improved by the corrected image from which the artifact is removed. Further, the corrected image, the artifact image, and the lesion image detected in advance from the artifact image can be input to the plaque component determination model together, which contributes to obtaining a more accurate plaque component determination result. In addition, the invention also provides an effective plaque component discrimination model training method, and specifically, firstly, a normal image without an artifact and a focus of the target region is obtained; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact, inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus, and inputting the first image into the focus simulation model to obtain a third image with the artifact and the focus; and finally, taking the third image as a training sample and the second image as a label training artifact correction model of the training sample. The training method can generate partial images required by training through a machine learning model, so that fewer original images are required, and the training effect of the model is better.
It should be noted that, for the convenience of description, the foregoing method embodiments are described as a series of acts, but those skilled in the art will appreciate that the present invention is not limited by the order of acts described, and that some steps may in fact be performed in other orders or concurrently. Moreover, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no acts or modules are necessarily required to implement the invention.
To facilitate a better implementation of the above-described aspects of embodiments of the present invention, the following also provides relevant means for implementing the above-described aspects.
Referring to fig. 3, an artificial intelligence based plaque artifact correction and component analysis apparatus 300 according to an embodiment of the present invention may include: an artifact acquisition unit 301, an artifact correction unit 302, and a detection unit 303.
The artifact obtaining unit 301 is configured to obtain an artifact image of the target region; the artifact correction unit 302 is configured to repair the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; the detecting unit 303 is configured to detect the corrected image and the artifact image according to a pre-trained plaque component determination model, and obtain a component determination result of the plaque in the target region.
In an embodiment of the present invention, the detecting unit 303 may be further configured to: inputting the corrected image and the artifact image into the plaque component discrimination model to obtain a plaque component discrimination result in the target region; alternatively, the corrected image, the artifact image, and a lesion image detected in advance from the artifact image are input to the plaque component determination model, and a result of determining the components of the plaque in the target region is obtained.
In a specific application, the artifact correction model is used for generating an impedance network; the device 300 may further comprise a training unit for: acquiring a normal image of the target region without artifacts and without lesions; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact; inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus; inputting the first image into the focus simulation model to obtain a third image with artifacts and focuses; and training the artifact correction model by taking the third image as a training sample and the second image as a label of the training sample.
As a preferred scheme, the artifact simulation model and the lesion simulation model are used for generating an antagonistic network; the artifact simulation model is formed by using an artifact sample as a training sample and using an artifact removal sample corresponding to the artifact sample as a label confrontation training; the focus simulation model is formed by training a focus sample as a training sample and a focus-free sample corresponding to the focus sample as a label.
Furthermore, in an embodiment of the present invention, the training unit may be further configured to: acquiring a systolic image of a target area and a diastolic image corresponding to the systolic image; and training the artifact correction model by using the systolic image as a training sample and the diastolic image as a label of the training sample.
According to the technical scheme of the embodiment of the invention, after the artifact image of the target area is obtained, firstly, the artifact image is repaired by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model so as to obtain a plaque component discrimination result in the target area. With the above steps, the accuracy of the detection of the plaque component can be improved by the corrected image from which the artifact is removed. Further, the corrected image, the artifact image, and the lesion image detected in advance from the artifact image can be input to the plaque component determination model together, which contributes to obtaining a more accurate plaque component determination result. In addition, the invention also provides an effective plaque component discrimination model training method, and specifically, firstly, a normal image without an artifact and a focus of the target region is obtained; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact, inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus, and inputting the first image into the focus simulation model to obtain a third image with the artifact and the focus; and finally, taking the third image as a training sample and the second image as a label training artifact correction model of the training sample. The training method can generate partial images required by training through a machine learning model, so that fewer original images are required, and the training effect of the model is better.
Fig. 4 illustrates an exemplary system architecture 400 to which an artificial intelligence based plaque artifact correction and composition analysis method or an artificial intelligence based plaque artifact correction and composition analysis apparatus of embodiments of the invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405 (this architecture is merely an example, and the components included in a particular architecture may be adapted according to application specific circumstances). The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have installed thereon various communication client applications, such as a plaque component determination application (for example only).
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server that provides various services, such as a background server (for example only) that supports a plaque component determination application operated by a user using the terminal apparatuses 401, 402, 403. The backend server may process the received plaque detection request and the like and feed back the processing results (e.g., the detected specific plaque components — just an example) to the terminal devices 401, 402, 403.
The plaque artifact correction and component analysis method based on artificial intelligence according to the embodiment of the present invention is generally executed by the server 405, and accordingly, the plaque artifact correction and component analysis apparatus based on artificial intelligence is generally installed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The invention also provides the electronic equipment. The electronic device of the embodiment of the invention comprises: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the artificial intelligence-based plaque artifact correction and component analysis method provided by the invention.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use in implementing an electronic device of an embodiment of the present invention. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the computer system 500 are also stored. The CPU501, ROM 502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, the processes described in the main step diagrams above may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the main step diagram. In the above-described embodiment, the computer program can be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the central processing unit 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. 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 of the computer readable storage medium may include, but are not limited to: 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 present invention, 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. In the present invention, 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, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an artifact acquisition unit, an artifact correction unit, and a detection unit. The names of these units do not in some cases constitute a limitation on the unit itself, for example, the artifact acquisition unit may also be described as a "unit providing an artifact image to the artifact correction unit".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to perform steps comprising: acquiring an artifact image of a target area; restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a plaque component discrimination result in the target area.
According to the technical scheme of the embodiment of the invention, after the artifact image of the target area is obtained, firstly, the artifact image is repaired by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image; and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model so as to obtain a plaque component discrimination result in the target area. With the above steps, the accuracy of the detection of the plaque component can be improved by the corrected image from which the artifact is removed. Further, the corrected image, the artifact image, and the lesion image detected in advance from the artifact image can be input to the plaque component determination model together, which contributes to obtaining a more accurate plaque component determination result. In addition, the invention also provides an effective plaque component discrimination model training method, and specifically, firstly, a normal image without an artifact and a focus of the target region is obtained; inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact, inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus, and inputting the first image into the focus simulation model to obtain a third image with the artifact and the focus; and finally, taking the third image as a training sample and the second image as a label training artifact correction model of the training sample. The training method can generate partial images required by training through a machine learning model, so that fewer original images are required, and the training effect of the model is better.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A plaque artifact correction and component analysis method based on artificial intelligence is characterized by comprising the following steps:
acquiring an artifact image of a target area;
restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image;
and detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain a plaque component discrimination result in the target area.
2. The method of claim 1, wherein the artifact correction model is trained to generate an antagonistic network by:
acquiring a normal image of the target region without artifacts and without lesions;
inputting the normal image into a pre-trained artifact simulation model to obtain a first image with an artifact;
inputting the normal image into a pre-trained focus simulation model to obtain a second image with a focus;
inputting the first image into the focus simulation model to obtain a third image with artifacts and focuses;
and training the artifact correction model by taking the third image as a training sample and the second image as a label of the training sample.
3. The method of claim 2, wherein the artifact simulation model and the lesion simulation model are both generation countermeasure networks; wherein the content of the first and second substances,
the artifact simulation model is formed by using an artifact sample as a training sample and using an artifact removal sample corresponding to the artifact sample as a label confrontation training;
the focus simulation model is formed by training a focus sample as a training sample and a focus-free sample corresponding to the focus sample as a label.
4. The method of claim 1, wherein the artifact correction model is trained to generate an antagonistic network by:
acquiring a systolic image of a target area and a diastolic image corresponding to the systolic image;
and training the artifact correction model by using the systolic image as a training sample and the diastolic image as a label of the training sample.
5. The method of claim 1, wherein the detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain the component discrimination result of the plaque in the target region comprises:
and inputting the corrected image and the artifact image into the plaque component discrimination model to obtain a plaque component discrimination result in the target region.
6. The method of claim 1, wherein the detecting the corrected image and the artifact image according to a pre-trained plaque component discrimination model to obtain the component discrimination result of the plaque in the target region comprises:
and inputting the corrected image, the artifact image and a focus image detected from the artifact image in advance into the plaque component judgment model to obtain a plaque component judgment result in the target region.
7. The utility model provides a plaque artifact is revised and composition analysis device based on artificial intelligence which characterized in that includes:
the artifact acquisition unit is used for acquiring an artifact image of the target area;
the artifact correction unit is used for restoring the artifact image by using a pre-trained artifact correction model to obtain a corrected image corresponding to the artifact image;
and the detection unit is used for detecting the corrected image and the artifact image according to a pre-trained plaque component distinguishing model to obtain a plaque component distinguishing result in the target area.
8. The apparatus of claim 7, wherein the detection unit is further configured to:
inputting the corrected image and the artifact image into the plaque component discrimination model to obtain a plaque component discrimination result in the target region; alternatively, the first and second electrodes may be,
and inputting the corrected image, the artifact image and a focus image detected from the artifact image in advance into the plaque component judgment model to obtain a plaque component judgment result in the target region.
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 method of any one of claims 1-6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110930360.1A CN113870178A (en) | 2021-08-13 | 2021-08-13 | Plaque artifact correction and component analysis method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110930360.1A CN113870178A (en) | 2021-08-13 | 2021-08-13 | Plaque artifact correction and component analysis method and device based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870178A true CN113870178A (en) | 2021-12-31 |
Family
ID=78990529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110930360.1A Pending CN113870178A (en) | 2021-08-13 | 2021-08-13 | Plaque artifact correction and component analysis method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870178A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063641A (en) * | 2022-08-19 | 2022-09-16 | 青岛美迪康数字工程有限公司 | CT artifact identification method and device based on deep learning |
| CN116485937A (en) * | 2023-06-21 | 2023-07-25 | 吉林大学 | CT motion artifact eliminating method and system based on graph neural network |
-
2021
- 2021-08-13 CN CN202110930360.1A patent/CN113870178A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063641A (en) * | 2022-08-19 | 2022-09-16 | 青岛美迪康数字工程有限公司 | CT artifact identification method and device based on deep learning |
| CN116485937A (en) * | 2023-06-21 | 2023-07-25 | 吉林大学 | CT motion artifact eliminating method and system based on graph neural network |
| CN116485937B (en) * | 2023-06-21 | 2023-08-29 | 吉林大学 | CT motion artifact eliminating method and system based on graph neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107680684B (en) | Method and device for acquiring information | |
| CN109961491B (en) | Multi-mode image truncation compensation method, device, computer equipment and medium | |
| US10810735B2 (en) | Method and apparatus for analyzing medical image | |
| CN111627508B (en) | Medical image reading method and device and computer readable medium | |
| CN107729929B (en) | Method and device for acquiring information | |
| CN113870178A (en) | Plaque artifact correction and component analysis method and device based on artificial intelligence | |
| CN110176010B (en) | Image detection method, device, equipment and storage medium | |
| CN113902642B (en) | Medical image processing method and device, electronic equipment and storage medium | |
| US20130016884A1 (en) | Methods, apparatuses, and computer program products for identifying a region of interest within a mammogram image | |
| US20200245969A1 (en) | Ultrasound Needle Positioning System and Ultrasound Needle Positioning Method Utilizing Convolutional Neural Networks | |
| WO2021005613A1 (en) | Chest radiograph image analysis system and a method thereof | |
| CN109671036A (en) | A kind of method for correcting image, device, computer equipment and storage medium | |
| CN112581554B (en) | CT imaging method, device, storage equipment and medical imaging system | |
| CN113658175A (en) | Method and device for determining symptom data | |
| CN115456947A (en) | Deep learning-based acetabulum injury repair method | |
| WO2020078252A1 (en) | Method, apparatus and system for automatic diagnosis | |
| CN115736939A (en) | Atrial fibrillation disease probability generation method and device, electronic equipment and storage medium | |
| CN111325675A (en) | Image processing method, device, equipment and storage medium | |
| CN111353039A (en) | File class detection method and device | |
| CN112086155A (en) | Diagnosis and treatment information structured collection method based on voice input | |
| CN109493396B (en) | CT image display method, device, equipment and medium | |
| CN111738986A (en) | Fat attenuation index generation method and device and computer readable medium | |
| CN110910361A (en) | Intravascular stent based detection method and device | |
| US20130034289A1 (en) | Filter approach to catheter electrode detection and tracking | |
| CN116523914B (en) | Aneurysm classification recognition device, method, equipment and storage medium |
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 |