CN112037147B - Medical image noise reduction method and device - Google Patents
Medical image noise reduction method and device Download PDFInfo
- Publication number
- CN112037147B CN112037147B CN202010909648.6A CN202010909648A CN112037147B CN 112037147 B CN112037147 B CN 112037147B CN 202010909648 A CN202010909648 A CN 202010909648A CN 112037147 B CN112037147 B CN 112037147B
- Authority
- CN
- China
- Prior art keywords
- image
- pharmacokinetic parameter
- pet
- pixel point
- denoising
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000009467 reduction Effects 0.000 title claims abstract description 27
- 238000012545 processing Methods 0.000 claims description 16
- 238000012905 input function Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000002595 magnetic resonance imaging Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 11
- 238000002591 computed tomography Methods 0.000 description 10
- 238000002059 diagnostic imaging Methods 0.000 description 8
- 229940079593 drug Drugs 0.000 description 8
- 239000003814 drug Substances 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 210000000056 organ Anatomy 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 239000000126 substance Substances 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 230000036267 drug metabolism Effects 0.000 description 6
- 230000002503 metabolic effect Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 230000004060 metabolic process Effects 0.000 description 5
- 230000037323 metabolic rate Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 3
- 239000008103 glucose Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000001727 in vivo Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 229940121896 radiopharmaceutical Drugs 0.000 description 2
- 239000012217 radiopharmaceutical Substances 0.000 description 2
- 230000002799 radiopharmaceutical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- AOYNUTHNTBLRMT-SLPGGIOYSA-N 2-deoxy-2-fluoro-aldehydo-D-glucose Chemical compound OC[C@@H](O)[C@@H](O)[C@H](O)[C@@H](F)C=O AOYNUTHNTBLRMT-SLPGGIOYSA-N 0.000 description 1
- ZCXUVYAZINUVJD-UKFBFLRUSA-N 2-deoxy-2-fluoro-alpha-D-glucose Chemical compound OC[C@H]1O[C@H](O)[C@H](F)[C@@H](O)[C@@H]1O ZCXUVYAZINUVJD-UKFBFLRUSA-N 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013170 computed tomography imaging Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000014113 dietary fatty acids Nutrition 0.000 description 1
- 230000029142 excretion Effects 0.000 description 1
- 229930195729 fatty acid Natural products 0.000 description 1
- 239000000194 fatty acid Substances 0.000 description 1
- 150000004665 fatty acids Chemical class 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004153 glucose metabolism Effects 0.000 description 1
- 230000005865 ionizing radiation Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 102000039446 nucleic acids Human genes 0.000 description 1
- 108020004707 nucleic acids Proteins 0.000 description 1
- 150000007523 nucleic acids Chemical class 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The application relates to a medical image denoising method and a device, wherein the medical image denoising method comprises the following steps: obtaining scanning data of a scanning object, reconstructing a medical image of the scanning object according to the scanning data, obtaining a pharmacokinetic parameter image according to the scanning data and/or the medical image, obtaining a reference image according to the medical image, and finally denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image. According to the application, the problems of inaccurate image characteristics and poor noise reduction effect obtained by calculation according to the pharmacokinetic parameter image due to higher noise level of the pharmacokinetic parameter image in the related technology are solved, and the noise of the pharmacokinetic parameter image is reduced while the focus contrast and the clear outline are maintained.
Description
Technical Field
The application relates to the technical field of medical images, in particular to a medical image noise reduction method and device.
Background
Clinical examination imaging techniques in the medical field require substances necessary for biological life metabolism, such as: glucose, protein, nucleic acid and fatty acid, short-lived radionuclide are marked, and after the radionuclide is injected into a human body, the situation of life metabolic activity is reflected through the aggregation of the substance in metabolism, so that the purpose of diagnosis is achieved. When the imaging device is used for analyzing the pharmacokinetic (Pharmacokinetic) parameter image of the metabolic model of the substance injected into the human body in vivo, the noise of the pharmacokinetic parameter image is often larger than that of the static image, so that the judgment of a focus and the judgment of the accuracy of the metabolic model are affected.
In the related art, noise reduction of a pharmacokinetic parameter image is generally achieved using image features of the pharmacokinetic parameter image itself, for example, distances between pixel points in the metabolic parameter image, similarities between pixel values, and the like. However, due to the high noise level of the pharmacokinetic parameter image itself, the image features calculated from the pharmacokinetic parameter image are not accurate enough.
At present, no effective solution is proposed for the problem of inaccurate image characteristics and poor noise reduction effect calculated according to the pharmacokinetic parameter image due to the high noise level of the pharmacokinetic parameter image in the related art.
Disclosure of Invention
The embodiment of the application provides a medical image noise reduction method, a device, an electronic device and a storage medium, which are used for at least solving the problems of inaccurate image characteristics and poor noise reduction effect, which are caused by higher noise level of a pharmacokinetic parameter image in the related technology.
In a first aspect, an embodiment of the present application provides a medical image denoising method, which is characterized in that the method includes:
Acquiring scanning data of a scanning object, and reconstructing a medical image of the scanning object according to the scanning data;
Obtaining a pharmacokinetic parameter image according to the scanning data and/or the medical image;
Acquiring a reference image according to the medical image;
And denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
In some of these embodiments, in addition to the above-described embodiments,
The scanning data are PET scanning data, and image reconstruction is carried out according to the PET scanning data to obtain at least two PET reconstructed images;
obtaining the pharmacokinetic parameter image according to the PET scanning data and/or PET reconstructed image;
And acquiring an image from the PET reconstructed image as the reference image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
In some of these embodiments, in addition to the above-described embodiments,
Selecting one pixel point from the reference image as a target pixel point, and taking the rest pixel points as reference pixel points;
Calculating the weight of the target pixel point according to the pixel value of the target pixel point and the pixel value of the reference pixel point;
sequentially taking each pixel point in the reference image as the target pixel point to obtain weights of all the pixel points;
And denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image.
In some of these embodiments, in addition to the above-described embodiments,
Selecting one pixel point from the reference image as a target pixel point, and taking the rest pixel points as reference pixel points;
calculating the weight of the target pixel point according to the distance value between the target pixel point and the reference pixel point;
sequentially taking each pixel point in the reference image as the target pixel point to obtain weights of all the pixel points;
And denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image.
In some of these embodiments, in addition to the above-described embodiments,
Dividing the reference image and the pharmacokinetic parameter image into a plurality of subareas, and selecting one subarea as a target area, wherein the target area comprises a plurality of pixel points;
Dividing adjacent areas of the target area into a plurality of reference areas, wherein each reference area at least comprises a pixel point;
Calculating the weight of the target area according to the distance value between the target area and the reference area;
taking each subarea in the reference image as the target area in turn, and obtaining the weight of all subareas in the reference image;
and denoising the subareas in the pharmacokinetic parameter image according to the weights of all subareas in the reference image to obtain a denoising-later pharmacokinetic parameter image.
In some of these embodiments, the obtaining a pharmacokinetic parameter image from the scan data and/or medical image comprises:
The pharmacokinetic parameter image is acquired from the scan data and/or medical image and an aortic input function.
In some of these embodiments, in addition to the above-described embodiments,
Performing image reconstruction on the PET scanning data according to the acquisition time sequence of the PET scanning data to obtain a PET reconstructed image with the time sequence;
And selecting the last PET reconstructed image from the PET reconstructed images with time sequence as the reference image.
In some of these embodiments, in addition to the above-described embodiments,
The scan data includes CT scan data and PET scan data;
performing image reconstruction according to the CT scanning data to obtain a CT reconstructed image;
Performing image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images;
obtaining a pharmacokinetic parameter image according to the PET scanning data and/or the PET reconstructed image;
and taking the CT reconstructed image as a reference image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
In some of these embodiments, in addition to the above-described embodiments,
The scan data includes MRI scan data and PET scan data;
performing image reconstruction according to the MRI scanning data to obtain an MRI reconstructed image;
Performing image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images;
obtaining a pharmacokinetic parameter image according to the PET scanning data and/or the PET reconstructed image;
And taking the MRI reconstructed image as a reference image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
In a second aspect, an embodiment of the present application provides a medical image noise reduction apparatus, which is characterized in that the apparatus includes: scanning module, rebuilding module and processing module:
The scanning module is used for acquiring scanning data of a scanning object;
the reconstruction module is used for reconstructing a medical image of a scanned object according to the scanning data;
The processing module comprises at least one processor and is used for obtaining a pharmacokinetic parameter image according to the scanning data and/or the medical image, obtaining a reference image according to the medical image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the medical image denoising method according to the first aspect, when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, implements a medical image denoising method as described in the first aspect above.
Compared with the related art, the medical image denoising method provided by the embodiment of the application has the advantages that the scanning data of the scanning object are acquired, the medical image of the scanning object is reconstructed according to the scanning data, the pharmacokinetic parameter image is obtained according to the scanning data and/or the medical image, the reference image is acquired according to the medical image, and finally the pharmacokinetic parameter image after denoising is obtained according to the reference image, so that the problems that the image characteristics obtained by calculation according to the pharmacokinetic parameter image are inaccurate and the denoising effect is poor due to the high noise level of the pharmacokinetic parameter image in the related art are solved, and the noise of the pharmacokinetic parameter image is reduced while the focus contrast and the clear outline are maintained.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic view of an application environment of a medical image denoising method according to an embodiment of the present application;
FIG. 2 is a flow chart of a medical image denoising method according to an embodiment of the present application;
FIG. 3 is a flow chart of a medical image denoising method based on a PET device according to an embodiment of the present application;
FIG. 4 is a flow chart of yet another medical image denoising method according to an embodiment of the present application;
FIG. 5 is a block diagram of a hardware architecture of a medical image noise reduction terminal according to an embodiment of the present application;
fig. 6 is a block diagram of a medical image noise reduction device according to an embodiment of the present application.
Detailed Description
The present application will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present application without making any inventive effort, are intended to fall within the scope of the present application. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the application can be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," and similar referents in the context of the application are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in connection with the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means greater than or equal to two. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
The medical image denoising method provided by the application can be applied to an application environment shown in fig. 1, and fig. 1 is a schematic diagram of the application environment of the medical image denoising method according to the embodiment of the application, as shown in fig. 1. Among other things, the medical device 100 may include a scanner 110, a network 120, one or more terminals 130, a processing engine 140, and a memory 150. All components in the medical device 100 may be interconnected by a network 120, and the scanner 110 may scan a scan object and generate scan data related to the scan object. In some embodiments, the scanner 110 may be a medical imaging device, such as an electronic computed tomography device (Computed Tomography, abbreviated as CT), a positron emission computed tomography (Positron Emission Computed Tomography, abbreviated as PET) device, a magnetic resonance imaging device (Magnetic Resonance Imaging, abbreviated as MRI), or the like, or any combination thereof, such as a PET-CT device or a CT-MRI device. The processing engine 140 may process data and/or information obtained from the scanner 110, the terminal 130, and/or the memory 150. In some embodiments, the processing engine 140 may be a single server or a group of servers. The server farm may be centralized or distributed. In some embodiments, processing engine 140 may be local or remote. For example, processing engine 140 may access information and/or data stored in scanner 110, terminal 130, and/or memory 150 via network 120. As another example, processing engine 140 may be directly connected to scanner 110, terminal 130, and/or memory 150 to access stored information and/or data. In some embodiments, processing engine 140 may be implemented on a cloud platform.
The embodiment provides a medical image noise reduction method. Fig. 2 is a flowchart of a medical image denoising method according to an embodiment of the present application, as shown in fig. 2, the method comprising the steps of:
Step S210, acquiring scanning data of a scanning object, and reconstructing a medical image of the scanning object according to the scanning data.
In this embodiment, the scan subject is a patient that is to be examined by a medical imaging device, and the patient has been injected with a radionuclide-labeled drug in vivo prior to scanning. The scanning object may be placed on a workbench of the medical imaging device, and the scanning data is obtained by scanning a region of interest of the scanning object by a scanner of the medical imaging device, and in particular, the region of interest may be an organ such as a heart, a kidney or a lung of the scanning object.
The scan data may originate from a single modality medical imaging device or from a multi-modality medical imaging device. In case the scan data originates from a single modality medical imaging device, the scan data is functional imaging data of the scan object, and in case the scan data originates from a multi-modality medical imaging device, the scan data comprises functional imaging data and anatomical imaging data of the scan object.
Further, after obtaining the scan data, a medical image of the scan object may also be reconstructed from the scan data to obtain a distribution of the shape of the organ and/or the drug metabolism in the medical image.
Step S220, obtaining a pharmacokinetic parameter image according to the scan data and/or the medical image.
In some of these embodiments, the pharmacokinetic parameter images may be obtained by a neural network model, in particular by inputting a plurality of medical images into a trained neural network model.
In some of these embodiments, pharmacokinetic parameter images may be obtained from the scan data, in particular: dividing the scanning data into a plurality of scanning data sets according to the sequence of the generation time, determining the parameters of the pharmacokinetic parameter image according to the data difference among the plurality of scanning data sets, and iteratively reconstructing the pharmacokinetic parameter image according to the parameters of the pharmacokinetic parameter image.
The pharmacokinetic is the speed of drug transport and transformation in the scanned object, the transport includes absorption, distribution and excretion, the transformation is metabolism, alternatively, the pharmacokinetic parameter image in this embodiment is an image of metabolism of a substance in the scanned object obtained by calculating the pharmacokinetic parameter, and in the pharmacokinetic parameter image, the numerical value of a pixel point may be the metabolism rate of the substance in the scanned object, for example, the glucose metabolism rate.
Further, the pixel values in the reconstructed medical image may reflect the distribution of the drug in the scanned object, so that the pharmacokinetic parameter image in this embodiment may be obtained from the medical image, specifically, the pharmacokinetic parameter image is determined according to the pixel values of the plurality of medical images and the pixel value differences between the plurality of medical images. Furthermore, the pharmacokinetic parameter image can also be obtained by scanning the data and the medical image, in particular: dividing the scanning data into a plurality of scanning data sets according to the sequence of the generation time, respectively reconstructing according to the scanning data in the data sets, determining the parameters of the pharmacokinetic parameter image according to the data difference among the plurality of scanning data sets, and iteratively reconstructing a first pharmacokinetic parameter image according to the parameters of the pharmacokinetic parameter image; and obtaining a second pharmacokinetic parameter image according to the medical image, and combining the first pharmacokinetic parameter image with the second pharmacokinetic parameter image to obtain the pharmacokinetic parameter image. To improve the accuracy of the pharmacokinetic parameter images.
Step S230, acquiring a reference image according to the medical image.
The organ or lesion in the reference image of the present embodiment is clearer with respect to the pharmacokinetic parameter image, and the noise in the reference image is lower. One frame of image with lower noise can be selected from the medical images to be used as a reference image, or a plurality of frames of images can be selected from the medical images to be synthesized to obtain the reference image. The reference image obtained by the medical image may be an image including only the focus and organ of the scanned object, or may be an image reflecting the condition of drug metabolism, and when the reference image may reflect the condition of drug metabolism, the pixels of the reference image may represent the standard uptake value (Standardized Uptake Value) of the drug.
In some of these embodiments, the reference image may be obtained by a neural network model, in particular by inputting a plurality of medical images into a trained neural network model.
Step S240, denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
Specifically, the pharmacokinetic parameter image may be noise reduced by a pixel distribution or pixel values in the reference image in the present embodiment.
Through the steps S210 to S240, the pharmacokinetic parameter image is noise reduced according to the reference image with lower noise and higher definition, so that the problems that the image characteristics obtained by calculation according to the pharmacokinetic parameter image are inaccurate and the noise reduction effect is poor due to higher noise level of the pharmacokinetic parameter image in the related technology are solved, and the noise of the pharmacokinetic parameter image is reduced while the focus contrast and the clear outline are maintained.
In some of these embodiments, fig. 3 is a flow chart of a method of PET device-based medical image denoising, as shown in fig. 3, according to an embodiment of the present application, the method comprising the steps of:
step S310, the scanning data are PET scanning data, and image reconstruction is carried out according to the PET scanning data, so that at least two PET reconstructed images are obtained.
In the case of a PET device, the PET reconstructed image is specifically that a radionuclide-labeled drug decays in a scanned object and generates positrons, and then the positrons generated after the decays travel about several tenths of a millimeter to several millimeters and meet electrons in the scanned object to generate a pair of photons with opposite directions and the same energy, and the pair of photons pass through tissues of the scanned object and are received by a detector of a PET system to obtain imaging data, and according to the imaging data, a medical image capable of reflecting the distribution of the drug in the scanned object is generated through a corresponding image reconstruction algorithm.
The PET reconstructed images obtained in this embodiment are medical images of the scan object, and the number of PET reconstructed images is at least two because of the need to observe the metabolic condition of the drug in the scan object.
Step S320, obtaining a pharmacokinetic parameter image according to the PET scanning data and/or the PET reconstruction image.
The pharmacokinetic parameter image can be obtained by analyzing and calculating PET scanning data, can be obtained by synthesizing and calculating at least two PET reconstruction images, and can be obtained simultaneously according to the calculation results of the PET scanning data and the PET reconstruction images.
Specifically, the process of obtaining the pharmacokinetic parameter image through the PET reconstructed image may be implemented based on a Patlak model, a Logan model, a1 t/2 ti and other pharmacokinetic parameter models, and based on the pharmacokinetic parameter model, the metabolic rate of the corresponding substance in the body may be obtained through calculation of the metabolic rate of the radiopharmaceutical in the scanning process, for example, in the case that the radiopharmaceutical is fluorodeoxyglucose (Fludeoxyglucose, abbreviated as FDG), the metabolic rate of glucose in the body of the scanned subject may be obtained, and further the pharmacokinetic parameter image may be obtained.
Step S330, an image is obtained from the PET reconstructed image as a reference image, and the pharmacokinetic parameter image is subjected to noise reduction according to the reference image, so as to obtain a noise-reduced pharmacokinetic parameter image.
The noise of the reference image obtained from the PET reconstructed image is smaller, and the focus is clearer. Furthermore, a plurality of PET reconstructed images with smaller noise can be selected, and the reconstructed images are synthesized to obtain a final reference image.
Through the steps S310 to S330, the pharmacokinetic parameter image and the reference image are obtained based on the scanning data of the PET equipment, and the pharmacokinetic parameter image is noise-reduced according to the reference image with smaller noise, so that the focus and the drug metabolism condition can be better observed, and the diagnosis efficiency of doctors is improved.
In some embodiments, in the process of realizing image noise reduction based on the scanning data of the PET equipment, the PET scanning data is subjected to image reconstruction according to the acquisition time sequence of the PET scanning data, so that a time-sequence PET reconstructed image is obtained, and the last PET reconstructed image is selected from the time-sequence PET reconstructed images to be used as a reference image. For example, according to the acquisition time of PET scanning data, a PET static image of 10 frames and 2 minutes is obtained by reconstruction, and the last frame image is selected as a reference image. The time of the scanning data corresponding to the reference image is in the later stage of drug metabolism, so that the reference image is less influenced by the drug metabolism condition, the image is clearer, the noise is smaller, the noise reduction effect on the pharmacokinetic parameter image is better, meanwhile, the reference image is selected based on the acquired PET reconstructed image, the operation is simple and quick, and the noise reduction efficiency is improved.
In some of these embodiments, the pharmacokinetic parameter image is denoised by a weight relationship between individual pixels in the reference image. Specifically, selecting a pixel point from a reference image as a target pixel point, and taking the rest pixel points as reference pixel points, wherein the rest pixel points refer to all the pixel points except the target pixel point in the reference image; after obtaining the target pixel point and the reference pixel point, calculating the weight of the target pixel point according to the pixel value of the target pixel point and the pixel value of the reference pixel point, wherein in the embodiment, the weight calculation between the target pixel point and the reference pixel point can be realized through a k-Nearest Neighbor (KNN) in Non-Local mean filtering (n-Local Means, abbreviated as NLM), and the weight calculation can also be realized through cosine similarity, for example, when the difference between the pixel value of the target pixel point and the pixel value of the reference pixel point is large, the weight of the reference pixel point to the target pixel point is low; in this embodiment, the weight relationship of each pixel in the reference image needs to be calculated, so that each pixel in the reference image is sequentially taken as a target pixel to obtain weights of all the pixels; finally, denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image, specifically, denoising the pharmacokinetic parameter image according to the weights of all the pixel points in the reference image can be realized by the following formula 1:
p1=w1 p1+w2 p … … +wn pn equation 1
In formula 1, p1 is a target pixel point in the pharmacokinetic parameter image, p2 to pn are reference pixel points in the pharmacokinetic parameter image, and the pixel points in the pharmacokinetic parameter image correspond to the pixel points in the reference image, so that before the pharmacokinetic parameter image is subjected to noise reduction, the reference image and the pharmacokinetic parameter image are required to be registered, and w1 to wn are weights between the target pixel point and the reference pixel point, which are obtained after the pixel points in the reference image are calculated.
According to the embodiment, the weight of the target pixel point is calculated through the difference among the pixel values of each pixel point in the reference image, and the pharmacokinetic parameter image is noise-reduced according to the calculated weight, so that the noise in the pharmacokinetic parameter image can be reduced while the focus contrast and the contour in the pharmacokinetic parameter image are kept clear.
In some embodiments, the weights of the pixels in the reference image may also be obtained by the distance between the pixels. Specifically, selecting one pixel point from a reference image as a target pixel point, and taking the rest pixel points as reference pixel points; calculating the weight of the target pixel point according to the distance value between the target pixel point and the reference pixel point, for example, the weight of the target pixel point is lower when the distance between the reference pixel point and the target pixel point is longer, and the weight of the target pixel point is higher when the distance between the reference pixel point and the target pixel point is shorter; sequentially taking each pixel point in the reference image as a target pixel point to obtain weights of all the pixel points; and denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image. According to the method, the weight of the target pixel point is calculated through the distance difference between the target pixel point and the reference pixel point in the reference image, the pharmacokinetic parameter image is noise-reduced according to the calculated weight, and noise in the pharmacokinetic parameter image can be reduced while focus contrast and clear outline in the pharmacokinetic parameter image are maintained.
In some of these embodiments, fig. 4 is a flowchart of yet another medical image denoising method according to an embodiment of the present application, as shown in fig. 4, the method further comprising the steps of:
In step S410, the reference image and the pharmacokinetic parameter image are divided into a plurality of sub-areas, and one sub-area is selected as a target area, wherein the target area includes a plurality of pixel points.
When the reference image and the pharmacokinetic parameter image are divided, the reference image and the pharmacokinetic parameter image can be divided into a plurality of subareas with the same area, the reference image and the pharmacokinetic parameter image can be divided into subareas with different area sizes according to the position of the organ and/or the focus of the scanning object, and the shape of the subareas can be set according to the requirement, for example, the subareas can be set into regular polygons or irregular polygons. Meanwhile, in order to perform weight calculation, pixel points should be included in each sub-region.
In step S420, the adjacent regions of the target region are divided into a plurality of reference regions, and each reference region includes at least one pixel point.
In this embodiment, the reference areas are adjacent to the target area in position, each reference area may include one or more sub-areas, and the areas of the reference areas may be different in size or shape.
In step S430, the weight of the target area is calculated according to the distance value between the target area and the reference area.
In this embodiment, the weight of the target region may be calculated by NLM algorithm or cosine similarity. Specifically, the larger the distance between the target area and the reference area, the smaller the weight, and the larger the distance between the target area and the reference area.
Step S440, taking each sub-region in the reference image as a target region, and calculating the weight of each target region, so as to obtain the weights of all the reference image sub-regions.
And S450, denoising the subareas in the pharmacokinetic parameter image according to the weights of all the reference image subareas to obtain a denoised pharmacokinetic parameter image.
And recalculating the pixel value of each sub-region in the pharmacokinetic parameter image by referring to the weight of each sub-region in the image, so as to obtain the pharmacokinetic parameter image after noise reduction.
Through the steps S410 to S450, the embodiment divides the reference image and the pharmacokinetic parameter image into a plurality of sub-areas, and calculates the weight according to the distance between the sub-areas, so that the calculation steps can be simplified, and the speed of denoising the pharmacokinetic parameter image can be increased.
In some of these embodiments, the process of obtaining the pharmacokinetic parameter image from the scan data and/or the medical image is: a pharmacokinetic parameter image is acquired from the scan data and/or the medical image and the aortic input function. Wherein the aortic input function is as shown in equation 2:
In formula 2, C T (t) is each frame of image, C P (t) is an aortic input function, K i is a metabolic rate of a substance in the scanned object, for example, a glucose metabolic rate, b is an offset, t represents a metabolic time, and t * represents a time when the drug reaches an equilibrium state in the body. Through calculation of the parameter K i, a pharmacokinetic parameter image can be obtained, and the pixel value in the pharmacokinetic parameter image is the value of the parameter K i.
In some embodiments, the scan data includes CT scan data and PET scan data, specifically, a tube is disposed on a gantry of the CT imaging apparatus, the tube emits X-rays, and the X-rays are received by a detector after passing through a scan object to form CT scan data; the computer equipment receives the CT scanning data, and performs image reconstruction according to the CT scanning data to obtain a CT reconstructed image; performing image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images; obtaining a pharmacokinetic parameter image according to PET scanning data and/or PET reconstruction images; and taking the CT reconstructed image as a reference image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image. In this embodiment, the low-noise CT reconstructed image is used as a reference image, and the pharmacokinetic parameter image obtained by the PET reconstructed image is noise-reduced, and because the organ boundary is clearer in the CT reconstructed image, the organ contour of the corrected pharmacokinetic parameter image is clearer.
In some of these embodiments, the scan data includes MRI scan data and PET scan data; performing image reconstruction according to the MRI scanning data to obtain an MRI reconstructed image; performing image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images; obtaining a pharmacokinetic parameter image according to PET scanning data and/or PET reconstruction images; taking the MRI reconstructed image as a reference image, and denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image. In particular, MRI imaging can obtain a high contrast, sharp image of the interior of a scanned object without damage and without ionizing radiation. Because the resolution of the MRI image is higher, the noise reduction effect on the pharmacokinetic parameter image by using the MRI reconstructed image as a reference image is better.
It should be noted that the steps illustrated in the above-described flow or flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
The method embodiment provided by the application can be executed in a terminal, a computer or similar computing device. Taking the operation on the terminal as an example, fig. 5 is a block diagram of the hardware structure of the medical image noise reduction terminal according to the embodiment of the present application. As shown in fig. 5, the terminal 50 may include one or more processors 502 (only one is shown in fig. 5) (the processor 502 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 504 for storing data, and optionally, a transmission device 506 for communication functions and an input-output device 508. It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely illustrative and is not intended to limit the structure of the terminal. For example, terminal 50 may also include more or fewer components than shown in fig. 5, or have a different configuration than shown in fig. 5.
The memory 504 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a detection method of a newly appeared entity in an embodiment of the present application, and the processor 502 executes the computer program stored in the memory 504 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 504 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 504 may further include memory located remotely from the processor 502, which may be connected to the terminal 50 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 506 is used to receive or transmit data via a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the terminal 50. In one example, the transmission device 506 includes a network adapter (Network Interface Controller, simply referred to as a NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 506 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
The embodiment also provides a medical image noise reduction device, which is used for realizing the above embodiment and the preferred embodiment, and is not described in detail. As used below, the terms "module," "unit," "sub-unit," and the like may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 6 is a block diagram of a medical image noise reduction device according to an embodiment of the present application, and as shown in fig. 6, the device includes a scanning module 61, a reconstruction module 62, and a processing module 63:
a scanning module 61 for acquiring scanning data of a scanning object;
a reconstruction module 62 for reconstructing a medical image of the scan object from the scan data;
The processing module 63 includes at least one processor for obtaining a pharmacokinetic parameter image from the scan data and/or the medical image, for obtaining a reference image from the medical image, and for denoising the pharmacokinetic parameter image from the reference image to obtain a denoised pharmacokinetic parameter image.
In this embodiment, the processing module 63 performs noise reduction on the pharmacokinetic parameter image according to the reference image with low noise and high definition, so as to solve the problem that in the related art, due to the high noise level of the pharmacokinetic parameter image, the image features obtained by calculation according to the pharmacokinetic parameter image are inaccurate, and the noise reduction effect is poor, thereby realizing that the noise of the pharmacokinetic parameter image is reduced while the focus contrast and the contour are kept clear.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
The present embodiment also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
s1, acquiring scanning data of a scanning object, and reconstructing a medical image of the scanning object according to the scanning data;
S2, obtaining a pharmacokinetic parameter image according to the scanning data and/or the medical image;
s3, acquiring a reference image according to the medical image;
s4, denoising the pharmacokinetic parameter image according to the reference image to obtain a denoised pharmacokinetic parameter image.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
In addition, in combination with the medical image noise reduction method in the above embodiment, the embodiment of the present application may be implemented by providing a storage medium. The storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements any of the medical image denoising methods of the above embodiments.
It should be understood by those skilled in the art that the technical features of the above-described embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above-described embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (7)
1. A method of medical image denoising, the method comprising:
acquiring scanning data of a scanning object; the scanning data are PET scanning data;
Performing image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images;
obtaining a pharmacokinetic parameter image according to the PET scanning data and/or the PET reconstructed image;
And acquiring one or more images from the PET reconstructed image as reference images, and denoising the pharmacokinetic parameter image according to the reference images to obtain a denoised pharmacokinetic parameter image.
2. The method of medical image denoising according to claim 1,
Selecting one pixel point from the reference image as a target pixel point, and taking the rest pixel points as reference pixel points;
Calculating the weight of the target pixel point according to the pixel value of the target pixel point and the pixel value of the reference pixel point;
sequentially taking each pixel point in the reference image as the target pixel point to obtain weights of all the pixel points;
And denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image.
3. The method of medical image denoising according to claim 1,
Selecting one pixel point from the reference image as a target pixel point, and taking the rest pixel points as reference pixel points;
calculating the weight of the target pixel point according to the distance value between the target pixel point and the reference pixel point;
sequentially taking each pixel point in the reference image as the target pixel point to obtain weights of all the pixel points;
And denoising the pixel points in the pharmacokinetic parameter image according to the weights of all the pixel points to obtain a denoised pharmacokinetic parameter image.
4. The method of medical image denoising according to claim 1,
Dividing the reference image and the pharmacokinetic parameter image into a plurality of subareas, and selecting one subarea as a target area, wherein the target area comprises a plurality of pixel points;
Dividing adjacent areas of the target area into a plurality of reference areas, wherein each reference area at least comprises a pixel point;
Calculating the weight of the target area according to the distance value between the target area and the reference area;
taking each subarea in the reference image as the target area in turn, and obtaining the weight of all subareas in the reference image;
and denoising the subareas in the pharmacokinetic parameter image according to the weights of all subareas in the reference image to obtain a denoising-later pharmacokinetic parameter image.
5. The medical image denoising method according to claim 1, wherein the obtaining a pharmacokinetic parameter image from the scan data and/or medical image comprises:
The pharmacokinetic parameter image is acquired from the scan data and/or medical image and an aortic input function.
6. The method of medical image denoising according to claim 1,
Performing image reconstruction on the PET scanning data according to the acquisition time sequence of the PET scanning data to obtain a PET reconstructed image with the time sequence;
And selecting the last PET reconstructed image from the PET reconstructed images with time sequence as the reference image.
7. A medical image noise reduction device, the device comprising: scanning module, rebuilding module and processing module:
The scanning module is used for acquiring scanning data of a scanning object; the scanning data are PET scanning data;
The reconstruction module is used for carrying out image reconstruction according to the PET scanning data to obtain at least two PET reconstructed images;
The processing module comprises at least one processor and is used for obtaining a pharmacokinetic parameter image according to the PET scanning data and/or the PET reconstruction image, obtaining one or more images from the PET reconstruction image as reference images, and denoising the pharmacokinetic parameter image according to the reference images to obtain a denoised pharmacokinetic parameter image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010909648.6A CN112037147B (en) | 2020-09-02 | 2020-09-02 | Medical image noise reduction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010909648.6A CN112037147B (en) | 2020-09-02 | 2020-09-02 | Medical image noise reduction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112037147A CN112037147A (en) | 2020-12-04 |
| CN112037147B true CN112037147B (en) | 2024-05-14 |
Family
ID=73591180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010909648.6A Active CN112037147B (en) | 2020-09-02 | 2020-09-02 | Medical image noise reduction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112037147B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927318B (en) * | 2021-02-22 | 2022-04-22 | 明峰医疗***股份有限公司 | Noise reduction reconstruction method of low-dose PET image and computer readable storage medium |
| CN113724158B (en) * | 2021-08-13 | 2024-01-02 | 浙江大学 | Noise reduction method for dynamic contrast enhanced magnetic resonance imaging |
| CN113674254B (en) * | 2021-08-25 | 2024-05-14 | 上海联影医疗科技股份有限公司 | Medical image outlier recognition method, apparatus, electronic device, and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104166971A (en) * | 2013-05-17 | 2014-11-26 | 上海联影医疗科技有限公司 | CT image reconstruction method |
| CN104725507A (en) * | 2010-10-19 | 2015-06-24 | 梅奥医学教育和研究基金会 | Human antibodies and diagnostic and therapeutic uses thereof for the treatment of neurological disease |
| CN108898567A (en) * | 2018-09-20 | 2018-11-27 | 北京旷视科技有限公司 | Image denoising method, apparatus and system |
| CN110168612A (en) * | 2017-01-06 | 2019-08-23 | 皇家飞利浦有限公司 | The reconstruction control of standardized uptake values (SUV) guidance of result robustness for improving in positron emission tomography (PET) imaging |
| CN110298897A (en) * | 2019-04-03 | 2019-10-01 | 上海联影医疗科技有限公司 | System and method for positron emission tomography image reconstruction |
| CN111010495A (en) * | 2019-12-09 | 2020-04-14 | 腾讯科技（深圳）有限公司 | Video denoising processing method and device |
| CN111103275A (en) * | 2019-12-24 | 2020-05-05 | 电子科技大学 | PAT prior information assisted dynamic FMT reconstruction method based on CNN and adaptive EKF |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1880345A4 (en) * | 2005-05-06 | 2012-11-28 | Icad Inc | Method for tracking of contrast enhancement pattern for pharmacokinetic and parametric analysis in fast-enhancing tissues using high-resolution mri |
| US20080095414A1 (en) * | 2006-09-12 | 2008-04-24 | Vladimir Desh | Correction of functional nuclear imaging data for motion artifacts using anatomical data |
| JP5813994B2 (en) * | 2010-06-03 | 2015-11-17 | 株式会社東芝 | Medical image diagnostic apparatus and image reconstruction method |
| US11497459B2 (en) * | 2018-01-26 | 2022-11-15 | General Electric Company | Methods and system for optimizing an imaging scan based on a prior scan |
-
2020
- 2020-09-02 CN CN202010909648.6A patent/CN112037147B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104725507A (en) * | 2010-10-19 | 2015-06-24 | 梅奥医学教育和研究基金会 | Human antibodies and diagnostic and therapeutic uses thereof for the treatment of neurological disease |
| CN104166971A (en) * | 2013-05-17 | 2014-11-26 | 上海联影医疗科技有限公司 | CT image reconstruction method |
| CN110168612A (en) * | 2017-01-06 | 2019-08-23 | 皇家飞利浦有限公司 | The reconstruction control of standardized uptake values (SUV) guidance of result robustness for improving in positron emission tomography (PET) imaging |
| CN108898567A (en) * | 2018-09-20 | 2018-11-27 | 北京旷视科技有限公司 | Image denoising method, apparatus and system |
| CN110298897A (en) * | 2019-04-03 | 2019-10-01 | 上海联影医疗科技有限公司 | System and method for positron emission tomography image reconstruction |
| CN111010495A (en) * | 2019-12-09 | 2020-04-14 | 腾讯科技（深圳）有限公司 | Video denoising processing method and device |
| CN111103275A (en) * | 2019-12-24 | 2020-05-05 | 电子科技大学 | PAT prior information assisted dynamic FMT reconstruction method based on CNN and adaptive EKF |
Non-Patent Citations (1)
| Title |
|---|
| "Pharmacokinetic Evaluation of the Tau PET Radiotracer 18F-T807 (18F-AV-1451) in Human Subjects";Dustin W. Wooten.et al;《THE JOURNAL OF NUCLEAR MEDICINE》;第58卷(第3期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112037147A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741284B (en) | System and method for correcting respiratory motion-induced mismatches in PET imaging | |
| CN112037147B (en) | Medical image noise reduction method and device | |
| CN107638188B (en) | Image attenuation correction method and device | |
| CN109308728B (en) | Positron emission computed tomography image processing method and device | |
| US10213179B2 (en) | Tomography apparatus and method of reconstructing tomography image | |
| CN106456098B (en) | The generation method and system of decay pattern | |
| EP2399238B1 (en) | Functional imaging | |
| US20180249979A1 (en) | Simultaneous ct-mri image reconstruction | |
| US10796464B2 (en) | Selective image reconstruction | |
| EP3338636B1 (en) | An apparatus and associated method for imaging | |
| US10803354B2 (en) | Cross-modality image synthesis | |
| CN112419303B (en) | Neural network training method, system, readable storage medium and device | |
| CN111612689B (en) | Medical image processing method, medical image processing device, computer equipment and readable storage medium | |
| US20100284598A1 (en) | Image registration alignment metric | |
| US20180184992A1 (en) | System and method for medical imaging | |
| CN112690810B (en) | Scanning method and medical scanning system based on priori information | |
| CN111445550B (en) | Iterative reconstruction method, device and computer readable storage medium for PET image | |
| US10013778B2 (en) | Tomography apparatus and method of reconstructing tomography image by using the tomography apparatus | |
| US11270434B2 (en) | Motion correction for medical image data | |
| Hashimoto et al. | Deep learning-based PET image denoising and reconstruction: a review | |
| CN112017258A (en) | PET image reconstruction method, apparatus, computer device, and storage medium | |
| CN113674254B (en) | Medical image outlier recognition method, apparatus, electronic device, and storage medium | |
| CN113712584B (en) | PET scanning method, device, electronic device and storage medium | |
| CN106548473B (en) | A kind of method and device constructing phase image | |
| CN114862980A (en) | Scattering correction method, PET imaging method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co.,Ltd. Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |