CN114677415A - Image registration method and device, computer equipment and readable storage medium - Google Patents
Image registration method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN114677415A CN114677415A CN202210237538.9A CN202210237538A CN114677415A CN 114677415 A CN114677415 A CN 114677415A CN 202210237538 A CN202210237538 A CN 202210237538A CN 114677415 A CN114677415 A CN 114677415A
- Authority
- CN
- China
- Prior art keywords
- image
- dynamic
- pet
- frame
- dynamic pet
- 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
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application relates to an image registration method, an image registration device, a computer device and a readable storage medium. The method comprises the following steps: acquiring respiratory data and initial dynamic PET data of an object to be detected in a first preset time period after applying a tracer, determining a corresponding multi-frame dynamic MR image in the first preset time period according to the respiratory data, acquiring a dynamic PET image corresponding to each frame dynamic MR image, obtaining a registered dynamic PET image through each frame dynamic PET image, and registering the multi-frame initial dynamic PET image based on the registered dynamic PET image to obtain the registered dynamic PET image. By adopting the method, the registered similar dynamic PET image can be obtained, and then the multi-frame initial dynamic PET image is registered based on the registered similar dynamic PET image, so that the registered dynamic PET image can embody the structural information and the obvious image characteristics, and the accuracy of the registration result of the dynamic PET image can be improved.
Description
Technical Field
The present application relates to the field of medical image processing technologies, and in particular, to an image registration method, an image registration apparatus, a computer device, and a readable storage medium.
Background
Kinetic parameter analysis based on dynamic Positron Emission Tomography (PET) can reveal biochemical processes of tracers, and provide a basis for clinical revealing of pathological mechanisms.
In order to analyze the biochemical process of the tracer, the tracer is injected into the detection imaging part of the object to be detected, then the initial PET image in a continuous period of time is acquired, and then the dynamic parameter analysis is carried out on the initial PET image. Because the body posture of the object to be measured is difficult to keep completely fixed for a long time, the initial PET images acquired at different time points generate displacement, and therefore, before the kinetic parameter analysis is performed, the initial PET images generally need to be subjected to registration processing, so that the accuracy of the quantification of the kinetic parameters is improved.
However, when the initial PET image is registered in the related art, there is a problem that the registration result is not accurate enough.
Disclosure of Invention
In view of the foregoing, it is necessary to provide an image registration method, an image registration apparatus, a computer device, and a readable storage medium.
In a first aspect, the present application provides an image registration method, including:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
Determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET data based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
In one embodiment, registering the multiple frames of initial dynamic PET images based on the registered dynamic-like PET images to obtain registered dynamic PET images includes:
performing time mapping on the initial dynamic PET data in a first preset time period based on each frame type dynamic PET image to obtain the mapped initial dynamic PET data of each frame type dynamic PET image;
reconstructing the mapping initial dynamic PET data of each frame type dynamic PET image to obtain a corresponding mapping initial dynamic PET image;
and registering the corresponding mapping initial dynamic PET image through the registered similar dynamic PET image to obtain a registered dynamic PET image.
In one embodiment, determining the registered motion-like PET image from the frame motion-like PET images comprises:
Acquiring a deformation field corresponding to each frame type dynamic MR image;
and registering the corresponding dynamic-like PET images according to the deformation fields corresponding to the dynamic MR images of the frames to obtain the registered dynamic-like PET images.
In one embodiment, acquiring a deformation field corresponding to each frame-like dynamic MR image includes:
determining a reference image based on the multi-frame sample MR images;
and respectively carrying out image registration on the dynamic MR images of each frame type through the reference image to obtain a deformation field corresponding to the dynamic MR images of each frame type.
In one embodiment, determining a plurality of frames of dynamic-like MR images corresponding to a first preset time period according to the respiration data includes:
and inputting the respiratory data into a prediction model to obtain a corresponding multi-frame dynamic MR image in a first preset time period.
In one embodiment, the method further includes:
acquiring multi-frame sample MR images and sample respiratory data in a second preset time period before the tracer is applied to the object to be detected;
and training the initial prediction model through the multi-frame sample MR image and the sample respiratory data to obtain the prediction model.
In one embodiment, acquiring a motion-like PET image corresponding to each frame of motion-like MR image includes:
Acquiring initial PET data in a first preset time period;
time mapping is carried out on each frame type dynamic MR image and the initial PET data in a first preset time period, and mapping PET data of each frame type dynamic MR image are obtained;
and reconstructing the mapping PET data to obtain a similar dynamic PET image corresponding to each frame of similar dynamic MR image.
In a second aspect, the present application provides an image registration apparatus, comprising:
the data acquisition module is used for acquiring respiratory data and initial dynamic PET data in a first preset time period after the tracer is applied to the object to be detected;
the first image determining module is used for determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
the second image determining module is used for acquiring the similar dynamic PET images corresponding to the frames of similar dynamic MR images and determining the registered similar dynamic PET images through the frames of similar dynamic PET images;
the registration module is used for registering the multi-frame initial dynamic PET images according to the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
In a third aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
Acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
In a fourth aspect, the present application provides a readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
The image registration method, the image registration device, the computer device and the readable storage medium are characterized in that the computer device obtains respiratory data and initial dynamic PET data in a first preset time period after a tracer is applied to an object to be detected, determines corresponding multi-frame dynamic MR images in the first preset time period according to the respiratory data, obtains similar dynamic PET images corresponding to the various frames of dynamic MR images, determines the registered similar dynamic PET images according to the various frames of dynamic PET images, and registers the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain the registered dynamic PET images; according to the method, the dynamic-like MR image can be directly obtained through the respiratory data, then the dynamic-like PET image with the tissue/organ structure characteristics of the imaging part is obtained based on the dynamic-like MR image and the initial dynamic PET data, and the multi-frame initial dynamic PET image is registered based on the registered dynamic-like PET image, so that the registered dynamic PET image can embody the structure information and the obvious image characteristics, and the accuracy of the registration result of the dynamic PET image can be improved.
Drawings
FIG. 1 is a diagram of an embodiment of an application environment of an image registration method;
FIG. 2 is a schematic flow chart diagram of a method for image registration in one embodiment;
FIG. 3 is a flowchart illustrating a method for registering a plurality of frames of initial dynamic PET images according to an embodiment;
FIG. 4 is a flowchart illustrating a method for obtaining a registered motion-like PET image from each frame of motion-like PET image according to another embodiment;
FIG. 5 is a schematic flow chart illustrating a method for obtaining a deformation field corresponding to each frame type of dynamic MR image according to another embodiment;
FIG. 6 is a diagram showing a plurality of frames of heterogeneous images during an image registration process in accordance with another embodiment;
FIG. 7 is a flowchart illustrating a method for obtaining a dynamic-like PET image corresponding to each frame of dynamic-like MR image according to another embodiment;
FIG. 8 is a graph of the correspondence between time points and sample MR data and respiration data for another embodiment;
FIG. 9 is a block diagram showing the structure of an image registration apparatus according to an embodiment;
fig. 10 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image registration method provided by the application can be applied to the image registration system shown in fig. 1, and can be applied to the medical image registration or medical image calibration scene. The image registration system comprises a scanning system and a computer device, wherein the scanning system comprises a medical scanning device and a tool capable of bearing an object to be measured, and the tool can be a scanning bed, a scanning frame, a scanning plate and the like. The communication connection between the computer device and the medical scanning device in the scanning system may be Wi-Fi, mobile network or bluetooth connection, etc. The medical scanning device may be an electronic computed tomography system, a computed radiography system, or a direct digital radiography system, a Magnetic Resonance (MR) scanning device, etc., and may also be a scanning system capable of acquiring various types of medical data; the computer device may be various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, but is not limited thereto. In practical application, an object to be detected can lie on the bearing tool in different postures, the medical scanning equipment can scan a target imaging part of the object to be detected to obtain scanning data, the medical scanning equipment sends the scanning data to the computer equipment, and the computer equipment reconstructs and analyzes the scanning data to finally realize image registration. Optionally, after the scanning of the medical scanning apparatus is finished, the magnetic resonance coil in the medical scanning apparatus may be moved away from the body of the object to be measured, and the carrying tool may be returned to its position. Optionally, the target imaging region may be a brain, a lung, an abdomen, a heart, a blood vessel, a joint, and other imaging regions of the object to be detected; the object to be measured can be a human body, an animal body and the like. In medicine, in order to provide basis for clinical revealing of pathological mechanisms, dynamic parameter analysis needs to be carried out on medical images obtained by scanning.
The dynamic parameter analysis can reveal the biochemical process of the tracer, so that the tracer needs to be applied to the object to be detected, then the object to be detected to which the tracer is applied is scanned to acquire a medical image, and then the dynamic parameter analysis is performed on the medical image acquired at the time. Optionally, the object to be tested is limited by the in vivo accumulation time characteristic of the tracer, therefore, in this embodiment, data of a certain time duration needs to be continuously collected, a dynamic medical image is generated after reconstruction, then, dynamic parameter analysis is performed on the dynamic medical image to reveal the biochemical process of the tracer, and further, medical care personnel can determine the pathological result of the object to be tested according to the biochemical process of the tracer. In an actual scene, a body posture of an object to be measured is difficult to keep complete for a long time, and an acquired dynamic medical image has deviation from the actual state, so that the dynamic medical image generally needs to be registered before being subjected to dynamic parameter analysis so as to improve the quantitative accuracy of dynamic parameters. The dynamic medical image may be a dynamic Positron Emission Tomography (PET) image, a Computed Tomography (CT) image, an MR image, or the like. In the present embodiment, however, the dynamic medical image is a dynamic PET image.
In one embodiment, as shown in fig. 2, an image registration method is provided, which is described by taking the method as an example applied to a computer device, and includes the following steps:
s100, respiratory data and initial dynamic PET data in a first preset time period after the tracer is applied to the object to be detected are obtained.
Specifically, before scanning any one or more imaging parts of the object to be detected, the medical staff may administer a certain amount of tracer to veins of the one or more imaging parts of the object to be detected, and as the tracer accumulates in tissues, a certain biochemical reaction may occur with tissues/organs of the imaging parts to which the tracer is administered in a certain time period, and during the biochemical reaction, tissues/organs of a lesion region may be clearly distinguished from tissues/organs of a non-lesion region, which can be reflected in a dynamic PET image.
Alternatively, during the biochemical reaction of the tissue/organ, the medical scanning device may scan the imaging region to which the tracer is applied to obtain the dynamic PET image, wherein the contrast of the dynamic PET image may significantly change with the accumulation of the tracer in the tissue/organ of the imaging region, but the longer the time is, the larger the contrast of the dynamic PET image is, and the contrast of the dynamic PET image may reach a peak value within a period of time, and thus, the specific time period includes a time point at which the contrast of the dynamic PET image reaches the peak value. Alternatively, the starting time point of the specific time period may be a time point at which the administration of the tracer is finished, and may also be a time point after the time point at which the administration of the tracer is finished. Optionally, the tracer may be a different nuclide drug, which is harmless to the object to be detected.
In practical applications, the medical scanning device may scan one or more imaging portions of the subject to be tested, where the tracer is administered, acquire initial PET data scanned within a first preset time period, and acquire respiratory data of the subject simultaneously with the acquisition of the initial PET data. The medical scanning equipment can send the initial PET data and the respiratory data acquired by scanning in the first preset time period to the computer equipment, and the computer equipment can reconstruct the initial PET data in a plurality of sub-time periods in the first preset time period to obtain a multi-frame dynamic PET image corresponding to the first preset time period. Each sub-period corresponds to one frame of dynamic PET image.
It should be noted that each frame of the dynamic PET image may correspond to the initial PET data in a sub-period of the first preset period. Optionally, the first preset time period may include a plurality of sub-time periods, where each sub-time period has a corresponding one-frame initial dynamic PET image; the corresponding time length of each sub-time period can be equal or unequal; the time length of the multiple sub-time periods combined together may be less than or equal to the time length corresponding to the first preset time period.
In addition, the computer device may perform static reconstruction on the initial PET data scanned by the medical scanning device to obtain a static PET image, but in this embodiment, the computer device reconstructs the initial PET data scanned by the medical scanning device into a dynamic PET image, and a dynamic reconstruction algorithm may be used when reconstructing the dynamic PET image. Wherein the contrast of the dynamic PET image is greater than the contrast of the static PET image. The dynamic reconstruction algorithm may be a back projection method, an iterative reconstruction algorithm, a filtered back projection method, a fourier transform method, and the like, which is not limited in this embodiment.
S200, determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data.
Specifically, the computer device may perform arithmetic operation, data conversion, analysis, data comparison and/or reconstruction, and the like on the respiratory data within the first preset time period to obtain a corresponding multi-frame dynamic MR image within the first preset time period. Or, the computer device may further perform preprocessing such as arithmetic operation, data conversion, analysis, data comparison and/or reconstruction on the respiratory data within the first preset time period, and then perform specific processing on the preprocessing result by using a specific algorithm to obtain a corresponding multi-frame dynamic MR image within the first preset time period. Alternatively, the arithmetic operation may be an addition operation, a subtraction operation, a division operation, a multiplication operation, an exponential operation, a logarithmic operation, and/or the like.
It should be noted that the lengths of the sub-periods corresponding to the frame-like dynamic MR images may be equal or unequal. Alternatively, the duration of the sub-period of each frame-like dynamic MR image may be greater than or equal to the duration of the sub-period of the initial dynamic PET image of the corresponding frame. Optionally, multiple frames of dynamic MR images may be acquired within a first preset time period; each frame-like dynamic MR image may be a dynamic MR image generated in a certain sub-period within a first preset period. Wherein, the sub-time period corresponding to each frame type dynamic MR image is different from the sub-time period corresponding to each frame dynamic PET image.
S300, acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image.
In the embodiment, the initial PET data in the first preset time period has a plurality of frames of dynamic PET-like images, and each frame of initial dynamic PET image has a corresponding dynamic PET-like image. In this embodiment, the initial PET data may also be referred to as dynamic PET data. Optionally, the duration of the sub-period of the initial dynamic PET image of each frame may be less than or equal to the duration of the sub-period of the dynamic PET image-like image of the corresponding frame.
It is understood that the computer device may perform mapping processing, conversion processing and/or analysis processing and the like on each frame type dynamic MR image and the dynamic PET image of the corresponding frame to obtain a dynamic PET image of each frame corresponding to each frame type dynamic MR image. Optionally, the mapping process may be understood as a process of performing operations such as superimposing or subtracting pixel values of two pixel points at the mapping position after mapping between pixel values of pixel points at corresponding positions in the dynamic-like MR image and the dynamic PET image with the same size. Alternatively, the conversion process may be understood as a process of performing an arithmetic operation on a preset value or a plurality of preset values and pixel values of pixel points at different positions in the dynamic-like MR image. The analysis processing can be understood as a process of analyzing the pixel resolution of each pixel point in the dynamic-like MR image.
Further, the computer device may use any one frame of dynamic MR image as a reference image, and perform image registration on each frame of dynamic PET image to obtain a registered dynamic PET image. The quasi-dynamic PET image can reflect the information of the boundary, the shape and the like of the tissue/organ of the imaging part of the object to be detected, namely, the quasi-dynamic PET image carries the structural information of the tissue/organ, and compared with other medical images, the quasi-dynamic PET image can reflect the obvious characteristic points in the image.
And S400, registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain the registered dynamic PET images. The multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
Further, the computer device can register the multi-frame initial dynamic PET images through the registered dynamic PET-like images carrying the tissue/organ structure information so as to improve the accuracy of the registration result of the dynamic PET images. The computer device can use the registered dynamic PET-like image as a reference image, and register each frame of initial dynamic PET image by using a registration algorithm to obtain a registered dynamic PET image. Optionally, the computer device may further perform arithmetic operation on the registered quasi-dynamic PET image and each frame of initial dynamic PET image, so as to register each frame of initial dynamic PET image, and obtain the registered dynamic PET image.
In this embodiment, the objects to be measured in the first preset time period are in almost the same posture. In actual processing, the dynamic PET image, the dynamic-like PET image, and the dynamic-like MR image may be the same size.
In the image registration method, the computer device may acquire respiratory data and initial dynamic PET data in a first preset time period after the tracer is applied to the object to be detected, determine a corresponding multi-frame dynamic MR image in the first preset time period according to the respiratory data, acquire a similar dynamic PET image corresponding to each frame of dynamic MR image, determine a registered similar dynamic PET image through each frame of dynamic PET image, and register the multi-frame initial dynamic PET image based on the registered similar dynamic PET image to obtain a registered dynamic PET image; according to the method, the dynamic-like MR image can be directly obtained through the respiratory data, then the dynamic-like PET image with the structural characteristics of the tissue/organ of the imaging part is obtained based on the dynamic-like MR image and the initial dynamic PET data, and the multi-frame initial dynamic PET image is registered based on the registered dynamic-like PET image, so that the registered dynamic PET image can embody the structural information and the obvious image characteristics, and the accuracy of the registration result of the dynamic PET image can be improved; meanwhile, the method can reduce the complexity of acquiring the dynamic MR images, and can also enable medical personnel to accurately acquire the pathological mechanism of the object to be detected from the registered dynamic PET images, so that the accuracy of the diagnosis and treatment method is further improved, and the object to be detected can be treated by adopting an effective treatment method in time.
As an embodiment, as shown in fig. 3, the step of registering multiple frames of initial dynamic PET images based on the registered similar dynamic PET image in S400 to obtain the registered dynamic PET image may be implemented by the following steps:
and S410, time mapping is carried out on the initial dynamic PET data in the first preset time period based on each frame type dynamic PET image, and the mapped initial dynamic PET data of each frame type dynamic PET image is obtained.
Specifically, each frame of dynamic PET image in the first preset time period corresponds to a part of the initial dynamic PET data, so the computer device may perform time mapping on each frame of dynamic PET image and each frame of initial dynamic PET data according to the sub-time period corresponding to each frame of dynamic PET image and the sub-time period corresponding to each frame of initial dynamic PET data, so as to obtain the mapped initial dynamic PET data of each frame of dynamic PET image.
And S420, reconstructing the mapping initial dynamic PET data of each frame type dynamic PET image to obtain a corresponding mapping initial dynamic PET image.
Specifically, the computer device may reconstruct the mapping initial dynamic PET data of each frame type of dynamic PET image by using a direct back projection method, an iterative method, or a two-dimensional fourier transform reconstruction method, to obtain a mapping initial dynamic PET image corresponding to each frame type of dynamic PET image.
For example, if there are two frames of dynamic PET images and four frames of initial dynamic PET images in the first preset time period, the two frames of dynamic PET images are dynamic PET image 1, dynamic PET image 2, the four frames of initial dynamic PET images are dynamic PET image 1, initial dynamic PET image 2, initial dynamic PET image 3, and initial dynamic PET image 4, respectively, where the sub-time period corresponding to dynamic PET image 1 is [0, 2], the sub-time period corresponding to dynamic PET image 2 is [2, 4], the sub-time period corresponding to initial dynamic PET image 1 is [0, 1], the sub-time period corresponding to initial dynamic PET image 2 is [1, 2], the sub-time period corresponding to initial dynamic PET image 3 is [2, 3], the sub-time period corresponding to initial dynamic PET image 4 is [3, 4] (the data in the interval all represent time points), the computer device may map the sub-time period [0 ] corresponding to initial dynamic PET image 1, 1] and the sub-period [1, 2] corresponding to the initial dynamic PET image 2 are mapped into the sub-period [0, 2] corresponding to the dynamic PET-like image 1, and the sub-period [2, 3] corresponding to the initial dynamic PET image 3 and the sub-period [3, 4] corresponding to the initial dynamic PET image 4 are mapped into the sub-period [2, 4] corresponding to the dynamic PET-like image 2, the initial dynamic PET image 1 and the initial dynamic PET image 2 are mapped to the dynamic PET image 1, and the initial dynamic PET image 3 and the initial dynamic PET image 4 are mapped to the dynamic PET image 2, respectively.
Or, if the sub-period corresponding to the quasi-dynamic PET image 1 in the first preset period is [0, 4], the sub-period corresponding to the quasi-dynamic PET image 2 is [5, 9], the sub-period corresponding to the initial dynamic PET image 1 is [0, 1.5], the sub-period corresponding to the initial dynamic PET image 2 is [2.5, 4], the sub-period corresponding to the initial dynamic PET image 3 is [5, 6.5], the sub-period corresponding to the initial dynamic PET image 4 is [7.5, 9] (the data in the interval all represent time points), the computer device may map the sub-period [0, 1.5] corresponding to the initial dynamic PET image 1 and the sub-period [2.5, 4] corresponding to the initial dynamic PET image 2 into the sub-period [0, 4] corresponding to the quasi-dynamic PET image 1, and map the sub-period [5, 6.5] corresponding to the initial dynamic PET image 3 and the sub-period [7.5 ] corresponding to the initial dynamic PET image 4, and 9] mapping to the sub-time periods [5 and 9] corresponding to the similar dynamic PET images 2, wherein the mapping initial dynamic PET image 1 and the mapping initial dynamic PET image 2 of the similar dynamic PET image 1, and the mapping initial dynamic PET image 3 and the mapping initial dynamic PET image 4 of the similar dynamic PET image 2 are respectively arranged in the corresponding sub-time periods [5 and 9 ].
In this embodiment, the durations of the sub-periods corresponding to the initial dynamic PET images of each frame may be equal; the duration of the sub-time period corresponding to each frame type dynamic PET image is greater than the duration of the corresponding sub-time period of each frame type initial dynamic PET image.
And S430, registering the corresponding mapping initial dynamic PET image through the registered similar dynamic PET image to obtain a registered dynamic PET image.
Specifically, each frame of dynamic PET image has a corresponding registered dynamic PET image. The computer device can respectively use the registered similar dynamic PET images of the frames as reference images, and register the mapping initial dynamic PET images corresponding to the registered similar dynamic PET images of the frames by adopting an image registration algorithm to obtain the registered dynamic PET images.
The image registration method can be used for registering the corresponding mapping initial dynamic PET image based on the registered quasi-dynamic PET image, so that the registered dynamic PET image can embody structural information and obvious image characteristics, and the accuracy of the registration result of the dynamic PET image can be improved; meanwhile, medical care personnel can accurately acquire the pathological mechanism of the object to be detected from the registered dynamic PET image through the method, the accuracy of the diagnosis and treatment method is further improved, and the object to be detected can be treated by adopting an effective treatment method in time.
As an embodiment, as shown in fig. 4, the step of determining the registered motion-like PET image from each frame of motion-like PET image in S300 may be implemented by the following steps:
And S310, acquiring a deformation field corresponding to each frame of dynamic MR image.
Specifically, the computer device may perform arithmetic operation, conversion, analysis and/or comparison on each frame type of dynamic MR image to obtain a deformation field corresponding to each frame type of dynamic MR image. In this embodiment, the image may be represented in the form of a matrix, and the size of the matrix may be the same as the size of the image. If the size of the image is 3 × 3, the size of the matrix is also 3 × 3, the data in the first row and the first column in the matrix may be the pixel values of the pixels in the first row and the first column in the image and the positions (1, 1) of the pixels in the first row and the first column, and the data in the first row and the second column in the matrix may be the pixel values of the pixels in the first row and the second column in the image and the positions (1, 2) of the pixels in the first row and the second column in the image, and the pixel values of other pixels in the image and the data in the corresponding positions in the matrix have a corresponding relationship.
It should be noted that the deformation field may be represented by a deformation field matrix, and the size of the deformation field matrix may be equal to the pixel matrix size of the dynamic-like MR image. Optionally, the values at different positions in the deformation field matrix may represent deformation values of corresponding pixels in the dynamic-like MR image.
As shown in fig. 5, the step of acquiring the deformation field corresponding to each frame-like dynamic MR image in S310 may include:
and S311, determining a reference image based on the multi-frame sample MR image.
Specifically, the medical scanning device may scan the imaging portion of the object to be tested, obtain sample MR data, and send the sample MR data to the computer device within a period of time before the medical staff administers a certain amount of tracer to one or more imaging portions of the object to be tested. The computer device can reconstruct the sample MR data in the time period to obtain a multi-frame sample MR image. Each frame of sample MR image has a corresponding sub-time period, and the time period of the combined sub-time periods corresponding to each frame of sample MR image is equal to the time period of the sample MR data acquired by the medical scanning equipment.
Wherein, the computer device can select any one frame of MR image from the multiple frames of sample MR images as a reference image. However, in this embodiment, the computer device may select one frame of the sample MR image corresponding to the sub-period closest to the start time point of the first preset period as the reference image. The relaxation properties of the tissue/organ may be carried in the corresponding sample MR data, that is, the T1WI sequence and/or the T2WI sequence, etc. may be included in the sample MR data. The T1WI sequence represents the nuclear magnetic resonance T1 sequence and the T2WI sequence represents the nuclear magnetic resonance T2 sequence.
And S312, respectively carrying out image registration on the dynamic MR images of each frame type through the reference image to obtain a deformation field corresponding to the dynamic MR images of each frame type.
It can be understood that the computer device may use an image registration algorithm to perform image registration on each frame type of dynamic MR image through the selected reference image, so as to obtain a deformation field corresponding to each frame type of dynamic MR image. The deformation field matrix corresponding to the deformation field may be equal to a difference between pixel values of each pixel point in the reference image and each frame-like dynamic MR image.
According to the embodiment, the deformation field corresponding to each frame type dynamic MR image can be obtained, and then the deformation field corresponding to each frame type dynamic MR image is used for conveniently registering each frame type dynamic PET image in a corresponding time period, so that the structure density of the similar dynamic MR image can be considered in the registering of the similar dynamic PET image, and the accuracy of the image registering result can be improved.
And S320, registering the corresponding dynamic-like PET images according to the deformation fields corresponding to the frame dynamic-like MR images to obtain the registered dynamic-like PET images.
Meanwhile, the computer device can adopt an image registration algorithm to register the corresponding dynamic-like PET image through the deformation field corresponding to each frame dynamic-like MR image, so as to obtain the registered dynamic-like PET image.
In this embodiment, the image registration algorithm may be an image gray-level-based matching algorithm or an image feature-based matching algorithm, and may also be another image matching algorithm, which is not limited in this embodiment. The matching algorithm based on the image gray level can be an average absolute difference algorithm, an absolute error sum algorithm, an error square sum algorithm, an average error square sum algorithm, a normalized product correlation algorithm, a sequential similarity algorithm and the like; the matching algorithm based on image features may be feature extraction, feature matching, model parameter estimation, image transformation, gray scale interpolation algorithm, and the like. Fig. 6 is a schematic diagram of a multi-frame dynamic-like MR image, a registered dynamic-like PET image, a dynamic PET image, and a registered dynamic PET image corresponding to an imaging portion of an object to be measured in an image registration process.
In the image registration method, the computer device may acquire respiratory data and multi-frame initial dynamic PET images within a first preset time period after the tracer is applied to the object to be detected, determine corresponding multi-frame dynamic MR images within the first preset time period according to the respiratory data, acquire similar dynamic PET images corresponding to the various frame dynamic MR images, obtain registered similar dynamic PET images through the various frame dynamic PET images, and register the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain the registered dynamic PET images; according to the method, the dynamic-like MR image can be directly obtained through the respiratory data, then the dynamic-like PET image with the structural characteristics of the tissue/organ of the imaging part is obtained based on the dynamic-like MR image and the initial dynamic PET data, and the multi-frame initial dynamic PET image is registered based on the registered dynamic-like PET image, so that the registered dynamic PET image can embody the structural information and the obvious image characteristics, and the accuracy of the registration result of the dynamic PET image can be improved; meanwhile, the method can also enable medical personnel to accurately acquire the pathological mechanism of the object to be detected from the registered dynamic PET image, further improve the accuracy of the diagnosis and treatment method, and can timely adopt an effective treatment method to treat the object to be detected.
As an embodiment, the step of determining, in S200, multiple frames of dynamic-like MR images corresponding to the first preset time period according to the respiration data may include: and inputting the respiratory data into a prediction model to obtain a corresponding multi-frame dynamic MR image in a first preset time period.
Specifically, the computer device may input the respiratory data of the first preset time period to the prediction model, and the prediction model outputs the corresponding multi-frame dynamic MR images within the first preset time period. The prediction model may be a pre-trained network model, and the prediction model is trained before the step in S200 is executed. The prediction model may be composed of at least one of a convolutional neural network model, a cyclic neural network model, and an antagonistic neural network model.
Before the step of inputting the respiratory data into the prediction model to obtain the corresponding multi-frame dynamic MR images within the first preset time period is performed, the image registration method may further include: acquiring multi-frame sample MR images and sample respiratory data in a second preset time period before the tracer is applied to the object to be detected; and training the initial prediction model through the multi-frame sample MR image and the sample respiratory data to obtain the prediction model.
It should be noted that the computer device may perform network model training on the initial prediction model through multiple frames of sample MR images and sample respiratory data within a second preset time period before applying the tracer, so as to obtain a pre-trained prediction model. Namely, inputting the multi-frame sample MR images and sample respiratory data in the second preset time period into the initial prediction model, and performing loop iteration training to obtain the optimal prediction model. Optionally, the duration of the second preset time period may be greater than, less than or equal to the duration of the first preset time period.
It can be understood that the computer device may input the multi-frame sample MR images and the sample respiratory data within the second preset time period into the initial prediction model to obtain a quasi-dynamic MR prediction result, calculate a prediction error value between the quasi-dynamic MR prediction result and the standard quasi-dynamic MR image through a loss function, update an initial network parameter in the initial prediction model according to the prediction error value, and continuously iterate the above training steps until the prediction error value meets a preset error threshold or the iteration number reaches a preset iteration number threshold, so as to obtain a pre-trained prediction model. During a second time period before the tracer is administered to the imaging site of the subject, the medical scanning device may scan the imaging site of the subject for sample MR data. The computer device may perform segmentation processing on the second time period to obtain a plurality of sub-time periods, and then reconstruct the sample MR data in each time period to obtain a multi-frame sample MR image corresponding to the plurality of sub-time periods. The time lengths of the sub-time periods corresponding to the MR images of the respective frames may be equal or unequal. The sub-time periods corresponding to the MR images of the frames combined together may be equal to a second preset time period. Alternatively, the standard dynamic-like MR image may be an idealized dynamic-like MR image.
The image registration method can acquire the quasi-dynamic MR image with structural information by utilizing respiratory data acquired synchronously with the dynamic PET data, thereby shortening the data acquisition time, meanwhile, the quasi-dynamic MR image can be directly acquired through the respiratory data, the dynamic MR data is not required to be acquired firstly, then the dynamic MR data is reconstructed into the dynamic MR image, and the quasi-dynamic MR image can be acquired through indirect processing of the dynamic MR image, thereby reducing the whole data processing process of image registration and shortening the image registration time.
As an embodiment, as shown in fig. 7, the step of acquiring a motion-like PET image corresponding to each frame of motion-like MR image in S300 may include:
s330, acquiring initial PET data in a first preset time period.
Specifically, after the imaging part of the object to be measured is applied with the tracer, the medical scanning device may scan the imaging part applied with the tracer for a period of time in real time to acquire initial PET data within a first preset time period, and send the acquired initial PET data to the computer device. Or, the computer device may further acquire the initial PET data acquired in the historical time period from the cloud or the local data, that is, the initial PET data in the first preset time period. In this embodiment, the manner of acquiring the initial PET data within the first preset time period may not be limited. Fig. 8 shows a correspondence of the first preset time period, the second preset time period, the point in time of tracer administration, and the corresponding initial PET data, sample MR data, and respiration data on the same time axis. In fig. 8, the training sequence may be sample MR data of a plurality of sub-periods acquired when the prediction model is trained; sequence 1, sequence 2 and sequence 3 may be sample MR data for 3 sub-periods of time corresponding to administration of the tracer, however, sample MR data for 3 sub-periods of time corresponding to administration of the tracer may not be used in the image registration process.
S340, time mapping is carried out on each frame type dynamic MR image and the initial PET data in the first preset time period, and the mapping PET data of each frame type dynamic MR image is obtained.
Specifically, performing time mapping on each frame type dynamic MR image and the initial PET data in the first preset time period may be understood as performing time mapping on a sub-time period of each frame type dynamic MR image and a corresponding sub-time period in the first preset time period to obtain mapped PET data of each frame type dynamic MR image.
And S350, reconstructing the mapping PET data to obtain a similar dynamic PET image corresponding to each frame of similar dynamic MR image.
Further, the computer device may reconstruct the mapping PET data in each sub-period to obtain a dynamic-like PET image corresponding to each frame of dynamic MR image.
The image registration method can acquire the quasi-dynamic PET images, further register the quasi-dynamic PET images, and then register the multi-frame initial dynamic PET images based on the registered quasi-dynamic PET images, so that the registered dynamic PET images can embody structural information and obvious image characteristics, and the accuracy of the registration result of the dynamic PET images can be improved.
To facilitate understanding of those skilled in the art, the image registration method provided in the present application is described by taking an implementation subject as a computer device as an example, and specifically, the method includes:
(1) And acquiring respiratory data and initial dynamic PET data of the object to be detected in a first preset time period after the tracer is applied.
(2) Acquiring a plurality of frames of sample MR images and sample respiratory data in a second preset time period before the tracer is applied to the object to be detected.
(3) And training the initial prediction model through the multi-frame sample MR image and the sample respiratory data to obtain the prediction model.
(4) And inputting the respiratory data into a prediction model to obtain a corresponding multi-frame dynamic MR image in a first preset time period.
(5) And carrying out time mapping on each frame type dynamic MR image and the initial PET data in the first preset time period to obtain the mapping PET data of each frame type dynamic MR image.
(6) And reconstructing the mapping PET data to obtain a similar dynamic PET image corresponding to each frame of similar dynamic MR image.
(7) A reference image is determined based on the multi-frame sample MR images.
(8) And respectively carrying out image registration on the dynamic MR images of each frame type through the reference image to obtain a deformation field corresponding to the dynamic MR images of each frame type.
(9) And registering the corresponding dynamic-like PET images according to the deformation fields corresponding to the dynamic MR images of the frames to obtain the registered dynamic-like PET images.
(10) And performing time mapping on each frame of initial dynamic PET data in a first preset time period based on each frame of dynamic PET image to obtain the mapped initial dynamic PET data of each frame of dynamic PET image.
(11) And reconstructing the mapping initial dynamic PET data of each frame type dynamic PET image to obtain a corresponding mapping initial dynamic PET image.
(12) And registering the corresponding mapping initial dynamic PET image through the registered similar dynamic PET image to obtain a registered dynamic PET image.
For the implementation processes of (1) to (12), reference may be specifically made to the description of the above embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
It should be understood that although the various steps in the flowcharts of fig. 2-5 and 7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least some of the steps in fig. 2-5 and 7 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed sequentially, but may be performed alternately or alternately with other steps or at least some of the other steps or stages.
In one embodiment, as shown in fig. 9, there is provided an image registration apparatus including: a data acquisition module 11, a first image determination module 12, a second image determination module 13 and a registration module 14, wherein:
the data acquisition module 11 is configured to acquire respiratory data and initial dynamic PET data within a first preset time period after the tracer is applied to the object to be detected;
the first image determining module 12 is configured to determine, according to the respiratory data, a corresponding multi-frame dynamic-like MR image within a first preset time period;
the second image determining module 13 is configured to acquire a dynamic-like PET image corresponding to each frame of dynamic MR image, and determine a registered dynamic-like PET image according to each frame of dynamic PET image;
the registration module 14 is configured to register the multiple frames of initial dynamic PET images according to the registered dynamic-like PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the registration module 14 includes: a first time mapping unit, a reconstruction unit and a first registration unit, wherein:
The first time mapping unit is used for carrying out time mapping on the initial dynamic PET data in the first preset time period according to each frame type dynamic PET image to obtain the mapping initial dynamic PET data of each frame type dynamic PET image;
the reconstruction unit is used for reconstructing the mapping initial dynamic PET data of each frame type dynamic PET image to obtain a corresponding mapping initial dynamic PET image;
and the first registration unit is used for registering the corresponding mapping initial dynamic PET image through the registered similar dynamic PET image to obtain a registered dynamic PET image.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the second image determining module 13 includes: a deformation field acquisition unit and a second registration unit, wherein:
the deformation field acquisition unit is used for acquiring a deformation field corresponding to each frame type dynamic MR image;
and the second registration unit is used for registering the corresponding dynamic-like PET images according to the deformation fields corresponding to the dynamic-like MR images of each frame to obtain the registered dynamic-like PET images.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the deformation field acquiring unit includes: a reference image determination subunit and an image registration subunit, wherein:
a reference image determining subunit, configured to determine a reference image from the multiple frames of sample MR images;
and the image registration subunit is used for respectively carrying out image registration on the dynamic MR images of each frame type through the reference image to obtain the deformation field corresponding to the dynamic MR images of each frame type.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the first image determining module 12 is specifically configured to input the respiratory data into the prediction model to obtain a corresponding multi-frame-like dynamic MR image within a first preset time period.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the image registration apparatus further includes: data acquisition module and training module, wherein:
the data acquisition module is used for acquiring multi-frame sample MR images and sample respiratory data in a second preset time period before the tracer is applied to the object to be detected;
And the training module is used for training the initial prediction model through the multi-frame sample MR image and the sample respiratory data to obtain the prediction model.
The image registration apparatus provided in this embodiment may perform the method embodiments, and the implementation principle and technical effect are similar, which are not described herein again.
In one embodiment, the second image determining module 13 includes: a data acquisition unit, a second time mapping unit and a data reconstruction unit, wherein:
the data acquisition unit is used for acquiring initial PET data in a first preset time period;
the second time mapping unit is used for performing time mapping on each frame type dynamic MR image and the initial PET data in the first preset time period to obtain the mapping PET data of each frame type dynamic MR image;
and the data reconstruction unit is used for reconstructing the mapping PET data to obtain a similar dynamic PET image corresponding to each frame of similar dynamic MR image.
The image registration apparatus provided in this embodiment may implement the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
For specific definition of the image registration apparatus, reference may be made to the above definition of the image registration method, which is not described herein again. The modules in the image registration apparatus can be implemented in whole or in part by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used to store respiratory data and dynamic PET images. The network interface of the computer device is used for communicating with an external endpoint through a network connection. The computer program is executed by a processor to implement a reinforcement level analysis method.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
In one embodiment, a readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
Acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame dynamic MR image in a first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing initial dynamic PET data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. An image registration method, characterized in that the method comprises:
acquiring respiratory data and initial dynamic PET data of a to-be-detected object within a first preset time period after the to-be-detected object applies a tracer;
determining a corresponding multi-frame type dynamic MR image in the first preset time period according to the respiratory data;
acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image, and determining the registered similar dynamic PET image through each frame of similar dynamic PET image;
Registering the multi-frame initial dynamic PET images based on the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing the initial dynamic PET data.
2. The image registration method according to claim 1, wherein the registering the multiple frames of initial dynamic PET images based on the registered dynamic-like PET images to obtain the registered dynamic PET images comprises:
performing time mapping on the initial dynamic PET data in the first preset time period based on each frame type dynamic PET image to obtain mapped initial dynamic PET data of each frame type dynamic PET image;
reconstructing the mapping initial dynamic PET data of each frame type dynamic PET image to obtain a corresponding mapping initial dynamic PET image;
and registering the corresponding mapping initial dynamic PET image through the registered similar dynamic PET image to obtain the registered dynamic PET image.
3. The image registration method according to claim 1 or 2, wherein the determining the registered dynamic-like PET image by each frame dynamic-like PET image comprises:
Acquiring a deformation field corresponding to each frame type dynamic MR image;
and registering the corresponding similar dynamic PET images according to the deformation fields corresponding to the various frames of similar dynamic MR images to obtain the registered similar dynamic PET images.
4. The image registration method according to claim 3, wherein the obtaining of the deformation field corresponding to each frame-like dynamic MR image comprises:
determining a reference image based on the multi-frame sample MR images;
and respectively carrying out image registration on the dynamic MR images of each frame type through the reference image to obtain a deformation field corresponding to the dynamic MR images of each frame type.
5. The image registration method according to claim 1 or 2, wherein the determining the corresponding multi-frame-like dynamic MR image within the first preset time period from the respiration data comprises:
and inputting the respiratory data into a prediction model to obtain a corresponding multi-frame dynamic MR image in the first preset time period.
6. The image registration method of claim 5, further comprising:
acquiring multi-frame sample MR images and sample respiratory data in a second preset time period before the tracer is applied to the object to be detected;
And training an initial prediction model through the multi-frame sample MR image and the sample respiratory data to obtain the prediction model.
7. The image registration method according to claim 1 or 2, wherein the acquiring a dynamic-like PET image corresponding to each frame of dynamic-like MR image comprises:
acquiring initial PET data in the first preset time period;
performing time mapping on the dynamic MR images of all frames and the initial PET data in the first preset time period to obtain the mapped PET data of the dynamic MR images of all frames;
and reconstructing the mapping PET data to obtain a similar dynamic PET image corresponding to each frame of similar dynamic MR image.
8. An image registration apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring respiratory data and initial dynamic PET data in a first preset time period after the tracer is applied to the object to be detected;
the first image determining module is used for determining a corresponding multi-frame type dynamic MR image in the first preset time period according to the respiratory data;
the second image determining module is used for acquiring a similar dynamic PET image corresponding to each frame of similar dynamic MR image and determining a registered similar dynamic PET image through each frame of similar dynamic PET image;
The registration module is used for registering the multi-frame initial dynamic PET images according to the registered similar dynamic PET images to obtain registered dynamic PET images; the multi-frame initial dynamic PET image is an image obtained by reconstructing the initial dynamic PET data.
9. A computer arrangement comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1-7.
10. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210237538.9A CN114677415A (en) | 2022-03-10 | 2022-03-10 | Image registration method and device, computer equipment and readable storage medium |
| PCT/CN2023/080829 WO2023169565A1 (en) | 2022-03-10 | 2023-03-10 | Image registration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210237538.9A CN114677415A (en) | 2022-03-10 | 2022-03-10 | Image registration method and device, computer equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114677415A true CN114677415A (en) | 2022-06-28 |
Family
ID=82072676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210237538.9A Pending CN114677415A (en) | 2022-03-10 | 2022-03-10 | Image registration method and device, computer equipment and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114677415A (en) |
| WO (1) | WO2023169565A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023169565A1 (en) * | 2022-03-10 | 2023-09-14 | 北京联影智能影像技术研究院 | Image registration method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102114415B1 (en) * | 2013-01-29 | 2020-05-22 | 삼성전자주식회사 | Method and Apparatus for medical image registration |
| CN107527359B (en) * | 2017-08-07 | 2020-04-10 | 东软医疗系统股份有限公司 | PET image reconstruction method and PET imaging equipment |
| CN113744264A (en) * | 2021-09-26 | 2021-12-03 | 上海联影医疗科技股份有限公司 | Image processing method and system |
| CN114677415A (en) * | 2022-03-10 | 2022-06-28 | 北京联影智能影像技术研究院 | Image registration method and device, computer equipment and readable storage medium |
-
2022
- 2022-03-10 CN CN202210237538.9A patent/CN114677415A/en active Pending
-
2023
- 2023-03-10 WO PCT/CN2023/080829 patent/WO2023169565A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023169565A1 (en) * | 2022-03-10 | 2023-09-14 | 北京联影智能影像技术研究院 | Image registration method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023169565A1 (en) | 2023-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240070863A1 (en) | Systems and methods for medical acquisition processing and machine learning for anatomical assessment | |
| US20210151187A1 (en) | Data-Driven Estimation of Predictive Digital Twin Models from Medical Data | |
| US9818191B2 (en) | Covariate modulate atlas | |
| CN110960241A (en) | Method and device for determining scanning parameters of medical image scanning and computer equipment | |
| US9317915B2 (en) | Computed-tomography system and method for determining volume information for a body | |
| CN110415310A (en) | Medical scanning imaging method, device, storage medium and computer equipment | |
| CN114943714A (en) | Medical image processing system, medical image processing apparatus, electronic device, and storage medium | |
| CN110458779B (en) | Method for acquiring correction information for attenuation correction of PET images of respiration or heart | |
| CN113989231A (en) | Method and device for determining kinetic parameters, computer equipment and storage medium | |
| CN114677415A (en) | Image registration method and device, computer equipment and readable storage medium | |
| KR20190114229A (en) | Apparatus and method for processing image | |
| CN112365479A (en) | PET parameter image processing method, device, computer equipment and storage medium | |
| CN108873047B (en) | Method, system, computer device and storage medium for detecting activity of radioactive source | |
| CN102196774B (en) | Method for characterizing object movement from CT imaging data | |
| EP2174292A1 (en) | A method, apparatus, computer-readable medium and use for pharmacokinetic modeling | |
| CN110215203B (en) | Electrocardiosignal acquisition method and device, computer equipment and storage medium | |
| EP3910597A1 (en) | Body representations | |
| CN114359431A (en) | Method and system for directly reconstructing parameter image | |
| CN113729686B (en) | Brain local function dynamic real-time measurement system | |
| WO2023131061A1 (en) | Systems and methods for positron emission computed tomography image reconstruction | |
| US12000919B2 (en) | Systems and methods for magnetic resonance imaging | |
| CN110992280B (en) | PET image attenuation correction method, device and computer equipment | |
| EP3828767A1 (en) | Probablistic regularization of convolutional neurual networks for multiple-feature detection based on correlations | |
| CN114266759A (en) | Image analysis method and device and computer equipment | |
| CN117455872A (en) | Method, device, computer equipment and storage medium for determining region of interest |
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 |