CN116630247B - Cerebral blood flow image processing method and device and cerebral blood flow monitoring system - Google Patents
Cerebral blood flow image processing method and device and cerebral blood flow monitoring system Download PDFInfo
- Publication number
- CN116630247B CN116630247B CN202310506055.9A CN202310506055A CN116630247B CN 116630247 B CN116630247 B CN 116630247B CN 202310506055 A CN202310506055 A CN 202310506055A CN 116630247 B CN116630247 B CN 116630247B
- Authority
- CN
- China
- Prior art keywords
- blood flow
- cerebral blood
- image
- target user
- image processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003727 cerebral blood flow Effects 0.000 title claims abstract description 320
- 238000003672 processing method Methods 0.000 title claims abstract description 35
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 238000013136 deep learning model Methods 0.000 claims abstract description 55
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000008344 brain blood flow Effects 0.000 claims description 47
- 230000005856 abnormality Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 210000004556 brain Anatomy 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/0263—Measuring blood flow using NMR
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
- A61B2576/026—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part for the brain
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Quality & Reliability (AREA)
- Neurology (AREA)
- Hematology (AREA)
- High Energy & Nuclear Physics (AREA)
- Fuzzy Systems (AREA)
- Psychiatry (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The application provides a cerebral blood flow image processing method and device and a cerebral blood flow monitoring system, wherein the method is used for determining the cerebral blood flow anomaly degree of a target user through image processing and comprises the following steps: acquiring a target physiological parameter value and a first cerebral blood flow image of a target user; inputting the target physiological parameter value into a pre-trained first deep learning model to obtain a second cerebral blood flow image corresponding to the target user; the second cerebral blood flow image is a cerebral blood flow image of the target user when the cerebral blood flow state is normal; generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image; and inputting the cerebral blood flow contrast characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly of the target user. According to the application, a deep learning model for image detection is not required to be established for each user, the cost is low, and the image detection can be accurately realized due to the adaptability of the deep learning model, so that the cerebral blood flow state of each user can be accurately monitored.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly relates to a cerebral blood flow image processing method and device and a cerebral blood flow monitoring system.
Background
At present, with the advent of the big data age, various detection is more intelligent. The labor cost can be reduced through intelligent processing, and compared with the mode of manual processing, the intelligent processing is more accurate. On the basis, the intelligent processing is also applied to the detection of medical images. For example, in the prior art, the degree of abnormality of cerebral blood flow is generally determined by detecting cerebral blood flow images, so as to determine the health state of the cranium. The concrete mode is as follows: and acquiring a cerebral blood flow image of a user, and intelligently detecting the cerebral blood flow image through a neural network and other deep learning models to automatically judge the degree of abnormality of cerebral blood flow.
However, the inventors of the present application found that the cerebral blood flow state of each user cannot be accurately determined using a unified deep learning model due to individual differences among different users. That is, the existing means cannot accurately judge the cerebral blood flow state of different users.
Disclosure of Invention
The application aims to provide a cerebral blood flow image processing method and device and a cerebral blood flow monitoring system, so as to solve the problem that cerebral blood flow states of different users cannot be accurately judged in the prior art.
In a first aspect of an embodiment of the present application, there is provided a cerebral blood flow image processing method for determining cerebral blood flow abnormality of a target user by image processing, the cerebral blood flow image processing method including:
acquiring a target physiological parameter value and a first cerebral blood flow image of the target user; the target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning;
inputting the target physiological parameter value into a pre-trained first deep learning model to obtain a second cerebral blood flow image corresponding to the target user; the second cerebral blood flow image is a cerebral blood flow image when the cerebral blood flow state of the target user is normal;
generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image;
and inputting the cerebral blood flow comparison characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly of the target user.
In one possible implementation manner, the cerebral blood flow image processing method further includes:
acquiring a plurality of physiological parameters related to the cerebral blood flow state, performing principal component analysis on the physiological parameters, and determining physiological parameters corresponding to the first N principal components as target physiological parameters; n is a preset value;
acquiring target physiological parameter values of a cerebral blood flow healthy person and cerebral blood flow images of the cerebral blood flow healthy person, and training to obtain a first deep learning model based on the target physiological parameter values of the cerebral blood flow healthy person and the cerebral blood flow images of the cerebral blood flow healthy person.
In a possible implementation manner, the generating the cerebral blood flow contrast feature corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image includes:
extracting image features in the first cerebral blood flow image to obtain first image features;
extracting image features in the second cerebral blood flow image to obtain second image features;
fusing the first cerebral blood flow image and the second cerebral blood flow image to obtain a third cerebral blood flow image;
extracting image features in the third cerebral blood flow image to obtain third image features;
and connecting the feature vectors of the first image feature, the second image feature and the third image feature to obtain brain blood flow contrast features corresponding to the target user.
In one possible implementation manner, the cerebral blood flow image processing method further includes:
acquiring a laser speckle image of the brain of the target user;
determining an actual cerebral blood flow velocity of the target user based on the laser speckle image;
judging whether to correct the brain blood flow abnormality according to the actual brain blood flow velocity.
In one possible implementation manner, the determining whether to correct the brain blood flow abnormality according to the actual brain blood flow velocity includes:
inputting the target physiological parameter value into a pre-trained third deep learning model to obtain a standard cerebral blood flow speed corresponding to the target user;
calculating the difference between the actual cerebral blood flow velocity and the standard cerebral blood flow velocity to obtain a velocity difference;
if the speed difference value is larger than a preset difference value, determining a second cerebral blood flow anomaly of the target user according to the speed difference value and the preset difference value;
correcting the cerebral blood flow anomaly based on the second cerebral blood flow anomaly.
In one possible implementation, the correcting the cerebral blood flow anomaly based on the second cerebral blood flow anomaly includes:
by W new ＝W old ×β+W 2 Calculating corrected cerebral blood flow anomaly degree by X (1-beta);
wherein W is new For correcting abnormal cerebral blood flow, W old For the degree of cerebral blood flow abnormality, W 2 And beta is a preset coefficient for the second cerebral blood flow anomaly degree.
In one possible implementation manner, the determining whether to correct the brain blood flow abnormality according to the actual brain blood flow velocity further includes:
and if the speed difference value is not larger than a preset difference value, not correcting the abnormal degree of the cerebral blood flow.
In a second aspect of the embodiments of the present application, there is provided a cerebral blood flow image processing apparatus for determining cerebral blood flow abnormality of a target user by image processing, the cerebral blood flow image processing apparatus including:
the data acquisition module is used for acquiring a target physiological parameter value and a first cerebral blood flow image of the target user; the target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning;
the image generation module is used for inputting the target physiological parameter value into a first deep learning model trained in advance to obtain a second cerebral blood flow image corresponding to the target user; the second cerebral blood flow image is a cerebral blood flow image when the cerebral blood flow state of the target user is normal;
the characteristic generation module is used for generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image;
and the image processing module is used for inputting the cerebral blood flow comparison characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly degree of the target user.
In a third aspect of the embodiments of the present application, there is provided a cerebral blood flow monitoring system, including a monitoring terminal, the monitoring terminal including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the cerebral blood flow image processing method described above when executing the computer program.
In a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the cerebral blood flow image processing method described above.
The cerebral blood flow image processing method and device provided by the embodiment of the application have the beneficial effects that:
considering that the cost of establishing different deep learning models for different users is too high and the different deep learning models cannot cover all users accurately, the embodiment of the application provides a cerebral blood flow image processing method based on two types of deep learning models, wherein the first type of deep learning model is the first deep learning model described in the embodiment of the application and is used for determining a cerebral blood flow image, namely a second cerebral blood flow image, of a user when the cerebral blood flow state is normal according to physiological parameters of the user. Based on this, the brain blood flow contrast feature of the user may be generated from the second brain blood flow image and the newly acquired first brain blood flow image of the user. The second class of deep learning model, namely the second deep learning model is obtained by the description of the embodiment of the application and is used for realizing intelligent detection of image characteristics. Based on this, the degree of cerebral blood flow abnormality of the user, that is, the cerebral blood flow state of the user, can be determined from the aforementioned generated cerebral blood flow contrast characteristic and the second deep learning model.
According to the embodiment of the application, when the user changes, the second cerebral blood flow image corresponding to the user also changes adaptively, and based on the mode, the embodiment of the application realizes personalized detection for different users. According to the scheme provided by the embodiment of the application, a deep learning model for image detection is not required to be established for each user, the cost is low, and the image detection can be accurately realized due to the adaptability of the deep learning model, so that the cerebral blood flow state of each user can be accurately monitored. Therefore, the embodiment of the application effectively solves the problems in the prior art.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a cerebral blood flow image processing method according to an embodiment of the present application;
FIG. 2 is a block diagram of a cerebral blood flow image processing apparatus according to an embodiment of the present application;
fig. 3 is a schematic block diagram of a monitoring terminal according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a schematic flow chart of a cerebral blood flow image processing method provided by an embodiment of the present application, where the cerebral blood flow image processing method provided by the embodiment of the present application is used for determining a cerebral blood flow anomaly degree of a target user through image processing, and the cerebral blood flow image processing method provided by the embodiment of the present application includes:
s101: a target physiological parameter value of a target user and a first cerebral blood flow image are acquired. The target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning.
In this embodiment, the first cerebral blood flow image may be acquired by magnetic resonance scanning of the brain of the target user.
In this embodiment, the target physiological parameter is a physiological parameter that is determined in advance to have a degree of correlation with the cerebral blood flow state greater than a preset degree.
S102: and inputting the target physiological parameter value into a pre-trained first deep learning model to obtain a second cerebral blood flow image corresponding to the target user. The second cerebral blood flow image is a cerebral blood flow image of the target user when the cerebral blood flow state is normal.
In this embodiment, the first deep learning model is used to output a corresponding second cerebral blood flow image according to the input target physiological parameter value. The second cerebral blood flow image is a standard image, namely, the cerebral blood flow image of the target user when the cerebral blood flow state is normal.
S103: and generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image.
In this embodiment, the cerebral blood flow contrast characteristic corresponding to the target user may be obtained by extracting the features in the first cerebral blood flow image and the second cerebral blood flow image, processing the first cerebral blood flow image and the second cerebral blood flow image, and the like. The cerebral blood flow contrast characteristic comprises a characteristic in a first cerebral blood flow image and a characteristic in a second cerebral blood flow image.
S104: and inputting the cerebral blood flow contrast characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly of the target user.
In this embodiment, the second deep learning model is used to output a corresponding brain blood flow anomaly according to the input brain blood flow contrast feature.
In this embodiment, the brain blood flow abnormality is used to describe the brain blood flow state of the target user, and is specifically used to characterize the abnormality of the brain blood flow state of the target user.
In this embodiment, considering that the cost of establishing different deep learning models for different users is too high and not capable of accurately covering all users, the embodiment of the application provides a cerebral blood flow image processing method based on two types of deep learning models, wherein the first type of deep learning model is the first deep learning model described in the embodiment of the application, and is used for determining a cerebral blood flow image, namely a second cerebral blood flow image, of a user when the cerebral blood flow state is normal according to physiological parameters of the user. Based on this, the brain blood flow contrast feature of the user may be generated from the second brain blood flow image and the newly acquired first brain blood flow image of the user. The second class of deep learning model, namely the second deep learning model is obtained by the description of the embodiment of the application and is used for realizing intelligent detection of image characteristics. Based on this, the degree of cerebral blood flow abnormality of the user, that is, the cerebral blood flow state of the user, can be determined from the aforementioned generated cerebral blood flow contrast characteristic and the second deep learning model.
According to the embodiment of the application, when the user changes, the second cerebral blood flow image corresponding to the user also changes adaptively, and based on the mode, the embodiment of the application realizes personalized detection for different users. According to the scheme provided by the embodiment of the application, a deep learning model for image detection is not required to be established for each user, the cost is low, and the image detection can be accurately realized due to the adaptability of the deep learning model, so that the cerebral blood flow state of each user can be accurately monitored. Therefore, the embodiment of the application effectively solves the problems in the prior art.
In one possible implementation manner, the cerebral blood flow image processing method further includes:
and acquiring a plurality of physiological parameters related to the cerebral blood flow state, performing principal component analysis on the physiological parameters, and determining the physiological parameters corresponding to the first N principal components as target physiological parameters. N is a preset value.
Acquiring target physiological parameter values of the cerebral blood flow healthy person and cerebral blood flow images of the cerebral blood flow healthy person, and training to obtain a first deep learning model based on the target physiological parameter values of the cerebral blood flow healthy person and the cerebral blood flow images of the cerebral blood flow healthy person.
In this embodiment, the physiological parameters include, but are not limited to, age, height, weight, gender, past medical history, and the like.
In this embodiment, a physiological parameter having a greater degree of correlation with the cerebral blood flow state may be selected as the target physiological parameter from a plurality of physiological parameters by the principal component analysis method. On the basis, the target physiological parameter value of the cerebral blood flow healthy person can be obtained, and the cerebral blood flow image of the cerebral blood flow healthy person can be trained to obtain a first deep learning model. Wherein, the brain blood flow healthy person refers to a person with normal brain blood flow state. When a brain blood flow healthy person is selected, people of various ages, heights, weights and the like need to be covered as much as possible, and generalization of the first deep learning model is ensured.
In this embodiment, the first deep learning model may be a neural network model.
In one possible implementation manner, the cerebral blood flow image processing method may further include:
and acquiring cerebral blood flow contrast characteristics of different users and cerebral blood flow anomaly of different users. On the basis, a second deep learning model is obtained based on brain blood flow contrast characteristics of different users and brain blood flow anomaly degree training of different users.
In this embodiment, the second deep learning model may also be a neural network model.
In one possible implementation, generating a cerebral blood flow contrast feature corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image includes:
and extracting image features in the first cerebral blood flow image to obtain first image features.
And extracting image features in the second cerebral blood flow image to obtain second image features.
And fusing the first cerebral blood flow image and the second cerebral blood flow image to obtain a third cerebral blood flow image.
And extracting image features in the third cerebral blood flow image to obtain third image features.
And connecting the feature vectors of the first image feature, the second image feature and the third image feature to obtain brain blood flow contrast features corresponding to the target user.
In this embodiment, the first image feature is essentially an image feature of the target user when the cerebral blood flow state is normal, the second image feature is essentially an image feature of the current cerebral blood flow state of the target user, the third image feature is essentially a contrast feature of the first image feature and the second image feature, and the three features are connected to effectively represent the cerebral blood flow contrast feature of the target user.
In the present embodiment, the connection of the feature vectors can be achieved by s= [ S1, S2, S3 ]. Wherein, S is a cerebral blood flow contrast feature corresponding to the target user, S1 is a feature vector corresponding to the first image feature, S2 is a feature vector corresponding to the second image feature, and S3 is a feature vector corresponding to the third image feature.
In one possible implementation manner, the cerebral blood flow image processing method further includes:
a laser speckle image of the brain of the target user is acquired.
An actual cerebral blood flow velocity of the target user is determined based on the laser speckle image.
Judging whether to correct the abnormal degree of the cerebral blood flow according to the actual cerebral blood flow velocity.
In this embodiment, a plurality of laser speckle images of the target user may also be acquired by scanning the brain of the target user with laser light. On this basis, the actual cerebral blood flow velocity of the target user can be determined according to the moving velocity of the speckle particles in the plurality of laser speckle images.
In this embodiment, after determining the actual cerebral blood flow velocity of the target user, it may be determined whether the determined cerebral blood flow anomaly needs to be corrected according to the actual cerebral blood flow velocity, so as to monitor the cerebral blood flow state of the target user more accurately.
In one possible implementation, determining whether to correct the brain blood flow anomaly based on the actual brain blood flow velocity includes:
and inputting the target physiological parameter value into a pre-trained third deep learning model to obtain the standard cerebral blood flow velocity corresponding to the target user.
And calculating the difference between the actual cerebral blood flow velocity and the standard cerebral blood flow velocity to obtain a velocity difference.
If the speed difference is greater than the preset difference, determining a second cerebral blood flow anomaly of the target user according to the speed difference and the preset difference.
The cerebral blood flow abnormality is corrected based on the second cerebral blood flow abnormality.
In this embodiment, the third deep learning model is used to output a corresponding standard cerebral blood flow velocity according to the input target physiological parameter value. Wherein, the standard cerebral blood flow speed of the target user refers to the cerebral blood flow speed of the target user when the cerebral blood flow state is normal.
In this embodiment, when the difference between the actual cerebral blood flow velocity and the standard cerebral blood flow velocity (i.e., the velocity difference) is large, it is indicated that the cerebral blood flow state of the target user is abnormal. At this time, the second cerebral blood flow abnormality of the target user may be determined based on the speed difference and the preset difference to correct the aforementioned cerebral blood flow abnormality.
Wherein can pass throughDetermining a second cerebral blood anomaly. Wherein W is 2 Is the second cerebral blood flow abnormality, V 1 For the standard cerebral blood flow velocity, V 2 For actual cerebral blood flow velocity, V 0 Is a preset reference value.
In one possible implementation manner, the cerebral blood flow image processing method may further include:
obtaining target physiological parameter values of the brain blood flow healthy person and standard brain blood flow velocity of the brain blood flow healthy person, and training based on the target physiological parameter values of the brain blood flow healthy person and the standard brain blood flow velocity of the brain blood flow healthy person to obtain a third deep learning model.
In this embodiment, the third deep learning model may also be a neural network model.
In one possible implementation, correcting the brain blood flow anomaly based on the second brain blood flow anomaly includes:
by W new ＝W old ×β+W 2 And (3) calculating corrected cerebral blood flow anomaly degree by X (1-beta).
Wherein W is new For correcting abnormal cerebral blood flow, W old For cerebral blood flow abnormality, W 2 And beta is a preset coefficient for the second cerebral blood flow anomaly.
In this embodiment, β is greater than 0.5.
In one possible implementation, the determining whether to correct the brain blood flow abnormality according to the actual brain blood flow velocity further includes:
if the speed difference is not greater than the preset difference, the brain blood flow abnormality is not corrected.
In this embodiment, if the speed difference is not greater than the preset difference, it is indicated that the brain blood flow speed of the target user is within the normal range, and there is no value of auxiliary correction, so that the foregoing brain blood flow abnormality is not corrected at this time.
Corresponding to the cerebral blood flow image processing method of the above embodiment, fig. 2 is a block diagram of a cerebral blood flow image processing apparatus according to an embodiment of the present application. For convenience of explanation, only portions relevant to the embodiments of the present application are shown. The cerebral blood flow image processing apparatus of the embodiment of the present application for determining a cerebral blood flow abnormality of a target user by image processing, referring to fig. 2, the cerebral blood flow image processing apparatus 20 includes: a data acquisition module 21, an image generation module 22, a feature generation module 23 and an image processing module 24.
The data acquisition module 21 is configured to acquire a target physiological parameter value of a target user and a first cerebral blood flow image. The target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning.
The image generating module 22 is configured to input the target physiological parameter value into a first deep learning model trained in advance, and obtain a second cerebral blood flow image corresponding to the target user. The second cerebral blood flow image is a cerebral blood flow image of the target user when the cerebral blood flow state is normal.
The feature generation module 23 is configured to generate a cerebral blood flow contrast feature corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image.
The image processing module 24 is configured to input the cerebral blood flow contrast feature into a second deep learning model trained in advance, so as to obtain the cerebral blood flow anomaly of the target user.
In one possible implementation, the image generation module 22 is further configured to:
and acquiring a plurality of physiological parameters related to the cerebral blood flow state, performing principal component analysis on the physiological parameters, and determining the physiological parameters corresponding to the first N principal components as target physiological parameters. N is a preset value.
Acquiring target physiological parameter values of the cerebral blood flow healthy person and cerebral blood flow images of the cerebral blood flow healthy person, and training to obtain a first deep learning model based on the target physiological parameter values of the cerebral blood flow healthy person and the cerebral blood flow images of the cerebral blood flow healthy person.
In one possible implementation, the feature generation module 23 is specifically configured to:
and extracting image features in the first cerebral blood flow image to obtain first image features.
And extracting image features in the second cerebral blood flow image to obtain second image features.
And fusing the first cerebral blood flow image and the second cerebral blood flow image to obtain a third cerebral blood flow image.
And extracting image features in the third cerebral blood flow image to obtain third image features.
And connecting the feature vectors of the first image feature, the second image feature and the third image feature to obtain brain blood flow contrast features corresponding to the target user.
In one possible implementation, the image processing module 24 is further configured to:
a laser speckle image of the brain of the target user is acquired.
An actual cerebral blood flow velocity of the target user is determined based on the laser speckle image.
Judging whether to correct the abnormal degree of the cerebral blood flow according to the actual cerebral blood flow velocity.
In one possible implementation, the image processing module 24 is specifically configured to:
and inputting the target physiological parameter value into a pre-trained third deep learning model to obtain the standard cerebral blood flow velocity corresponding to the target user.
And calculating the difference between the actual cerebral blood flow velocity and the standard cerebral blood flow velocity to obtain a velocity difference.
If the speed difference is greater than the preset difference, determining a second cerebral blood flow anomaly of the target user according to the speed difference and the preset difference.
The cerebral blood flow abnormality is corrected based on the second cerebral blood flow abnormality.
In one possible implementation, the first and second data are recorded by W new ＝W old ×β+W 2 And (3) calculating corrected cerebral blood flow anomaly degree by X (1-beta).
Wherein W is new For correcting abnormal cerebral blood flow, W old For cerebral blood flow abnormality, W 2 And beta is a preset coefficient for the second cerebral blood flow anomaly.
In one possible implementation, the image processing module 24 is specifically configured to perform the following steps:
if the speed difference is not greater than the preset difference, the brain blood flow abnormality is not corrected.
The embodiment of the application also provides a cerebral blood flow monitoring system, which comprises a monitoring terminal. On the basis, the cerebral blood flow monitoring system can further comprise a magnetic resonance scanning device, a laser scanning device and a communication device. On the basis, the magnetic resonance scanning device is used for scanning a first cerebral blood flow image of the target user and transmitting the scanned first cerebral blood flow image to the monitoring terminal through the communication device. The laser scanning device is used for scanning the laser speckle image of the target user and transmitting the scanned laser speckle image to the monitoring terminal through the communication device. On the basis, the monitoring terminal executes the cerebral blood flow image processing method in the embodiment to complete detection of cerebral blood flow images.
For the monitoring terminal, reference may be made to fig. 3, and fig. 3 is a schematic block diagram of the monitoring terminal according to an embodiment of the present application. The terminal 300 in the present embodiment as shown in fig. 3 may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303, and the memory 304 communicate with each other via a communication bus 305. The memory 304 is used to store a computer program comprising program instructions. The processor 301 is configured to execute program instructions stored in the memory 304. Wherein the processor 301 is configured to invoke program instructions to perform the following functions of the modules/units in the above described device embodiments, such as the functions of the modules 21 to 24 shown in fig. 2.
It should be appreciated that in embodiments of the present application, the processor 301 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 302 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.
The memory 304 may include read only memory and random access memory and provides instructions and data to the processor 301. A portion of memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information of device type.
In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present application may execute the implementation described in the first embodiment and the second embodiment of the cerebral blood flow image processing method provided in the embodiments of the present application, and may also execute the implementation of the terminal described in the embodiments of the present application, which is not described herein again.
In another embodiment of the present application, a computer readable storage medium is provided, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, where the program instructions, when executed by a processor, implement all or part of the procedures in the method embodiments described above, or may be implemented by instructing related hardware by the computer program, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by the processor, implements the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The computer readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, such as a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store a computer program and other programs and data required for the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working procedures of the terminal and the unit described above may refer to the corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In several embodiments provided by the present application, it should be understood that the disclosed terminal and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via some interfaces or units, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present application, and these modifications and substitutions are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A cerebral blood flow image processing method for determining cerebral blood flow abnormality of a target user by image processing, the cerebral blood flow image processing method comprising:
acquiring a target physiological parameter value and a first cerebral blood flow image of the target user; the target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning;
inputting the target physiological parameter value into a pre-trained first deep learning model to obtain a second cerebral blood flow image corresponding to the target user; the second cerebral blood flow image is a cerebral blood flow image when the cerebral blood flow state of the target user is normal;
generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image;
and inputting the cerebral blood flow comparison characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly of the target user.
2. The cerebral blood flow image processing method according to claim 1, characterized in that the cerebral blood flow image processing method further comprises:
acquiring a plurality of physiological parameters related to the cerebral blood flow state, performing principal component analysis on the physiological parameters, and determining physiological parameters corresponding to the first N principal components as target physiological parameters; n is a preset value;
acquiring target physiological parameter values of a cerebral blood flow healthy person and cerebral blood flow images of the cerebral blood flow healthy person, and training to obtain a first deep learning model based on the target physiological parameter values of the cerebral blood flow healthy person and the cerebral blood flow images of the cerebral blood flow healthy person.
3. The cerebral blood flow image processing method according to claim 1, wherein the generating the cerebral blood flow contrast feature corresponding to the target user from the first cerebral blood flow image and the second cerebral blood flow image includes:
extracting image features in the first cerebral blood flow image to obtain first image features;
extracting image features in the second cerebral blood flow image to obtain second image features;
fusing the first cerebral blood flow image and the second cerebral blood flow image to obtain a third cerebral blood flow image;
extracting image features in the third cerebral blood flow image to obtain third image features;
and connecting the feature vectors of the first image feature, the second image feature and the third image feature to obtain brain blood flow contrast features corresponding to the target user.
4. The cerebral blood flow image processing method according to claim 1, characterized in that the cerebral blood flow image processing method further comprises:
acquiring a laser speckle image of the brain of the target user;
determining an actual cerebral blood flow velocity of the target user based on the laser speckle image;
judging whether to correct the brain blood flow abnormality according to the actual brain blood flow velocity.
5. The cerebral blood flow image processing method according to claim 4, wherein the determining whether to correct the cerebral blood flow abnormality based on the actual cerebral blood flow velocity includes:
inputting the target physiological parameter value into a pre-trained third deep learning model to obtain a standard cerebral blood flow speed corresponding to the target user;
calculating the difference between the actual cerebral blood flow velocity and the standard cerebral blood flow velocity to obtain a velocity difference;
if the speed difference value is larger than a preset difference value, determining a second cerebral blood flow anomaly of the target user according to the speed difference value and the preset difference value;
correcting the cerebral blood flow anomaly based on the second cerebral blood flow anomaly.
6. The cerebral blood flow image processing method according to claim 5, wherein the correcting the cerebral blood flow anomaly based on the second cerebral blood flow anomaly comprises:
by W new ＝W old ×β+W 2 ×(1-β) Calculating corrected cerebral blood flow anomaly;
wherein W is new For correcting abnormal cerebral blood flow, W old For the degree of cerebral blood flow abnormality, W 2 And beta is a preset coefficient for the second cerebral blood flow anomaly degree.
7. The brain blood flow image processing method according to claim 5, wherein said determining whether to correct said brain blood flow abnormality based on said actual brain blood flow velocity further comprises:
and if the speed difference value is not larger than a preset difference value, not correcting the abnormal degree of the cerebral blood flow.
8. A cerebral blood flow image processing apparatus for determining a cerebral blood flow abnormality of a target user by image processing, the cerebral blood flow image processing apparatus comprising:
the data acquisition module is used for acquiring a target physiological parameter value and a first cerebral blood flow image of the target user; the target physiological parameter is a predetermined physiological parameter, and the first cerebral blood flow image is obtained through magnetic resonance scanning;
the image generation module is used for inputting the target physiological parameter value into a first deep learning model trained in advance to obtain a second cerebral blood flow image corresponding to the target user; the second cerebral blood flow image is a cerebral blood flow image when the cerebral blood flow state of the target user is normal;
the characteristic generation module is used for generating cerebral blood flow contrast characteristics corresponding to the target user according to the first cerebral blood flow image and the second cerebral blood flow image;
and the image processing module is used for inputting the cerebral blood flow comparison characteristic into a pre-trained second deep learning model to obtain the cerebral blood flow anomaly degree of the target user.
9. A cerebral blood flow monitoring system, comprising: monitoring a terminal;
the monitoring terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506055.9A CN116630247B (en) | 2023-05-06 | 2023-05-06 | Cerebral blood flow image processing method and device and cerebral blood flow monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506055.9A CN116630247B (en) | 2023-05-06 | 2023-05-06 | Cerebral blood flow image processing method and device and cerebral blood flow monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116630247A CN116630247A (en) | 2023-08-22 |
| CN116630247B true CN116630247B (en) | 2023-10-20 |
Family
ID=87616267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310506055.9A Active CN116630247B (en) | 2023-05-06 | 2023-05-06 | Cerebral blood flow image processing method and device and cerebral blood flow monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116630247B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103700083A (en) * | 2013-12-26 | 2014-04-02 | 中国人民解放军广州军区武汉总医院 | CT (Computed Tomography) perfusion image intelligent fusing method on basis of adaptive fuzzy neural network model |
| CN112446867A (en) * | 2020-11-25 | 2021-03-05 | 上海联影医疗科技股份有限公司 | Method, device and equipment for determining blood flow parameters and storage medium |
| WO2021115130A1 (en) * | 2019-12-09 | 2021-06-17 | 平安科技（深圳）有限公司 | Intelligent detection method and apparatus for cerebral hemorrhage spots, electronic device and storage medium |
| CN113298800A (en) * | 2021-06-11 | 2021-08-24 | 沈阳东软智能医疗科技研究院有限公司 | Processing method, device and equipment of CT angiography CTA source image |
| CN113706560A (en) * | 2021-09-23 | 2021-11-26 | 南京鼓楼医院 | Ischemia area segmentation method, device, equipment and storage medium |
| CN114533121A (en) * | 2022-02-18 | 2022-05-27 | 首都医科大学附属北京友谊医院 | Brain perfusion state prediction device, method and equipment and model training device |
| CN115670512A (en) * | 2021-07-23 | 2023-02-03 | 深圳迈瑞生物医疗电子股份有限公司 | Blood flow measuring method based on ultrasound and ultrasonic imaging system |
| CN115760708A (en) * | 2022-10-27 | 2023-03-07 | 沈阳先进医疗设备技术孵化中心有限公司 | Intracranial collateral circulation automatic evaluation method and device, storage medium and computing equipment |
-
2023
- 2023-05-06 CN CN202310506055.9A patent/CN116630247B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103700083A (en) * | 2013-12-26 | 2014-04-02 | 中国人民解放军广州军区武汉总医院 | CT (Computed Tomography) perfusion image intelligent fusing method on basis of adaptive fuzzy neural network model |
| WO2021115130A1 (en) * | 2019-12-09 | 2021-06-17 | 平安科技（深圳）有限公司 | Intelligent detection method and apparatus for cerebral hemorrhage spots, electronic device and storage medium |
| CN112446867A (en) * | 2020-11-25 | 2021-03-05 | 上海联影医疗科技股份有限公司 | Method, device and equipment for determining blood flow parameters and storage medium |
| CN113298800A (en) * | 2021-06-11 | 2021-08-24 | 沈阳东软智能医疗科技研究院有限公司 | Processing method, device and equipment of CT angiography CTA source image |
| CN115670512A (en) * | 2021-07-23 | 2023-02-03 | 深圳迈瑞生物医疗电子股份有限公司 | Blood flow measuring method based on ultrasound and ultrasonic imaging system |
| CN113706560A (en) * | 2021-09-23 | 2021-11-26 | 南京鼓楼医院 | Ischemia area segmentation method, device, equipment and storage medium |
| CN114533121A (en) * | 2022-02-18 | 2022-05-27 | 首都医科大学附属北京友谊医院 | Brain perfusion state prediction device, method and equipment and model training device |
| CN115760708A (en) * | 2022-10-27 | 2023-03-07 | 沈阳先进医疗设备技术孵化中心有限公司 | Intracranial collateral circulation automatic evaluation method and device, storage medium and computing equipment |
Non-Patent Citations (3)
| Title |
|---|
| Cheng Qian et al..Precise Characterization of the Penumbra Revealed by MRI: A Modified Photothrombotic Stroke Model Study.《Precise Imaging of Penumbra and Stroke Model》.2016,第1-13页. * |
| Samuel Kuttner et al..Cerebral blood flow measurements with 15 O-water PET using a non-invasive machine-learning-derived arterial input function.《Journal of Cerebral Blood Flow & Metabolism》.2021,第41卷(第9期),第2229–2241页. * |
| 刘祺.局部脑缺血急性期的高分辨率...力学和血管网络光学成像技术.《中国博士学位论文全文数据库 医药卫生科技辑》.2019,E070-8. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116630247A (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11562222B2 (en) | Systems and methods of identity analysis of electrocardiograms | |
| KR102243830B1 (en) | System for providing integrated medical diagnostic service and method thereof | |
| CN107491166B (en) | Method for adjusting parameters of virtual reality equipment and virtual reality equipment | |
| US11547334B2 (en) | Psychological stress estimation method and apparatus | |
| CN112634246B (en) | Oral cavity image recognition method and related equipment | |
| CN108765447B (en) | Image segmentation method, image segmentation device and electronic equipment | |
| CN101165706B (en) | Image processing apparatus and image acquisition method | |
| CN112861947B (en) | Sensor data processing method and device and computing equipment | |
| CN113990482A (en) | Health data processing system and method | |
| CN115844696A (en) | Method and device for generating visual training scheme, terminal equipment and medium | |
| CN113613123B (en) | Audio data processing method and device, earphone and storage medium | |
| CN116630247B (en) | Cerebral blood flow image processing method and device and cerebral blood flow monitoring system | |
| JP6796525B2 (en) | Image processing equipment, image processing system and image processing method | |
| CN110265127B (en) | Disease charge calculation method and device and terminal equipment | |
| CN117357080A (en) | Near infrared spectrum signal denoising method and device, terminal equipment and storage medium | |
| KR20230049609A (en) | Method and apparatus for controlling artificial pancreas comprising insulin patch | |
| US9451906B2 (en) | Retrieving mental images of faces from the human brain | |
| CN113297993B (en) | Neural stimulation signal determination apparatus and method | |
| CN107329411B (en) | Magnetic resonance apparatus, noise control method, and non-volatile computer storage medium | |
| CN110175522A (en) | Work attendance method, system and Related product | |
| CN115111182A (en) | Method and device for detecting running state of direct current fan and terminal equipment | |
| CN114299019A (en) | Scanning method, system and device for nuclear medicine equipment | |
| CN113040717A (en) | Intelligent face beauty instrument | |
| CN112951383A (en) | Intelligent medical image display device | |
| CN113052930A (en) | Chest DR dual-energy digital subtraction image generation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |