CN115530820B - Oxygen uptake fraction measuring method, device, equipment and storage medium - Google Patents
Oxygen uptake fraction measuring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115530820B CN115530820B CN202211515305.7A CN202211515305A CN115530820B CN 115530820 B CN115530820 B CN 115530820B CN 202211515305 A CN202211515305 A CN 202211515305A CN 115530820 B CN115530820 B CN 115530820B
- Authority
- CN
- China
- Prior art keywords
- blood volume
- image
- brain tissue
- cerebral blood
- venous
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 69
- 239000001301 oxygen Substances 0.000 title claims abstract description 69
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 68
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 210000004369 blood Anatomy 0.000 claims abstract description 217
- 239000008280 blood Substances 0.000 claims abstract description 217
- 230000002490 cerebral effect Effects 0.000 claims abstract description 128
- 210000005013 brain tissue Anatomy 0.000 claims abstract description 121
- 238000006392 deoxygenation reaction Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 110
- 238000003384 imaging method Methods 0.000 claims description 91
- 230000010412 perfusion Effects 0.000 claims description 88
- 238000002372 labelling Methods 0.000 claims description 43
- 230000015654 memory Effects 0.000 claims description 29
- 230000003111 delayed effect Effects 0.000 claims description 16
- 210000001367 artery Anatomy 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000000691 measurement method Methods 0.000 claims description 7
- 230000035945 sensitivity Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 21
- 238000005259 measurement Methods 0.000 abstract description 9
- 238000010801 machine learning Methods 0.000 abstract description 6
- 210000004556 brain Anatomy 0.000 description 19
- 230000008569 process Effects 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 230000008557 oxygen metabolism Effects 0.000 description 8
- 238000007637 random forest analysis Methods 0.000 description 7
- 210000001519 tissue Anatomy 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 239000002872 contrast media Substances 0.000 description 4
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- INGWEZCOABYORO-UHFFFAOYSA-N 2-(furan-2-yl)-7-methyl-1h-1,8-naphthyridin-4-one Chemical compound N=1C2=NC(C)=CC=C2C(O)=CC=1C1=CC=CO1 INGWEZCOABYORO-UHFFFAOYSA-N 0.000 description 3
- 208000032382 Ischaemic stroke Diseases 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000003727 cerebral blood flow Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 108010002255 deoxyhemoglobin Proteins 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000005534 hematocrit Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 208000014644 Brain disease Diseases 0.000 description 1
- 206010008092 Cerebral artery thrombosis Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 206010020850 Hyperthyroidism Diseases 0.000 description 1
- 238000012307 MRI technique Methods 0.000 description 1
- 208000001647 Renal Insufficiency Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003743 erythrocyte Anatomy 0.000 description 1
- 230000005281 excited state Effects 0.000 description 1
- 210000003722 extracellular fluid Anatomy 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000000302 ischemic effect Effects 0.000 description 1
- 201000006370 kidney failure Diseases 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000008035 nerve activity Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 150000002926 oxygen Chemical class 0.000 description 1
- 230000005408 paramagnetism Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- 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
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Neurology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Hematology (AREA)
- Cardiology (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a method, a device, equipment and a storage medium for measuring oxygen uptake fraction, wherein the method comprises the following steps: acquiring a venous cerebral blood volume image and a cerebral blood volume image of a brain tissue to be detected; processing the venous cerebral blood volume image and the cerebral blood volume image by using a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected; determining an oxygen uptake score image of the brain tissue to be tested based on the deoxygenated blood volume image. According to the method for measuring the oxygen uptake fraction, the deoxygenation blood volume is predicted by using a machine learning model through combining the venous cerebral blood volume image and the cerebral blood volume image, the oxygen uptake fraction is further calculated, and the accuracy of the deoxygenation blood volume calculation result and the oxygen uptake fraction measurement result can be improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method, a device, equipment and a storage medium for measuring oxygen uptake fraction.
Background
The normal operation of nerve cells is highly dependent on the supply of oxygen, and nerve cells require a large amount of oxygen to maintain the most basic nerve activity in a resting state, while the demand for oxygen is greater in nerve cells in a nerve excited state. Oxygen metabolism indexes such as Oxygen uptake Fraction (OEF) and brain Oxygen metabolism Rate (CMRO 2) Of brain tissue in vivo are quantitatively measured, which can reflect neurophysiological conditions, are very important for understanding brain tissue functions under normal and pathological conditions, and can assist in diagnosis and treatment Of brain diseases.
In the existing magnetic resonance imaging, the oxygen metabolism index is usually measured quantitatively by using a Blood oxygen Level-Dependent (BOLD) principle, which is called a quantitative Blood oxygen Level-Dependent (qBOLD) technique. The technology provides a signal attenuation model, and on the basis, oxygen metabolism indexes such as OEF (organic optical fiber) Of brain tissues are quantitatively measured by using a Gradient Echo Sampling Of Spin Echo (GESSE) technology, an Asymmetric Spin Echo (ASE) technology or an Alternating Unbalanced Steady State Free Precession Free Induction attenuation And Echo (Alternating Unbalanced Steady State-Free-compression Free-Induction-Decay Echo) technology And the like. The method has the disadvantages that the accuracy of the measurement result highly depends on the signal-to-noise ratio of the acquisition sequence, and the accurate measurement result can be obtained only under the conditions of sufficient data volume, sufficient signal-to-noise ratio and reasonable optimization method.
Disclosure of Invention
In view of the above problems in the prior art, an object of the present invention is to provide an oxygen uptake fraction measuring method, apparatus, device and storage medium, which can improve the accuracy of the oxygen uptake fraction measurement result.
In order to solve the above problems, the present invention provides an oxygen uptake fraction measuring method comprising:
acquiring a venous cerebral blood volume image and a cerebral blood volume image of a brain tissue to be detected;
processing the venous cerebral blood volume image and the cerebral blood volume image by using a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected;
determining an oxygen uptake fraction image of the brain tissue to be tested based on the deoxygenated blood volume image.
Further, the acquiring the venous cerebral blood volume image of the brain tissue to be detected comprises:
acquiring velocity selective venous spin labeling perfusion imaging data of a brain tissue to be detected;
and determining a venous cerebral blood volume image of the brain tissue to be detected according to the speed selective venous spin labeling perfusion imaging data.
Further, the acquiring a cerebral blood volume image of the brain tissue to be detected includes:
acquiring dynamic magnetic sensitive contrast enhanced perfusion imaging data of the brain tissue to be detected or artery spin labeling perfusion imaging data delayed after a plurality of labels;
and determining a cerebral blood volume image of the brain tissue to be detected according to the dynamic magnetic sensitivity contrast enhanced perfusion imaging data or the artery spin labeling perfusion imaging data delayed after the labeling.
Further, the method further comprises:
registering the venous cerebral blood volume image to a cerebral blood volume image space to obtain a venous cerebral blood volume image of the cerebral blood volume image space;
respectively registering the venous cerebral blood volume image of the cerebral blood volume image space and the cerebral blood volume image to a standard cerebral space to obtain a venous cerebral blood volume image and a cerebral blood volume image of the standard cerebral space.
Further, the determining an oxygen uptake score image of the brain tissue under test based on the deoxygenated blood volume image comprises:
obtaining the brain tissue to be testedR 2 Parametric image andR * 2 a parameter image;
according to the deoxygenated blood volume image, theR 2 Parametric image and method for producing the sameR * 2 A parametric image, the oxygen uptake score image determined using a multi-parameter quantitative blood oxygen level dependent model.
Further, the method for obtaining the brain tissue to be detectedR 2 Parametric image andR * 2 the parametric image includes:
acquiring multi-echo autorotation echo data and multi-echo gradient echo data of the brain tissue to be detected;
obtaining the brain tissue to be detected according to the fitting of the multi-echo autorotation echo dataR 2 A parameter image;
obtaining the brain tissue to be tested according to the fitting of the multi-echo gradient echo dataR * 2 A parametric image.
Further, the method further comprises the step of training the deoxygenated blood volume prediction model in advance, and the training process of the deoxygenated blood volume prediction model comprises the following steps:
acquiring a training data set, wherein the training data set comprises quantitative blood oxygen level dependent data, velocity selective venous spin labeling perfusion imaging data and dynamic magnetic sensitive contrast enhanced perfusion imaging data of a plurality of brain tissues or a plurality of labeled delayed arterial spin labeling perfusion imaging data;
determining corresponding deoxygenated blood volume training images according to the quantitative blood oxygen level dependence data of each brain tissue;
determining corresponding venous cerebral blood volume training images according to the speed selective venous spin labeling perfusion imaging data of each brain tissue;
determining corresponding cerebral blood volume training images according to the dynamic magnetic sensitive contrast enhanced perfusion imaging data of each cerebral tissue or the artery spin labeling perfusion imaging data marked and delayed by the plurality of labels;
and training a preset neural network model by taking the venous cerebral blood volume training image and the cerebral blood volume training image corresponding to each cerebral tissue as input data and the deoxygenation blood volume training image as supervision data to obtain the deoxygenation blood volume prediction model.
Another aspect of the present invention provides an oxygen uptake fraction measuring apparatus comprising:
the acquisition module is used for acquiring a venous cerebral blood volume image and a cerebral blood volume image of the brain tissue to be detected;
the prediction module is used for processing the venous cerebral blood volume image and the cerebral blood volume image by utilizing a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected;
a determination module for determining an oxygen uptake score image of the brain tissue to be tested based on the deoxygenated blood volume image.
Another aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the oxygen uptake fraction measuring method as described above.
Another aspect of the present invention provides a computer readable storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the oxygen uptake fraction measurement method as described above.
Due to the technical scheme, the invention has the following beneficial effects:
oxygen uptake fraction measuring method according to embodiment of the inventionThe method, calculating Venous Cerebral Blood Volume by using velocity selective Venous spin labeling perfusion imaging data (Venous Cerebral Blood Volume,CBV v ) Calculating a Cerebral Blood Volume (CBV) image by using dynamic magnetic sensitive contrast enhanced perfusion imaging data or a plurality of marked delayed arterial spin labeling perfusion imaging data, predicting a Deoxygenated Blood Volume (DBV) image by using a Deoxygenated Blood Volume prediction model based on the venous Cerebral Blood Volume image and the Cerebral Blood Volume image, and finally obtaining a Deoxygenated Blood Volume (DBV) image according to the DBV,R 2 Parameters andR * 2 the parameters directly calculate oxygen metabolism indexes such as OEF and the like. According to the method, the oxygen metabolism index is quantitatively measured by a multi-parameter quantitative blood oxygen level dependence (mqBOLD) technology, so that the strong dependence on high signal-to-noise ratio is effectively avoided, and the accuracy of the calculation result of the deoxygenated blood volume can be improved by combining the venous cerebral blood volume image and the cerebral blood volume image and utilizing a method for predicting the deoxygenated blood volume by using a machine learning model, so that the accuracy of the oxygen uptake fraction measurement result can be improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the embodiment or the description of the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can also be derived from them without inventive effort.
FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the invention;
FIG. 2 is a flow chart of a method of measuring oxygen uptake fraction provided by one embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for measuring oxygen uptake fraction provided by an embodiment of the present invention;
FIG. 4 is a flow chart of training a deoxygenated blood volume prediction model provided by one embodiment of the present invention;
FIG. 5 is a schematic diagram of a deoxygenated blood volume prediction model training process provided by one embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an oxygen uptake fraction measuring apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Referring to the specification, fig. 1 is a schematic diagram illustrating an implementation environment provided by an embodiment of the invention. As shown in fig. 1, the implementation environment may include at least one medical scanning device 110 and a computer device 120, where the computer device 120 and each medical scanning device 110 may be directly or indirectly connected through wired or wireless communication, and the embodiment of the present invention is not limited thereto.
The computer device 120 may acquire medical image data of the brain tissue to be measured scanned by each of the medical scanning devices 110, such as Velocity-Selective Venous-Spin-Labeling (VS-VSL) perfusion imaging data, dynamic magnetic sensitivity Contrast enhancement (DSC) perfusion imaging data, or Arterial Spin Labeling (ASL) perfusion imaging data of Multiple Post-Labeling Delays (Multiple Post-Labeling Delays, multi-PLD), and the like, and determine an oxygen uptake score image of the brain tissue to be measured by the oxygen uptake score measurement method provided by the embodiment of the present invention for a doctor to review and guide a measure to be taken.
The medical scanning device 110 may be but not limited to a magnetic resonance imaging device, and the like, the computer device 120 may be but not limited to various servers, personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, the server may be an independent server or a server cluster or a distributed system composed of a plurality of servers, and may also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content Delivery Networks (CDNs), and big data and artificial intelligence platforms.
It should be noted that fig. 1 is only an example. It will be appreciated by those skilled in the art that although only 1 medical scanning device 110 is shown in fig. 1, it is not intended to limit embodiments of the present invention and more or fewer medical scanning devices 110 than those shown may be included in a practical application.
Referring to the specification and the drawings 2, there is shown a flow chart of a method for measuring oxygen uptake fraction according to an embodiment of the present invention, which can be applied to the computer device 120 in fig. 1, and particularly as shown in fig. 2, the method can include the following steps:
s210: and acquiring a venous cerebral blood volume image and a cerebral blood volume image of the brain tissue to be detected.
In the embodiment of the invention, the VS-VSL perfusion imaging technology in the magnetic resonance imaging technology can be utilized to collect the image of the brain tissue to be detected, so as to obtain the corresponding VS-VSL perfusion imaging data, and then the VS-VSL perfusion imaging data is utilized to calculate and obtain the venous cerebral blood volume image of the brain tissue to be detected. The brain tissue to be detected can be the brain tissue of a patient possibly suffering from ischemic stroke, the VS-VSL principle is similar to the ASL principle, the difference is that the VS-VSL marker is venous blood, and the marking mode is a speed selection marker, namely only blood meeting a certain speed condition can be marked.
Specifically, the acquiring the venous cerebral blood volume image of the brain tissue to be detected may include:
acquiring velocity selective venous spin labeling perfusion imaging data of a brain tissue to be detected;
and determining a venous cerebral blood volume image of the brain tissue to be detected according to the speed selective venous spin labeling perfusion imaging data.
In an embodiment of the present invention, the VS-VSL perfusion imaging data may include a control (control) image and a tag (tag) image, and the venous cerebral blood volume image may be calculated by the control image and the tag image, and the specific calculation formula is as follows:
wherein,S con a control image is represented by a control image,S tag representing a tag image.
It should be noted that since only venous blood with velocity higher than the set threshold is labeled in the VS-VSL perfusion imaging technique, slow blood in the small veins close to the capillaries is missed, and furthermore, the model is applied to the brain tissue and venous blood T 2 Consistent assumptions may also lead to calculatedCBV v The image is different from the DBV image.
In the embodiment of the invention, the image of the brain tissue to be detected can be acquired by using a DSC perfusion imaging technology in the magnetic resonance imaging technology to obtain corresponding DSC perfusion imaging data, and then the brain blood volume image of the brain tissue to be detected is calculated by using the DSC perfusion imaging data. Wherein, the brain tissue to be detected can be the brain tissue of a patient possibly suffering from cerebral arterial thrombosis.
Specifically, the acquiring a cerebral blood volume image of the brain tissue to be detected may include:
acquiring dynamic magnetic sensitive contrast enhanced perfusion imaging data of the brain tissue to be detected;
and determining a cerebral blood volume image of the brain tissue to be detected according to the dynamic magnetic sensitive contrast enhanced perfusion imaging data.
In the embodiment of the invention, DSC perfusion imaging data is common data for clinical diagnosis of cerebral apoplexy, and the specific calculation process for calculating the CBV image through the DSC perfusion imaging data can refer to the following formula:
wherein H LV 、H SV Correction values for large/small vessel hematocrit with the hreus-Lindquist effect, respectively, ρ is brain tissue density, c t (t) is a time-dependent curve of signal values of DSC perfusion imaging data, c a (t) is the arterial input curve. It should be noted that the CBV image calculated from the DSC perfusion imaging data is an image containing the total volume of arterial and venous blood and therefore has some difference from the DBV image.
In a possible embodiment, for example, in a case where the brain tissue to be tested cannot be injected with the contrast medium (for example, renal insufficiency of the patient, allergy to the contrast medium, or hyperthyroidism), the ASL perfusion imaging technique in the magnetic resonance imaging technique may be used to acquire an image of the brain tissue to be tested, so as to obtain Multi-PLD ASL perfusion imaging data without radiation and contrast medium, and further, the Multi-PLD ASL perfusion imaging data is used to calculate a cerebral blood volume image of the brain tissue to be tested.
Specifically, the acquiring a cerebral blood volume image of the brain tissue to be detected may include:
acquiring a plurality of artery spin labeling delayed perfusion imaging data of the brain tissue to be detected;
and determining a cerebral blood volume image of the brain tissue to be detected according to the artery spin labeling perfusion imaging data delayed after the plurality of labels.
It should be noted that, for the specific calculation process of calculating the CBV image according to the Multi-PLD ASL perfusion imaging data, reference may be made to the prior art, and the embodiment of the present invention is not described herein again. For example, an Arterial Transit Time (ATT) image of the brain tissue to be tested may be determined according to the Multi-PLD ASL perfusion imaging data, a Cerebral Blood Flow (CBF) image of the brain tissue to be tested may be determined according to the Arterial Transit Time image, and a Cerebral Blood volume image of the brain tissue to be tested may be determined according to the Arterial Transit Time image and the Cerebral Blood Flow image. The detailed calculation process of each step may refer to the prior art, and is not described herein again in the embodiments of the present invention.
Note that the above calculation of perfusion imaging data using VS-VSLCBV v The method of imaging, the method of calculating a CBV image using DSC perfusion imaging data, and the method of calculating a CBV image using Multi-PLD ASL perfusion imaging data may be performed by a computer device implementing the methods provided by embodiments of the invention, or by another device, and may use the resulting perfusion imaging data to generate a CBV imageCBV v The image and the CBV image are sent to the computer device, which is not limited by the embodiments of the present invention.
In one possible embodiment, the acquisition isCBV v After the image and the CBV image are obtained, the images and the CBV image can be respectively registered to a standard brain space to obtain the standard brain spaceCBV v Images and CBV images to simplify subsequent processing.
It should be noted that the registration method in the prior art can be adopted to perform the above-mentioned stepsCBV v The image and the CBV image are registered to a standard brain space, respectively, e.g. the image may be based on a T1 structure image of the brain tissue to be examinedCBV v Registering the image and the CBV image to a standard brain space to obtain the standard brain spaceCBV v Images, CBV images, etc., as embodiments of the present invention are not limited in this respect.
In a preferred embodiment, saidCBV v The images are registered to the cerebral blood volume image space to obtain the cerebral blood volume image spaceCBV v Imaging, and spatial mapping of the cerebral blood volumeCBV v Respectively registering the image and the CBV image to a standard brain space to obtain the standard brain spaceCBV v Images and CBV images.
It can be understood that different images are not completely consistent due to different resolutions, motion of a scanned object and the like, and therefore, all images of the brain tissue to be detected can be firstly subjected to personal registration to keep all images of the brain tissue to be detected consistent, and then the images are registered to a standard brain space, so that the robustness of a registration result can be improved.
S220: and processing the venous cerebral blood volume image and the cerebral blood volume image by using a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected.
In the embodiments of the present invention, the above may be combinedCBV v And estimating the deoxygenation blood volume of the brain tissue to be detected by utilizing a machine learning algorithm according to the image and the CBV image to obtain a deoxygenation blood volume image. As shown in fig. 3, theCBV v The image and the CBV image are input into a deoxygenated blood volume prediction model, and the deoxygenated blood volume prediction model can be used for the inputCBV v And analyzing and processing the image and the CBV image to obtain and output a deoxygenated blood volume image corresponding to the brain tissue to be detected.
In particular, the deoxygenated blood volume prediction model may be perfused by VS-VSLLike calculation of dataCBV v The method comprises the steps of obtaining an image, taking a CBV image calculated through DSC perfusion imaging data or Multi-PLD ASL perfusion imaging data as input data, taking a DBV image obtained through fitting a signal attenuation model through qBOLD data as supervision data, and carrying out deep learning training on a preset neural network model through a machine learning algorithm. The preset neural network model may include, but is not limited to, a model commonly used in the prior art, and for example, the model may be a model of Random Forest (RF), fuzzy clustering, ridge regression, or a deep neural network, which is not limited in this embodiment of the present invention.
S230: determining an oxygen uptake score image of the brain tissue to be tested based on the deoxygenated blood volume image.
In the embodiment of the present invention, as shown in fig. 3, after the DBV image output by the deoxygenated blood volume prediction model is obtained, the DBV image may be obtained according to the brain tissue to be detectedR 2 (transverse relaxation Rate) parametric image,R * 2 (gradient echo transverse relaxation rate) parameter images and the deoxygenated blood volume images, OEF images were determined using an mqBOLD model.
Specifically, the determining an oxygen uptake fraction image of the brain tissue under test based on the deoxygenated blood volume image may include:
obtaining said brain tissue to be examinedR 2 Parametric image andR * 2 a parameter image;
according to the deoxygenated blood volume image, theR 2 Parametric image and the methodR * 2 A parametric image, the oxygen uptake score image determined using a multi-parameter quantitative blood oxygen level dependent model.
Specifically, the method for obtaining the brain tissue to be testedR 2 Parametric image andR * 2 the parametric image may include:
acquiring multi-echo autorotation echo data and multi-echo gradient echo data of the brain tissue to be detected;
obtaining the brain tissue to be tested according to the fitting of the multi-echo autorotation echo dataR 2 A parameter image;
obtaining the brain tissue to be detected according to the fitting of the multi-echo gradient echo dataR * 2 A parametric image.
In the embodiment of the invention, the Spin Echo (SE) data and the Gradient Echo (GRE) data of the brain tissue to be detected can be respectively collected, and the change of the multi-Echo SE data and the multi-Echo GRE data along with time satisfies the following formula:
therefore, by respectively performing linear fitting on the logarithms of the multi-echo SE data and the multi-echo GRE data, the method can obtainR 2 Parametric image andR * 2 for the parametric image, the prior art may be referred to for a specific fitting process, and the embodiment of the present invention is not described herein again.
It should be noted that in some possible embodiments, other measurements may be usedR 2 AndR * 2 obtaining the brain tissue to be tested by the acquisition sequence and the calculation methodR 2 Parametric image andR * 2 parametric images, such as Strategically Acquired Gradient Echo (STAGE) data, may be Acquired of the brain tissue under test, and the determination may be made using the STAGE dataR 2 Parametric image and R * 2 Parametric images, etc. for determining the R of the brain tissue to be measured in the embodiments of the present invention 2 Parametric image andR * 2 the method of the parametric image is not particularly limited.
It should be noted that the above determination is based on multi-echo SE data and multi-echo GRE data or other dataDetermining the brain tissue to be examinedR 2 Parametric image andR * 2 the method for parameter image can be executed by computer equipment for realizing the method provided by the embodiment of the invention, and can also be executed by other equipment, and the obtained result is obtainedR 2 Parametric image andR * 2 the parameter image is sent to the computer device, which is not limited in this embodiment of the present invention.
In practical application, because deoxyhemoglobin has paramagnetism, unlike the weak diamagnetism of most tissues in the human body, deoxyhemoglobin can be regarded as a natural contrast agent, and a high-concentration area of the deoxyhemoglobin can present local magnetic field nonuniformity, thereby influencing a magnetic resonance signal. Specifically, the signal relaxation rate caused by the magnetic field inhomogeneity due to deoxygenated blood can be represented by the following formula:
wherein,R ’ 2 represents the signal relaxation rate caused by the magnetic field inhomogeneity due to deoxygenated blood, andR ’ 2 =R * 2 - R 2 Δ ω represents the frequency parameter corresponding to the magnetic field inhomogeneity, γ represents the proton magnetic rotation ratio 0 Representing the difference in magnetic susceptibility between fully oxygenated and fully deoxygenated erythrocytes, hct representing the hematocrit under normal conditions, B 0 Representing the main magnetic field strength. As shown in formula (5), the product of DBV and OEF can be measured by measuring R 2 Parameter and R * 2 And obtaining parameters.
From equation (5), an mqBOLD model for calculating OEF can be obtained, and the mqBOLD model can be represented by the following equation:
hair brushIn the illustrated embodiment, the brain tissue to be tested is obtainedR 2 Parametric image andR * 2 after the parametric image, the DBV image, theR 2 Parametric image and method for producing the sameR * 2 And (4) calculating the parameter image according to the formula (6) to obtain an OEF image of the brain tissue to be detected.
In summary, the oxygen uptake fraction measurement method according to the embodiment of the present invention calculates by using velocity selective venous spin labeling perfusion imaging dataCBV v Image, calculating CBV image by using dynamic magnetic sensitive contrast enhanced perfusion imaging data or a plurality of artery spin labeling perfusion imaging data delayed after labeling, and calculating CBV image based on the above dataCBV v Predicting to obtain DBV image by using deoxygenated blood volume prediction model, and finally obtaining the image according to DBV,R 2 Parameters andR * 2 the parameters directly calculate oxygen metabolism indexes such as OEF and the like. The method quantitatively measures the oxygen metabolism index through the mqBOLD technology, effectively avoids strong dependence on high signal-to-noise ratio, and combinesCBV v The images and the CBV images can improve the accuracy of the calculation result of the deoxygenation blood volume by utilizing the method for predicting the deoxygenation blood volume by utilizing the machine learning model, and further can improve the accuracy of the measurement result of the oxygen uptake fraction.
In a possible embodiment, referring to fig. 4 in conjunction with the description, the method may further include pre-training the deoxygenated blood volume prediction model, and the training process of the deoxygenated blood volume prediction model may include the following steps:
s410: a training data set is acquired that includes quantitative blood oxygen level dependent data for a plurality of brain tissues, velocity selective venous spin labeling perfusion imaging data, and dynamic magnetic sensitive contrast enhanced perfusion imaging data or a plurality of post-labeling delayed arterial spin labeling perfusion imaging data.
In the embodiment of the invention, the system can collect the healthy brain tissue and the patients with acute ischemic strokeThe qboll data, VS-VSL perfusion imaging data and DSC perfusion imaging data for a plurality of brain tissues, including the brain tissue, make up a training dataset. Alternatively, qBOLD data, VS-VSL perfusion imaging data, and Multi-PLD ASL perfusion imaging data for a plurality of brain tissues including healthy brain tissue and brain tissue of a patient with acute ischemic stroke may be collected to form a training data set. The data in the training data set is the DBV image with excellent scanning quality and no motion artifact, and is obtained through calculation,CBV v Both the image and CBV image have no data of artifacts.
Illustratively, qBOLD, VS-VSL and DSC perfusion imaging data for at least 200 healthy brain tissues and 100 brain tissues of patients with acute ischemic stroke may be acquired, wherein the scan quality is excellent, no motion artifacts are present, and the calculated DBV image, the data are selected,CBV v The data with no artifacts for both the images and the CBV images were used as training data sets.
S420: and determining corresponding deoxygenated blood volume training images according to the quantitative blood oxygen level dependence data of the brain tissues.
In the embodiment of the invention, a relatively accurate DBV training image can be calculated by adopting a method of fitting a multi-echo fitting signal attenuation model according to the quantitative blood oxygen level dependent data and is used as supervision data for training the deoxygenation blood volume prediction model. The processing method of the basic signal attenuation model in which the tissue signal is attenuated with time will be described below by taking as an example the qBOLD data acquired by the ges sequence.
Specifically, a basic signal attenuation model of tissue signal attenuation over time can be represented by the following equation:
wherein,
represents the transverse relaxation rate of brain tissue at time t,R ’ 2 represents the signal relaxation rate, S, caused by the magnetic field inhomogeneity due to deoxygenated blood 0 Indicating the initial signal strength.
First, the basic signal attenuation model shown in the formula (7) can be eliminatedR t 2 Can be calculated in particular directly using signals which are time-symmetric with respect to the spin echoR t 2 The method of (3) eliminates. Illustratively, two echo calculations may be made with TE as the symmetryR t 2 The calculation formula is as follows:
wherein TE is the SE echo time of the GESSE series, and tau is the time difference between the selected echo and TE.
Cancellation ofR t 2 As can be seen from the formula (7),
satisfies the following formula:
it can be seen that when t>1.5t c When the temperature of the water is higher than the set temperature,
is in a linear relation with the t,R ’ 2 the constant C may be determined by acquiring signals corresponding to multiple echo times (i.e., the GESSE sequence in this example), and choosing to satisfy t>1.5t c Data for the conditions were obtained by linear fitting. The specific method of linear fitting may refer to the prior art, and the embodiments of the present invention are not described herein again.
Further, the DBV can be obtained by the following formula:
wherein S is S (0) Is the signal actually acquired at the time t =0, S L,extrap (0) Is (7) wherein S L (t) extrapolating the resulting signal at t = 0. The final OEF can be calculated from the equation (5). The specific method of extrapolation may refer to the prior art, and the embodiments of the present invention are not described herein again.
By adopting the method, the corresponding DBV training image can be calculated according to the quantitative blood oxygen level dependence data of each brain tissue and can be used as the supervision data for training the deoxygenated blood volume prediction model.
It should be noted that, in some possible embodiments, other multi-echo acquisition sequences, such as ASE series, auseide series, etc., may also be used to fit the basic signal attenuation model to obtain the deoxygenated blood volume, and the embodiment of the present invention does not specifically limit the type of the acquisition sequence used.
In a possible embodiment, when fitting the signal attenuation model by using ASE series, the signal attenuation model can be eliminated by fixing the acquisition time tR t 2 The influence of (c).
It should be noted that, in some possible embodiments, in addition to the basic signal attenuation model described above, other signal attenuation models, such as a multi-component model (including a blood signal, a cerebrospinal fluid/interstitial fluid signal into a model) diffusion qBOLD model, etc., may be used to calculate the deoxygenated blood volume, and the type of the signal attenuation model used is not particularly limited by the embodiments of the present invention.
As can be understood, the method for fitting the signal attenuation model by multiple echoes can obtain more accurate DBV training images under the conditions of sufficient data volume, sufficient signal-to-noise ratio and reasonable optimization method because the fine model structure of the method is more in accordance with the real condition, and the DBV training images can be used as supervision data for training the deoxygenation blood volume prediction model, so that more accurate models can be obtained by training, and follow-up basis is improvedCBV v Predicting DBV pictures for pictures and CBV picturesAccuracy, and accuracy of calculating oxygen uptake fraction.
In one possible embodiment, after obtaining the DBV training image, the DBV training image may be registered to a standard brain space to obtain the DBV training image of the standard brain space, so as to simplify the subsequent processing procedure.
In a preferred embodiment, the DBV training image may be registered to a cerebral blood volume image space to obtain a DBV training image of the cerebral blood volume image space, and then the DBV training image of the cerebral blood volume image space is registered to a standard cerebral space to obtain a standard cerebral space DBV training image.
S430: and determining corresponding venous cerebral blood volume training images according to the speed selective venous spin labeling perfusion imaging data of each brain tissue.
In the embodiment of the invention, corresponding perfusion imaging data can be obtained through calculation according to VS-VSL perfusion imaging dataCBV v The training image, the specific calculation method can refer to the calculation in step S210CBV v The content of the image is not described herein again in the embodiments of the present invention.
In one possible embodiment, obtainingCBV v After training the image, the image may be processedCBV v The training images are registered to the standard brain space to obtain the standard brain spaceCBV v The images are trained to simplify subsequent processing.
In a preferred embodiment, saidCBV v The training image is firstly registered to the cerebral blood volume image space to obtain the cerebral blood volume image spaceCBV v Training images, and spatial mapping of the cerebral blood volume imagesCBV v The training image is registered to the standard brain space to obtain the standard brain spaceCBV v And (5) training the image.
It can be understood that different images are not completely consistent due to different resolutions, motion of a scanning object and the like, so that the images of the brain tissues can be registered individually first, so that all the images of the brain tissues are consistent, and then the images are registered to a standard brain space, thereby improving the robustness of the registration result.
S440: and determining a corresponding cerebral blood volume training image according to the dynamic magnetic sensitivity contrast enhanced perfusion imaging data of each cerebral tissue or the artery spin labeling perfusion imaging data delayed after the labeling.
In the embodiment of the present invention, the corresponding CBV training image may be obtained by calculation according to DSC perfusion imaging data, and the specific calculation method may refer to the content of the CBV image calculated in step S210, which is not described herein again.
In a possible embodiment, the corresponding CBV training image may also be obtained by calculation according to Multi-PLD ASL perfusion imaging data, and the specific calculation method may refer to the content of the CBV image calculated in step S210, which is not described herein again in the embodiments of the present invention.
In one possible embodiment, after the CBV training image is obtained, the CBV training image may be registered to a standard brain space to obtain a CBV training image of the standard brain space, so as to simplify the subsequent processing procedure.
S450: and training a preset neural network model by taking the venous cerebral blood volume training image and the cerebral blood volume training image corresponding to each cerebral tissue as input data and the deoxygenation blood volume training image as supervision data to obtain the deoxygenation blood volume prediction model.
In the embodiment of the present invention, as shown in fig. 5, DBV training images obtained by fitting qBOLD data to a signal attenuation model may be used as supervision data, and DBV training images obtained by filling imaging data with VS-VSL may be used as supervision dataCBV v And taking a training image and a CBV training image obtained through DSC perfusion imaging data or Multi-PLDASL perfusion imaging data as input data, and performing deep learning training on a preset neural network model through a machine learning algorithm to obtain the deoxygenated blood volume prediction model.
The preset neural network model may include, but is not limited to, a model commonly used in the prior art, and for example, the model may be a model of a random forest, a fuzzy cluster, a ridge regression, or a deep neural network, which is not limited in this embodiment of the present invention.
Specifically, in the process of training the deoxygenated blood volume prediction model, the data in the training data set may be cross-divided into a training set and a test set (for example, the data may be divided into five groups, any four groups of the five groups are taken as the training set each time, and the remaining group is the test set), and the data in the training set is used for calculation to obtain the dataCBV v Training the deoxygenation blood volume prediction model by using a training image, a CBV training image and a DBV training image, and calculating by using data in a test setCBV v Training the images, CBV training images and DBV training images to test the performance of the deoxygenation blood volume prediction model obtained by training, evaluating the performance of the deoxygenation blood volume prediction model, and completing the training until the trained deoxygenation blood volume prediction model meets the preset training conditions to obtain a reliable modelCBV v The image and CBV image are input to predict a model of a DBV image of brain tissue.
The preset training condition may be preset, and may be set to be calculated based on data in the test set by using a trained deoxygenated blood volume prediction modelCBV v The similarity between the DBV image predicted by the training image and the CBV training image and the DBV training image calculated by using the data in the test set is greater than a preset threshold, and the preset threshold may be set according to an actual situation, which is not limited in the embodiment of the present invention.
It can be understood that the DBV training image obtained by using qBOLD data is taken as supervision data, and the VS-VSL perfusion imaging data is takenCBV v The CBV training image obtained by the training image, the DSC perfusion imaging data or the Multi-PLDASL perfusion imaging data is used as input data, model training for deep learning is carried out to obtain a prediction model for predicting the deoxygenation blood volume, and the reliability of the deoxygenation blood volume prediction model obtained by training can be improved, so that the reliability of the oxygen uptake fraction measurement result is ensured.
Referring to the specification and to fig. 6, there is shown a structure of an oxygen uptake fraction measuring apparatus 600 according to an embodiment of the present invention. As shown in fig. 6, the apparatus 600 may include:
an obtaining module 610, configured to obtain a venous cerebral blood volume image and a cerebral blood volume image of a brain tissue to be detected;
the prediction module 620 is configured to process the venous cerebral blood volume image and the cerebral blood volume image by using a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected;
a determining module 630, configured to determine an oxygen uptake score image of the brain tissue to be tested based on the deoxygenated blood volume image.
In one possible embodiment, the apparatus 600 may further include a registration module for registering the venous cerebral blood volume image and the cerebral blood volume image to a standard cerebral space, respectively, to obtain a venous cerebral blood volume image and a cerebral blood volume image of the standard cerebral space.
In a possible embodiment, the registration module may be further configured to register the venous cerebral blood volume image to a cerebral blood volume image space, so as to obtain a venous cerebral blood volume image of the cerebral blood volume image space; and respectively registering the venous cerebral blood volume image and the cerebral blood volume image of the cerebral blood volume image space to a standard cerebral space to obtain a venous cerebral blood volume image and a cerebral blood volume image of the standard cerebral space.
In one possible embodiment, the apparatus 600 may further include a model training module, and the model training module may include:
a training data set acquisition unit for acquiring a training data set comprising quantitative blood oxygen level dependent data, velocity selective venous spin labeling perfusion imaging data, and dynamic magnetic sensitive contrast enhanced perfusion imaging data or a plurality of labeled delayed arterial spin labeling perfusion imaging data of a plurality of brain tissues;
a first training image determining unit, configured to determine a corresponding deoxygenated blood volume training image according to the quantitative blood oxygen level dependency data of each brain tissue;
the second training image determining unit is used for determining corresponding venous cerebral blood volume training images according to the speed selective venous spin labeling perfusion imaging data of all brain tissues;
a third training image determining unit, configured to determine a corresponding cerebral blood volume training image according to the dynamic magnetic sensitivity contrast enhanced perfusion imaging data of each brain tissue or the artery spin labeling perfusion imaging data delayed after labeling;
and the model training unit is used for training a preset neural network model by taking the venous cerebral blood volume training image and the cerebral blood volume training image corresponding to each brain tissue as input data and the deoxygenated blood volume training image as supervision data to obtain the deoxygenated blood volume prediction model.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, the division of each functional module is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the apparatus provided in the above embodiments and the corresponding method embodiments belong to the same concept, and specific implementation processes thereof are detailed in the corresponding method embodiments and are not described herein again.
An embodiment of the present invention further provides an electronic device, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the oxygen uptake fraction measuring method provided in the above method embodiment.
The memory may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.
In a specific embodiment, fig. 7 is a schematic diagram illustrating a hardware structure of an electronic device for implementing the oxygen uptake score measurement method provided by the embodiment of the present invention, where the electronic device may be a computer terminal, a mobile terminal, or other devices, and the electronic device may also participate in forming or including the oxygen uptake score measurement apparatus provided by the embodiment of the present invention. As shown in fig. 7, the electronic device 700 may include one or more computer-readable storage medium memories 710, one or more processing cores' processors 720, an input unit 730, a display unit 740, a Radio Frequency (RF) circuit 750, a wireless fidelity (WiFi) module 760, and a power supply 770, among other components. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 7 does not constitute a limitation of electronic device 700 and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. Wherein:
the memory 710 may be used to store software programs and modules, and the processor 720 executes various functional applications and data processing by operating or executing the software programs and modules stored in the memory 710 and calling data stored in the memory 710. The memory 710 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 710 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device. Accordingly, memory 710 may also include a memory controller to provide processor 720 access to memory 710.
The processor 720 is a control center of the electronic device 700, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device 700 and processes data by operating or executing software programs and/or modules stored in the memory 710 and calling data stored in the memory 710, thereby performing overall monitoring of the electronic device 700. The Processor 720 may be a central processing unit, or may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input unit 730 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, the input unit 730 may include a touch-sensitive surface 731 as well as other input devices 732. In particular, the touch-sensitive surface 731 may include, but is not limited to, a touch pad or touch screen, and the other input devices 732 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 740 may be used to display information input by or provided to a user and various graphic user interfaces of the electronic device, which may be configured by graphics, text, icons, video, and any combination thereof. The Display unit 740 may include a Display panel 741, and optionally, the Display panel 741 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.
The RF circuit 750 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, for receiving downlink information of a base station and then processing the received downlink information by the one or more processors 720; in addition, data relating to uplink is transmitted to the base station. In general, RF circuit 750 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuit 750 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), general Packet Radio Service (GPRS), code Division Multiple Access (CDMA), wideband Code Division Multiple Access (WCDMA), long Term Evolution (LTE), email, short Messaging Service (SMS), and the like.
WiFi belongs to short-range wireless transmission technology, and the electronic device 700 can help the user send and receive email, browse web pages, access streaming media, etc. through the WiFi module 760, which provides the user with wireless broadband internet access. Although fig. 7 shows the WiFi module 760, it is understood that it does not belong to the essential constitution of the electronic device 700, and may be omitted entirely as needed within the scope not changing the essence of the invention.
The electronic device 700 further comprises a power supply 770 (e.g., a battery) for providing power to the various components, which may preferably be logically connected to the processor 720 via a power management system, such that the power management system may manage charging, discharging, and power consumption. The power supply 770 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
It should be noted that, although not shown, the electronic device 700 may further include a bluetooth module, and the like, which is not described herein again.
An embodiment of the present invention further provides a computer-readable storage medium, which may be disposed in an electronic device to store at least one instruction or at least one program for implementing an oxygen uptake fraction measuring method, where the at least one instruction or the at least one program is loaded and executed by the processor to implement the oxygen uptake fraction measuring method provided by the above method embodiment.
Optionally, in an embodiment of the present invention, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
An embodiment of the invention also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the oxygen uptake fraction measurement method provided in the various alternative embodiments described above.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method of measuring oxygen uptake fraction, comprising:
acquiring a venous cerebral blood volume image and a cerebral blood volume image of a brain tissue to be detected;
processing the venous cerebral blood volume image and the cerebral blood volume image by utilizing a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected;
determining an oxygen uptake fraction image of the brain tissue to be tested based on the deoxygenated blood volume image.
2. The method of claim 1, wherein obtaining the venous cerebral blood volume image of the brain tissue to be tested comprises:
acquiring velocity selective venous spin labeling perfusion imaging data of brain tissues to be detected;
and determining a venous cerebral blood volume image of the brain tissue to be detected according to the speed selective venous spin labeling perfusion imaging data.
3. The method of claim 1, wherein obtaining a cerebral blood volume image of the brain tissue to be tested comprises:
acquiring dynamic magnetic sensitive contrast enhanced perfusion imaging data of the brain tissue to be detected or artery spin labeling perfusion imaging data delayed after a plurality of labels;
and determining a cerebral blood volume image of the brain tissue to be detected according to the dynamic magnetic sensitivity contrast enhanced perfusion imaging data or the artery spin labeling perfusion imaging data delayed after the labeling.
4. The method of claim 1, further comprising:
registering the venous cerebral blood volume image to a cerebral blood volume image space to obtain a venous cerebral blood volume image of the cerebral blood volume image space;
respectively registering the venous cerebral blood volume image of the cerebral blood volume image space and the cerebral blood volume image to a standard cerebral space to obtain a venous cerebral blood volume image and a cerebral blood volume image of the standard cerebral space.
5. The method of claim 1, wherein the determining an oxygen uptake score image of the brain tissue under test based on the deoxygenated blood volume image comprises:
obtaining R of the brain tissue to be detected 2 Parametric image and R * 2 A parameter image;
according to the deoxygenated blood volume image and the R 2 Parametric image and said R * 2 A parametric image, the oxygen uptake score image determined using a multi-parameter quantitative blood oxygen level dependent model.
6. The method of claim 5, wherein obtaining R of the brain tissue to be tested 2 Parametric image and R * 2 The parametric image includes:
acquiring multi-echo autorotation echo data and multi-echo gradient echo data of the brain tissue to be detected;
obtaining R of the brain tissue to be detected according to the fitting of the multi-echo autorotation echo data 2 A parameter image;
obtaining the R of the brain tissue to be detected according to the fitting of the multi-echo gradient echo data * 2 A parametric image.
7. The method of claim 1, further comprising pre-training the deoxygenated blood volume prediction model, wherein the training of the deoxygenated blood volume prediction model comprises:
acquiring a training data set, wherein the training data set comprises quantitative blood oxygen level dependent data, velocity selective venous spin labeling perfusion imaging data and dynamic magnetic sensitive contrast enhanced perfusion imaging data of a plurality of brain tissues or a plurality of labeled delayed arterial spin labeling perfusion imaging data;
determining corresponding deoxygenated blood volume training images according to the quantitative blood oxygen level dependence data of each brain tissue;
determining corresponding venous cerebral blood volume training images according to the velocity-selective venous spin labeling perfusion imaging data of each brain tissue;
determining a corresponding cerebral blood volume training image according to the dynamic magnetic sensitivity contrast enhanced perfusion imaging data of each cerebral tissue or the artery spin labeling perfusion imaging data delayed after labeling;
and training a preset neural network model by taking the venous cerebral blood volume training image and the cerebral blood volume training image corresponding to each cerebral tissue as input data and the deoxygenation blood volume training image as supervision data to obtain the deoxygenation blood volume prediction model.
8. An oxygen uptake fraction measuring device, comprising:
the acquisition module is used for acquiring a venous cerebral blood volume image and a cerebral blood volume image of the brain tissue to be detected;
the prediction module is used for processing the venous cerebral blood volume image and the cerebral blood volume image by utilizing a pre-trained deoxygenated blood volume prediction model to obtain a deoxygenated blood volume image of the brain tissue to be detected;
a determination module for determining an oxygen uptake score image of the brain tissue to be tested based on the deoxygenated blood volume image.
9. An electronic device, comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the oxygen uptake score measurement method of any of claims 1-7.
10. A computer-readable storage medium, having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to perform the oxygen uptake fraction measurement method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211515305.7A CN115530820B (en) | 2022-11-30 | 2022-11-30 | Oxygen uptake fraction measuring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211515305.7A CN115530820B (en) | 2022-11-30 | 2022-11-30 | Oxygen uptake fraction measuring method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115530820A CN115530820A (en) | 2022-12-30 |
| CN115530820B true CN115530820B (en) | 2023-01-31 |
Family
ID=84722355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211515305.7A Active CN115530820B (en) | 2022-11-30 | 2022-11-30 | Oxygen uptake fraction measuring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115530820B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693491A (en) * | 2017-04-07 | 2018-10-23 | 康奈尔大学 | Steady quantitative susceptibility imaging system and method |
| CN111096748A (en) * | 2019-12-19 | 2020-05-05 | 首都医科大学宣武医院 | Method for dynamically measuring brain oxygen metabolic rate |
| WO2022040449A1 (en) * | 2020-08-20 | 2022-02-24 | Cornell University | System and method of accurate quantitative mapping of biophysical parameters from mri data |
| CN114303169A (en) * | 2019-05-28 | 2022-04-08 | 康奈尔大学技术许可中心 | System and method for quantitative measurement of physical properties |
| WO2022231167A1 (en) * | 2021-04-29 | 2022-11-03 | 경북대학교 산학협력단 | Magnetic resonance imaging device and method for precisely measuring cerebral oxygen metabolism |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6679467B2 (en) * | 2016-11-07 | 2020-04-15 | 株式会社日立製作所 | Magnetic resonance imaging apparatus and method for calculating oxygen uptake rate |
| EP3631425A4 (en) * | 2017-05-22 | 2021-02-24 | The Regents of The University of California | Simultaneous ph and oxygen weighted mri contrast using multi-echo chemical exchange saturation transfer imaging (me-cest) |
| US11965946B2 (en) * | 2020-12-04 | 2024-04-23 | Max-Planck-Gesellschaft Zur Foerderung Der Wissenschaften E. V. | Machine learning based processing of magnetic resonance data, including an uncertainty quantification |
-
2022
- 2022-11-30 CN CN202211515305.7A patent/CN115530820B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693491A (en) * | 2017-04-07 | 2018-10-23 | 康奈尔大学 | Steady quantitative susceptibility imaging system and method |
| CN114303169A (en) * | 2019-05-28 | 2022-04-08 | 康奈尔大学技术许可中心 | System and method for quantitative measurement of physical properties |
| CN111096748A (en) * | 2019-12-19 | 2020-05-05 | 首都医科大学宣武医院 | Method for dynamically measuring brain oxygen metabolic rate |
| WO2022040449A1 (en) * | 2020-08-20 | 2022-02-24 | Cornell University | System and method of accurate quantitative mapping of biophysical parameters from mri data |
| WO2022231167A1 (en) * | 2021-04-29 | 2022-11-03 | 경북대학교 산학협력단 | Magnetic resonance imaging device and method for precisely measuring cerebral oxygen metabolism |
Non-Patent Citations (3)
| Title |
|---|
| Cerebral oxygen extraction fraction MRI: Techniques and applications;Dengrong Jiang 等;《Magn Reson Med. 2022》;20220505;全文 * |
| Substituting Gadolinium in Brain MRI Using DeepContrast;Haoran Sun;《2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)》;20200407;全文 * |
| Whole-brain 3D mapping of oxygen metabolism using constrained quantitative BOLD;Hyunyeol Lee 等;《NeuroImage 250 (2022) 》;20220129;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115530820A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bane et al. | Consensus-based technical recommendations for clinical translation of renal BOLD MRI | |
| Erus et al. | Imaging patterns of brain development and their relationship to cognition | |
| Kudo et al. | Oxygen extraction fraction measurement using quantitative susceptibility mapping: comparison with positron emission tomography | |
| Hagmann et al. | White matter maturation reshapes structural connectivity in the late developing human brain | |
| Smirnakis et al. | Spatial specificity of BOLD versus cerebral blood volume fMRI for mapping cortical organization | |
| CN113628207B (en) | Image area segmentation method, device, equipment and storage medium | |
| CN114820602B (en) | Ischemia area segmentation method, device, equipment and storage medium | |
| US11931208B2 (en) | Cerebral perfusion state classification apparatus and method, device, and storage medium | |
| US20230056555A1 (en) | Cerebral perfusion state classification apparatus, method and device, and model training apparatus | |
| He et al. | Automated truncation method for myocardial T2* measurement in thalassemia | |
| Markenroth Bloch et al. | Investigation of cerebrospinal fluid flow in the cerebral aqueduct using high-resolution phase contrast measurements at 7T MRI | |
| CN113706560A (en) | Ischemia area segmentation method, device, equipment and storage medium | |
| Fujiwara et al. | Comparison of long-labeled pseudo-continuous arterial spin labeling (ASL) features between young and elderly adults: special reference to parameter selection | |
| Fki et al. | Machine learning with internet of things data for risk prediction: application in ESRD | |
| Wu et al. | The apparent diffusion coefficient is strongly correlated with extracellular volume, a measure of myocardial fibrosis, and subclinical cardiomyopathy in patients with systemic lupus erythematosus | |
| CN109920528A (en) | Health monitoring all-in-one machine and health monitor method | |
| CN115530820B (en) | Oxygen uptake fraction measuring method, device, equipment and storage medium | |
| Langner et al. | Large-scale inference of liver fat with neural networks on uk biobank body mri | |
| Vaziri-Bozorg et al. | Diffusion-weighted magnetic resonance imaging for diagnosis of liver fibrosis and inflammation in chronic viral hepatitis: the performance of low or high B values and small or large regions of interest | |
| Schelbert et al. | Exploiting differences in myocardial compartments with native T1 and extracellular volume fraction for the diagnosis of hypertrophic cardiomyopathy | |
| Ibrahim et al. | MRI T2* imaging for assessment of liver iron overload: study of different data analysis approaches | |
| Lee et al. | Improved 3‐Tesla cardiac cine imaging using wideband | |
| Alvi et al. | Burden of cardiac siderosis in a Thalassemia-Major endemic population: a preliminary report from Pakistan | |
| CN113616160A (en) | FFR (fringe field reflectometry) determination method, device, equipment and medium based on multi-modal medical images | |
| Yoshino et al. | Directed proximal magnetic resonance coronary angiography compared with conventional contrast coronary angiography |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230907 Address after: Room 1504-C, Building 1, Paddy Internet Industrial Park, No. 399, Xiarong Street, East the Taihu Lake Ecological Tourism Resort (the Taihu Lake New Town), Wujiang District, Suzhou City, Jiangsu Province, 215224 Patentee after: Naoxi (Suzhou) Intelligent Technology Co.,Ltd. Address before: Room 1702-3, building 1, rice Internet Industrial Park, No. 399, Xiarong street, Taihu new town, Wujiang District, Suzhou, Jiangsu 215224 Patentee before: Naoxi (Suzhou) Intelligent Technology Co.,Ltd. Patentee before: SHANGHAI FOURTH PEOPLE'S Hospital |
|
| TR01 | Transfer of patent right |