Brain network extraction method and device, and magnetic resonance imaging equipment

Abstract

The application provides a brain network extraction method and device and a magnetic resonance imaging equipment. The method comprises the following steps: acquiring at least two functional magnetic resonance imaging data of a subject in a resting state, wherein the at least two functional magnetic resonance imaging data comprises a blood oxygen level dependent signal and a blood vessel spatial occupancy signal; and extracting a brain network of the subject based on the blood oxygen level dependent signal and the blood vessel spatial occupancy signal. The application extracts the brain network of the subject based on the blood oxygen level dependent signal and the blood vessel spatial occupancy signal, can provide a more accurate synchronous signal position, eliminates the influence of noises such as head movement and breathing on the brain network, and thus can reduce the randomness of the extracted brain network, and improve the accuracy and reliability of the brain network.

Description

Technical Field

[0001] This invention relates to the field of brain influence analysis technology, specifically to a brain network extraction method, apparatus, and magnetic resonance imaging equipment. Background Technology

[0002] Functional magnetic resonance imaging (fMRI) provides a powerful technical means for the extraction and analysis of brain functional networks, greatly promoting the progress of brain science research. Currently, extracting brain networks using fMRI data has become a very important research topic.

[0003] Current brain network extraction methods utilize blood oxygen level dependent (BOLD) signals to extract brain networks. The principle is as follows: deoxygenated hemoglobin in the blood is paramagnetic, while oxygenated hemoglobin is diamagnetic. When brain tissue is excited, local blood vessels dilate, allowing a large influx of fresh, oxygen-rich blood. As a result, the content of diamagnetic substances, i.e., oxygenated hemoglobin, in venous blood increases, thereby prolonging the transverse relaxation time T2. Images acquired by an MRI system show enhanced signals in activated brain regions, thus allowing synchronously changing different brain regions to be classified into a brain network.

[0004] However, there are technical problems with extracting brain networks using BOLD signals: when measuring a single subject, the extracted brain network has high randomness and low accuracy due to noise such as head movement and breathing. Summary of the Invention

[0005] In view of this, it is necessary to provide a brain network extraction method, device, and magnetic resonance imaging equipment to solve the technical problems of high randomness and low accuracy of the extracted brain networks in the prior art.

[0006] On one hand, the present invention provides a method for extracting brain networks, comprising:

[0007] Acquire at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest, the at least two fMRI data points including blood oxygen level-dependent signals and vascular space occupancy signals;

[0008] The subject's brain network was extracted based on the blood oxygen level-dependent signal and the vascular space occupancy signal.

[0009] In some possible implementations, acquiring at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest includes:

[0010] Acquire the antipulse signal and determine the tissue signal of the subject after the blood signal is eliminated based on the antipulse signal;

[0011] The tissue signals are acquired within a preset acquisition time and in a preset acquisition method, thereby obtaining the vascular space occupancy signal and the blood oxygen level dependent signal in sequence.

[0012] In some possible implementations, the preset acquisition method is a planar accelerated acquisition method.

[0013] In some possible implementations, extracting the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal includes:

[0014] The blood oxygen level-dependent signal and the vascular space occupancy signal are spliced ​​together in the time direction to obtain a spliced ​​signal;

[0015] The brain network is extracted based on the spliced ​​signal.

[0016] In some possible implementations, extracting the brain network based on the spliced ​​signal includes:

[0017] The spliced ​​signal is processed using independent component analysis to obtain a spatially independent component distribution, which is the brain network.

[0018] In some possible implementations, prior to extracting the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal, the method further includes:

[0019] The resolutions of the blood oxygen level dependent signal and the vascular space occupancy signal are adjusted so that the resolution of the blood oxygen level dependent signal is the same as that of the vascular space occupancy signal.

[0020] In some possible implementations, the blood oxygen level-dependent signal includes multiple blood oxygen level-dependent sub-signals, and the vascular space occupancy signal includes multiple vascular space occupancy sub-signals; the extraction of the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal further includes:

[0021] Identify multiple brain regions of interest in the subject's brain regions;

[0022] Based on the multiple blood oxygen level dependent sub-signals and the multiple blood vessel space occupancy sub-signals, the average blood oxygen level dependent signal and the average blood vessel space occupancy signal of each of the multiple brain regions of interest are determined;

[0023] The subject's first initial brain network was determined based on the mean blood oxygen level-dependent signal.

[0024] The subject's second initial brain network was determined based on the average vascular space occupancy signal;

[0025] Identify overlapping brain regions of interest between the first initial brain network and the second initial brain network, wherein the overlapping brain regions of interest are the brain networks of the subject.

[0026] In some possible implementations, determining the subject's first initial brain network based on the mean blood oxygen level-dependent signal includes:

[0027] The first correlation coefficient between any two brain regions of interest among the plurality of brain regions of interest is determined based on the mean blood oxygen level dependent signal.

[0028] The first initial brain network is determined based on the first correlation coefficient and a preset first correlation coefficient threshold.

[0029] The determination of the subject's second initial brain network based on the average vascular space occupancy signal includes:

[0030] A second correlation coefficient between any two brain regions of interest among the plurality of brain regions of interest is determined based on the average vascular space occupancy signal;

[0031] The second initial brain network is determined based on the second correlation coefficient and a preset second correlation coefficient threshold.

[0032] On the other hand, the present invention also provides a brain network extraction device, comprising:

[0033] A functional magnetic resonance imaging (fMRI) data acquisition unit is used to acquire at least two fMRI data points of a subject in a resting state, wherein the at least two fMRI data points include blood oxygen level-dependent signals and vascular space occupancy signals.

[0034] A brain network extraction unit is used to extract the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal.

[0035] On the other hand, the present invention also provides a magnetic resonance imaging device, including a memory and a processor, wherein,

[0036] The memory is used to store programs;

[0037] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the brain network extraction method in any of the above implementations.

[0038] The beneficial effects of the above embodiments are as follows: The brain network extraction method provided by the present invention obtains the blood oxygen level-dependent signal and vascular space occupancy signal of the subject in the resting state, and extracts the subject's brain network based on the blood oxygen level-dependent signal and vascular space occupancy signal. Since the vascular space occupancy signal has a high response speed and localization specificity to neuronal activity, compared with the existing method of extracting the brain network based only on the blood oxygen level-dependent signal, the method of extracting the subject's brain network based on both the blood oxygen level-dependent signal and the vascular space occupancy signal can provide a more accurate synchronization signal location, and to a certain extent eliminate the influence of noise such as head movement and breathing on the brain network, thereby reducing the randomness of the extracted brain network and improving the accuracy and reliability of the brain network. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic flowchart of an embodiment of the brain network extraction method provided by the present invention;

[0041] Figure 2 For the present invention Figure 1 A schematic diagram of an embodiment of step S101;

[0042] Figure 3 A timing diagram of the acquisition of blood oxygen level-dependent signals and vascular space occupancy signals provided in an embodiment of the present invention;

[0043] Figure 4 For the present invention Figure 1 A schematic flowchart of an embodiment of step S102;

[0044] Figure 5 This is a schematic diagram of an embodiment of brain network extraction based on independent component analysis provided by the present invention;

[0045] Figure 6 For the present invention Figure 1 A schematic diagram of another embodiment of step S102;

[0046] Figure 7 For the present invention Figure 6 A schematic flowchart of an embodiment of step S603;

[0047] Figure 8 For the present invention Figure 6 A schematic flowchart of an embodiment of step S604;

[0048] Figure 9 A schematic diagram of an embodiment of the brain network extraction device provided by the present invention;

[0049] Figure 10 This is a schematic diagram of an embodiment of the magnetic resonance imaging device provided by the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0051] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0052] Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0053] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0054] This invention provides a brain network extraction method, apparatus, and magnetic resonance imaging device, which are described below.

[0055] Figure 1 This is a schematic flowchart of an embodiment of the brain network extraction method provided by the present invention, as shown below. Figure 1 As shown, brain network extraction methods include:

[0056] S101. Acquire at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest, including blood oxygen level-dependent signals and vascular space occupancy signals.

[0057] S102. Extracting the subject's brain network based on blood oxygen level-dependent signals and vascular space occupancy signals.

[0058] Oxygen level-dependent signals refer to the signals resulting from changes in the local tissue T2 relaxation time caused by changes in the ratio of oxyhemoglobin to deoxyhemoglobin in the local blood of brain activity areas.

[0059] Vascular space occupancy signal refers to the signal obtained from the change that occurs when the blood volume of small blood vessels in the local activation area increases due to the activity of neurons, resulting in a corresponding decrease in the volume of extravascular tissue.

[0060] Compared with existing technologies, the brain network extraction method provided in this invention obtains the blood oxygen level-dependent signal and vascular space occupancy signal of the subject in a resting state, and extracts the subject's brain network based on the blood oxygen level-dependent signal and vascular space occupancy signal. Since the vascular space occupancy signal has a high response speed and localization specificity to neuronal activity, compared with the existing method of extracting the brain network based only on the blood oxygen level-dependent signal, extracting the subject's brain network based on both the blood oxygen level-dependent signal and the vascular space occupancy signal can provide more accurate synchronization signal location, and to a certain extent eliminate the influence of noise such as head movement and breathing on the brain network, thereby reducing the randomness of the extracted brain network and improving the accuracy and reliability of the brain network.

[0061] In some embodiments of the present invention, step S101 may obtain functional magnetic resonance imaging data from a Picture Archiving and Communication Systems (PACS) server or from a functional magnetic resonance imaging (fMRI) device.

[0062] To improve the accuracy and reliability of the acquired functional magnetic resonance imaging (fMRI) data, and thus improve the accuracy and reliability of the extracted brain network, in some embodiments of the present invention, the fMRI data should be preprocessed before executing step S102. The preprocessing includes at least one of the following preprocessing procedures: removing unstable timepoints, slice timing, head motion correction, spatial smoothing, detrend removal, despiking, filtering, nuisance covariates regression, and scrubbing.

[0063] In some embodiments of the present invention, the specific implementation process of step S102 is as follows: after obtaining the blood oxygen level dependent signal and the vascular space occupancy signal, the common spatial pattern of the blood oxygen level dependent signal and the vascular space occupancy signal is extracted to obtain the subject's brain network.

[0064] In a specific embodiment of the present invention, steps S101-S102 are implemented as follows: functional magnetic resonance imaging (fMRI) data is obtained from a PACS server or fMRI device, wherein the fMRI data includes blood oxygen level-dependent signals and vascular space occupancy signals. Then, at least one preprocessing procedure is performed on the fMRI data, including removing unstable time points, time-layer correction, head movement correction, spatial smoothing, delinear drift removal, peak removal, filtering, regression covariates, and removal of time points with excessive head movement. Finally, the spatial pattern of the preprocessed blood oxygen level-dependent signals and vascular space occupancy signals is extracted to obtain the subject's brain network.

[0065] Because blood oxygenation level-dependent signals are influenced by blood signals, including those from large blood vessels and those from microvessels (capillaries), and brain networks are generated by microvessels (capillaries) within gray matter, blood signals from large blood vessels should be eliminated before collecting blood oxygenation level-dependent signals to ensure the accuracy of the collected signals, thereby further ensuring the accuracy of the extracted brain network. Therefore, in some embodiments of the present invention, such as... Figure 2 As shown, step S101 includes:

[0066] S201. Acquire the anti-pulse signal and determine the tissue signal of the subject after the blood signal is eliminated based on the anti-pulse signal;

[0067] S202. Acquire tissue signals within a preset acquisition time using a preset acquisition method, and sequentially obtain vascular space occupancy signals and blood oxygen level dependent signals.

[0068] Specifically, step S201 involves applying an anti-pulse signal to the subject to obtain the tissue signal after the blood signal has been eliminated.

[0069] This invention improves the accuracy of the obtained blood oxygen level-dependent signal by applying an anti-pulse signal to the subject before acquiring the blood oxygen level-dependent signal, thereby suppressing the blood signal caused by large blood vessels. This further enhances the accuracy and reliability of the extracted brain network.

[0070] In some embodiments of the present invention, such as Figure 3 As shown, after applying a counterpulse signal (RF) to the subject, vascular space occupancy signal (VASO) and blood oxygen level dependent signal (BOLD) were acquired sequentially.

[0071] The preset acquisition time can be at least one repetition time (TR). The specific number of repetition times (TR) can be determined and adjusted according to the number of vascular space occupancy sub-signals and blood oxygen level dependent sub-signals to be obtained. One repetition time (TR) is 2s-4s.

[0072] Since the echo time (TE) needs to be set short enough to ensure successful acquisition of the vascular space occupancy signal, the echo time (TE) can be set to 10ms-30ms.

[0073] Since the embodiments of the present invention require sequential acquisition of vascular space occupancy signals and blood oxygen level dependent signals, the signal acquisition time is longer compared to acquiring only vascular level dependent signals. In order to improve signal acquisition efficiency, in some embodiments of the present invention, the preset acquisition method in step S202 is a planar accelerated acquisition method.

[0074] This invention, by setting the preset acquisition mode to a planar accelerated acquisition mode, can simultaneously acquire data from multiple layers, thereby increasing the speed of obtaining vascular space occupancy signals and blood oxygen level dependent signals, and thus improving the extraction speed of the subject's brain network.

[0075] In specific embodiments of the present invention, the planar accelerated acquisition method includes, but is not limited to, the fast reconstruction method through Generalized Auto-Calibrating Partially Parallel Acquisitions (GRAPPA), the fast reconstruction method through Multi-Planner Reformation (MPR), or the partial echo acquisition method.

[0076] In a specific embodiment of the present invention, steps S201-S202 are implemented as follows: an anti-pulse signal is applied to the subject, and the tissue signal after the subject's blood signal is eliminated is obtained based on the anti-pulse signal; then, within at least one repetition time TR, the vascular space occupancy signal and the blood oxygen level dependent signal are obtained sequentially through GRAPPA fast reconstruction method, MPR fast reconstruction method or partial echo acquisition method.

[0077] In some embodiments of the present invention, such as Figure 4 As shown, step S102 includes:

[0078] S401. The blood oxygen level-dependent signal and the vascular space occupancy signal are spliced ​​together in the time direction to obtain the spliced ​​signal;

[0079] S402. Extract brain networks based on spliced ​​signals.

[0080] Both the blood oxygenation level-dependent signal and the vascular space occupancy signal are four-dimensional matrices representing the three-dimensional spatial locations of the brain at multiple time points, exhibiting temporal continuity. Therefore, by arranging the three-dimensional spatial locations of the blood oxygenation level-dependent signal and the vascular space occupancy signal in chronological order along the time axis, each row represents brain data at a single time point. By extracting specific signals from the spliced ​​signals, the brain network can be obtained.

[0081] In a specific embodiment of the present invention, step S402 is: processing the spliced ​​signal based on the Independent Component Analysis (ICA) method to obtain the spatial independent component distribution, which is a brain network.

[0082] In specific embodiments of the present invention, such as Figure 5 As shown, FMRI data1 is the blood oxygen level-dependent signal, and FMRI data2 is the vascular spatial occupancy signal. The horizontal axis represents space, and the vertical axis represents time. FMRI data1 and FMRI data2 are spliced ​​along the vertical axis to obtain the spliced ​​signal. After splicing, the spatially independent distributions are extracted to obtain the brain network.

[0083] In a specific embodiment of the present invention, steps S401-S402 are implemented as follows: obtain blood oxygen level dependent signals and vascular space occupancy signals with the horizontal axis representing space and the vertical axis representing time; splice the blood oxygen level dependent signals and vascular space occupancy signals along the vertical axis to obtain spliced ​​signals; each row of the spliced ​​signals is brain data at a time point; decompose the spliced ​​signals based on the independent component analysis method to obtain independent components in time and space; the independent components in space are the brain network.

[0084] Since independent component analysis is a statistical method, its success depends on the time series lengths of the blood oxygen level-dependent signal and the vascular spatial occupancy signal being the same. Therefore, to ensure successful acquisition of spatial independent component analysis of the spliced ​​signal, in some embodiments of the present invention, before step S401, the following steps are also included:

[0085] Adjust the resolution of the oxygen level-dependent signal and the vascular space occupancy signal so that the resolution of the oxygen level-dependent signal is the same as that of the vascular space occupancy signal.

[0086] Here, resolution refers to the number of sampling time points for the blood oxygen level dependent signal and the vascular space occupancy signal. In other words, ensuring that the number of sampling time points for the blood oxygen level dependent signal and the vascular space occupancy signal is the same guarantees that the resolution of the blood oxygen level dependent signal and the vascular space occupancy signal is the same.

[0087] In this embodiment of the invention, the resolution of the blood oxygen level dependent signal and the vascular spatial occupancy signal is adjusted so that the resolution of the blood oxygen level dependent signal is the same as that of the vascular spatial occupancy signal. This ensures that the number of signal points in the blood oxygen level dependent signal is the same as the number of signal points in the vascular spatial occupancy signal. In other words, the time series lengths of the blood oxygen level dependent signal and the vascular spatial occupancy signal are the same, thus ensuring successful acquisition of spatially independent component analysis.

[0088] In some embodiments of the present invention, the number of signal points in the blood oxygen level dependent signal and the number of signal points in the vascular space occupancy signal are both 50-500. Specifically, the number of signal points in the blood oxygen level dependent signal and the number of signal points in the vascular space occupancy signal are both 215.

[0089] It should be noted that the number of signal points in the blood oxygen level dependent signal and the number of signal points in the vascular space occupancy signal can be adjusted or limited according to the actual application scenario or empirical values, and are not limited to a range or specific value.

[0090] In some embodiments of the present invention, the blood oxygen level dependent signal includes multiple blood oxygen level dependent sub-signals, and the vascular space occupancy signal includes multiple vascular space occupancy signals; then as follows Figure 6 As shown, step S102 includes:

[0091] S601. Identify multiple brain regions of interest in the subject's brain regions;

[0092] S602. Based on multiple blood oxygenation level-dependent sub-signals and multiple vascular space occupancy sub-signals, determine the average blood oxygenation level-dependent signal and average vascular space occupancy signal of each brain region of interest in multiple brain regions of interest.

[0093] S603. Determine the subject's first initial brain network based on mean blood oxygen level-dependent signals;

[0094] S604. Determine the subject's second initial brain network based on the average vascular space occupancy signal;

[0095] S605. Identify the overlapping brain regions of interest between the first and second initial brain networks, where the overlapping brain regions of interest are the subject's brain networks.

[0096] This invention determines a subject's first initial brain network based on mean blood oxygen level dependent signals and a second initial brain network based on mean vascular space occupancy signals. Then, it identifies the overlapping brain regions of interest between the first and second initial brain networks and uses these overlapping brain regions as the subject's brain network. This eliminates the randomness of the determined brain network caused by relying solely on mean blood oxygen level dependent signals or solely on mean vascular space occupancy signals, further improving the reliability and accuracy of the brain network.

[0097] In a specific embodiment of the present invention, the method for determining multiple brain regions of interest in the subject's brain region in step S601 can be any of the following methods: medical staff manually delineate and determine multiple brain regions of interest, divide the brain region based on a standard brain region template to determine multiple brain regions of interest, or automatically determine multiple brain regions of interest based on a preset brain region of interest extraction model.

[0098] Among them, brain region of interest extraction models include, but are not limited to, various deep neural networks.

[0099] In a specific embodiment of the present invention, the average blood oxygen level dependent signal in step S602 is the average of multiple blood oxygen level dependent sub-signals, and the average vascular space occupancy signal is the average of multiple vascular space occupancy sub-signals.

[0100] In a specific embodiment of the present invention, steps S601 to S605 are implemented as follows: First, multiple brain regions of interest are extracted from the subject's brain regions based on a preset brain region of interest extraction method. Then, the average blood oxygen level dependent signal and average blood vessel space occupancy signal of each brain region of interest are determined based on multiple blood oxygen level dependent sub-signals and multiple blood vessel space occupancy sub-signals. The first initial brain network and the second initial brain network of the subject are determined by the correlation coefficient discrimination method. Finally, the overlapping regions of interest that change in both the first initial brain network and the second initial brain network are determined, thereby obtaining the subject's brain network.

[0101] The embodiments of the present invention provide two analysis methods for extracting the subject's brain network, namely steps S401-S402 and steps S601-S605, which can improve the diversity of brain network extraction methods and increase the success rate of brain network extraction.

[0102] It should be noted that, in order to further improve the reliability of the extracted brain network, in some embodiments of the present invention, the subject's brain network can be obtained simultaneously based on two analysis methods, steps S401-S402 and S601-S605. When the difference between the brain network obtained based on step S401-S402 and the brain network obtained based on step S601-S605 is less than or equal to a preset difference, the brain network obtained based on step S401-S402 or the brain network obtained based on step S601-S605 is taken as the subject's final determined brain network. When the difference between the brain network obtained based on step S401-S402 and the brain network obtained based on step S601-S605 is greater than a preset difference, the subject's brain network is re-determined based on both steps S401-S402 and S601-S605 until the difference between the two is less than the preset difference.

[0103] In this embodiment of the invention, the brain network obtained by either the method based on steps S401-S402 or the method based on steps S601-S605 is used as the final brain network determined by the subject only when the difference between the brain networks obtained by the method based on steps S401-S402 and the method based on steps S601-S605 is less than or equal to a preset difference. This ensures the reliability and accuracy of the determined brain network.

[0104] It should be understood that the preset differences can be set or adjusted according to the actual work scenario or experience value, which will not be elaborated here.

[0105] In some embodiments of the present invention, such as Figure 7 As shown, step S603 includes:

[0106] S701. Determine the first correlation coefficient between any two brain regions of interest among multiple brain regions of interest based on the mean blood oxygen level dependent signal;

[0107] S702. Determine the first initial brain network based on the first correlation coefficient and the preset first correlation coefficient threshold.

[0108] Specifically, step S702 involves setting the connection between two brain regions of interest with a first correlation coefficient greater than or equal to the first correlation coefficient threshold to 1, and setting the connection between two brain regions of interest with a first correlation coefficient less than the first correlation coefficient threshold to 0. That is, only brain regions of interest with a first correlation coefficient greater than or equal to the first correlation coefficient threshold are retained, thereby obtaining the first initial brain network.

[0109] Since a brain network refers to the topological structure formed by multiple brain regions of interest with high correlation, the embodiments of the present invention use brain regions of interest with a first correlation coefficient greater than or equal to a first correlation coefficient threshold as the first initial brain network, which can improve the correlation between the regions of interest in the first initial brain network, thereby improving the accuracy and reliability of the determined first initial brain network.

[0110] It should be noted that the first correlation coefficient can be any one of the Pearson correlation coefficient, Kendall correlation coefficient, or Spearman correlation coefficient.

[0111] It should be understood that the threshold for the first correlation coefficient can be set or adjusted according to the actual application scenario or empirical value, and no specific limitation is made here.

[0112] In a specific embodiment of the present invention, steps S701-S702 are implemented as follows: a first correlation coefficient between any two brain regions of interest is determined based on the Pearson correlation coefficient calculation formula, the Kendall correlation coefficient calculation formula, or the Spearman correlation coefficient calculation formula and the mean blood oxygen level dependent signal; then, brain regions of interest whose first correlation coefficient is greater than or equal to the first correlation coefficient threshold are used as the first initial brain network.

[0113] In some embodiments of the present invention, such as Figure 8 As shown, step S604 includes:

[0114] S801. Determine the second correlation coefficient between any two brain regions of interest among multiple brain regions of interest based on the average vascular space occupancy signal;

[0115] S802. Determine the second initial brain network based on the second correlation coefficient and the preset second correlation coefficient threshold.

[0116] Specifically, step S802 involves setting the connection between two brain regions of interest with a second correlation coefficient greater than or equal to the second correlation coefficient threshold to 1, and setting the connection between two brain regions of interest with a second correlation coefficient less than the second correlation coefficient threshold to 0. That is, only brain regions of interest with a second correlation coefficient greater than or equal to the second correlation coefficient threshold are retained, thereby obtaining the second initial brain network.

[0117] In a specific embodiment of the present invention, steps S801-S802 are implemented as follows: a second correlation coefficient between any two brain regions of interest is determined based on the Pearson correlation coefficient calculation formula, the Kendall correlation coefficient calculation formula, or the Spearman correlation coefficient calculation formula and the average vascular space occupancy; then, brain regions of interest whose second correlation coefficient is greater than or equal to the second correlation coefficient threshold are used as the second initial brain network.

[0118] By using brain regions of interest with a second correlation coefficient greater than or equal to a second correlation coefficient threshold as the second initial brain network, the present invention can improve the correlation between regions of interest in the second initial brain network, thereby improving the accuracy and reliability of the determined second initial brain network.

[0119] It should be noted that the second correlation coefficient can be any one of the Pearson correlation coefficient, Kendall correlation coefficient, or Spearman correlation coefficient.

[0120] It should be understood that the threshold for the second correlation coefficient can be set or adjusted according to the actual application scenario or empirical value, and no specific limitation is made here.

[0121] To better implement the brain network extraction method in the embodiments of the present invention, based on the brain network extraction method, correspondingly, as follows: Figure 9 As shown, this embodiment of the invention also provides a brain network extraction device 900, comprising:

[0122] Functional magnetic resonance imaging (fMRI) data acquisition unit 901 is used to acquire at least two fMRI data points of the subject in a resting state, the at least two fMRI data points including blood oxygen level dependent signal and vascular space occupancy signal.

[0123] Brain network extraction unit 902 is used to extract the subject's brain network based on blood oxygen level-dependent signals and vascular space occupancy signals.

[0124] The brain network extraction device 900 provided in the above embodiments can realize the technical solutions described in the above brain network extraction method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above brain network extraction method embodiments, and will not be repeated here.

[0125] like Figure 10 As shown, the present invention also provides a magnetic resonance imaging device 1000. The magnetic resonance imaging device 1000 includes a processor 1001, a memory 1002, and a display 1003. Figure 10Only some components of the magnetic resonance imaging device 1000 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0126] In some embodiments, memory 1002 may be an internal storage unit of the magnetic resonance imaging device 1000, such as a hard disk or memory of the magnetic resonance imaging device 1000. In other embodiments, memory 1002 may also be an external storage device of the magnetic resonance imaging device 1000, such as a pluggable hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the magnetic resonance imaging device 1000.

[0127] Furthermore, the memory 1002 may include both internal storage units of the magnetic resonance imaging device 1000 and external storage devices. The memory 1002 is used to store application software and various types of data for which the magnetic resonance imaging device 1000 is installed.

[0128] In some embodiments, processor 1001 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 1002 or process data, such as the brain network extraction method of the present invention.

[0129] In some embodiments, display 1003 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 1003 is used to display information from the magnetic resonance imaging device 1000 and to display a user interface for visualization. Components 1001-1003 of the magnetic resonance imaging device 1000 communicate with each other via a system bus.

[0130] In some embodiments of the present invention, when the processor 1001 executes the brain network extraction program in the memory 1002, the following steps can be implemented:

[0131] Acquire at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest, including blood oxygen level-dependent signals and vascular space occupancy signals;

[0132] Brain networks of subjects were extracted based on blood oxygen level-dependent signals and vascular space occupancy signals.

[0133] It should be understood that when the processor 1001 executes the brain network extraction program in the memory 1002, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0134] Furthermore, this embodiment of the invention does not specifically limit the type of magnetic resonance imaging device 1000 mentioned. The magnetic resonance imaging device 1000 can be a portable magnetic resonance imaging device such as a tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. The aforementioned portable magnetic resonance imaging device can also be other portable magnetic resonance imaging devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, the magnetic resonance imaging device 1000 may not be a portable magnetic resonance imaging device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0135] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0136] The brain network extraction method, apparatus, and magnetic resonance imaging equipment provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for extracting brain networks, characterized in that, include: Acquire at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest, the at least two fMRI data points including blood oxygen level-dependent signals and vascular space occupancy signals; The blood oxygen level-dependent signal and the vascular space occupancy signal are spliced ​​together in the time direction to obtain a spliced ​​signal; The brain network is extracted based on the spliced ​​signal.

2. The brain network extraction method according to claim 1, characterized in that, The acquisition of at least two functional magnetic resonance imaging (fMRI) data points of the subject at rest includes: Acquire the antipulse signal and determine the tissue signal of the subject after the blood signal is eliminated based on the antipulse signal; The tissue signals are acquired within a preset acquisition time and in a preset acquisition method, thereby obtaining the vascular space occupancy signal and the blood oxygen level dependent signal in sequence.

3. The brain network extraction method according to claim 2, characterized in that, The preset acquisition method is a planar accelerated acquisition method.

4. The brain network extraction method according to claim 1, characterized in that, The extraction of the brain network based on the spliced ​​signal includes: The spliced ​​signal is processed using independent component analysis to obtain a spatially independent component distribution, which is the brain network.

5. The brain network extraction method according to claim 1, characterized in that, Prior to extracting the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal, the method further includes: The resolutions of the blood oxygen level dependent signal and the vascular space occupancy signal are adjusted so that the resolution of the blood oxygen level dependent signal is the same as that of the vascular space occupancy signal.

6. The brain network extraction method according to claim 1, characterized in that, The blood oxygen level-dependent signal includes multiple blood oxygen level-dependent sub-signals, and the vascular space occupancy signal includes multiple vascular space occupancy sub-signals; the extraction of the subject's brain network based on the blood oxygen level-dependent signal and the vascular space occupancy signal further includes: Identify multiple brain regions of interest in the subject's brain regions; Based on the multiple blood oxygen level dependent sub-signals and the multiple blood vessel space occupancy sub-signals, the average blood oxygen level dependent signal and the average blood vessel space occupancy signal of each of the multiple brain regions of interest are determined; The subject's first initial brain network was determined based on the mean blood oxygen level-dependent signal. The subject's second initial brain network was determined based on the average vascular space occupancy signal; Identify overlapping brain regions of interest between the first initial brain network and the second initial brain network, wherein the overlapping brain regions of interest are the brain networks of the subject.

7. The brain network extraction method according to claim 6, characterized in that, The determination of the subject's first initial brain network based on the mean blood oxygen level-dependent signal includes: The first correlation coefficient between any two brain regions of interest among the plurality of brain regions of interest is determined based on the mean blood oxygen level dependent signal. The first initial brain network is determined based on the first correlation coefficient and a preset first correlation coefficient threshold. The determination of the subject's second initial brain network based on the average vascular space occupancy signal includes: A second correlation coefficient between any two brain regions of interest among the plurality of brain regions of interest is determined based on the average vascular space occupancy signal; The second initial brain network is determined based on the second correlation coefficient and a preset second correlation coefficient threshold.

8. A brain network extraction device, characterized in that, include: A functional magnetic resonance imaging (fMRI) data acquisition unit is used to acquire at least two fMRI data points of a subject in a resting state, wherein the at least two fMRI data points include blood oxygen level-dependent signals and vascular space occupancy signals. The brain network extraction unit is used to splice the blood oxygen level-dependent signal and the vascular space occupancy signal in the time direction to obtain a spliced ​​signal; and to extract the brain network based on the spliced ​​signal.

9. A magnetic resonance imaging device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the brain network extraction method according to any one of claims 1 to 7.

Images