Method, device, equipment, and storage medium for identifying the location and laterality of brain functional areas

Abstract

The present disclosure provides a method, device, electronic device, and storage medium for localizing and laterally identifying brain function division. The method for localizing and laterally identifying brain function division includes: acquiring brain structural magnetic resonance image data and brain functional magnetic resonance image data of a subject; determining brain function mapping of the subject (including brain functional area labels and corresponding voxel sets of at least two brain functional areas) based on the brain structural magnetic resonance image data and the brain functional magnetic resonance image data; determining a brain functional area label corresponding to each clinically intervened voxel in the clinically intervened voxel set based on the clinically intervened voxel and the brain function mapping; and determining brain functional laterality of the brain functional area of ​​the target surgical area. Accurate and non-invasive preoperative localization of brain functional areas can be realized for individual subjects.

Description

[Technical Field]

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for localizing and laterally determining functional brain regions. [Background technology]

[0002] Brain lateralization is an important organizational principle of the human brain and a potential marker of brain development. Studying the rules of brain lateralization can help us understand the cognitive processing patterns of the human brain. In particular, accurately localizing and lateralizing a patient's functional brain activity is a key point in improving clinical practice and treatment. Currently, there is no risk-free, accurate, and reliable technical method for preoperative localization and lateralization of functional brain areas in the surgical field. Therefore, clinically, there is a need for safe and accurate localization and lateralization techniques to help physicians plan neurosurgery. The present application provides a brain functional area localization and laterality method, device, electronic device and storage medium for localizing and laterally locating brain functional areas in a target surgical area.

[0003] According to a first aspect, the present application provides a method for determining a brain function mapping of the subject (including brain function region markers of at least two brain function regions and corresponding voxel sets) based on the brain structure magnetic resonance image data and the brain function magnetic resonance image data, and for each clinical intervention voxel in the clinical intervention voxel set, determining a brain function region marker (including the brain function region marker in the brain function mapping) corresponding to the clinical intervention voxel in accordance with the clinical intervention voxel and the brain function mapping. a brain functional region locating method including: determining a set of voxels to be clinically intervened according to a brain functional region label corresponding to each of the voxels to be clinically intervened; dividing the set of voxels to be clinically intervened according to a brain functional region label corresponding to each of the voxels to be clinically intervened to obtain at least one subset of voxels to be clinically intervened (the voxels to be clinically intervened in each subset of voxels to be clinically intervened correspond to the same brain functional region label); and determining, for each subset of voxels to be clinically intervened, brain function lateralization corresponding to the subset of voxels to be clinically intervened based on the brain function mapping. In some alternative embodiments, the method further comprises:

[0004] For each subset of voxels of the brain functional region to be clinically intervened, a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined based on the brain function lateralization corresponding to the subset of voxels of the brain functional region to be clinically intervened. In some alternative embodiments, the method further comprises:

[0005] For each subset of voxels in the brain functional region to be clinically intervened, a pixel value corresponding to the subset of voxels in the brain functional region to be clinically intervened is determined based on the surgical risk value corresponding to the subset of voxels in the brain functional region to be clinically intervened, and the subset of voxels in the brain functional region to be clinically intervened is displayed according to the determined pixel value.

[0006] In some alternative embodiments, determining a brain function mapping of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data includes: Based on the brain structural magnetic resonance image data, it is determined whether the subject's brain structure has damage. If the subject's brain structure is not damaged, a brain function map of the subject is determined based on the brain function magnetic resonance image data.

[0007] In some alternative embodiments, determining brain function mapping of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data further includes:

[0008] If the subject's brain structure is damaged, a damaged brain region and an undamaged brain region of the subject are identified, and the damaged brain region includes M voxels, where M is a positive integer greater than or equal to 2.

[0009] A brain function map of an undamaged brain region is determined based on the brain functional magnetic resonance image data, and the brain function map of an undamaged brain region includes N brain functional regions, where N is a positive integer equal to or greater than 2. A correlation degree between each voxel in the M voxels corresponding to the damaged brain region and each brain functional region in the N brain functional regions is determined.

[0010] For each voxel among the M voxels, the brain functional area corresponding to the voxel is identified according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area among the N brain functional areas, thereby obtaining a brain functional mapping of the subject.

[0011] In some alternative embodiments, identifying the brain functional area corresponding to the voxel according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area in the N brain functional areas includes: Of the N brain functional areas, the brain functional area having the highest correlation with the voxel is identified as the brain functional area corresponding to the voxel.

[0012] In some alternative embodiments, determining the brain functional area corresponding to the voxel according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area in the N brain functional areas includes:

[0013] In response to determining that the correlation between each of the N brain functional areas and the voxel is smaller than a predetermined correlation threshold, the brain functional area corresponding to the voxel is determined to be an invalid brain functional area.

[0014] In some alternative embodiments, determining the brain functional area corresponding to the voxel according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area in the N brain functional areas includes:

[0015] Among the N brain functional regions, the brain functional region with the highest correlation with the voxel is determined as the brain functional region corresponding to the voxel, and a first iterative brain functional mapping of the damaged brain region is obtained.

[0016] The following iterative operation is performed: a first iterative brain functional mapping of the damaged brain region is combined with a brain functional mapping of the undamaged brain region to obtain an iterative brain functional mapping, which includes N iterative brain functional regions; a correlation between the voxel and each of the N iterative brain functional regions is determined; a brain functional region among the N brain functional regions with the highest correlation with the voxel is determined as the voxel's brain functional region, thereby obtaining a second iterative brain functional mapping of the damaged brain region; a determination is made as to whether the degree of agreement between the second iterative brain functional mapping of the damaged brain region and the first iterative brain functional mapping of the damaged brain region is greater than a predetermined agreement threshold; if so, the second iterative brain functional mapping of the damaged brain region is determined as the brain functional mapping of the damaged brain region, the iterative operation is terminated, and the brain functional mapping of the damaged brain region is used to characterize the brain functional region corresponding to the voxel; if not, the first iterative brain functional mapping of the damaged brain region is updated to the second iterative brain functional mapping of the damaged brain region, and the iterative operation is continued.

[0017] In some alternative embodiments, for each subset of voxels of the brain functional region to be clinically intervened, determining a brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the brain function mapping includes:

[0018] Based on the hemispheric autonomic index of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined.

[0019] Alternatively, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined based on the area of ​​the left and right functional region surfaces of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened.

[0020] In some alternative embodiments, the surgical risk value includes a left-sided risk value and a right-sided risk value, and determining the surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened includes:

[0021] Based on the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened, a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened are determined.

[0022] In some alternative embodiments, the brain function mapping also includes a functional connectivity reliability between two different voxels, and determining pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on a surgical risk value corresponding to the subset of voxels in the brain functional region to be clinically intervened further includes: The functional connectivity reliability of each voxel in the subset of voxels in the brain functional region to be clinically intervened is determined as a weight of the risk value, and a risk weight matrix is ​​obtained. Based on the risk weight matrix, a left risk weight matrix and a right risk weight matrix are determined. Based on the left risk weight matrix and the left risk value, a left pixel value corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined. Based on the right risk weight matrix and the right risk value, a right pixel value corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined. Pixel values ​​corresponding to a subset of voxels of the brain functional region to be clinically intervened are determined based on the left pixel values ​​and the right pixel values.

[0023] According to a second aspect, the present application provides an apparatus for localizing and laterally identifying functional brain regions, comprising the following units:

[0024] a data acquisition unit arranged to acquire structural and functional brain magnetic resonance image data of the subject; a processing unit configured to determine a brain functional mapping of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, the mapping comprising brain functional region labels of at least two brain functional regions and corresponding voxel sets; a position determination unit, which is configured to determine, for each clinically intervened voxel in the set of clinically intervened voxels, the clinically intervened voxel and a brain function region mark corresponding to the clinically intervened voxel based on the brain function mapping (including the brain function region mark in the brain function mapping); a laterality determination unit configured to divide the set of clinically intervened voxels according to a brain functional region label corresponding to each clinically intervened voxel to obtain at least one subset of clinically intervened brain functional region voxels, wherein the clinically intervened voxels in each subset of clinically intervened brain functional region voxels correspond to the same brain functional region label, and to determine, for each subset of clinically intervened brain functional region voxels, a brain functional laterality corresponding to the subset of clinically intervened brain functional region voxels based on the brain function mapping.

[0025] In some alternative embodiments, the device further comprises the following units:

[0026] a risk value determination unit, configured to determine, for each subset of brain functional region voxels to be clinically intervened, a surgical risk value corresponding to the subset of brain functional region voxels to be clinically intervened based on a brain function laterality corresponding to the subset of brain functional region voxels to be clinically intervened. In some alternative embodiments, the device further comprises the following units:

[0027] a presentation unit configured to, for each subset of voxels of the brain functional region to be clinically intervened, determine pixel values ​​corresponding to the subset of voxels of the brain functional region to be clinically intervened based on a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened, and present the subset of voxels of the brain functional region to be clinically intervened according to the determined pixel values. In some alternative embodiments, the processing unit is further configured as follows: Based on the brain structural magnetic resonance image data, it is determined whether the subject's brain structure has damage. If the subject's brain structure is not damaged, a brain function map of the subject is determined based on the brain function magnetic resonance image data. In some alternative embodiments, the processing unit is further configured as follows:

[0028] If the subject's brain structure is damaged, the damaged brain region and the undamaged brain region of the subject are identified, where the damaged brain region includes M voxels, where M is a positive integer greater than or equal to 2; and a brain functional map of the undamaged brain region is determined based on the brain functional magnetic resonance image data, where the brain functional map of the undamaged brain region includes N brain functional regions, where N is a positive integer greater than or equal to 2. A correlation degree between each voxel in the M voxels corresponding to the damaged brain region and each brain functional region in the N brain functional regions is determined.

[0029] For each voxel among the M voxels, the brain functional area corresponding to the voxel is determined according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area among the N brain functional areas, thereby obtaining a brain function map of the subject. In some alternative embodiments, the processing unit is further configured as follows: Of the N brain functional areas, the brain functional area having the highest correlation with the voxel is determined as the brain functional area corresponding to the voxel. In some alternative embodiments, the processing unit is further configured as follows:

[0030] In response to determining that the correlation between each of the N brain functional areas and the voxel is smaller than a predetermined correlation threshold, the brain functional area corresponding to the voxel is determined to be an invalid brain functional area. In some alternative embodiments, the processing unit is further configured as follows:

[0031] Among the N brain functional regions, the brain functional region with the highest correlation with the voxel is determined as the brain functional region corresponding to the voxel, and a first iterative brain functional mapping of the damaged brain region is obtained.

[0032] The following iterative operation is performed: a first iterative brain functional mapping of the damaged brain area is combined with a brain functional mapping of the undamaged brain area to obtain an iterative brain functional mapping, which includes N iterative brain functional areas; a correlation between the voxel and each of the N iterative brain functional areas is determined; a brain functional area among the N brain functional areas with the highest correlation with the voxel is determined as the brain functional area of ​​the voxel, thereby obtaining a second iterative brain functional mapping of the damaged brain area; a determination is made as to whether the degree of agreement between the second iterative brain functional mapping of the damaged brain area and the first iterative brain functional mapping of the damaged brain area is greater than a predetermined agreement threshold; if so, the second iterative brain functional mapping of the damaged brain area is determined as the brain functional mapping of the damaged brain area, the iterative operation is terminated, and the brain functional mapping of the damaged brain area is used to characterize the brain functional area corresponding to the voxel; if not, the first iterative brain functional mapping of the damaged brain area is updated to the second iterative brain functional mapping of the damaged brain area, and the iterative operation is continued. In some alternative embodiments, the laterality determination unit is further configured as follows:

[0033] Based on the hemispheric autonomic index of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined.

[0034] Alternatively, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined based on the area of ​​the left and right functional region surfaces of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened. In some alternative embodiments, the risk value determining unit is further configured as follows:

[0035] Based on the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened, a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened are determined.

[0036] In some alternative embodiments, the brain function mapping further includes functional connectivity reliability between each voxel, and the presentation units are further arranged as follows: The functional connectivity reliability of each voxel in the subset of voxels in the brain functional region to be clinically intervened is determined as a weight of the risk value, and a risk weight matrix is ​​obtained. The left risk weight matrix and the right risk weight matrix are determined according to the risk weight matrix. Based on the left risk weight matrix and the left risk value, a left pixel value corresponding to a subset of voxels of the brain functional region to be clinically intervened is determined. Based on the right risk weight matrix and the right risk value, a right pixel value corresponding to a subset of voxels in the functional brain region to be clinically intervened is determined. Based on the left pixel value and the right pixel value, pixel values ​​corresponding to the subset of voxels of the brain functional region to be clinically intervened are determined.

[0037] According to a third aspect, the present application provides a method for manufacturing a semiconductor device comprising: one or more processors; a storage device storing one or more programs; An electronic device comprising: The one or more programs, when executed by one or more processors, provide an electronic device that causes the one or more processors to perform the method of any one of the first aspects.

[0038] According to a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program that, when executed by one or more processors, performs a method according to any of the embodiments of the first aspect.

[0039] Currently, common technical means for realizing the localization and laterality of brain functional areas are as follows: 1. Intraoperative Wake-up Electrical Stimulation Currently, the main method for preoperative localization of functional areas is to wake the patient from anesthesia before resecting the lesion and use electrophysiological termination to accurately locate the brain functional area and explore the relationship between the lesion and the functional area. However, craniotomy is required, which increases the surgical risk and is prone to complications such as airway obstruction, respiratory depression, epileptic seizures, and increased intracranial pressure during and after surgery, which may increase the recurrence rate of the lesion.

[0040] 2. Wada Test The main method currently used to determine the laterality of brain function in clinical practice is to use cerebral angiography to puncture the bilateral carotid arteries or meridian artery insertion tubes, inject relevant anesthetics such as isopentane barbital to anesthetize one side of the brain, put the anesthetized brain into a functionally suspended state, and then conduct language and memory tests on the patient to determine the behavioral expressions of language, memory, etc. of the contralateral hemisphere. Its drawbacks are that the Wadak test is invasive to a certain extent, making patients prone to complications such as epileptic seizures, stroke, and transient ischemic lesions, and is susceptible to allergies and infections, complicated to operate, expensive, and has a low application rate. This method can only be used to determine the functionally dominant side of brain function, and cannot more accurately locate functional areas.

[0041] 3. Magnetic Resonance Lateral Localization Method Based on Task State Function By performing specific tasks, the brain's functional activation areas are obtained, and the lateralization index is calculated to identify specific functional areas. For example, observing the location and lateralization of the language functional areas of brain tumor patients related to the language functional area, the subject performs several semantic and grammatical sentence accuracy judgment tasks, and areas such as the bilateral middle frontal gyrus, bilateral superior frontal gyrus, bilateral superior temporal gyrus, and left inferior temporal gyrus are activated. These activated areas are identified as language functional areas, and then the language functional lateralization index is calculated. The drawback is that the results are highly dependent on the task design and the degree of matching to the task during the patient scanning process, and in many cases, patients (especially children, patients with cognitive impairment, and patients with severe functional impairment) are unable to effectively complete the task.

[0042] 4. Magnetic Resonance Lateral Localization Method Based on Resting State Function The resting state refers to the fact that during wakefulness, there is a large amount of spontaneous neuronal activity in the brain, the expression of which depends on blood oxygen level signals, and the low-frequency oscillations during resting state exhibit a high degree of synchronization between different brain regions in the brain functional network. Lateralization and localization are performed based on resting-state magnetic resonance data, for example, based on the strength of left and right brain functional connectivity. This deficiency is due to the low sensitivity and accuracy of functional region laterality localization by most current resting-state functional magnetic resonance methods.

[0043] The method, device, apparatus, and storage medium for locating and laterally identifying brain functional regions provided by the present application include: first acquiring structural brain magnetic resonance image data and functional brain magnetic resonance image data of a subject, wherein the functional brain magnetic resonance image data includes a blood oxygen level-dependent BOLD signal sequence corresponding to each voxel in a predetermined number of voxels; and then determining a brain functional map of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, wherein the brain functional map includes a plurality of brain functional regions, and for each clinical intervention voxel in a clinical intervention voxel set, determining a blood oxygen level-dependent BOLD signal sequence corresponding to the clinical intervention voxel in the clinical intervention voxel set. and determining functional brain region labels corresponding to the clinically intervened voxels based on the functional brain mapping, and dividing the set of clinically intervened voxels according to the functional brain region labels corresponding to each clinically intervened voxel to obtain at least one subset of voxels of the clinically intervened brain functional region, wherein the clinically intervened voxels in each subset of voxels of the clinically intervened brain functional region correspond to the same functional brain region label, and for each subset of voxels of the clinically intervened brain functional region, determining functional laterality corresponding to the subset of voxels of the clinically intervened brain functional region based on the functional brain mapping. That is, by using the subject's personalized functional brain region segmentation technology to identify functional brain regions and functional laterality based on functional brain magnetic resonance image data, brain functions can be detected non-invasively, and accurate location and laterality of functional brain regions can be achieved, providing physicians with powerful support for brain surgery planning and effectively solving the problems of previous methods, such as inaccurate location and laterality of functional regions due to differences in individual structure and function, and the likelihood of postoperative complications. [Brief explanation of the drawings]

[0044] The drawings illustrate by way of example, and not by way of limitation, various embodiments discussed in the present document.

[0045] [Figure 1] FIG. 1 is a diagram illustrating an exemplary system configuration to which an embodiment of the present application can be applied. [Figure 2] FIG. 2 is a flowchart of one embodiment of the method for localizing and laterally identifying functional brain regions of the present application. [Figure 3] FIG. 3 is a broken-down flowchart of one embodiment of step 202 in the method for localizing and laterally determining functional brain regions shown in FIG. [Figure 4] FIG. 4 is a decomposition flowchart of one embodiment of step 306 in the embodiment shown in FIG. [Figure 5] Figure 5A is a decomposed flowchart of one embodiment of step 205 in the method for locating and laterally identifying functional brain regions shown in Figure 2. Figure 5B is a decomposed flowchart of another embodiment of step 205 in the method for locating and laterally identifying functional brain regions shown in Figure 2. [Figure 6] FIG. 6 is a structural schematic diagram of an embodiment of the device for identifying the location and laterality of a brain functional region of the present invention. [Figure 7] 1 is a schematic structural diagram of a computer system suitable for implementing a terminal device or server of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0046] In order to provide a more detailed understanding of the features and technical contents of the embodiments of the present application, the implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings, which are merely for reference and explanation purposes and are not intended to limit the embodiments of the present application.

[0047] It should be understood that the terms "first, second, and third" used in the embodiments of the present application distinguish between similar objects and do not represent a particular order for the objects, and that the specific order or precedence of "first, second, and third" may be interchanged where permitted. The distinctions between "first, second, and third" may be interchanged where appropriate so that the embodiments of the present application described herein may be implemented in an order other than that illustrated or described herein. FIG. 1 shows an exemplary system configuration diagram 100 of an embodiment to which the method for localizing and laterally identifying functional brain regions or the device for localizing and laterally identifying functional brain regions of the present application can be applied.

[0048] 1, system configuration diagram 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is used to provide a medium for a communication link between terminal devices 101, 102, 103, and server 105. Network 104 may include various connection types, such as, for example, wired, wireless communication links, or fiber optic cables.

[0049] Users can use terminal devices 101, 102, 103 to interact with server 105 via network 104 and receive or send messages, etc. Various communication client applications may be installed on terminal devices 101, 102, 103, such as a magnetic resonance imaging control application, a functional magnetic resonance imaging control application, a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, etc.

[0050] The terminal devices 101, 102, and 103 may be hardware or software. If the terminal devices 101, 102, and 103 are hardware, they may be various electronic devices having a display, including, but not limited to, smartphones, tablet computers, laptop portable computers, and desktop computers. If the terminal devices 101, 102, and 103 are software, they may be installed in the electronic devices listed above. This may be realized as multiple software programs or software modules (e.g., processing for providing structural brain magnetic resonance image data or functional brain magnetic resonance image data), or as a single software program or software module. No specific limitations are provided here.

[0051] The server 105 may be a server that provides various services, for example, a background data processing server that processes magnetic resonance image data sent by the terminal devices 101, 102, 103. The background data processing server can determine brain function mapping of the subject based on the brain structural magnetic resonance image data and brain functional magnetic resonance image data, and send it to the terminal devices.

[0052] It should be noted that server 105 may be hardware or software. If server 105 is hardware, it may be realized as a distributed server cluster consisting of multiple servers, or as a single server. If server 105 is software, it may be realized as multiple pieces of software or software modules (for example, for providing distributed services), or as a single piece of software or software module. No specific limitations are provided here.

[0053] It should be noted that the method for localizing and laterally identifying functional brain regions according to the present application is generally executed by the server 105, and accordingly, the device for localizing and laterally identifying functional brain regions is generally provided in the server 105.

[0054] In some cases, the method for localizing and laterally identifying brain functional regions according to the present application may be executed by the server 105, by the terminal devices 101, 102, and 103, or jointly by the server 105 and the terminal devices 101, 102, and 103. Accordingly, the device for localizing and laterally identifying brain functional regions may be installed in the server 105, or in the terminal devices 101, 102, and 103, or partly installed in the server 105 and partly installed in the terminal devices 101, 102, and 103. Accordingly, the system configuration diagram 100 may include only the server 105, or only the terminal devices 101, 102, and 103, or may include the terminal devices 101, 102, and 103, the network 104, and the server 105. This is not a limitation of the present application.

[0055] The number of terminal devices, networks, and servers in Figure 1 is merely an example, and any number of terminal devices, networks, and servers may be included as needed.

[0056] 2, there is shown a flow chart 200 of an embodiment of the method for localizing and laterally locating functional brain regions of the present application, which includes the following steps: Step 201: Brain structural magnetic resonance image data and brain functional magnetic resonance image data of a subject are obtained.

[0057] In this embodiment, the entity executing the brain functional region positioning and laterality identification method (e.g., the server shown in Figure 1) can first acquire, locally or remotely, brain structural magnetic resonance image data and brain functional magnetic resonance image data of the subject from other electronic devices (e.g., the terminal devices shown in Figure 1) connected to the entity network.

[0058] In an embodiment of the present application, the structural brain magnetic resonance image data includes data obtained by performing structural magnetic resonance imaging on the subject's brain, and the functional brain magnetic resonance image data includes data obtained by performing functional magnetic resonance imaging on the subject's brain, and the functional brain magnetic resonance image data includes a blood oxygen level dependent (BOLD) signal sequence corresponding to each voxel in a predetermined number of voxels.

[0059] The data obtained by functional magnetic resonance imaging contains time-series information equivalent to a four-dimensional image. For example, if functional magnetic resonance imaging is acquired, a three-dimensional image matrix (Length × Width × Height, L × M × N) is acquired, and one frame is acquired every two seconds, 150 frames of data can be acquired in six minutes, forming an L × M × N × 150 functional magnetic resonance image data signal.

[0060] The data obtained by magnetic resonance imaging are high-resolution 3D grayscale images of anatomical structures, such as T1w (T1-weighted image---the difference in T1 relaxation (longitudinal relaxation) of prominent tissues) and its correlation images, T2w (T2-weighted image---the difference in T2 relaxation (transverse relaxation) of prominent tissues) and its related images, and sequences (fluid attenuated inversion recovery, FLAIR) and its related images. In some embodiments of the present application, the functional magnetic resonance images may include task-state functional magnetic resonance images and / or resting-state functional magnetic resonance images.

[0061] A resting-state functional magnetic resonance image can be understood to be a magnetic resonance image obtained by performing a magnetic resonance scan on a subject's brain when the subject is not performing any task during the scan. A task-state functional magnetic resonance image can be understood to be a magnetic resonance image obtained by performing a magnetic resonance scan on a subject's brain when the subject is performing a target task. In some embodiments of the present application, brain functional magnetic resonance image data of a subject can be obtained using resting-state functional magnetic resonance imaging, which reduces the complexity of the test, does not require the patient to perform the task cooperatively, and reduces the dependency of the patient's state on the degree of coordination between the performed task and the patient's state.

[0062] After obtaining a subject's structural brain magnetic resonance scan data, various methods can be used to determine the subject's structural brain map based on the structural brain magnetic resonance scan data, i.e., to determine which specific regions in the subject's brain are which structural components. For example, this can be achieved using conventional software for processing 3D brain scan data, such as the magnetic resonance data processing software FreeSurfer. Another example is to train a deep learning model based on a large amount of sample brain structural image scan data and corresponding marks of brain structural components, and then input the subject's structural brain magnetic resonance scan data into the trained deep learning model to obtain the corresponding structural brain map.

[0063] In some alternative embodiments, the executing entity acquires structural brain magnetic resonance image data and functional brain magnetic resonance image data of the subject, and then performs preprocessing on the structural brain magnetic resonance image data and functional brain magnetic resonance image data. In the present application, the processing method of the preprocessing is not specifically limited, and for example, the preprocessing may include the following: Preprocessing of the structural brain magnetic resonance image data may include, for example, skull removal, field intensity correction, individual anatomical structure segmentation, and cerebral cortex reconstruction. Preprocessing of the brain functional magnetic resonance image data may include, for example, the following. (1) Temporal layer correction, head motion correction, temporal signal filtering, noise component regression, spatial smoothing, etc. (2) Matching of functional brain magnetic resonance imaging data images with structural images. (3) Projection of functional brain magnetic resonance imaging data signals onto structural images.

[0064] Here, the structural image may include structural brain magnetic resonance image data of the subject, or a structural brain image of the average level of the cerebral cortex or correlated groups reconstructed based on the structural brain magnetic resonance image data of the subject. Step 202: Determine the brain function mapping of the subject based on the brain structural magnetic resonance image data and the brain functional magnetic resonance image data.

[0065] Here, the brain function mapping may include voxel sets corresponding to brain function area labels of at least two brain function areas. The specific number of brain function areas may be determined according to the actual division required. For example, according to the actual application, the brain function mapping may include 2 to 1000 brain function areas.

[0066] Brain functional atlas, also known as "brain mapping," "brain map," "functional mapping," or "brain functional network mapping," is a mapping technique that divides the cerebral cortex into functional regions and labels the different regions responsible for different brain functions. The labeled regions are also called "functional regions" or "functional networks," i.e., brain functional regions.

[0067] FIG. 3 is a decomposition flowchart of step 202 in the method for locating and laterally identifying brain functional areas shown in FIG. 2, and in some alternative embodiments, the above step 202 may specifically include the following steps:

[0068] Step 301: Determine whether the subject's brain structure has damage based on the brain structure magnetic resonance image data. If not, perform step 302; if yes, perform step 303.

[0069] In this application, damage to a brain structure refers to a brain structure that has a defect, space occupancy, or other lesion compared to a complete, standard brain anatomical structure, such as a brain structure defect due to preclinical intervention or trauma, a brain structure defect due to local atrophy of the brain, or a brain structure loss due to space occupancy by a tumor.

[0070] Here, by comparing the brain structure magnetic resonance image data with the standard brain structure model data, it may be determined whether the subject's brain structure has damage, or it may be determined based on medical diagnosis whether the subject's brain structure in the brain structure magnetic resonance image data has damage. Step 302: Determine the brain function mapping of the subject based on the brain function magnetic resonance imaging data.

[0071] First, the group-level brain functional mapping is projected onto the subject's brain functional magnetic resonance imaging data. Then, a normalization algorithm incrementally adjusts the boundaries of these functional regions based on the subject's brain functional magnetic resonance imaging data until the network segmentation results stabilize or an iteration termination condition is reached, e.g., the number of iterations reaches a set value. The normalization process determines the extent of network boundary adjustment based on the patient's individual brain connectivity variability distribution and the patient's own brain imaging signal-to-noise ratio. Finally, the functional networks obtained from each anatomical region are fused according to signal correlation to obtain the subject's brain functional mapping. Finally, 2 to 1,000 functional regions can be identified across the whole brain, depending on actual needs.

[0072] In the present application, brain function mapping may include surface-based two-dimensional brain function mapping or volume-based three-dimensional brain function mapping. Step 303: Determine the subject's damaged brain region and non-damaged brain region, where the damaged brain region includes M voxels, where M is a positive integer greater than or equal to 2.

[0073] The damaged brain region of the subject can be identified based on the structural brain magnetic resonance image data. For example, by comparing the standard structural brain image data with the structural brain magnetic resonance image data of the subject, the region in the structural brain magnetic resonance image data of the subject that has a structural brain defect compared to the standard structural brain image data can be identified as the damaged brain region of the subject. By creating a damaged brain region mask and a non-damaged brain region mask, the subject's brain regions and non-damaged brain regions can be identified.

[0074] A mask is a binary image consisting of 0s and 1s, and in this application, a mask may be a two-dimensional or three-dimensional mask corresponding to brain function mapping. When a mask is applied to a function, the one-value regions are processed and the masked zero-value regions are not included in the calculation. An image mask may be defined by specified data values, data ranges, finite or infinite values, regions of interest, and annotation files, or a mask may be created by applying any combination of the above options as input. Here, the method for determining the damage to the brain region mask can include one of the following:

[0075] (1) Obtain a mask of the damaged brain region handwritten by a physician based on his or her experience. (2) Using conventional structural segmentation templates, such as automatic anatomical mark mapping templates, Brodmann maps, and Deskan-Killiany Atlas, we determine which structures are involved based on the damaged areas, and combine these structures to form a damaged brain area mask.

[0076] (3) Using a conventional brain function segmentation template, such as the Yeo 17 functional network template, we identify which functional areas are involved based on the damaged area, and combine these functional areas to form a damaged brain area mask. (4) Determine the damaged brain area mask using methods such as machine learning and deep learning. The undamaged brain area is the area excluding the brain area, which is obtained by subtracting the brain area from the total brain area.

[0077] Step 304: Determine a brain function map of an undamaged brain region based on the brain function magnetic resonance image data, where the brain function map of an undamaged brain region includes N brain function regions, where N is a positive integer greater than or equal to 2.

[0078] Here, the method for determining brain function mapping of non-damaged brain regions can be the same as that for general brain function mapping, for example, the brain function mapping determination method in step 302, and the description thereof will be omitted here. Step 306: Determine the correlation degree between each voxel in the M voxels corresponding to the damaged brain region and each brain functional region in the N brain functional regions.

[0079] In the present application, the correlation degree can be determined by the BOLD signal sequence corresponding to voxels. Illustratively, the BOLD signal sequence corresponding to each voxel includes T BOLD values, where T is the sampling number of the time dimension corresponding to the scanning time, where the correlation degree between two voxels can be calculated by the Pearson correlation coefficient based on the T BOLD values ​​corresponding to the voxels, and the correlation degree between a voxel and a brain functional region can be calculated by the Pearson correlation coefficient based on the average value between the BOLD signal sequence corresponding to the voxel and the BOLD signal sequence of each voxel in the brain functional region. In this application, the correlation coefficient is the Pearson correlation coefficient, which is a coefficient for evaluating the linearity between variables. The calculation formula is as follows:

number

[0080] The formula is that the Pearson correlation coefficient (ρx,y) of two continuous variables (X,Y) is equal to their covariance cov(X,Y) divided by the product of their respective standard deviations (σX,σY). The value of the coefficient is always between -1.0 and 1.0, with variables close to 0 being uncorrelated and those close to 1 or -1 being said to be highly correlated.

[0081] Step 307: For each voxel in the M voxels, determine the brain functional area corresponding to the voxel according to the predetermined functional area classification rules based on the correlation between the voxel and each brain functional area in the N brain functional areas, and obtain the brain functional mapping of the subject.

[0082] Regarding the above step 307, since the brain function mapping of the undamaged brain functional area is determined in step 305, that is, the brain function area corresponding to each voxel in the undamaged brain functional area of ​​the subject is determined, it can be understood that after the brain function area corresponding to each voxel in the M voxels corresponding to the brain area is determined, that is, the brain function area corresponding to each voxel in the whole-brain functional magnetic resonance image data of the subject is determined, and further the brain function mapping of the subject is obtained. This allows the brain functional region label of each voxel in the M voxels in the brain region to be determined. In some alternative embodiments, the above step 307 may specifically include: Of the N brain functional areas, the brain functional area with the highest correlation with the voxel is identified as the brain functional area corresponding to the voxel.

[0083] In this way, the brain functional areas of M voxels in the damaged brain area can be quickly identified, and each voxel corresponds to the brain functional area in the undamaged brain area with which it has the highest correlation, clearly indicating the degree of correlation between each location in the damaged brain area and the brain functional area corresponding to the undamaged brain area. In some alternative embodiments, the above step 307 may specifically include:

[0084] In response to determining that the correlation between each of the N brain functional areas and the voxel is smaller than a predetermined correlation threshold, the brain functional area corresponding to the voxel is determined to be an invalid brain functional area.

[0085] In this application, the term "invalid brain functional region" may include functional regions that have no obvious functional relationship with the subject's undamaged brain region. For example, in brain tumor patients, some vertices or voxels in the tumor region have low functional connections with the whole brain, and can be classified as invalid brain functional regions, and the removal or destruction of these functional regions will not cause functional damage to the patient. For example, in patients with brain tissue necrosis, the function of the necrotic part of the brain tissue is completely lost after the cessation of cell metabolism, and the vertices or voxels in the necrotic brain region have no functional connection with the whole brain, and can be classified as invalid brain functional regions, and the remaining voxels are redistributed according to the functional region with the strongest correlation coefficient. Here, the preset correlation threshold can be set according to actual needs, for example, 0.2.

[0086] 4 is a decomposition flowchart of step 307 in the embodiment shown in FIG. 3. In some alternative embodiments, the above step 307 may specifically include:

[0087] Step 3071: Among the N brain functional areas, the brain functional area with the highest correlation with the voxel is determined as the brain functional area corresponding to the voxel, and the first iteration brain functional mapping of the damaged brain area is obtained.

[0088] Step 3072: combine the first iterative brain function mapping of the damaged brain region with the brain function mapping of the non-damaged brain region to obtain an iterative brain function mapping, where the iterative brain function mapping includes N iterative brain function regions. Step 3073: Determine the correlation degree between the voxel and each of the N repeated brain functional regions.

[0089] Step 3074: Among the N brain functional regions, the brain functional region with the highest correlation with the voxel is determined as the brain functional region of the voxel, and a second iteration brain functional mapping of the damaged brain region is obtained.

[0090] Step 3075: Determine whether the degree of agreement between the second iteration brain function mapping of the damaged brain area and the first iteration brain function mapping of the damaged brain area is greater than a preset degree of agreement threshold; if not, execute step 3076; if yes, execute step 3077.

[0091] In some alternative embodiments, step 3075 further includes determining the number of times step 3075 is performed, and performing step 3077 when the number of times the step 3075 is performed reaches a preset cycle number threshold.

[0092] Step 3076: Update the first iteration brain function mapping of the damaged brain region in step 3072 to the second iteration brain function mapping of the damaged brain region, and then execute step 3072. Step 3077: Determine the second iteration brain function mapping of the damaged brain region as the brain function mapping of the damaged brain region. Here, brain functional mapping of damaged brain regions is used to characterize the brain functional regions corresponding to the voxels. By the method of iterative calculation, the brain function area of ​​each voxel in the brain region is continuously corrected, and the obtained brain function mapping of the brain region becomes more accurate.

[0093] In some alternative embodiments, step 307 may include: determining the correlation between each voxel in the damaged brain region and each of the N functional regions in the non-damaged brain region, determining the functional region with the highest correlation between each voxel in the damaged brain functional region and the N functional regions as the functional region of the voxel, obtaining a brain functional map of the damaged brain region, and combining it with the brain functional map of the non-damaged brain region to obtain a new whole-brain functional map. Then, employing a normalization algorithm, the normalization algorithm calculates the correlation coefficient between each voxel in the damaged brain region and each functional region in the new whole-brain functional map, and adjusting the voxel in each damaged brain region to the functional region with the highest correlation coefficient with the voxel. The brain functional mapping of the damaged brain region is generated, and the new whole-brain functional mapping is combined with the brain functional mapping of the non-damaged brain region to form the whole-brain functional mapping influence signal in the next normalization operation. The boundaries of these functional regions are gradually adjusted based on the image signals of the subject's damaged brain region until the network segmentation result becomes stable or the iteration termination condition is reached, for example, until the number of iterations reaches a set value (in the normalization process, the range of network boundary adjustment is determined using the patient's individual brain connection difference distribution and the subject's own brain image signal-to-noise ratio), and the final brain functional mapping of the subject's damaged brain region is obtained.

[0094] In step 203, for each clinically-intervention voxel in the clinically-intervention voxel set, a brain functional region label corresponding to the clinically-intervention voxel is determined based on the clinically-intervention voxel and the brain functional mapping. Here, the brain functional regions include brain functional region markers and invalid brain functional region markers in brain function mapping.

[0095] Clinical intervention involves influencing the progression of a disease by various therapeutic means, including, for example, clinically common surgical treatments, chemical drug treatments, radiation treatments, targeted therapies, immunotherapy, interventional therapies, and the like.

[0096] Here, the voxel set to be clinically intervened is a voxel set corresponding to the brain region of the subject to be clinically intervened. The voxel set corresponding to the brain region of the subject to be clinically intervened can be determined by projecting the brain region of the subject to be clinically intervened onto the subject's structural brain magnetic resonance image data and / or functional brain magnetic resonance image data. The brain region of the subject to be clinically intervened may include the subject's lesioned brain structural region, such as a brain structural region of brain tissue necrosis due to preclinical intervention or trauma, a brain structural region of tumor space occupation, etc. Although the above description is given by way of example, in actual application, the brain region of the subject to be clinically intervened can be determined based on the subject's preoperative diagnosis.

[0097] The above step 202 obtains a brain function mapping of the subject, which characterizes the division of the subject's brain functional areas. By projecting the brain structural areas corresponding to the brain areas of the subject receiving clinical intervention onto the subject's brain function mapping, it is possible to identify the brain functional areas included in the brain structural areas corresponding to the brain areas of the subject receiving clinical intervention, i.e., the brain functional areas of the brain areas of the subject receiving clinical intervention.

[0098] Step 204: Divide the set of clinically intervened voxels according to the brain functional region label corresponding to each clinically intervened voxel to obtain at least one subset of clinically intervened brain functional region voxels, and the clinically intervened voxels in each subset of clinically intervened brain functional region voxels correspond to the same brain functional region label. A clinically intervened voxel is a voxel that is included in the clinically intervened voxel set.

[0099] Here, by dividing the voxels to be clinically intervened that have the same brain functional region label into subsets of voxels to be clinically intervened in the same brain functional region, brain functional region division of the voxels to be clinically intervened in the target surgical region can be realized, and all of the voxels to be clinically intervened in the subset of voxels to be clinically intervened in the brain functional region belong to the same brain functional region, and the subset of voxels to be clinically intervened in the brain functional region that consists of voxels to be clinically intervened that have the same brain functional region label is used to determine the brain functional laterality based on the same brain functional region.

[0100] Step 205: for each subset of voxels in the brain functional region to be clinically intervened, determine the brain functional laterality corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the brain function mapping. In the present application, the brain function laterality of a brain functional region is expressed by the Latent lateralization index (LI). In some alternative embodiments, the above step 205 may specifically include:

[0101] Based on the hemispheric autonomy index (AI) of the brain functional area corresponding to the subset of voxels of the brain functional area to be clinically intervened, the brain functional laterality corresponding to the subset of voxels of the brain functional area to be clinically intervened is determined, which is specifically as follows: First, calculate the LI of the brain functional area in the target surgical area using the following formula:

[0102]

number

[0103] AI L : represents the sum or average of the AI ​​or standardized AI of the brain functional area of ​​the left surgical area. R : Represents the sum or average of the AI ​​or standardized AI of the brain functional area of ​​the right surgical area.

[0104] Furthermore, the LI is normalized to fall within the range of -1 to 1. In the present application, when the LI value is [-1, 0], it indicates that the cerebral functional laterality is on the left side, and when the LI value is (0, 1), it indicates that the cerebral functional laterality is on the right side, and the magnitude of the absolute value of the LI is positively correlated with the degree of cerebral functional laterality. In the present application, the LI can be normalized by, for example, employing any one of the following schemes 1 to 4. Scheme 1, LI_norm=(LI-LI(min)) / (LI(max)-LI(min)). LI_norm is the normalized lateralization index, LI(min) is the minimum value of the lateralization index, and LI(max) is the maximum value of the lateralization index. Scheme 2, LI_norm=(LI-LI(mean)) / (LI(max)-LI(min)). LI(mean) is the mean lateralization index. Scheme 3, LI_norm = lg(LI). Scheme 4: LI_norm=atan(LI)*2 / π. The AI ​​can be calculated, for example, as follows:

[0105] Each vertex / voxel in the brain functional magnetic resonance imaging data is treated as a region of interest (ROI), and for each ROI, the functional connectivity strength with the ipsilateral hemisphere ROI and the functional connectivity strength with the contralateral hemisphere ROI are calculated. By setting a threshold value (0.1-1), the number of ipsilateral hemisphere connections Ni and the number of contralateral hemisphere connections Nc that are greater than the threshold value are counted for each ROI. The autonomy index AI is calculated using the following formula:

number

[0106] The brain functional laterality corresponding to the subset of voxels in the brain functional region to be clinically intervened is determined based on the surface area of ​​the left or right functional region of the brain functional region corresponding to the subset of voxels in the brain functional region to be clinically intervened, where the surface area of ​​the functional region is expressed as the area corresponding to the number of voxels in the brain functional region, and is calculated by the following formula: LI=(LR) / (L+R) where L is the number of surface voxels in the left functional region and R is the number of surface voxels in the right functional region. As shown in FIG. 2, in some alternative embodiments, the process 200 further includes the following steps:

[0107] Step 206: For each subset of voxels in the brain functional region to be clinically intervened, determine a surgical risk value corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the brain functional laterality corresponding to the subset of voxels in the brain functional region to be clinically intervened.

[0108] Step 207: For each subset of voxels in the brain functional region to be clinically intervened, determine pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the surgical risk value corresponding to the subset of voxels in the brain functional region to be clinically intervened, and present the subset of voxels in the brain functional region to be clinically intervened according to the determined pixel values.

[0109] In some alternative embodiments, the above step 207 specifically presents pixel values ​​corresponding to the subset of voxels of the brain functional region to be clinically intervened in the brain function mapping according to the determined pixel values, and obtains a risk map of brain functional region and brain functional laterality that characterizes the subset of voxels of the brain functional region to be clinically intervened in the subject's target surgical region.

[0110] By determining a subset of voxels in each functional brain region to be clinically intervened in the target surgical area and determining the functional laterality corresponding to each subset of voxels in the functional brain region to be clinically intervened, accurate localization of the functional brain region relative to the target surgical area is achieved, and a risk map of the surgically relevant functional region is obtained. The risk map can indicate the functional importance of the area to be resected in the target surgical area by marking the pixel values ​​of the voxels, indicating the risk of functional impairment to the patient after resection of the area. The importance is positively correlated with the risk level, for example, red indicates important and high risk, yellow indicates average and medium risk, and green indicates not important and low risk. By determining the risk map, neurosurgeons can formulate a personalized surgical plan tailored to each patient, shortening the surgical time, improving the success rate of the surgery, and reducing the risk of functional impairment to the patient after surgery.

[0111] 5A is a decomposition flowchart of one embodiment of step 206 in the method for localizing and laterally identifying brain functional regions shown in FIG. 2. The surgical risk value includes a left-sided risk value and a right-sided risk value. In some alternative embodiments, the above step 206 may specifically include:

[0112] Step a501: based on the brain function laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened, determine a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened; Here, the left risk value is A, the right risk value is B, and the lateralization index is C. The left risk value and the right risk value must simultaneously satisfy the following conditions: Condition 1: A+B=1 Condition 2: AB=C Based on the above two conditions, by substituting the value of C into the calculation, the values ​​of A and B are obtained. In step a502, the left risk value and the right risk value are normalized.

[0113] Here, A and B can be normalized in various ways. For example, A and B can be divided by the larger of A and B, and the normalized values ​​A_norm and B_norm of A and B can be determined. That is, if A>B, A_norm=A / A=1, B_norm=A / B, A <Bであれば、A_norm=A / B、B_norm=B / B=1である。 Accordingly, step 206 may specifically include visualizing the normalized left and right risk values.

[0114] Here, visualization may be achieved, for example, by projecting the normalized left and right risk values ​​onto the subject's brain function mapping. For example, the left and right risk values ​​are assigned to two colors, respectively, and the pixel values ​​corresponding to each voxel in the brain function mapping are assigned based on the magnitude of the risk value values, thereby achieving visualization.

[0115] FIG. 5B is a decomposition flowchart of another example of step 206 and step 207 in the method for localizing and laterally identifying functional brain regions shown in FIG. 2, and in some alternative embodiments, step 206 may specifically include:

[0116] Step b501: determining a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened; In step b502, the left risk value and the right risk value are normalized.

[0117] Here, the specific embodiments and technical effects of steps b501 and b502 are basically the same as the specific embodiments and technical effects of steps a501 and a502 in the above embodiment, and therefore the description thereof will be omitted here. Accordingly, the above step 207 may specifically include:

[0118] Step b503: determine the functional connectivity reliability of each voxel in the subset of voxels in the brain functional region to be clinically intervened as a weight of the risk value, and obtain a risk weight matrix.

[0119] In the process of determining the subject's brain function mapping, in addition to the subject's brain functional regions, the functional connectivity coefficient between each voxel and each brain functional region in the subject's brain functional magnetic resonance image data is determined, where the functional connectivity coefficient is used to represent the correlation between the voxel and the brain functional region. The functional connectivity coefficients of each voxel and each brain functional region are ranked, and the ratio of the first functional connectivity coefficient to the second functional connectivity coefficient is taken as the functional connectivity confidence value of the voxel. The functional connectivity confidence value of a voxel reflects the confidence of the brain functional region with the largest functional connectivity coefficient between the voxel and it, and the higher the functional connectivity confidence value of a voxel, the stronger the confidence. Step b504: Determine a left risk weight matrix and a right risk weight matrix based on the risk weight matrix.

[0120] For example, assuming that the risk weight matrix is ​​W, specifically, the executing entity sets the values ​​corresponding to the vertices / voxels of the right brain functional area related to the surgery in W to 0, thereby obtaining a left brain risk weight matrix W(L), i.e., a left risk weight matrix, and sets the values ​​corresponding to the vertices / voxels of the left brain functional area related to the surgery in the risk weight matrix W to 0, thereby obtaining a right brain risk weight matrix W(R), i.e., a right risk weight matrix.

[0121] Step b505: Based on the left risk weight matrix and the left risk value, determine left pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened; based on the right risk weight matrix and the right risk value, determine right pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened.

[0122] The main structure of the human brain is divided into the left and right hemispheres, and in practice, it is necessary to describe the left and right hemispheres during surgery, so a left risk map and a right risk map can be determined, where the left risk map is used to indicate the left risk voxels in the target surgical area, and the right risk map is used to indicate the right risk voxels in the target surgical area.

[0123] The left risk weight matrix W(L) is multiplied by the left normalized risk value A_norm to obtain the left risk map Riskmap(L), i.e., Riskmap(L)=W(L)*A_norm, and the right risk weight matrix W(R) is multiplied by the right normalized risk value B_norm to obtain the right risk map Riskmap(R), i.e., Riskmap(R)=W(R)*B_norm. Step b506: Determine pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the left pixel value and the right pixel value. The left and right pixel values ​​are combined to obtain pixel values ​​corresponding to the subset of voxels in the functional brain region that is the subject of clinical intervention.

[0124] In some alternative embodiments, the above step b505 may specifically include projecting the left pixel values ​​corresponding to the brain function mapping to present a left risk map corresponding to the subset of voxels in the brain functional region of the subject that will be clinically intervened, and projecting the right pixel values ​​corresponding to the brain function mapping to present a right risk map corresponding to the subset of voxels in the brain functional region of the subject that will be clinically intervened.

[0125] Accordingly, the above step b506 may specifically include combining the left risk map and the right risk map to obtain a risk map corresponding to a subset of voxels of the brain functional region to be clinically intervened. The left and right risk maps Riskmap(L) and Riskmap(R) of the target surgical area can also be combined to obtain a risk map of the target surgical area.

[0126] The present application does not specifically limit the method for visualizing the risk map, and it is sufficient that the executing entity can select a combination of grayscale, color, and brightness according to the actual surgery to visualize and display the risk map, and can clearly display the risk of resection of the brain function area in the target surgical area.

[0127] The method for localizing and laterally identifying functional brain regions according to the embodiments of the present application uses functional brain magnetic resonance data to locate the dominant brain side and functional regions based on the functional brain regions of an individual subject. Conventional preoperative laterality localization methods are unable to safely and effectively identify functional brain laterality and functional regions. Magnetic resonance and functional magnetic resonance imaging techniques can be used to detect brain function non-invasively. The present application utilizes functional brain magnetic resonance images to accurately localize brain function laterally based on personalized functional brain region segmentation technology, providing powerful theoretical and technical support for surgeons planning brain surgery. This effectively solves the problem of inaccurate laterality in functional regions due to differences in individual structure and function, which can easily lead to postoperative complications. Accurate preoperative laterality localization technology is developed, and accurate laterality localization is achieved using personalized functional brain region segmentation technology.

[0128] Further, referring to FIG. 6, as a realization of the method shown in each of the above figures, the present application provides an embodiment of an apparatus for localizing and laterally identifying brain functional areas, which corresponds to the embodiment of the method shown in FIG. 2, and which can be specifically applied to various electronic devices.

[0129] As shown in FIG. 6, the brain functional region localization and laterality determination device 600 of this embodiment includes a data acquisition unit 601, a processing unit 602, a localization unit 603 and a laterality determination unit 604. The data acquisition unit 601 is arranged to acquire structural and functional brain magnetic resonance image data of the subject.

[0130] The processing unit 602 is configured to determine a brain function mapping of the subject based on the brain structural magnetic resonance image data and the brain functional magnetic resonance image data, where the brain function mapping includes brain functional region markers and corresponding voxel sets of at least two brain functional regions.

[0131] The localization unit 603 is configured to, for each clinically intervened voxel in the set of clinically intervened voxels, determine a brain function region marker corresponding to the clinically intervened voxel based on the clinically intervened voxel and brain function mapping, where the brain function region marker includes the brain function region marker in the brain function mapping.

[0132] The laterality determination unit 604 is configured to divide the set of clinically intervened voxels according to a brain functional region label corresponding to each clinically intervened voxel, obtain at least one subset of clinically intervened brain functional region voxels, the clinically intervened voxels in each subset of clinically intervened brain functional region voxels correspond to the same brain functional region label, and for each subset of clinically intervened brain functional region voxels, determine a brain functional laterality corresponding to the subset of clinically intervened brain functional region voxels based on brain function mapping. In some alternative embodiments, the brain functional region localization and laterality determination device 600 may further include the following units:

[0133] The risk value determination unit 605 is configured to, for each subset of voxels of the brain functional region to be clinically intervened, determine a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened. In some alternative embodiments, the brain functional region localization and laterality determination device 600 may further include the following units:

[0134] The presentation unit 606 is configured to, for each subset of voxels of the brain functional region to be clinically intervened, determine pixel values ​​corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened, and present the subset of voxels of the brain functional region to be clinically intervened according to the determined pixel values. In some alternative embodiments, the processing unit 602 is further arranged as follows: Based on the structural brain magnetic resonance image data, it is determined whether the subject's brain structure has damage. If the subject's brain structure is not damaged, a functional brain mapping of the subject is determined from the functional brain magnetic resonance image data. In some alternative embodiments, the processing unit 602 is further arranged as follows: If the subject has a damaged brain structure, the damaged brain structure of the subject is determined. The subject's damaged brain region and undamaged brain region are determined based on the damaged brain structural region, where the damaged brain region includes M voxels, where M is a positive integer equal to or greater than 2.

[0135] A brain functional map of an undamaged brain region is determined based on the brain functional magnetic resonance imaging data, and the brain functional map of an undamaged brain region includes N brain functional regions, where N is a positive integer equal to or greater than 2. The correlation degree between each voxel in the M voxels corresponding to the damaged brain region and each brain functional region in the N brain functional regions is determined.

[0136] For each of the M voxels, the brain functional area corresponding to the voxel is determined according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each of the N brain functional areas, and a brain functional mapping of the subject is obtained. In some alternative embodiments, the processing unit 602 is further arranged as follows: Of the N brain functional areas, the brain functional area with the highest correlation with the voxel is identified as the brain functional area corresponding to the voxel. In some alternative embodiments, the processing unit 602 is further arranged as follows:

[0137] In response to determining that the correlation between each of the N brain functional areas and the voxel is smaller than a predetermined correlation threshold, the brain functional area corresponding to the voxel is determined to be an invalid brain functional area. In some alternative embodiments, the processing unit 602 is further arranged as follows:

[0138] The brain functional area among the N brain functional areas that has the highest correlation with the voxel is determined as the brain functional area corresponding to the voxel, and a first iterative brain functional mapping of the damaged brain area is obtained.

[0139] The following iterative operation is performed: a first iterative brain functional mapping of the damaged brain region is combined with a brain functional mapping of a non-damaged brain region to obtain an iterative brain functional mapping, which includes N iterative brain functional regions; a correlation between the voxel and each of the N iterative brain functional regions is determined; the brain functional region with the highest correlation with the voxel among the N brain functional regions is determined as the voxel's brain functional region, thereby obtaining a second iterative brain functional mapping of the damaged brain region; a match between the second iterative brain functional mapping of the damaged brain region and the first iterative brain functional mapping of the damaged brain region is determined to be greater than a preset match threshold; if so, the second iterative brain functional mapping of the damaged brain region is determined as the brain functional mapping of the damaged brain region, the iterative operation is terminated, and the brain functional mapping of the damaged brain region is used to characterize the brain functional region corresponding to the voxel; if not, the first iterative brain functional mapping of the damaged brain region is updated to the second iterative brain functional mapping of the damaged brain region, and the iterative operation is continued. In some alternative embodiments, the laterality determination unit 604 is further configured as follows:

[0140] Based on the hemispheric autonomic index of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined.

[0141] Alternatively, the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined based on the area of ​​the left and right functional region surfaces of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened. In some alternative embodiments, the risk value determination unit 605 is further arranged as follows:

[0142] Based on the functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened, a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened are determined.

[0143] In some alternative embodiments, the brain function mapping further includes functional connectivity reliability between each voxel, and the presentation unit 606 is further arranged as follows: The functional connectivity reliability of each voxel in the subset of voxels in the brain functional region to be clinically intervened is determined as a weight of the risk value, and a risk weight matrix is ​​obtained. A left risk weight matrix and a right risk weight matrix are determined based on the risk weight matrix. Based on the left risk weight matrix and the left risk value, a left pixel value corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined. Based on the right risk weight matrix and the right risk value, a right pixel value corresponding to the subset of voxels of the brain functional region to be clinically intervened is determined. Based on the left pixel value and the right pixel value, pixel values ​​corresponding to the subset of voxels of the brain functional region to be clinically intervened are determined.

[0144] Note that the detailed implementation and technical effects of each unit in the device for identifying the location and laterality of a brain functional region according to the present application can be referred to in other embodiments of the present application, and therefore a description thereof will be omitted here.

[0145] 7, there is shown a schematic diagram of a computer system 700 for realizing the terminal device or server of the present application. The terminal device or server shown in FIG. 7 is merely an example and does not impose any limitations on the functions and scope of use of the present application.

[0146] 7, computer system 700 includes a central processing unit (CPU) 701 capable of performing various appropriate operations and processes in accordance with a program stored in read-only memory (ROM) 702 or loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 also stores various programs and data necessary for the operation of system 700. CPU 701, ROM 702, and RAM 703 are interconnected by bus 704. An input / output (I / O) interface 705 is also connected to bus 704.

[0147] An input unit 706 including a keyboard, a mouse, etc., an output unit 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc., a storage unit 708 including a hard disk, etc., and a communication unit 709 including a network interface card such as a LAN (Local Area Network) card and a modem, are connected to the I / O interface 705. The communication unit 709 performs communication processing via a network such as the Internet.

[0148] In particular, according to an embodiment of the present application, the processes described with reference to the flowcharts above may be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product including a computer program loaded onto a computer-readable medium, the computer program including program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication unit 709. When the computer program is executed by the central processing unit (CPU) 701, the functions defined in the method of the present application are performed. Note that the computer-readable medium of the present application may be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer magnetic disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, loaded with computer-readable program code. Such propagated data signals may take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above.The computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any suitable medium, including, but not limited to, any suitable medium.

[0149] Computer program code for carrying out operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, Python, and further including conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. When a remote computer is involved, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).

[0150] The flowcharts and block diagrams in the figures illustrate possible system architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, block, or portion of code, including one or more executable instructions for implementing a given logical function. It should be noted that the functions described in the blocks may alternatively occur in a different order from the order described in the figures. For example, two blocks shown in succession may actually be executed essentially in parallel, or in some cases, they may be executed in the reverse order, as determined by such functionality. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented in a system using dedicated hardware that performs a given function or operation, or may be implemented using a combination of dedicated hardware and computer instructions.

[0151] The units described herein may be implemented in software or hardware. The described units may be provided in a processor, and may be described as including, for example, a scan data acquisition unit, a processing unit, a localization unit, and a laterality determination unit. However, the names of these units may not necessarily be limiting.

[0152] In another aspect, the present application further provides a computer-readable medium, which may be included in the device described in the above embodiments, or may exist independently and not be integrated into the device. The computer-readable medium has one or more programs loaded thereon. When the one or more programs are executed by the device, the device acquires structural brain magnetic resonance image data and functional brain magnetic resonance image data of a subject, and determines a brain function map of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, wherein the brain function map includes brain function region markers of at least two brain function regions and corresponding voxel sets, and for each clinical intervention voxel in the clinical intervention voxel set, determines a clinical intervention target voxel based on the clinical intervention voxel and the brain function map. determine brain functional region markers corresponding to the voxels to be clinically intervened, where the brain functional region markers include brain functional region markers in the brain functional mapping; divide the set of voxels to be clinically intervened according to the brain functional region markers corresponding to each voxel to be clinically intervened to obtain at least one subset of voxels to be clinically intervened, the voxels to be clinically intervened in each subset of voxels to be clinically intervened in the brain functional region have the same brain functional region marker; and for each subset of voxels to be clinically intervened in the brain functional region, determine brain functional laterality corresponding to the subset of voxels to be clinically intervened in the brain functional mapping.

[0153] The above description merely describes the preferred embodiments and operational technical principles of the present application. Those skilled in the art should understand that the scope of the present disclosure is not limited to the specific combination of the above technical features, but also includes other technical forms formed by any combination of the above technical features or their equivalent features, as long as it does not deviate from the above inventive idea. For example, technical means formed by mutually replacing the above features with technical features having similar functions (not limited to) disclosed in the present application. The technical aspects described in the embodiments of the present application may be arbitrarily combined if they do not conflict with each other.

[0154] As described above, the present application merely provides specific embodiments, and the scope of protection of the present application is not limited thereto. Those skilled in the art may easily devise modifications or substitutions within the technical scope disclosed in the present application, and all such modifications or substitutions shall be included in the scope of protection of the present application. Therefore, the scope of protection of the present application shall be governed by the scope of protection of the claims.

Claims

1. a data acquisition unit arranged to acquire structural and functional brain magnetic resonance image data of the subject; a processing unit configured to determine a brain function mapping of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, the brain function mapping including brain function region markers and corresponding voxel sets of at least two brain function regions; a position determination unit configured to determine, for each clinically intervened voxel in the clinically intervened voxel set, a brain function region marker corresponding to the clinically intervened voxel based on the clinically intervened voxel and the brain function mapping, such that the brain function region marker contains the brain function region marker in the brain function mapping; a laterality determination unit, which is configured to divide the set of voxels to be clinically intervened according to a brain functional region label corresponding to each voxel to obtain at least one subset of voxels to be clinically intervened, wherein the voxels in each subset of voxels to be clinically intervened correspond to the same brain functional region label, and to determine, for each subset of voxels to be clinically intervened, a brain functional laterality corresponding to the subset of voxels to be clinically intervened based on the brain function mapping; 1. A device for localizing and laterally identifying functional brain regions, comprising:

2. 2. The device of claim 1, further comprising a risk value determination unit configured to, for each subset of voxels of the brain functional region to be clinically intervened, determine a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on a brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened.

3. 3. The device of claim 2, further comprising a presentation unit configured to, for each subset of voxels of the brain functional region to be clinically intervened, determine a pixel value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened, and present the subset of voxels of the brain functional region to be clinically intervened according to the determined pixel value.

4. The processing unit determining a brain function map of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, determining whether the subject's brain structure has damage based on the brain structural magnetic resonance image data; If the subject's brain structure is not damaged, determining a brain function map of the subject based on the brain function magnetic resonance image data; The apparatus of claims 1 to 3, further comprising:

5. The processing unit determining a brain function map of the subject based on the structural brain magnetic resonance image data and the functional brain magnetic resonance image data, If the subject's brain structure is damaged, identifying a damaged brain region and an undamaged brain region of the subject, where the damaged brain region includes M voxels, where M is a positive integer greater than or equal to 2; determining a brain function map of an undamaged brain region based on the brain functional magnetic resonance image data (the brain function map of an undamaged brain region includes N brain functional regions, where N is a positive integer equal to or greater than 2); Determining a correlation between each voxel in the M voxels corresponding to the damaged brain region and each brain functional area in the N brain functional areas; For each voxel among the M voxels, determine the brain functional area corresponding to the voxel according to a predetermined functional area classification rule based on the degree of correlation between the voxel and each brain functional area among the N brain functional areas, thereby obtaining a brain function mapping of the subject; The apparatus of claim 4 further comprising:

6. The processing unit Based on the degree of correlation between the voxel and each of the N brain functional areas, Determining the brain functional area corresponding to the voxel according to a predetermined functional area classification rule includes: determining, among the N brain functional areas, the brain functional area having the highest correlation with the voxel as the brain functional area corresponding to the voxel; The apparatus of claim 5 further comprising:

7. The processing unit Based on the degree of correlation between the voxel and each of the N brain functional areas, Determining the brain functional area corresponding to the voxel according to a predetermined functional area classification rule includes: determining, in response to determining that the correlation between each of the N brain function areas and the voxel is smaller than a predetermined correlation threshold, the brain function area corresponding to the voxel as an invalid brain function area; The apparatus of claim 5 further comprising:

8. The processing unit: Based on the degree of correlation between the voxel and each of the N brain functional areas, Determining the brain functional area corresponding to the voxel according to a predetermined functional area classification rule includes determining the brain functional area that has the highest correlation with the voxel among the N brain functional areas as the brain functional area corresponding to the voxel, and obtaining a first iterative brain functional mapping of the damaged brain area; performing the following iterative operations, combining the first iterative brain function mapping of the damaged brain area with the brain function mapping of the non-damaged brain area to obtain an iterative brain function mapping, the iterative brain function mapping including N iterative brain areas; an iterative operation of determining the correlation between the voxel and each iterative brain function area in the N iterative brain function areas; an iterative operation of determining the brain function area among the N brain function areas that has the highest correlation with the voxel as the brain function area corresponding to the voxel, to obtain a second iterative brain function mapping of the damaged brain area; an iterative operation of determining whether the degree of coincidence between the second iterative brain function mapping of the damaged brain area and the first iterative brain function mapping of the damaged brain area is greater than a preset threshold value; if the degree of coincidence is greater, the second iterative brain function mapping of the damaged brain area is determined as the brain function mapping of the damaged brain area, and the iterative operation is terminated; the brain function mapping of the damaged brain area is used to characterize the brain function area corresponding to the voxel; if not, the first iterative brain function graph of the damaged brain area is updated to the second iterative brain function mapping of the damaged brain area, and then the iterative operation is continued; The apparatus of claim 5 further comprising:

9. The laterality identification unit For each subset of voxels in the brain functional region to be clinically intervened, determining a brain functional laterality corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the brain function mapping includes: determining the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the hemispheric autonomic index of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened, or determining the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the area of ​​the left and right functional area surfaces of the brain functional region corresponding to the subset of voxels of the brain functional region to be clinically intervened; The apparatus of claims 1 to 3, further comprising:

10. The risk value determination unit: the surgical risk value includes a left-sided risk value and a right-sided risk value; Based on the brain functional laterality corresponding to the subset of voxels in the brain functional region to be clinically intervened, determining a surgical risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened includes determining a left risk value and a right risk value corresponding to the subset of voxels of the brain functional region to be clinically intervened based on the brain functional laterality corresponding to the subset of voxels of the brain functional region to be clinically intervened; The apparatus of claim 3 further comprising:

11. The presentation unit The brain functional mapping also includes a functional connectivity reliability between two different voxels; Determining pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the surgical risk values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened includes: determining the functional connectivity reliability of each voxel in the subset of brain functional region voxels to be clinically intervened as a risk value weight to obtain a risk weight matrix; determining a left risk weight matrix and a right risk weight matrix based on the risk weight matrix; determining left pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the left risk weight matrix and the left risk value; determining right pixel values ​​corresponding to the subset of voxels in the brain functional region to be clinically intervened based on the right risk weight matrix and the right risk value; determining pixel values ​​corresponding to a subset of voxels in the brain functional region to be clinically intervened based on the left pixel values ​​and the right pixel values; The apparatus of claim 10 further comprising:

12. one or more processors; a storage device storing one or more programs; An electronic device comprising: When the one or more programs are executed by the one or more processors, the one or more processors realize the functions of each unit in the brain functional area location and laterality identification device described in any one of claims 1 to 11.

13. A computer-readable storage medium storing a computer program, the computer program being executed by one or more processors to realize the functions of each unit in the device for localizing and laterally identifying brain functional regions according to any one of claims 1 to 11.

Images