Core determination method and device, computer equipment and storage medium
The method enhances nucleus determination accuracy in DBS by identifying feature points, registering medical images with a target atlas, and performing three-dimensional reconstruction, addressing the issue of unclear nuclei in patient images.
Patent Information
- Application Number
- CN202310659243.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-05
- Publication Date
- 2024-12-06
AI Technical Summary
Current methods for determining target nuclei in deep brain stimulation (DBS) are inaccurate due to unclear visualization of nuclei in patient images, especially on lower-field magnetic resonance equipment, and individual anatomical variations.
A method involving feature point identification in medical images, registration with a target atlas, and three-dimensional reconstruction to enhance nucleus visibility and accuracy, using a computer device for precise nucleus determination.
Improves the accuracy of nucleus determination by providing clear and intuitive three-dimensional visualization of target nuclei, facilitating more precise target location identification.
Smart Images

Figure CN119090792A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical technology, and in particular to a method, apparatus, computer device and storage medium for determining a nucleus. Background Art
[0002] Deep brain stimulation (DBS) is mainly used to treat Parkinson's disease. During DBS, doctors need to determine the target location of the target nucleus in the area of interest, and then implant the electrode to the target location and apply electrical stimulation.
[0003] At present, doctors usually use patient images to first determine the target nucleus in the patient image based on experience, and then determine the target location based on the target nucleus. However, most of the target nuclei are not clear in the patient images, so the current nucleus determination method has the problem of low accuracy in determining the nucleus. Summary of the invention
[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for determining nuclei that can improve the accuracy in order to solve the above technical problems.
[0005] In a first aspect, the present application provides a method for determining a nucleus, the method comprising:
[0006] Determine a first feature point of a first medical image of a region of interest;
[0007] According to the first feature point and the second feature point in the target atlas of the region of interest, the first medical image and the target atlas are registered to determine first distribution information of target nuclei in each first image layer of the first medical image; the target atlas includes a plurality of second image layers having second distribution information of the target nuclei;
[0008] According to the first distribution information, a target nucleus in the first medical image is three-dimensionally reconstructed to obtain and display third distribution information of the target nucleus.
[0009] In one embodiment, the method further comprises:
[0010] Acquire a second medical image after the target electrode is implanted in the region of interest; the second medical image includes a plurality of third image layers;
[0011] Performing three-dimensional reconstruction on the target electrode in the second medical image according to the size information of the target electrode to obtain target electrode information;
[0012] registering the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image;
[0013] According to the fourth distribution information, the target nucleus in the second medical image is three-dimensionally reconstructed, fifth distribution information of the target nucleus is determined, and the target electrode information and the fifth distribution information are displayed.
[0014] In one embodiment, determining the first feature point of the first medical image of the region of interest includes:
[0015] Identifying feature information corresponding to each of the first image layers according to the grayscale value of each pixel in each of the first image layers;
[0016] Determining a first feature point in the region of interest according to feature information corresponding to each of the first image layers;
[0017] The first feature points include structural feature points and / or edge feature points.
[0018] In one embodiment, if the first feature point includes the structural feature point, determining the first feature point in the region of interest according to the feature information corresponding to each of the first image layers includes:
[0019] Determine the target part according to the feature information corresponding to each of the first image layers and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts;
[0020] The structural feature point is determined according to feature information corresponding to the first image layer where the target part is located.
[0021] In one embodiment, if the first feature point includes the edge feature point, determining the first feature point in the region of interest according to the feature information corresponding to each of the first image layers includes:
[0022] Determining, according to the feature information corresponding to each of the first image layers, an interesting contour of the interesting region in each of the first image layers;
[0023] The feature point on each of the contours of interest with the smallest distance from the corresponding preset edge of the first image layer is used as the edge feature point.
[0024] In one embodiment, the first medical image and the target atlas of the region of interest are registered according to the first feature point to determine first distribution information of target nuclei in each first image layer of the first medical image, including:
[0025] Determine a difference value between each of the first image layers and each of the second image layers according to the first feature point and the second feature point;
[0026] Determine the registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer;
[0027] According to the registration result, the second image layer is mapped to the corresponding first image layer to determine the first distribution information.
[0028] In one embodiment, the method further comprises:
[0029] Determine the position information of the target feature point in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature point includes the structural feature point and / or the edge feature point in the first distribution information;
[0030] An analysis result of the first distribution information is determined according to the position information.
[0031] In one embodiment, the method further comprises:
[0032] Determine the target location based on the displayed third distribution information;
[0033] According to the target position, a puncture path is determined; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front-back tilt angle of the guide, and the second puncture angle is used to indicate the left-right tilt angle of the guide.
[0034] In a second aspect, the present application also provides a nucleus determination device, the device comprising:
[0035] A first determining module, used to determine a first feature point of a first medical image of a region of interest;
[0036] A second determination module is used to register the first medical image and the target atlas according to the first feature point and the second feature point in the target atlas of the region of interest, so as to determine the first distribution information of the target nuclei in each first image layer of the first medical image; the target atlas includes a plurality of second image layers having the second distribution information of the target nuclei;
[0037] The first reconstruction module is used to perform three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtain and display third distribution information of the target nucleus.
[0038] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.
[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the next step of any of the above methods is implemented.
[0040] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.
[0041] The above-mentioned nucleus determination method, device, computer equipment and storage medium first determine the first feature point of the first medical image of the region of interest, and then align the first medical image and the target map according to the first feature point and the second feature point in the target map of the region of interest to determine the first distribution information of the target nucleus in each first image layer of the first medical image, so as to perform three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtain and display the third distribution information of the target nucleus. Since the target map includes multiple second image layers with the second distribution information of the target nucleus, after the first medical image and the target map are aligned, the more accurate first distribution information in the first medical image can be indirectly determined. Further, the target nucleus in the first medical image can be reconstructed in three dimensions using the first distribution information, so as to determine clear and intuitive third distribution information. In this way, the problem that the current nucleus is not clear in the patient image, resulting in inaccurate determination of the nucleus, can be avoided, and the accuracy of the determined nucleus is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 This is an application environment diagram of the nucleus determination method in the embodiment of the present application;
[0043] Figure 2 This is a schematic diagram of the process of the method for determining a nucleus group in an embodiment of the present application;
[0044] Figure 3 A schematic diagram of a registration result in an embodiment of the present application;
[0045] Figure 4 This is a schematic diagram of a nucleus result in an embodiment of the present application;
[0046] Figure 5 A schematic diagram of a process for determining a display result in an embodiment of the present application;
[0047] Figure 6 This is a schematic diagram showing the results of an embodiment of the present application;
[0048] Figure 7 This is a schematic diagram of a process for determining a first feature point in an embodiment of the present application;
[0049] Figure 8 This is a schematic diagram of a process for determining structural feature points in an embodiment of the present application;
[0050] Fig. 9 This is a schematic diagram of a process for determining edge feature points in an embodiment of the present application;
[0051] Fig.10 This is a schematic diagram of a process for determining first distribution information in an embodiment of the present application;
[0052] Fig.11 A schematic diagram of a process for determining an analysis result in an embodiment of the present application;
[0053] Fig.12 This is a schematic diagram of a process for determining a puncture path in an embodiment of the present application;
[0054] Fig.13 This is a schematic diagram of a process of a nucleus determination method in an embodiment of the present application;
[0055] Fig.14 4 is a structural block diagram of a nucleus determination device in an embodiment of the present application. DETAILED DESCRIPTION
[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0057] At present, doctors usually use patient images to determine the target location. Taking the patient image as an MRI image as an example, the doctor first uses the MRI image and combines anatomical experience to determine the target nucleus on the MRI image, such as the subthalamic nucleus (STN), and then uses the coordinates of the STN in the reference coordinate system summarized by anatomical experience to comprehensively determine the target location.
[0058] However, firstly, some target nuclei cannot be visualized in magnetic resonance images. For example, the globus pallidus internas (Gpi) is not visible in magnetic resonance images. Secondly, even for nuclei such as STN that can be visualized in magnetic resonance images, their visualization is only relatively clear on 3.0T high-field strength magnetic resonance equipment, and the utilization rate of high-field strength magnetic resonance equipment is not high. Conventional hospitals only have 1.5T field strength magnetic resonance equipment. In addition, the nuclei visualized on magnetic resonance images lack clear structural boundaries and only have a vague outline. At the same time, the anatomical empirical coordinate values are summarized based on a large data set of normal human brains, and some patients often do not conform to the anatomical empirical coordinates due to individual differences and brain atrophy.
[0059] In summary, the current nucleus determination method has the problem that the accuracy of the determined nucleus is not high. Based on this, it is necessary to provide a nucleus determination method for the above technical problems, and the nucleus determination method will be introduced below.
[0060] Figure 1 FIG. 1 is an application environment diagram of the method for determining a nucleus group in an embodiment of the present application. In an embodiment of the present application, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a nucleus is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0061] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0062] This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.
[0063] Figure 2 This is a flow chart of the method for determining a nucleus group in the embodiment of the present application. The method can be applied to Figure 1 In the computer device shown, in one embodiment, as Figure 2 As shown, the following steps are included:
[0064] S201, determining a first feature point of a first medical image of a region of interest.
[0065] In this embodiment, the computer device first needs to obtain a first medical image of a region of interest. The region of interest refers to a part where electrodes need to be implanted, for example, the region of interest in DBS is the brain. The following examples are all based on the region of interest being the brain.
[0066] The first medical image is used to reflect the structural morphology of the region of interest, and the first medical image is a preoperative image of the region of interest, that is, the first medical image is an image of the region of interest before the electrode is implanted. Further, the first medical image includes multiple first image layers, for example, the first medical image includes 256 first image layers.
[0067] The first medical image includes, but is not limited to, CT (Computed Tomography) images, MRI (Magnetic Resonance Imaging) images, PET-CT images, and PET-MR images.
[0068] The following examples are all based on the first medical image being a magnetic resonance image. This embodiment does not limit the number of modalities of magnetic resonance images. For example, the first medical image can be a T1 image, a T2 image, or an image obtained by fusing the T1 image and the T2 image. Among them, the T1 image and the T2 image are different sequences in the magnetic resonance image. The T1 image can reflect the difference in longitudinal relaxation of the region of interest, and the T2 image can reflect the difference in transverse relaxation of the region of interest.
[0069] Optionally, the computer device may receive the first medical image of the region of interest sent by the medical device, and the computer device may also store the first medical image of the region of interest in advance.
[0070] Furthermore, the computer device can determine the first characteristic point of the first medical image of the region of interest, wherein the first characteristic point is used to indicate an easily distinguishable feature on the region of interest, such as a boundary point of the brain, such as the anterior point (AP), the posterior point (PP), the leftmost point (LP), the rightmost point (RP), the superior point (SP), and the inferior point (IP).
[0071] Optionally, the computer device can respond to the doctor's operation to determine the first feature point selected by the doctor on the first medical image. The computer device can also automatically determine the first feature point on the first medical image based on the first medical image and a preset algorithm. This embodiment does not impose any restrictions.
[0072] S202, aligning the first medical image and the target map based on the first feature point and the second feature point in the target map of the region of interest to determine the first distribution information of the target nuclei in each first image layer of the first medical image; the target map includes multiple second image layers having the second distribution information of the target nuclei.
[0073] In this embodiment, the computer device can obtain the target spectrum. Optionally, the computer device receives the target spectrum sent by other electronic devices, and the computer device can also store the target spectrum in advance and call it when needed.
[0074] Further optionally, the computer device may determine a target atlas corresponding to the attribute information from each candidate atlas based on the attribute information of the first medical image. The attribute information of the first medical image includes, but is not limited to, the age group and gender to which the first medical image belongs. Exemplarily, the computer device stores candidate atlases corresponding to different ages and different genders, and determines the target atlas based on the age and gender corresponding to the first medical image.
[0075] The target atlas is determined based on a large number of patient samples and is used to indicate the location of the target nucleus in the region of interest, and has a certain degree of universality. In other words, the target atlas includes a plurality of second image layers having second distribution information of the target nucleus.
[0076] The number of the second image layers may be the same as or different from the number of the first image layers. In order to improve the matching effect, generally speaking, the number of the second image layers may be greater than or equal to the number of the first image layers.
[0077] The target map also has a second feature point corresponding to the first feature point. For example, if the first medical image has AP, PP, LP, RP, SP, and IP, then the target map also has AP, PP, LP, RP, SP, and IP. The second feature point on the target map can be a feature point determined by a doctor after manual correction based on a preset algorithm, or it can be a feature point determined by other methods.
[0078] Furthermore, the computer device can register the first medical image and the target atlas according to the first feature point and the second feature point in the target atlas of the region of interest to determine the first distribution information of the target nuclei in each first image layer of the first medical image. The process of registering the first medical image and the target atlas is the process of determining the mapping relationship between the first image layer and the second image layer according to the first feature point and the second feature point. In this way, based on the mapping relationship, the target atlas can be mapped to the first medical image to determine the first distribution information.
[0079] The first distribution information includes a coordinate set of the target nucleus in the image coordinate system of the first medical image, such as a first position of the STN nucleus in the first image layer 18 and a second position of the STN nucleus in the first image layer 20 of the first medical image.
[0080] For example, Figure 3 is a schematic diagram of a registration result in an embodiment of the present application, such as Figure 3 As shown, after the first medical image and the target atlas are registered, the computer device can determine the position of the target nucleus in the first medical image by combining the axial plane, coronal plane, and sagittal plane of the first medical image.
[0081] S203: Perform three-dimensional reconstruction on the target nucleus in the first medical image according to the first distribution information, and obtain and display third distribution information of the target nucleus.
[0082] In this embodiment, after determining the first distribution information, the computer device can perform three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtain and display the third distribution information of the target nucleus. The third distribution information includes a coordinate set of the target nucleus corresponding to the first medical image in the three-dimensional coordinate system.
[0083] That is to say, after using the target atlas for registration, the computer device can first determine the shape, size, and position of the target nucleus with clear boundaries and clear development in the first medical image, and then the computer device can perform three-dimensional visualization of the target nucleus in the first medical image based on the first distribution information to reconstruct the third distribution information. Furthermore, the computer device can display the third distribution information of the target nucleus. In this way, based on the third distribution information, the doctor can more flexibly, clearly and intuitively determine the shape, size, and position of the target nucleus in the area of interest, which is conducive to the subsequent determination of the target position.
[0084] Figure 4 Schematic diagram of a nucleus result in an embodiment of the present application, such as Figure 4 As shown, Figure 4 (a) is the preoperative T2 image of the region of interest, combined with Figure 4 (b) and Figure 4 (c) It can be seen that the STN nucleus and the Gpi nucleus are not clearly visible in this image. Therefore, it is not easy for doctors to determine the boundaries, shapes, sizes, etc. of the STN nucleus and the Gpi nucleus from this image. Therefore, the accuracy of the nuclei determined by doctors based on this image is not high, which will also affect the subsequent determination of targets.
[0085] Figure 4 (d) is the third distribution information of the STN nucleus and the Gpi nucleus determined by the method provided in this embodiment. It can be seen that the boundary, shape and size of the nucleus determined by the method provided in this embodiment are relatively clear, so the accuracy of the determined nucleus is high, which is conducive to the subsequent determination of the target.
[0086] The nucleus determination method provided in this embodiment first determines the first feature point of the first medical image of the region of interest, and then aligns the first medical image and the target map according to the first feature point and the second feature point in the target map of the region of interest to determine the first distribution information of the target nucleus in each first image layer of the first medical image, thereby performing three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtaining and displaying the third distribution information of the target nucleus. Since the target map includes multiple second image layers with the second distribution information of the target nucleus, after aligning the first medical image and the target map, the more accurate first distribution information in the first medical image can be indirectly determined. Further, the target nucleus in the first medical image can be three-dimensionally reconstructed using the first distribution information, so as to determine clear and intuitive third distribution information. In this way, the problem that the current nucleus is not clear in the patient image, resulting in inaccurate determination of the nucleus, can be avoided, and the accuracy of the determined nucleus is improved.
[0087] Figure 5 This is a schematic diagram of a process for determining a display result in an embodiment of the present application, referring to Figure 5 This embodiment relates to an optional implementation method of how to display the target electrode information and the fourth distribution information. Based on the above embodiment, the above nucleus determination method further includes the following steps:
[0088] S501, acquiring a second medical image after the target electrode is implanted in the region of interest; the second medical image includes a plurality of third image layers.
[0089] In this embodiment, the computer device also needs to obtain a second medical image after the target electrode is implanted in the region of interest. In other words, the second medical image is an image after the electrode is implanted in the region of interest. The second medical image includes multiple third image layers, for example, the third medical image also includes 256 third image layers.
[0090] Likewise, the computer device may receive the second medical image sent by the medical device, and the computer device may also store the second medical image of the region of interest in advance.
[0091] It should be noted that, in some embodiments, in order to improve the registration effect of the first medical image and the second medical image, the type of the second medical image needs to be the same as that of the first medical image, and the number of first image layers is equal to the number of second image layers.
[0092] S502, performing three-dimensional reconstruction on the target electrode in the second medical image according to the size information of the target electrode to obtain target electrode information.
[0093] In this embodiment, the size information of the target electrode is known, for example, the computer device can determine the size, length, location of the stimulation contact, etc. of the target electrode implanted in the region of interest.
[0094] Then, the computer device can perform three-dimensional reconstruction of the target electrode in the second medical image according to the size information of the target electrode to obtain the target electrode information. In other words, the computer device performs three-dimensional visualization of the target electrode to reconstruct the target electrode information. The target electrode information includes the coordinate set of the target electrode in the three-dimensional coordinate system and the location of the stimulation electric shock in the target electrode.
[0095] S503: Register the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image.
[0096] In this embodiment, since the computer device has determined the first distribution information of the target nuclei in the first image layer of the first medical image, the computer device will also register the second medical image with the first medical image to determine the fourth distribution information of the target nuclei in the second medical image. The fourth distribution information includes the coordinate set of the target nuclei in the image coordinate system where the second medical image is located.
[0097] In some embodiments, the registration process of the first medical image and the second medical image is similar in principle to the registration process of the first medical image and the target atlas. The computer device can determine the mapping relationship between the first image layer of the first medical image and the third image layer in the second medical image based on the first feature point in the first medical image and the third feature point in the second medical image corresponding to the first feature point, for example, based on the AP, PP, LP, RP, SP, IP in the first medical image and the AP, PP, LP, RP, SP, IP in the second medical image, and then map the first image layer carrying the fourth distribution information to the corresponding third image layer, thereby obtaining the fourth distribution information of the target nucleus in each third image layer of the second medical image.
[0098] Of course, the computer device may also use other methods to register the second medical image with the first medical image, and this embodiment is not limited thereto.
[0099] S504, performing three-dimensional reconstruction on the target nucleus in the second medical image according to the fourth distribution information, determining fifth distribution information of the target nucleus, and displaying the target electrode information and the fifth distribution information.
[0100] In this embodiment, after S503, the computer device can determine the fourth distribution information of the target nuclei in each third image layer of the second medical image, and then the computer device can perform three-dimensional reconstruction of the target nuclei in the second medical image according to the fourth distribution information, and obtain and display the fifth distribution information of the target nuclei. The fifth distribution information includes a coordinate set of the target nuclei corresponding to the second medical image in the three-dimensional coordinate system.
[0101] Furthermore, the computer device can display the target electrode information and the fifth distribution information. In this way, the doctor can determine the three-dimensional position relationship of the contact point of the target electrode relative to the target nucleus on the basis of the original two-dimensional position relationship, so as to more flexibly and intuitively judge whether the contact point of each target electrode has reached the target nucleus, thereby assisting the doctor in formulating the best programming parameter strategy.
[0102] Figure 6 This is a schematic diagram showing the results of an embodiment of the present application. Figure 6 As shown, the computer device can display the target nucleus information and the target electrode information, and perform postoperative evaluation based on the target nucleus information and the target electrode information. Figure 6 Are the stimulation contacts of the implantable stimulation electrodes placed Figure 6 The number of stimulation contacts placed in the bilateral STN nuclei, etc.
[0103] This embodiment obtains a second medical image after the target electrode is implanted in the region of interest, and performs three-dimensional reconstruction of the target electrode in the second medical image based on the size information of the target electrode to obtain the target electrode information, and then aligns the second medical image with the first medical image to determine the fourth distribution information of the target nucleus in the second medical image, thereby performing three-dimensional reconstruction of the target nucleus in the second medical image based on the fourth distribution information, determining the fifth distribution information of the target nucleus, and displaying the target electrode information and the fifth distribution information. Since the third distribution information before surgery and the fifth distribution information after surgery can be compared, the efficiency and accuracy of nucleus determination are improved, and it is beneficial for doctors to conduct preoperative and postoperative evaluations.
[0104] Figure 7 This is a schematic diagram of a process for determining a first feature point in an embodiment of the present application, referring to Figure 7This embodiment relates to an optional implementation method of how to determine the first feature point of the first medical image of the region of interest. Based on the above embodiment, the above S201, determining the first feature point of the first medical image of the region of interest, includes the following steps:
[0105] S701 : Identify feature information corresponding to each first image layer according to the gray value of each pixel in each first image layer.
[0106] S702, determining first feature points in the region of interest according to feature information corresponding to each first image layer; the first feature points include structural feature points and / or edge feature points.
[0107] In this embodiment, assuming that the first medical image includes 256 first image layers, and each first image layer includes 100 pixels, the computer device can determine the feature information corresponding to each first image layer according to the grayscale values of the 100 pixels in each first image layer. The feature information is used to indicate the feature structure of the image in the first image layer, for example, the computer device determines that the pixels 20 to 40 of the first image layer form a rectangular shape.
[0108] Furthermore, the computer device can determine the first feature point in the region of interest according to the feature information corresponding to each first image layer, wherein the first feature point includes a structural feature point and / or an edge feature point.
[0109] The structural feature points include indicative structural points on the region of interest. The structural feature points may include the anterior commissure (AC) point, the posterior commissure (PC) point, and the IH point, wherein the IH point is any point on the midsagittal plane (MSP) that is not collinear with the AC-PC line. The MSP represents the midsagittal plane of the brain, which passes through the cerebral sulcus and divides the brain into left and right hemispheres.
[0110] The edge feature points include the boundary points of the region of interest. The edge feature points may include the aforementioned AP, PP, LP, RP, SP, and IP, which represent the front end, rear end, left end, right end, top end, and bottom end of the brain, respectively.
[0111] This embodiment identifies the feature information corresponding to each first image layer according to the gray value of each pixel point in each first image layer, and determines the first feature point in the region of interest according to the feature information corresponding to each first image layer. The first feature point includes a structural feature point and / or an edge feature point. Therefore, the computer device can automatically determine the first feature point according to the first medical image without manual confirmation by the doctor, thereby improving the efficiency of determining the first feature point.
[0112] Figure 8 This is a schematic diagram of a process for determining structural feature points in an embodiment of the present application, referring to Figure 8 This embodiment relates to an optional implementation method of how to determine the structural feature points. Based on the above embodiment, if the first feature points include structural feature points, the above S702, based on the feature information corresponding to each first image layer, determines the first feature points in the region of interest, including the following steps:
[0113] S801, determining a target part according to feature information corresponding to each first image layer and a first corresponding relationship; the first corresponding relationship includes a corresponding relationship between different feature information and different parts.
[0114] S802: Determine structural feature points according to feature information corresponding to the first image layer where the target part is located.
[0115] In this embodiment, the computer device has first correspondences between different feature information and different parts. For example, the computer device determines that feature information 1 corresponds to the third ventricle, and feature information 2 corresponds to the lateral ventricle.
[0116] Furthermore, after determining the feature information corresponding to each first image layer, the computer device can determine the target part according to the feature information corresponding to each first image layer and the first corresponding relationship. In other words, the computer device can determine which target parts the first image layer corresponds to according to the gray value of each pixel in the first image layer. For example, the computer device determines that the third ventricle exists in the first image layer 1.
[0117] Furthermore, the computer device can determine the structural feature points according to the feature information corresponding to the first image layer where the target part is located. It is understandable that the process of determining the structural feature points needs to refer to the doctor's anatomical experience.
[0118] For example, after the computer device finds the first image layer where the third ventricle exists, it can find the midpoint of the structure where the third ventricle is located as point AC based on the characteristic information of the third ventricle in the first image layer. The same is true for other structural feature points. In this way, the computer device can determine the structural feature points on the first medical image. In other words, the computer device also determines the position of the structural feature points in the image coordinate system where the first medical image is located, for example, point AC is located at the pixel point of the 3rd row and the 3rd column in the first image layer 1.
[0119] In this embodiment, since the first correspondence includes the correspondence between different feature information and different parts, the target part is determined according to the feature information corresponding to each first image layer and the first correspondence, and further, the structural feature point is determined according to the feature information corresponding to the first image layer where the target part is located. In this way, the computer device can automatically determine the structural feature point, thereby improving processing efficiency.
[0120] Fig. 9 This is a schematic diagram of a process for determining edge feature points in an embodiment of the present application, referring to Fig. 9 This embodiment relates to an optional implementation method of how to determine the first feature point of the first medical image of the region of interest. Based on the above embodiment, if the first feature point includes an edge feature point, the above S702, based on the feature information corresponding to each first image layer, determines the first feature point in the region of interest, including the following steps:
[0121] S901, determining an interesting contour of an interesting region in each first image layer according to feature information corresponding to each first image layer.
[0122] S902: Taking the feature point on each contour of interest with the smallest distance from the corresponding preset edge of the first image layer as the edge feature point.
[0123] In this embodiment, after the computer device determines the feature information corresponding to each first image layer, it can also determine the contour of interest of the region of interest in each first image layer according to the feature information corresponding to each first image layer. For example, the computer device can determine the contour of the brain in each first image layer.
[0124] Furthermore, the computer device uses the feature point on each contour of interest with the smallest distance from the corresponding preset edge of the first image layer as the edge feature point, wherein the preset edge may be at least one edge of top, bottom, left, right, front, and back.
[0125] Exemplarily, the computer device traverses all first image layers, determines the brain contour in each first image layer, and determines the point with the minimum distance between the brain contour and the left edge of the first image layer as LP. Similarly, the computer device can also determine other edge feature points.
[0126] This embodiment determines the contour of interest of the region of interest in each first image layer according to the feature information corresponding to each first image layer, and uses the feature point on each contour of interest with the smallest distance from the preset edge of the corresponding first image layer as the edge feature point. In this way, the computer device can automatically determine the edge feature point, thereby improving processing efficiency.
[0127] In some embodiments, the computer device may also determine edge feature points based on the structural feature points, feature information corresponding to each first image layer, and the contour of interest of the region of interest in the first image layer. For example, the computer device determines AP and PP respectively from the forward intersection point and the backward intersection point of the AC-PC line with the brain contour, determines SP from the intersection point of the upper extension line of the axial plane perpendicular to the PC point with the brain contour; determines IP from the lower extension line of the axial plane perpendicular to the AC point; determines LP and RP respectively from the left and right intersection points of the perpendicular line of the midsagittal plane passing through the PC point with the brain contour.
[0128] Fig.10 This is a schematic diagram of a process for determining first distribution information in an embodiment of the present application, referring to Fig.10 This embodiment relates to an optional implementation method of how to determine the first distribution information. Based on the above embodiment, the above S202, according to the first feature point and the second feature point in the target map of the region of interest, aligns the first medical image and the target map to determine the first distribution information of the target nuclei in each first image layer of the first medical image, includes the following steps:
[0129] S1001: Determine a difference value between each first image layer and each second image layer according to the first feature point and the second feature point.
[0130] In this embodiment, when the first medical image and the target atlas need to be registered, the computer device first determines the difference value between each first image layer and each second image layer based on the first feature point of the first medical image and the second feature point of the target atlas.
[0131] Exemplarily, assuming that the first medical image includes first image layers 1 to 100, and the target atlas includes second image layers 1 to 100, the computer device can traverse the second image layers 1 to 100, and determine the difference values between the first image layer 1 and the second image layers 1 to 100 respectively. Then, the computer device determines the difference values between the first image layer 2 and the second image layers 1 to 100 respectively, until the first image layers 1 to 100 are traversed to determine the difference values between each first image layer and each second image layer.
[0132] The difference value may be the sum of the distances between the first feature point and the corresponding second feature point, a weighted average value, a variance, etc. This embodiment does not impose any limitation thereto, as long as it can reflect the information entropy between the first image layer and each second image layer.
[0133] S1002, determining a registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer.
[0134] In this embodiment, continuing with the above example, after the computer device determines the difference values between the first image layer 1 and the second image layers 1 to 100, respectively, it can determine the minimum difference values between the first image layer 1 and the second image layers 1 to 100. For example, if the difference value between the first image layer 1 and the second image layer 2 is the smallest, the computer device can determine that there is a mapping relationship between the first image layer 1 and the second image layer 2. Similarly, after the computer device traverses the first image layer 1 to the first image layer 100, it can determine the mapping relationship between each first image layer and the second image layer. In this way, the computer device determines the registration result according to the first image layer and the second image layer corresponding to the minimum difference value.
[0135] In one embodiment, optionally, after determining the difference value between each first image layer and each second image layer, if the difference value between each first image layer and each second image layer is greater than a preset difference threshold, the computer device may adjust the length, width or overall scaling ratio of the target atlas until the difference value between each first image layer and each second image layer is not greater than the preset difference threshold. Thereafter, the computer device executes step S1002 to determine the registration result.
[0136] S1003: Map the second image layer to the corresponding first image layer according to the registration result to determine first distribution information.
[0137] In this embodiment, after obtaining the registration result, the computer device determines the mapping relationship between the first image layer and the second image layer. Then, the computer device can map the second image layer to the corresponding first image layer according to the registration result, that is, map the target atlas onto the first medical image to determine the first distribution information.
[0138] This embodiment determines the difference value between each first image layer and each second image layer based on the first feature point and the second feature point, and determines the registration result based on the first image layer and the second image layer corresponding to the minimum difference value. Since the registration result includes the mapping relationship between the first image layer and the second image layer, the second image layer can be mapped to the corresponding first image layer according to the registration result to determine the first distribution information, so that the target nucleus that is clearly visible in the first medical image can be determined.
[0139] Fig.11 This is a schematic diagram of a process for determining an analysis result in an embodiment of the present application, referring to Fig.11 This embodiment relates to an optional implementation method of how to determine the analysis result of the first distribution information. Based on the above embodiment, the above nucleus determination method also includes the following steps:
[0140] S1101, determine the position information of the target feature points in the first distribution information in the reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information.
[0141] In this embodiment, after the computer device determines the structural feature points based on the first medical image, a reference coordinate system can be established based on the structural feature points. For example, after the computer device determines the AC point, the PC point, and the IH point, the AC point can be used as the origin, the PC-AC direction can be used as the Y-axis direction, the direction perpendicular to the MSP can be used as the X-axis, and the Z-axis direction can be determined based on the X-axis and the Y-axis, thereby determining the Talairach coordinate (Talairach coordinate system), that is, the reference coordinate system.
[0142] Further, the computer device determines the position information of the target feature point in the first distribution information in the reference coordinate system. Wherein, the target feature point includes the structural feature point and / or the edge feature point in the first distribution information. Exemplarily, the computer device determines the coordinate value of the AC point in the first distribution information in the reference coordinate system.
[0143] S1102: Determine an analysis result of the first distribution information according to the location information.
[0144] It is understandable that in the medical field, based on anatomical experience, the position information of the target feature point in the reference coordinate system will be within a fixed range. Therefore, after determining the position information of the target feature point in the first distribution information in the reference coordinate system, the analysis result can be determined based on the position information, and the analysis result is used to indicate the accuracy of the first distribution information.
[0145] Exemplarily, assuming that the position information of the AC point in the first distribution information in the reference coordinate system differs from the position information of the AC point in the reference coordinate system in the anatomical experience by more than a preset difference, it means that the first distribution information determined using the target atlas has a large deviation. In this case, the computer device can replace the target atlas for realignment, or it can perform fine-tuning based on the first distribution information to update the first distribution information with a large deviation.
[0146] In this embodiment, since the reference coordinate system is determined based on the structural feature points in the first medical image, and the target feature points include the structural feature points and / or edge feature points in the first distribution information, after determining the position information of the target feature points in the first distribution information in the reference coordinate system, the analysis result of the first distribution information can be determined based on the position information. In this way, after determining the first distribution information, this embodiment can measure whether the first distribution information deviates too much from the actual situation, so as to improve the flexibility and accuracy of the nucleus determination process.
[0147] Fig.12 This is a schematic diagram of a process for determining a puncture path in an embodiment of the present application, referring to Figure 3 This embodiment relates to an optional implementation method of how to determine the puncture path. Based on the above embodiment, the above nucleus determination method also includes the following steps:
[0148] S1201, determining the target location based on the displayed third distribution information.
[0149] S1202, determining a puncture path according to the target position; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear tilt angle of the guide, and the second puncture angle is used to indicate the left and right tilt angle of the guide.
[0150] In this embodiment, after the computer device displays the third distribution information, the computer device can determine the target point position based on the displayed third distribution information. In other words, the target point position is a position determined based on the target nucleus.
[0151] Optionally, the doctor can refer to the third distribution information for path planning. In this way, the computer device can respond to the doctor's operation and continuously fine-tune the coordinate value of the target position in the reference coordinate system until the coordinate value of the target position in the reference coordinate system meets the clinical requirements, thereby determining the target position.
[0152] Furthermore, the doctor searches for a suitable puncture position based on the target position, and the computer device can determine the puncture path according to the target position. The puncture path includes a first puncture angle and a second puncture angle, wherein the first puncture angle is used to indicate the front-back tilt angle of the guide, and the second puncture angle is used to indicate the left-right tilt angle of the guide.
[0153] In other words, the guide is used to puncture the area of interest, and the computer device can determine the angle and position of the guide during the puncture process based on the target position, thereby determining the puncture path.
[0154] In some embodiments, the puncture path may also include other information such as puncture depth, which is not limited in this embodiment.
[0155] Since this embodiment can determine the target position based on the displayed third distribution information, and determine the puncture path according to the target position, and the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear inclination angle of the guide, and the second puncture angle is used to indicate the left and right inclination angle of the guide, thereby improving the accuracy and efficiency of the puncture.
[0156] In order to more clearly introduce the nucleus determination method in this application, Fig.13 Provide explanation. Fig.13 FIG. 1 is a schematic diagram of a process of determining a nucleus group in an embodiment of the present application. Fig.13 As shown, the computer device executes the nucleus determination method according to the following process.
[0157] S1301 , identifying feature information corresponding to each first image layer according to the gray value of each pixel in each first image layer of the first medical image.
[0158] S1302, determining a target part according to feature information corresponding to each first image layer and a first corresponding relationship; the first corresponding relationship includes a corresponding relationship between different feature information and different parts.
[0159] S1303: Determine structural feature points according to feature information corresponding to the first image layer where the target part is located.
[0160] S1304: Determine an interesting contour of an interesting region in each first image layer according to feature information corresponding to each first image layer.
[0161] S1305: Take the feature point on each contour of interest with the smallest distance from the corresponding preset edge of the first image layer as the edge feature point.
[0162] S1306, determining the difference value between each first image layer and each second image layer according to the first feature point of the first medical image and the second feature point of the target atlas; the first feature point includes a structural feature point and / or an edge feature point.
[0163] S1307: Determine a registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer.
[0164] S1308: Map the second image layer to the corresponding first image layer according to the registration result to determine the first distribution information.
[0165] S1309: Perform three-dimensional reconstruction on the target nucleus in the first medical image according to the first distribution information, and obtain and display third distribution information of the target nucleus.
[0166] S1310, determining position information of target feature points in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on structural feature points in the first medical image; the target feature points include structural feature points and / or edge feature points in the first distribution information.
[0167] S1311, determining an analysis result of the first distribution information according to the location information.
[0168] S1312, determining the target location based on the displayed third distribution information.
[0169] S1313, determining a puncture path according to the target position; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear tilt angle of the guide, and the second puncture angle is used to indicate the left and right tilt angle of the guide.
[0170] S1314, obtaining a second medical image after the target electrode is implanted in the region of interest; the second medical image includes a plurality of third image layers.
[0171] S1315, performing three-dimensional reconstruction on the target electrode in the second medical image according to the size information of the target electrode to obtain target electrode information.
[0172] S1316: Register the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image.
[0173] S1317, based on the fourth distribution information, perform three-dimensional reconstruction on the target nucleus in the second medical image, determine the fifth distribution information of the target nucleus, and display the target electrode information and the fifth distribution information.
[0174] The above S1301 to S1317 can refer to the above embodiment and will not be described in detail here.
[0175] It can be seen that in the above-mentioned nucleus determination method, the three-dimensional structural information of the target nucleus can be determined and visualized during the DBS preoperative planning and postoperative evaluation process. Since the segmented and reconstructed target nucleus has a clear shape and boundary, the positional relationship between each stimulation contact in the planned path or the actual path and the target position in the target nucleus can be more clearly and vividly displayed, so that a more quantitative study can be conducted. At the same time, the first medical image and the second medical image do not rely on 3.0T high-field strength magnetic resonance equipment. In the case of T1 or T2 sequences under 1.5T magnetic resonance, nuclei that are not visible in the medical image can also be determined, which also reduces the experience requirements of doctors and the requirements of hospital imaging equipment.
[0176] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0177] Based on the same inventive concept, the embodiment of the present application also provides a nucleus determination device for implementing the nucleus determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more nucleus determination device embodiments provided below can refer to the limitations of the nucleus determination method above, and will not be repeated here.
[0178] Fig.14 is a structural block diagram of a nucleus determination device in an embodiment of the present application, such as Fig.14 As shown, in an embodiment of the present application, a nucleus determination device 1400 is provided, comprising: a first determination module 1401, a second determination module 1402 and a first reconstruction module 1403, wherein:
[0179] The first determination module 1401 is used to determine the first feature point of the first medical image of the region of interest.
[0180] The second determination module 1402 is used to align the first medical image and the target map based on the first feature points and the second feature points in the target map of the area of interest to determine the first distribution information of the target nuclei in each first image layer of the first medical image; the target map includes multiple second image layers with second distribution information of the target nuclei.
[0181] The first reconstruction module 1403 is used to perform three-dimensional reconstruction on the target nucleus in the first medical image according to the first distribution information, and obtain and display third distribution information of the target nucleus.
[0182] The nucleus determination device provided in this embodiment first determines the first feature point of the first medical image of the region of interest, and then aligns the first medical image and the target map according to the first feature point and the second feature point in the target map of the region of interest to determine the first distribution information of the target nucleus in each first image layer of the first medical image, thereby performing three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtaining and displaying the third distribution information of the target nucleus. Since the target map includes multiple second image layers with the second distribution information of the target nucleus, after aligning the first medical image and the target map, the more accurate first distribution information in the first medical image can be indirectly determined. Further, the target nucleus in the first medical image can be three-dimensionally reconstructed using the first distribution information, so as to determine clear and intuitive third distribution information. In this way, the problem that the current nucleus is not clear in the patient image, resulting in inaccurate determination of the nucleus, can be avoided, and the accuracy of the determined nucleus is improved.
[0183] Optionally, the nucleus determination device 1400 further includes:
[0184] The acquisition module is used to acquire a second medical image after the target electrode is implanted in the region of interest; the second medical image includes multiple third image layers.
[0185] The second reconstruction module is used to perform three-dimensional reconstruction on the target electrode in the second medical image according to the size information of the target electrode to obtain the target electrode information.
[0186] The third determination module is used to register the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image.
[0187] The display module is used to display the target electrode information and the fourth distribution information.
[0188] Optionally, the first determining module 1401 includes:
[0189] The identification unit is used to identify the feature information corresponding to each first image layer according to the gray value of each pixel point in each first image layer.
[0190] The first determining unit is used to determine the first feature point in the region of interest according to the feature information corresponding to each first image layer; the first feature point includes a structural feature point and / or an edge feature point.
[0191] Optionally, if the first feature point includes a structural feature point, the first determining unit includes:
[0192] The first determination subunit is used to determine the target part according to the feature information corresponding to each first image layer and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts.
[0193] The second determining subunit is used to determine the structural feature points according to the feature information corresponding to the first image layer where the target part is located.
[0194] Optionally, if the first feature point includes a structural feature point, the first determining unit includes:
[0195] The third determining subunit is configured to determine an interesting contour of the area of interest in each first image layer according to the feature information corresponding to each first image layer.
[0196] The fourth determining subunit is configured to take the feature point on each contour of interest with the smallest distance from the corresponding preset edge of the first image layer as the edge feature point.
[0197] Optionally, the second determining module 1402 includes:
[0198] The second determining unit is used to determine the difference value between each first image layer and each second image layer according to the first feature point and the second feature point.
[0199] The third determining unit is used to determine a registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer.
[0200] The fourth determining unit is configured to map the second image layer to the corresponding first image layer according to the registration result, so as to determine the first distribution information.
[0201] Optionally, the nucleus determination device 1400 further includes:
[0202] The fourth determination module is used to determine the position information of the target feature point in the first distribution information in the reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information.
[0203] The fifth determination module is used to determine the analysis result of the first distribution information according to the location information.
[0204] Optionally, the nucleus determination device 1400 further includes:
[0205] The sixth determination module is used to determine the target location based on the displayed third distribution information.
[0206] The seventh determination module is used to determine the puncture path according to the target position; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear tilt angle of the guide, and the second puncture angle is used to indicate the left and right tilt angle of the guide.
[0207] Each module in the above-mentioned nucleus determination device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0208] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0209] Determine a first feature point of a first medical image of a region of interest;
[0210] The first medical image and the target map are registered according to the first feature point and the second feature point in the target map of the region of interest to determine first distribution information of target nuclei in each first image layer of the first medical image; the target map includes a plurality of second image layers having second distribution information of the target nuclei;
[0211] According to the first distribution information, the target nucleus in the first medical image is three-dimensionally reconstructed to obtain and display third distribution information of the target nucleus.
[0212] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0213] Acquire a second medical image after implanting the target electrode in the region of interest; the second medical image includes a plurality of third image layers; perform three-dimensional reconstruction of the target electrode in the second medical image based on the size information of the target electrode to obtain target electrode information; align the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image; perform three-dimensional reconstruction of the target nucleus in the second medical image based on the fourth distribution information to determine fifth distribution information of the target nucleus, and display the target electrode information and the fifth distribution information.
[0214] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0215] According to the grayscale value of each pixel in each of the first image layers, the feature information corresponding to each of the first image layers is identified; according to the feature information corresponding to each of the first image layers, the first feature point in the region of interest is determined; the first feature point includes a structural feature point and / or an edge feature point.
[0216] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0217] Determine the target part according to the feature information corresponding to each of the first image layers and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts;
[0218] The structural feature points are determined according to feature information corresponding to the first image layer where the target part is located.
[0219] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0220] According to the feature information corresponding to each of the first image layers, an interesting contour of the interesting region in each of the first image layers is determined; and a feature point on each of the interesting contours with the smallest distance from a preset edge of the corresponding first image layer is used as the edge feature point.
[0221] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0222] According to the first feature point and the second feature point, determine the difference value between each of the first image layers and each of the second image layers; determine the registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer; according to the registration result, map the second image layer to the corresponding first image layer to determine the first distribution information.
[0223] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0224] Determine the position information of the target feature points in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information; and determine the analysis results of the first distribution information based on the position information.
[0225] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0226] Based on the displayed third distribution information, the target position is determined; according to the target position, the puncture path is determined; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear inclination angle of the guide, and the second puncture angle is used to indicate the left and right inclination angle of the guide.
[0227] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0228] Determine a first feature point of a first medical image of a region of interest;
[0229] The first medical image and the target map are registered according to the first feature point and the second feature point in the target map of the region of interest to determine first distribution information of target nuclei in each first image layer of the first medical image; the target map includes a plurality of second image layers having second distribution information of the target nuclei;
[0230] According to the first distribution information, the target nucleus in the first medical image is three-dimensionally reconstructed to obtain and display third distribution information of the target nucleus.
[0231] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0232] Acquire a second medical image after implanting the target electrode in the region of interest; the second medical image includes a plurality of third image layers; perform three-dimensional reconstruction of the target electrode in the second medical image based on the size information of the target electrode to obtain target electrode information; align the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image; perform three-dimensional reconstruction of the target nucleus in the second medical image based on the fourth distribution information to determine fifth distribution information of the target nucleus, and display the target electrode information and the fifth distribution information.
[0233] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0234] According to the grayscale value of each pixel in each of the first image layers, the feature information corresponding to each of the first image layers is identified; according to the feature information corresponding to each of the first image layers, the first feature point in the region of interest is determined; the first feature point includes a structural feature point and / or an edge feature point.
[0235] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0236] Determine the target part according to the feature information corresponding to each of the first image layers and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts;
[0237] The structural feature points are determined according to feature information corresponding to the first image layer where the target part is located.
[0238] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0239] According to the feature information corresponding to each of the first image layers, an interesting contour of the interesting region in each of the first image layers is determined; and a feature point on each of the interesting contours with the smallest distance from a preset edge of the corresponding first image layer is used as the edge feature point.
[0240] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0241] According to the first feature point and the second feature point, determine the difference value between each of the first image layers and each of the second image layers; determine the registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer; according to the registration result, map the second image layer to the corresponding first image layer to determine the first distribution information.
[0242] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0243] Determine the position information of the target feature points in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information; and determine the analysis results of the first distribution information based on the position information.
[0244] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0245] Based on the displayed third distribution information, the target position is determined; according to the target position, the puncture path is determined; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear inclination angle of the guide, and the second puncture angle is used to indicate the left and right inclination angle of the guide.
[0246] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0247] Determine a first feature point of a first medical image of a region of interest;
[0248] The first medical image and the target map are registered according to the first feature point and the second feature point in the target map of the region of interest to determine first distribution information of target nuclei in each first image layer of the first medical image; the target map includes a plurality of second image layers having second distribution information of the target nuclei;
[0249] According to the first distribution information, the target nucleus in the first medical image is three-dimensionally reconstructed to obtain and display third distribution information of the target nucleus.
[0250] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0251] Acquire a second medical image after implanting the target electrode in the region of interest; the second medical image includes a plurality of third image layers; perform three-dimensional reconstruction of the target electrode in the second medical image based on the size information of the target electrode to obtain target electrode information; align the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image; perform three-dimensional reconstruction of the target nucleus in the second medical image based on the fourth distribution information to determine fifth distribution information of the target nucleus, and display the target electrode information and the fifth distribution information.
[0252] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0253] According to the grayscale value of each pixel in each of the first image layers, the feature information corresponding to each of the first image layers is identified; according to the feature information corresponding to each of the first image layers, the first feature point in the region of interest is determined; the first feature point includes a structural feature point and / or an edge feature point.
[0254] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0255] Determine the target part according to the feature information corresponding to each of the first image layers and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts;
[0256] The structural feature points are determined according to feature information corresponding to the first image layer where the target part is located.
[0257] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0258] According to the feature information corresponding to each of the first image layers, an interesting contour of the interesting region in each of the first image layers is determined; and a feature point on each of the interesting contours with the smallest distance from a preset edge of the corresponding first image layer is used as the edge feature point.
[0259] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0260] According to the first feature point and the second feature point, determine the difference value between each of the first image layers and each of the second image layers; determine the registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer; according to the registration result, map the second image layer to the corresponding first image layer to determine the first distribution information.
[0261] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0262] Determine the position information of the target feature points in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information; and determine the analysis results of the first distribution information based on the position information.
[0263] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0264] Based on the displayed third distribution information, the target position is determined; according to the target position, the puncture path is determined; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear inclination angle of the guide, and the second puncture angle is used to indicate the left and right inclination angle of the guide.
[0265] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0266] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0267] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0268] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for determining a nucleus, characterized in that: The method comprises: Determine a first feature point of a first medical image of a region of interest; The first medical image and the target map are registered according to the first feature point and the second feature point in the target map of the region of interest to determine first distribution information of target nuclei in each first image layer of the first medical image; the target map includes a plurality of second image layers having second distribution information of the target nuclei; According to the first distribution information, the target nucleus in the first medical image is three-dimensionally reconstructed to obtain and display third distribution information of the target nucleus.
2. The method according to claim 1, characterized in that The method further comprises: Acquire a second medical image after the target electrode is implanted in the region of interest; the second medical image includes a plurality of third image layers; Performing three-dimensional reconstruction on the target electrode in the second medical image according to the size information of the target electrode to obtain target electrode information; registering the second medical image with the first medical image to determine fourth distribution information of the target nucleus in the second medical image; According to the fourth distribution information, a target nucleus in the second medical image is three-dimensionally reconstructed, fifth distribution information of the target nucleus is determined, and the target electrode information and the fifth distribution information are displayed.
3. The method according to claim 1 or 2, characterized in that: The determining of the first feature point of the first medical image of the region of interest includes: identifying feature information corresponding to each of the first image layers according to the grayscale value of each pixel in each of the first image layers; Determine a first feature point in the region of interest according to feature information corresponding to each of the first image layers; The first feature points include structural feature points and / or edge feature points.
4. The method according to claim 3, characterized in that If the first feature points include the structural feature points, determining the first feature points in the region of interest according to the feature information corresponding to each of the first image layers includes: Determine the target part according to the feature information corresponding to each of the first image layers and the first corresponding relationship; the first corresponding relationship includes the corresponding relationship between different feature information and different parts; The structural feature points are determined according to feature information corresponding to the first image layer where the target part is located.
5. The method according to claim 3, characterized in that: If the first feature points include the edge feature points, determining the first feature points in the region of interest according to the feature information corresponding to each of the first image layers includes: determining, according to feature information corresponding to each of the first image layers, an interesting contour of the area of interest in each of the first image layers; The feature point on each of the contours of interest with the smallest distance from the corresponding preset edge of the first image layer is used as the edge feature point.
6. The method according to claim 1 or 2, characterized in that: The registering the first medical image and the target atlas according to the first feature point and the second feature point in the target atlas of the region of interest to determine first distribution information of target nuclei in each first image layer of the first medical image includes: Determine, according to the first feature points and the second feature points, a difference value between each of the first image layers and each of the second image layers; Determine the registration result according to the first image layer and the second image layer corresponding to the minimum difference value; the registration result includes a mapping relationship between the first image layer and the second image layer; According to the registration result, the second image layer is mapped to the corresponding first image layer to determine the first distribution information.
7. The method according to claim 3, characterized in that The method further comprises: Determine the position information of the target feature point in the first distribution information in a reference coordinate system; the reference coordinate system is determined based on the structural feature points in the first medical image; the target feature points include the structural feature points and / or edge feature points in the first distribution information; An analysis result of the first distribution information is determined according to the position information.
8. The method according to claim 1 or 2, characterized in that: The method further comprises: Determine the target location based on the displayed third distribution information; The puncture path is determined according to the target position; the puncture path includes a first puncture angle and a second puncture angle, the first puncture angle is used to indicate the front and rear tilt angle of the guide, and the second puncture angle is used to indicate the left and right tilt angle of the guide.
9. A nucleus determination device, characterized in that: The device comprises: A first determining module, used to determine a first feature point of a first medical image of a region of interest; A second determination module is used to register the first medical image and the target atlas according to the first feature point and the second feature point in the target atlas of the region of interest, so as to determine the first distribution information of the target nuclei in each first image layer of the first medical image; the target atlas includes a plurality of second image layers having the second distribution information of the target nuclei; The first reconstruction module is used to perform three-dimensional reconstruction of the target nucleus in the first medical image according to the first distribution information, and obtain and display third distribution information of the target nucleus.
10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.
