Neural tube labeling methods, electronic devices, and readable storage media

Abstract

This invention provides a method for marking neural tubes, an electronic device, and a readable storage medium. The marking method includes preprocessing a three-dimensional medical image to be marked to obtain a target three-dimensional medical image; acquiring the positional information of multiple sample points on the target three-dimensional medical image and acquiring a slice sequence on the target three-dimensional medical image along the extension direction corresponding to the target neural tube; selecting a slice containing the target neural tube from the slice sequence as a target slice; extracting the center point of the target neural tube layer by layer from each target slice according to the sample points to obtain the centerline of the target neural tube; and marking the target neural tube according to the centerline. This invention can effectively ensure the accuracy of the extracted center point of the target neural tube, thereby improving the accuracy of target neural tube marking and effectively improving the safety and reliability of the surgical procedure.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a neural tube labeling method, an electronic device, and a readable storage medium. Background Technology

[0002] In recent years, with the continuous development of oral medical technology, dental implant surgery has become increasingly common. During dental implant surgery, the location and direction of the mandibular nerve canal are crucial considerations in oral surgery. The procedure must avoid the mandibular nerve canal to prevent damage and complications such as mandibular numbness.

[0003] In existing technologies, most methods still use a purely manual approach to mark the mandibular nerve canal. This purely manual marking method relies on the judgment of dentists, who need to have certain professional knowledge and experience. Moreover, the purely manual marking method is inefficient and consumes a lot of human and time resources during the planning stage of dental implant surgery.

[0004] To address the inefficiency of manual labeling of the mandibular nerve canal, technologies that rely on artificial intelligence or machine learning for automatic labeling of the mandibular nerve canal have emerged. However, these technologies require a large amount of training data to train the model.

[0005] It should be noted that the information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a neural tube marking method, electronic device, and readable storage medium, which can effectively improve the marking efficiency and accuracy of neural tubes, thereby reducing preoperative planning time and improving the safety and reliability of the surgical procedure.

[0007] To achieve the above objectives, the present invention provides a neural tube labeling method, comprising:

[0008] The acquired three-dimensional medical images to be labeled are preprocessed to obtain a three-dimensional medical image of the target, including the target neural tube.

[0009] The location information of multiple sample points on the target three-dimensional medical image is obtained, and the slice sequence of the target three-dimensional medical image along the direction corresponding to the extension direction of the target neural tube is obtained, wherein one sample point is located in the starting end of the target neural tube, one sample point is located in the terminating end of the target neural tube, and the multiple sample points are all located in different segments of the target neural tube.

[0010] Based on the position information of the sample point located at the beginning end of the target neural tube and the position information of the sample point located at the end end of the target neural tube, a slice including the target neural tube is selected from the slice sequence as the target slice.

[0011] Based on the sample points, the center point of the target neural tube is extracted layer by layer for each layer of the target slice to obtain the center line of the target neural tube.

[0012] The target neural tube is marked on the three-dimensional medical image to be marked or the target three-dimensional medical image based on the centerline of the target neural tube.

[0013] Optionally, the step of extracting the center point of the target neural tube from each layer of the target slice based on the sample points to obtain the centerline of the target neural tube includes:

[0014] The target slice containing one of the sample points located at the beginning end of the target neural tube and the sample points located at the end end of the target neural tube is used as the starting target slice, and the target slice containing the other sample point is used as the ending target slice.

[0015] Connectivity analysis is performed on the initial target slice to extract the connected component where the target neural tube is located on the initial target slice, and standard parameters for identifying the target neural tube and the center point of the target neural tube on the initial target slice are obtained based on the connected component where the target neural tube is located on the initial target slice.

[0016] Following the order from the starting target slice to the ending target slice, the target neural tube center point is extracted layer by layer from each target slice except the starting target slice according to the standard parameters;

[0017] Based on all the center points of the target neural canal, obtain the centerline of the target neural canal.

[0018] Optionally, the step of performing connected component analysis on the initial target slice to extract the connected component where the target neural tube is located includes:

[0019] The connected components of the starting target slice are extracted to extract all connected components on the starting target slice;

[0020] From all connected regions on the initial target slice, the connected region including the sample point is extracted as the connected region where the target neural tube is located.

[0021] Optionally, the standard parameters include at least one of standard area, standard grayscale, and standard roundness;

[0022] The step of obtaining standard parameters for identifying the target neural tube based on the connected region where the target neural tube is located on the initial target slice includes:

[0023] Based on the area of ​​the connected region containing the target neural tube on the initial target slice, obtain the standard area used to identify the target neural tube; and / or

[0024] Based on the average grayscale value of all pixels in the connected region containing the target neural tube on the initial target slice, obtain a standard grayscale value for identifying the target neural tube; and / or

[0025] Based on the roundness of the connected region where the target neural tube is located on the initial target slice, obtain the standard roundness for identifying the target neural tube;

[0026] The step of obtaining the center point of the target neural canal on the initial target slice based on the connected region where the target neural canal is located on the initial target slice includes:

[0027] The centroid of the connected region containing the target neural tube on the initial target slice is taken as the center point of the target neural tube on the initial target slice.

[0028] Optionally, the step of extracting the target neural tube center point from each layer of the target slice (excluding the starting target slice) according to the standard parameters, in the order from the starting target slice to the ending target slice, includes:

[0029] Step A: Take the next layer of the target slice after the initial target slice as the current slice to be analyzed;

[0030] Step B: Extract connected components from the current slice to be analyzed, so as to extract all connected components on the current slice to be analyzed;

[0031] Step C: For each connected component on the current slice to be analyzed, determine whether the connected component meets the recognition requirements of the target neural tube according to the standard parameters. If so, the connected component is taken as the target connected component of the current slice to be analyzed.

[0032] Step D: Determine whether the number of target connected components in the current slice to be analyzed is one;

[0033] If yes, proceed to step E; otherwise, proceed to step F.

[0034] Step E: Take the centroid of the target connected region as the center point of the target neural tube on the current slice to be analyzed, and continue to execute step F;

[0035] Step F: Determine whether the current slice to be analyzed is the termination target slice;

[0036] If not, proceed to step G;

[0037] Step G: Take the next layer of the target slice to be analyzed as the new current slice to be analyzed, and return to step B.

[0038] Optionally, determining whether each connected component on the current slice to be analyzed satisfies the recognition requirements of the target neural tube based on the standard parameters includes:

[0039] For each connected component on the current slice to be analyzed:

[0040] Obtain the identification parameters and centroid of the connected component, wherein the identification parameters include at least one of area, mean gray value, and roundness;

[0041] Determine whether the difference between each parameter item in the identification parameters of the connected component and the corresponding parameter item in the standard parameters is within the corresponding preset error range, and whether the distance between the centroid of the connected component and the center point of the previous target neural tube is less than a first preset distance threshold or whether the distance between the centroid of the connected component and the sample point closest to the current slice to be analyzed is less than a second preset distance threshold.

[0042] If so, the connected component is determined to meet the recognition requirements of the target neural tube.

[0043] Optionally, obtaining the centerline of the target neural canal based on all the center points of the target neural canal includes:

[0044] A first preset algorithm is used to select target neural tube center points that meet the first preset conditions from all the target neural tube center points as candidate target neural tube center points;

[0045] The second preset algorithm is used to select the candidate target neural tube center points that meet the second preset conditions from all the candidate target neural tube center points as the final target neural tube center points;

[0046] Based on all the center points of the final target neural tube, the centerline of the target neural tube is obtained.

[0047] Optionally, the step of using a first preset algorithm to select target neural tube center points that meet the first preset conditions from all the target neural tube center points as candidate target neural tube center points includes:

[0048] For each target neural tube center point, the sample point closest to the target slice containing that neural tube center point is identified as the target sample point.

[0049] Determine whether the difference between the coordinate value of the center point of the target neural tube on the first coordinate axis parallel to the extension direction of the target neural tube and the coordinate value of the center point of the target neural tube on the first coordinate axis on the target slice where the target sample point is located is within a first preset range;

[0050] If not, then the center point of the target neural tube shall be taken as the candidate center point of the target neural tube;

[0051] If so, determine whether the target neural tube center point meets the following conditions: the difference between the coordinate value of the target neural tube center point on the second coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the second coordinate axis on the target slice where the target sample point is located is within a second preset range, and the difference between the coordinate value of the target neural tube center point on the third coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the third coordinate axis on the target slice where the target sample point is located is within a third preset range;

[0052] If so, then the center point of the target neural tube is taken as the candidate center point of the target neural tube;

[0053] If not, then delete the center point of the target neural tube.

[0054] Optionally, the step of using a second preset algorithm to select candidate target neural tube center points that meet the second preset conditions as the final target neural tube center points includes:

[0055] Based on the location information of the center point of each candidate target neural tube, a spatial curve is fitted to obtain the corresponding spatial curve;

[0056] For each candidate target neural tube center point, determine whether the distance between the candidate target neural tube center point and the spatial curve is less than a third preset distance threshold. If so, the candidate target neural tube center point is taken as the final target neural tube center point; otherwise, the candidate target neural tube center point is deleted.

[0057] To achieve the above objectives, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the neural tube labeling method described above.

[0058] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the neural tube labeling method described above.

[0059] Compared with the prior art, the neural tube labeling method, electronic device, and readable storage medium provided by the present invention have the following advantages:

[0060] This invention first preprocesses the acquired 3D medical image to be labeled to obtain a target 3D medical image including a target neural tube. Then, it acquires the positional information of multiple sample points on the target 3D medical image, wherein one sample point is located within the starting end of the target neural tube, one sample point is located within the ending end of the target neural tube, and all sample points are located within different segments of the target neural tube. A slice sequence is then acquired from the target 3D medical image along the direction corresponding to the extension of the target neural tube. Next, based on the positional information of the sample points located within the starting and ending ends of the target neural tube, a slice including the target neural tube is selected from the slice sequence as the target slice. Then, based on the sample points, the center point of the target neural tube is extracted layer by layer from each layer of the target slice to obtain the centerline of the target neural tube. Finally, the target neural tube is marked on the 3D medical image to be labeled or the target 3D medical image based on the centerline of the target neural tube. Therefore, the neural tube marking method provided by this invention can use multiple sample points located within the target neural tube as prior knowledge, effectively ensuring the accuracy of the extracted target neural tube center point, thereby improving the accuracy of target neural tube marking and effectively enhancing the safety and reliability of the surgical procedure. Furthermore, the neural tube marking method provided by this invention marks the position of the target neural tube using the extracted centerline. Compared to existing machine learning-based marking methods, this method does not rely on prior training data and model training, resulting in shorter processing time and higher accuracy, thus reducing preoperative planning time and improving the safety and reliability of the surgical procedure. Additionally, the neural tube marking method provided by this invention selects target slices for target neural tube center point extraction based on the position information of sample points located at the beginning and end of the target neural tube, further improving marking efficiency.

[0061] Since the electronic device and readable storage medium provided by this invention belong to the same inventive concept as the neural tube labeling method provided by this invention, the electronic device and readable storage medium provided by this invention have all the advantages of the neural tube labeling method provided by this invention. Therefore, the beneficial effects of the electronic device and readable storage medium provided by this invention will not be described in detail here. Attached Figure Description

[0062] Figure 1 A flowchart of a neural tube marking method provided in one embodiment of the present invention;

[0063] Figure 2 A flowchart illustrating the selection of mandibular nerve canal sample points according to an embodiment of the present invention;

[0064] Figure 3a A 3D view of a target three-dimensional medical image provided as a specific example of the present invention;

[0065] Figure 3b This is a schematic diagram illustrating the selection of mandibular nerve canal sample points on a coronal section, as a specific example of the present invention.

[0066] Figure 4 A flowchart for acquiring a target three-dimensional medical image provided by one embodiment of the present invention;

[0067] Figure 5 A flowchart for extracting the centerline of the target neural tube according to an embodiment of the present invention;

[0068] Figure 6 A flowchart for obtaining standard parameters for identifying a target neural tube, provided by one embodiment of the present invention;

[0069] Figure 7 A flowchart for obtaining the center point of the target neural tube according to an embodiment of the present invention;

[0070] Figure 8a This is a specific slice to be analyzed provided in this invention;

[0071] Figure 8b for Figure 8a The results of connected component extraction for the current slice to be analyzed are shown.

[0072] Figure 9 A flowchart for determining a target connected component provided in one embodiment of the present invention;

[0073] Figure 10 A flowchart for extracting the centerline of a target neural tube based on the center point of the target neural tube, provided as an embodiment of the present invention;

[0074] Figure 11A flowchart for screening candidate mandibular nerve canal center points according to an embodiment of the present invention;

[0075] Figure 12 This is a block diagram of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0076] The neural tube labeling method, electronic device, and readable storage medium proposed in this invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of this invention will become clearer from the following description. It should be noted that the drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clarify the illustration of the embodiments of this invention. Please refer to the drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for illustrative purposes and to enable those skilled in the art to understand and read them, and are not intended to limit the implementation conditions of this invention. Any modifications to the structure, changes in proportions, or adjustments to the size, provided that the effects and objectives achieved by this invention are the same or similar, should still fall within the scope of the technical content disclosed in this invention.

[0077] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] Furthermore, in the description of this specification, the reference to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0079] The core idea of ​​this invention is to provide a neural tube marking method, electronic device, and readable storage medium, which can effectively improve the marking efficiency and accuracy of neural tubes, thereby reducing preoperative planning time and improving the safety and reliability of the surgical procedure.

[0080] It should be noted that the neural tube marking method provided in this embodiment of the invention can be applied to the electronic device provided in this embodiment of the invention. The electronic device can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, tablet computer, or other hardware device with various operating systems. It should also be noted that although this article uses the mandibular nerve canal as an example of the target neural tube, as those skilled in the art will understand, this does not constitute a limitation of the invention. The neural tube marking method provided in this invention can also be applied to the marking of other neural tubes besides the mandibular nerve canal. Furthermore, it should be noted that, as those skilled in the art will understand, the term "multiple" in this article includes the case of two.

[0081] To achieve the above-mentioned goals, this invention provides a neural tube labeling method, please refer to [reference needed]. Figure 1 ,like Figure 1 As shown, the neural tube labeling method provided by the present invention includes the following steps:

[0082] Step S100: Preprocess the acquired three-dimensional medical image to be labeled to obtain a target three-dimensional medical image including the target neural tube.

[0083] Step S200: Obtain the position information of multiple sample points on the target three-dimensional medical image, and obtain the slice sequence of the target three-dimensional medical image along the direction corresponding to the extension direction of the target neural tube, wherein one sample point is located in the starting end of the target neural tube, one sample point is located in the terminating end of the target neural tube, and the multiple sample points are all located in different segments of the target neural tube.

[0084] Step S300: Based on the position information of the sample point located at the beginning end of the target neural tube and the position information of the sample point located at the end end of the target neural tube, select a slice including the target neural tube from the slice sequence as the target slice.

[0085] Step S400: Based on the sample points, extract the center point of the target neural tube layer by layer for each layer of the target slice to obtain the center line of the target neural tube.

[0086] Step S500: Mark the target neural tube on the three-dimensional medical image to be marked or the target three-dimensional medical image according to the center line of the target neural tube.

[0087] Therefore, the neural tube marking method provided by this invention can use multiple sample points located within the target neural tube as prior knowledge, effectively ensuring the accuracy of the extracted target neural tube center point, thereby improving the accuracy of target neural tube marking and effectively enhancing the safety and reliability of the surgical procedure. Furthermore, the neural tube marking method provided by this invention marks the position of the target neural tube using the extracted centerline. Compared to existing machine learning-based marking methods, the neural tube marking method provided by this invention does not rely on prior training data and model training, resulting in shorter processing time and higher accuracy, thus reducing preoperative planning time and improving the safety and reliability of the surgical procedure. Additionally, the neural tube marking method provided by this invention selects target slices for target neural tube center point extraction based on the position information of sample points located at the beginning and end of the target neural tube, further improving marking efficiency. It should be noted that, as those skilled in the art will understand, when there are multiple target nerve tubes, steps S200 to S400 are performed for each target nerve tube to obtain the center line of each target nerve tube, and the corresponding target nerve tube is marked on the three-dimensional medical image to be marked or the target three-dimensional medical image based on the center line of each target nerve tube.

[0088] Specifically, the three-dimensional medical image to be labeled can be, but is not limited to, cone-beam computed tomography (CBCT) images, computed tomography (CT) images, and magnetic resonance imaging (MRI) images. It should be noted that, as those skilled in the art will understand, the three-dimensional medical image to be labeled can be acquired in real time from medical imaging equipment, obtained from an image database, or received from an external device; this invention does not limit the method of acquiring the three-dimensional medical image to be labeled. It should also be noted that, as those skilled in the art will understand, the sample points can be points manually selected by the operator or points automatically selected by a computer according to a pre-set algorithm, and the number of sample points can be set according to specific circumstances; this invention does not limit this, for example, the number of sample points can be 5 to 10. Preferably, the plurality of sample points are evenly distributed along the extension direction of the target neural canal. Furthermore, it should be noted that, as those skilled in the art will understand, the present invention does not limit the order of selecting sample points and obtaining slice sequences. In some embodiments, sample points can be selected first, followed by obtaining slice sequences; in other embodiments, slice sequences can be obtained first, followed by selecting sample points. Additionally, it should be noted that, as those skilled in the art will understand, in some embodiments, multiple sample points can be directly selected on the target three-dimensional medical image, or multiple sample points can be selected on each layer of slices in the slice sequence of the target three-dimensional medical image along the direction corresponding to the extension direction of the target neural canal. Furthermore, it should be noted that, as those skilled in the art will understand, the slice sequence of the target three-dimensional medical image along the coronal plane (i.e., along the anterior-posterior direction of the human body, i.e., along the Y-direction) includes multiple coronal slices; the slice sequence of the target three-dimensional medical image along the sagittal plane (i.e., along the lateral direction of the human body, i.e., along the X-direction) includes multiple sagittal slices; and the slice sequence of the target three-dimensional medical image along the vertical plane (i.e., along the vertical direction of the human body, i.e., along the Z-direction) includes multiple transverse slices. If the target neural tube extends along the left-right direction of the human body, then the slice sequence of the target three-dimensional medical image along the sagittal direction is selected for analysis; if the target neural tube extends along the front-back direction of the human body, then the slice sequence of the target three-dimensional medical image along the coronal direction is obtained for analysis; if the target neural tube extends along the vertical direction of the human body, then the slice sequence of the target three-dimensional medical image along the vertical direction is obtained for analysis.

[0089] Taking the three-dimensional medical image to be labeled as the three-dimensional oral cavity image to be labeled, the target three-dimensional medical image as the target three-dimensional oral cavity image, and the target nerve canal as a certain mandibular nerve canal as an example, the sample point located in the starting end of the target nerve canal is a sample point located in the mandibular foramen of the mandibular nerve canal, and the sample point located in the terminating end of the target nerve canal is a sample point located in the mental foramen of the mandibular nerve canal; since the mandibular nerve canal extends in the anteroposterior direction in the human body, the slice sequence of the target three-dimensional medical image along the direction corresponding to the extension direction of the target nerve canal (i.e., the coronal direction) is a slice sequence including multiple coronal slices, wherein different sample points are located on different coronal slices.

[0090] Please continue to refer to this. Figure 2 ,like Figure 2 As shown, you can first view the 3D image of the target 3D oral cavity (e.g., Figure 3a As shown in the image, the area within the rectangle represents the location of the mandibular nerve canal. In the coronal view (i.e., coronal slice), locate the mandibular foramen of the mandibular nerve canal to be marked (i.e., the target nerve canal), and select the first sample point (i.e., the initial point) within this foramen. Then, select one coronal slice every preset number of layers, locate the mandibular nerve canal to be marked within this coronal slice, and select a sample point. Repeat this process until the 2nd to n-1th sample points are found. Finally, in the 3D view or coronal view (i.e., coronal slice) of the target 3D oral cavity image, locate the mental foramen of the mandibular nerve canal to be marked (i.e., the target nerve canal), and select the last sample point (i.e., the nth sample point, or the end point) within this mental foramen. This completes the selection of sample points. Further details can be found by referring to... Figure 3b ,like Figure 3b As shown, the method of selecting points by slicing can be used. By browsing the coronal slices and clicking on the coronal slice to generate sample points, the process of selecting sample points on the current coronal slice can be completed. The scroll wheel can be used to switch coronal slices to continue selecting sample points. After all sample points have been selected, click the OK button.

[0091] Please continue to refer to this. Figure 4 ,like Figure 4 As shown, in one exemplary embodiment, the preprocessing of the acquired three-dimensional medical image to be labeled to obtain a target three-dimensional medical image including the target neural tube includes:

[0092] The three-dimensional medical image to be labeled is filtered to obtain a first three-dimensional medical image;

[0093] A windowing operation is performed on the first three-dimensional medical image to obtain a second three-dimensional medical image;

[0094] The second three-dimensional medical image is subjected to edge enhancement to obtain a third three-dimensional medical image;

[0095] A morphological closing operation is performed on the third three-dimensional medical image to obtain the target three-dimensional medical image.

[0096] Specifically, a Gaussian filter can be used to filter the three-dimensional medical image to be labeled to remove noise. By adjusting the window size of the first three-dimensional medical image according to a preset window level and width, the region where the target neural tube is located can be highlighted, making it easier to identify the target neural tube region on each layer of the target slice more accurately. By performing edge enhancement on the second three-dimensional medical image, the outline of the target neural tube can be enhanced, further ensuring that the region where the target neural tube is located can be identified more accurately on each layer of the target slice. By performing a morphological closing operation (dilation followed by erosion) on the third three-dimensional medical image, small pores in the third three-dimensional medical image can be closed, further ensuring that the region where the target neural tube is located can be identified more accurately on each layer of the target slice. It should be noted that, as those skilled in the art will understand, the relevant content on how to perform windowing operation on the first three-dimensional medical image and how to perform morphological closing operation on the third three-dimensional medical image can be referred to the prior art, and will not be elaborated here.

[0097] Furthermore, the Canny or Sobel operator can be used to perform edge enhancement on the second 3D medical image. Specifically, the Canny or Sobel operator can first be used to perform edge detection on the second 3D medical image to obtain the corresponding edge image, and then the edge image can be superimposed on the second 3D medical image to obtain the third 3D medical image. It should be noted that, as those skilled in the art will understand, the relevant content on how to use the Canny or Sobel operator to perform edge detection on the second 3D medical image to obtain the corresponding edge image can be found in existing technology and will not be elaborated here.

[0098] Please continue to refer to this. Figure 5 ,like Figure 5 As shown, in one exemplary embodiment, the step of extracting the center point of the target neural tube from each layer of the target slice based on the sample points to obtain the centerline of the target neural tube includes:

[0099] The target slice containing one of the sample points located at the beginning end of the target neural tube and the sample points located at the end end of the target neural tube is used as the starting target slice, and the target slice containing the other sample point is used as the ending target slice.

[0100] Connectivity analysis is performed on the initial target slice to extract the connected component where the target neural tube is located on the initial target slice, and standard parameters for identifying the target neural tube and the center point of the target neural tube on the initial target slice are obtained based on the connected component where the target neural tube is located on the initial target slice.

[0101] Following the order from the starting target slice to the ending target slice, the target neural tube center point is extracted layer by layer from each target slice except the starting target slice according to the standard parameters;

[0102] Based on all the center points of the target neural canal, obtain the centerline of the target neural canal.

[0103] Therefore, by extracting the connected region of the target nerve tube from the target slice where the starting or ending end of the target nerve tube is located, and determining the standard parameters for identifying the target nerve tube based on the connected region, a theoretical basis can be provided for identifying the region where the target nerve tube is located on other target slices. This effectively ensures the accurate identification of the region where the target nerve tube is located on other target slices, thereby effectively ensuring the accuracy of the extracted centerline of the target nerve tube and further improving the accuracy of the nerve tube marking method provided by this invention. Specifically, taking a mandibular nerve tube as an example, the target slice containing either a sample point located in the mandibular foramen or a sample point located in the mental foramen of the mandibular nerve tube can be used as the starting target slice, and the target slice containing the other can be used as the ending target slice.

[0104] In one exemplary implementation, the connected component analysis of the initial target slice to extract the connected component containing the target neural tube includes:

[0105] The connected components of the starting target slice are extracted to extract all connected components on the starting target slice;

[0106] From all connected regions on the initial target slice, the connected region including the sample point is extracted as the connected region where the target neural tube is located.

[0107] Specifically, a two-pass scanning method or a seed-filling method can be used to extract connected components from the initial target slice to extract all connected components on the initial target slice. Based on the position information of the sample point on the initial target slice, the connected component containing that sample point is selected from all the extracted connected components as the connected component containing the target neural tube. It should be noted that, as those skilled in the art will understand, the relevant content regarding how to use the two-pass scanning method or the seed-filling method to extract all connected components on the initial target slice can be found in existing technologies and will not be elaborated upon here. It should also be noted that, as those skilled in the art will understand, if the starting target slice is a target slice containing sample points located at the beginning end of the target neural tube, then the connected region on the starting target slice including the sample points located at the beginning end of the target neural tube is taken as the connected region where the target neural tube is located; if the starting target slice is a target slice containing sample points located at the end end of the target neural tube, then the connected region on the starting target slice including the sample points located at the end end of the target neural tube is taken as the connected region where the target neural tube is located.

[0108] In one exemplary embodiment, the standard parameters include at least one of standard area, standard grayscale, and standard roundness;

[0109] The step of obtaining standard parameters for identifying the target neural tube based on the connected region where the target neural tube is located on the initial target slice includes:

[0110] Based on the area of ​​the connected region containing the target neural tube on the initial target slice, obtain the standard area used to identify the target neural tube; and / or

[0111] Based on the average grayscale value of all pixels in the connected region containing the target neural tube on the initial target slice, obtain a standard grayscale value for identifying the target neural tube; and / or

[0112] Based on the roundness of the connected region where the target neural tube is located on the initial target slice, a standard roundness for identifying the target neural tube is obtained.

[0113] Specifically, the area of ​​the connected region refers to the total number of pixels included in the connected region, and the average grayscale value of all pixels in the connected region refers to the average grayscale value of the pixels included in the connected region. It should be noted that, as those skilled in the art will understand, the relevant content regarding how to calculate the roundness of the connected region can be found in existing technologies and will not be elaborated upon here.

[0114] Preferably, the standard parameters include standard area, standard grayscale, and standard roundness. Therefore, by simultaneously using standard area, standard grayscale, and standard roundness as standard parameters for identifying the target neural tube, it is possible to effectively ensure the accurate identification of the target neural tube region on other target slices, thereby effectively ensuring the accuracy of the extracted centerline of the target neural tube and further improving the accuracy of the neural tube marking method provided by this invention.

[0115] Please continue to refer to this. Figure 6 ,like Figure 6 As shown, each connected component on the starting target slice is traversed sequentially. If the i-th connected component being traversed includes the starting sample point (i.e., the sample point on the starting target slice), the average gray level, area, and roundness of the connected component are calculated to obtain the standard gray level, standard area, and standard roundness for identifying the target neural tube. If the i-th connected component being traversed does not include the starting sample point (i.e., the sample point on the starting target slice), the next connected component is traversed.

[0116] In one exemplary embodiment, obtaining the center point of the target neural tube on the initial target slice based on the connected region where the target neural tube is located on the initial target slice includes:

[0117] The centroid of the connected region containing the target neural tube on the initial target slice is taken as the center point of the target neural tube on the initial target slice.

[0118] Specifically, for information on how to obtain the centroid of a connected component, please refer to existing technologies, which will not be elaborated here.

[0119] Please continue to refer to this. Figure 7 ,like Figure 7 As shown, in one exemplary embodiment, the step of extracting the target neural tube center point from each layer of the target slice (excluding the starting target slice) according to the standard parameters, following the order from the starting target slice to the ending target slice, includes:

[0120] Step A: Take the next layer of the target slice after the initial target slice as the current slice to be analyzed;

[0121] Step B: Extract connected components from the current slice to be analyzed, so as to extract all connected components on the current slice to be analyzed;

[0122] Step C: For each connected component on the current slice to be analyzed, determine whether the connected component meets the recognition requirements of the target neural tube according to the standard parameters. If so, the connected component is taken as the target connected component of the current slice to be analyzed.

[0123] Step D: Determine whether the number of target connected components in the current slice to be analyzed is one;

[0124] If yes, proceed to step E; otherwise, proceed to step F.

[0125] Step E: Take the centroid of the target connected region as the center point of the target neural tube on the current slice to be analyzed, and continue to execute step F;

[0126] Step F: Determine whether the current slice to be analyzed is the termination target slice;

[0127] If not, proceed to step G;

[0128] Step G: Take the next layer of the target slice to be analyzed as the new current slice to be analyzed, and return to step B.

[0129] Specifically, two-pass scanning or seed-filling methods can be used to extract connected components from the current slice to be analyzed, thereby extracting all connected components on the current slice. For details, please refer to... Figure 8a and Figure 8b ,like Figure 8a and Figure 8b As shown, by extracting the connected components of the current slice to be analyzed, all connected components (connected component 1 to connected component n) on the current slice to be analyzed can be extracted.

[0130] When there is one and only one connected region on the current slice to be analyzed that satisfies the identification requirements of the target neural tube, this connected region is the region where the target neural tube is located on the current slice to be analyzed, and the centroid of this connected region is the center point of the target neural tube on the current slice to be analyzed. When there is no connected region on the current slice to be analyzed that satisfies the identification requirements of the target neural tube, or when there are multiple (including two) connected regions that satisfy the identification requirements of the target neural tube, if the current slice to be analyzed is not a termination slice, it indicates that the extraction of the center point of the target neural tube has failed, and the analysis continues to the next layer of target slices; if the current slice to be analyzed is a termination slice, the extraction process of the center point of the target neural tube ends.

[0131] In one exemplary implementation, determining whether each connected component on the current slice to be analyzed satisfies the recognition requirements of the target neural tube based on the standard parameters includes:

[0132] For each connected component on the current slice to be analyzed:

[0133] Obtain the identification parameters of the connected component and the centroid of the connected component, wherein the identification parameters include at least one of the area, gray mean, and roundness;

[0134] Determine whether the difference between each parameter item in the identification parameters of the connected component and the corresponding parameter item in the standard parameters is within the corresponding preset error range, and whether the distance between the centroid of the connected component and the center point of the previous target neural tube is less than a first preset distance threshold or whether the distance between the centroid of the connected component and the sample point closest to the current slice to be analyzed is less than a second preset distance threshold.

[0135] If so, the connected component is determined to meet the recognition requirements of the target neural tube.

[0136] Specifically, when the standard parameter includes a standard area, the recognition parameter includes area; when the standard parameter includes a standard grayscale, the recognition parameter includes the grayscale mean; when the standard parameter includes a standard roundness, the recognition parameter includes roundness; that is, the parameter items in the recognition parameter correspond one-to-one with the parameter items in the standard parameter. When the standard parameter includes a standard area, standard grayscale, and standard roundness, for each connected component on the current slice to be analyzed, if the difference between the area of ​​the connected component and the standard area is within a first preset error range, the difference between the grayscale mean of the connected component and the standard grayscale is within a second preset error range, the difference between the roundness of the connected component and the standard roundness is within a third preset error range, and the position of the centroid of the connected component also meets the requirements (i.e., the distance between the centroid of the connected component and the center point of the previous target neural tube is less than a first preset distance threshold or the distance between the centroid of the connected component and the sample point closest to the current slice to be analyzed is less than a second preset distance threshold), then the connected component is determined to meet the recognition requirements of the target neural tube. Therefore, the neural tube marking method provided by the present invention, when selecting the target connected region on the current slice to be analyzed, not only considers whether the identification parameters of the connected region meet the standard parameters, but also considers whether the position of the connected region meets the requirements, thereby further improving the accuracy of the identified target connected region as the region where the target neural tube is located.

[0137] Furthermore, if the distance between the center point of the previous target neural tube and the current slice to be analyzed is smaller than the distance between the nearest sample point to the current slice to be analyzed and the current slice to be analyzed, then if the distance between the centroid of the connected region and the center point of the previous target neural tube is less than the first preset distance threshold, then the position of the centroid of the connected region is determined to meet the requirements; if the distance between the center point of the previous target neural tube and the current slice to be analyzed is larger than the distance between the nearest sample point to the current slice to be analyzed and the current slice to be analyzed, then if the distance between the centroid of the connected region and the nearest sample point to the current slice to be analyzed is less than the second preset distance threshold, then the position of the centroid of the connected region is determined to meet the requirements.

[0138] Please continue to refer to this. Figure 9 ,like Figure 9 As shown, all connected components on the current slice to be analyzed are traversed sequentially. If the area of ​​the i-th connected component being traversed meets the standard area (i.e., the difference between the area of ​​the connected component and the standard area is within the first preset error range, i.e., it meets the size requirement), the grayscale mean meets the standard grayscale (i.e., the difference between the grayscale mean of the connected component and the standard grayscale is within the second preset error range, i.e., it meets the average grayscale requirement), the roundness meets the standard roundness (i.e., the difference between the roundness of the connected component and the standard roundness is within the third preset error range, i.e., it meets the roundness requirement), and the centroid position also meets the requirements (i.e., the distance between the centroid of the connected component and the center point of the previous target neural tube is less than the first preset distance threshold, or the distance between the centroid of the connected component and the nearest sample point to the current slice to be analyzed is less than the second preset distance threshold), then the connected component is determined as the target connected component; if the connected component does not meet any of the above requirements, then the connected component is excluded.

[0139] Please continue to refer to this. Figure 10 ,like Figure 10 As shown, in one exemplary embodiment, obtaining the centerline of the target neural canal based on all the target neural canal center points includes:

[0140] A first preset algorithm is used to select target neural tube center points that meet the first preset conditions from all the target neural tube center points as candidate target neural tube center points;

[0141] The second preset algorithm is used to select the candidate target neural tube center points that meet the second preset conditions from all the candidate target neural tube center points as the final target neural tube center points;

[0142] Based on all the center points of the final target neural tube, the centerline of the target neural tube is obtained.

[0143] Therefore, by selecting the target neural tube center point that simultaneously meets the first preset condition and the second preset condition as the final target neural point, and obtaining the center line of the target neural tube, abnormal target neural tube center points can be effectively excluded, thereby further improving the accuracy of the extracted center line of the target neural tube and further improving the accuracy of the neural tube marking method provided by the present invention.

[0144] In one exemplary embodiment, the step of using a first preset algorithm to select target neural tube center points that meet the first preset conditions as candidate target neural tube center points from all the target neural tube center points includes:

[0145] For each target neural tube center point, the sample point closest to the target slice containing that neural tube center point is identified as the target sample point.

[0146] Determine whether the difference between the coordinate value of the center point of the target neural tube on the first coordinate axis parallel to the extension direction of the target neural tube and the coordinate value of the center point of the target neural tube on the first coordinate axis on the target slice where the target sample point is located is within a first preset range;

[0147] If not, then the center point of the target neural tube shall be taken as the candidate center point of the target neural tube;

[0148] If so, determine whether the target neural tube center point meets the following conditions: the difference between the coordinate value of the target neural tube center point on the second coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the second coordinate axis on the target slice where the target sample point is located is within a second preset range, and the difference between the coordinate value of the target neural tube center point on the third coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the third coordinate axis on the target slice where the target sample point is located is within a third preset range;

[0149] If so, then the center point of the target neural tube is taken as the candidate center point of the target neural tube;

[0150] If not, then delete the center point of the target neural tube.

[0151] Therefore, through the above operations, the center points of the target nerve canal that are significantly offset from the center line of the target nerve canal can be effectively deleted, thereby further ensuring the accuracy of the extracted center line of the target nerve canal. It should be noted that, as those skilled in the art will understand, when the target nerve canal extends along the anterior-posterior direction of the human body (i.e., along the Y-axis), for example, when the target nerve canal is the mandibular nerve canal, the first coordinate axis is the Y-axis, the second coordinate axis is one of the X-axis and Z-axis, and the third coordinate axis is the other of the X-axis and Z-axis.

[0152] Please continue to refer to this. Figure 11 ,like Figure 11 As shown, taking the mandibular nerve canal as an example, all extracted mandibular nerve canal center points can be stored sequentially in the same center point set, and the index number i of the mandibular nerve canal center point in the center point set starts from 0. Starting from i=0, the mandibular nerve canal center points are traversed. It is determined whether the difference between the Y coordinate of the currently traversed mandibular nerve canal center point i and the Y coordinate of its corresponding target sample point is within a first preset range. If not, the mandibular nerve canal center point is regarded as a candidate mandibular nerve canal center point. If yes, it is further determined whether the mandibular nerve canal center point i simultaneously satisfies the following conditions: the difference between the X coordinate of the mandibular nerve canal center point i and the X coordinate of its corresponding target sample point is within a second preset range and the difference between the Z coordinate of the mandibular nerve canal center point i and the Z coordinate of its corresponding target sample point is within a third preset range. If yes, the mandibular nerve canal center point is regarded as a candidate mandibular nerve canal center point; if not, the mandibular nerve canal center point is deleted from the center point set. Repeat the above steps until all mandibular canal centers in the set of centers have been traversed.

[0153] In one exemplary embodiment, the step of using a second preset algorithm to select candidate target neural tube center points that meet the second preset conditions as the final target neural tube center points includes:

[0154] Based on the location information of the center point of each candidate target neural tube, a spatial curve is fitted to obtain the corresponding spatial curve;

[0155] For each candidate target neural tube center point, determine whether the distance between the candidate target neural tube center point and the spatial curve is less than a third preset distance threshold. If so, the candidate target neural tube center point is taken as the final target neural tube center point; otherwise, the candidate target neural tube center point is deleted.

[0156] Specifically, the least squares method can be used to perform curve fitting on each of the candidate target neural tube center points to fit a first spatial curve (for ease of distinction, the spatial curve fitted based on each of the candidate target neural tube center points will be represented as the first spatial curve). After the first spatial curve fitting is completed, all the candidate target neural tube center points are screened, and those that deviate significantly from the first spatial curve (i.e., the distance between them and the first spatial curve is greater than or equal to a third preset distance threshold) will be removed. It should be noted that, as those skilled in the art will understand, the relevant content on how to use the least squares method to fit the first spatial curve can be referred to in the prior art, and will not be elaborated here.

[0157] In one exemplary embodiment, obtaining the centerline of the target neural canal based on all the final target neural canal center points includes:

[0158] Based on the location information of the center points of each of the final target neural tubes, a spatial curve is fitted to obtain the center line of the target neural tube.

[0159] Specifically, the least squares method can be used to fit a spatial curve to each of the final target neural tube center points. The fitted second spatial curve (for ease of distinction, the spatial curve fitted based on each of the final target neural tube center points will be represented as the second spatial curve) is the centerline of the target neural tube. It should be noted that, as those skilled in the art will understand, the relevant content on how to use the least squares method to fit the second spatial curve can be found in the prior art, and will not be elaborated here.

[0160] Based on the same inventive concept, the present invention also provides an electronic device, please refer to... Figure 12 ,like Figure 12 As shown, the electronic device includes a processor 101 and a memory 103. The memory 103 stores a computer program, which, when executed by the processor 101, implements the neural tube marking method described above. Since the electronic device provided by this invention can implement the neural tube marking method provided by this invention, it possesses all the advantages of the neural tube marking method provided by this invention. For details, please refer to the relevant description above; therefore, further elaboration is not required here.

[0161] like Figure 12As shown, the electronic device also includes a communication interface 102 and a communication bus 104, wherein the processor 101, the communication interface 102, and the memory 103 communicate with each other via the communication bus 104. The communication bus 104 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 104 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 102 is used for communication between the aforementioned electronic device and other devices.

[0162] The processor 101 referred to in this invention may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 101 is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0163] The memory 103 can be used to store the computer program. The processor 101 implements various functions of the electronic device by running or executing the computer program stored in the memory 103 and calling the data stored in the memory 103.

[0164] The memory 103 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0165] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can implement the neural tube marking method described above. Since the readable storage medium provided by the present invention can implement the neural tube marking method provided by the present invention, it possesses all the advantages of the neural tube marking method provided by the present invention. For details, please refer to the relevant description above; therefore, it will not be repeated here.

[0166] The readable storage medium provided in the embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0167] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0168] In summary, compared with the prior art, the neural tube labeling method, electronic device, and readable storage medium provided by the present invention have the following advantages:

[0169] This invention first preprocesses the acquired 3D medical image to be labeled to obtain a target 3D medical image including a target neural tube. Then, it acquires the positional information of multiple sample points on the target 3D medical image, wherein one sample point is located within the starting end of the target neural tube, one sample point is located within the ending end of the target neural tube, and all sample points are located within different segments of the target neural tube. A slice sequence is then acquired from the target 3D medical image along the direction corresponding to the extension of the target neural tube. Next, based on the positional information of the sample points located within the starting and ending ends of the target neural tube, a slice including the target neural tube is selected from the slice sequence as the target slice. Then, based on the sample points, the center point of the target neural tube is extracted layer by layer from each layer of the target slice to obtain the centerline of the target neural tube. Finally, the target neural tube is marked on the 3D medical image to be labeled or the target 3D medical image based on the centerline of the target neural tube. Therefore, this invention can use the acquired sample points located within the target neural tube as prior knowledge, effectively ensuring the accuracy of the extracted target neural tube center point, thereby improving the accuracy of target neural tube marking and effectively enhancing the safety and reliability of the surgical procedure. Furthermore, this invention marks the position of the target neural tube using the extracted centerline. Compared to existing machine learning-based marking methods, this invention does not rely on prior training data and model training, resulting in shorter processing time and higher accuracy, thus reducing preoperative planning time and improving the safety and reliability of the surgical procedure. Additionally, this invention further improves marking efficiency by selecting target slices for target neural tube center point extraction based on the positional information of sample points located at the beginning and end of the target neural tube.

[0170] It should be noted that, as those skilled in the art will understand, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0171] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0172] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for marking neural tubes, characterized in that, include: The acquired three-dimensional medical images to be labeled are preprocessed to obtain a three-dimensional medical image of the target, including the target neural tube. The location information of multiple sample points on the target three-dimensional medical image is obtained, and the slice sequence of the target three-dimensional medical image along the direction corresponding to the extension direction of the target neural tube is obtained, wherein one sample point is located in the starting end of the target neural tube, one sample point is located in the terminating end of the target neural tube, and the multiple sample points are all located in different segments of the target neural tube. Based on the position information of the sample point located at the beginning end of the target neural tube and the position information of the sample point located at the end end of the target neural tube, a slice including the target neural tube is selected from the slice sequence as the target slice. Based on the sample points, the center point of the target neural tube is extracted layer by layer for each layer of the target slice to obtain the center line of the target neural tube. The target neural tube is marked on the three-dimensional medical image to be marked or the target three-dimensional medical image according to the center line of the target neural tube; The step of extracting the center point of the target neural tube from each layer of the target slice based on the sample points to obtain the centerline of the target neural tube includes: The target slice containing one of the sample points located at the beginning end of the target neural tube and the sample points located at the end end of the target neural tube is used as the starting target slice, and the target slice containing the other sample point is used as the ending target slice. Connectivity analysis is performed on the initial target slice to extract the connected component where the target neural tube is located on the initial target slice. Based on the connected component where the target neural tube is located on the initial target slice, standard parameters for identifying the target neural tube and the center point of the target neural tube on the initial target slice are obtained, wherein the connected component where the target neural tube is located includes the sample point. Following the order from the starting target slice to the ending target slice, the target neural tube center point is extracted layer by layer for each target slice except the starting target slice, according to the standard parameters. Based on all the center points of the target neural canal, obtain the centerline of the target neural canal.

2. The neural tube marking method according to claim 1, characterized in that, The preprocessing of the acquired three-dimensional medical image to be labeled, to obtain a target three-dimensional medical image including the target neural tube, includes: The three-dimensional medical image to be labeled is filtered to obtain a first three-dimensional medical image; A windowing operation is performed on the first three-dimensional medical image to obtain a second three-dimensional medical image; The second three-dimensional medical image is subjected to edge enhancement to obtain a third three-dimensional medical image; A morphological closing operation is performed on the third three-dimensional medical image to obtain the target three-dimensional medical image.

3. The neural tube marking method according to claim 1, characterized in that, The connected component analysis of the initial target slice to extract the connected component containing the target neural tube includes: The connected components of the starting target slice are extracted to extract all connected components on the starting target slice; From all connected regions on the initial target slice, the connected region including the sample point is extracted as the connected region where the target neural tube is located.

4. The neural tube marking method according to claim 3, characterized in that, The standard parameters include at least one of standard area, standard grayscale, and standard roundness; The step of obtaining standard parameters for identifying the target neural tube based on the connected region where the target neural tube is located on the initial target slice includes: Based on the area of ​​the connected region containing the target neural tube on the initial target slice, obtain the standard area used to identify the target neural tube; and / or Based on the average grayscale value of all pixels in the connected region containing the target neural tube on the initial target slice, obtain a standard grayscale value for identifying the target neural tube; and / or Based on the roundness of the connected region where the target neural tube is located on the initial target slice, obtain the standard roundness for identifying the target neural tube; The step of obtaining the center point of the target neural canal on the initial target slice based on the connected region where the target neural canal is located on the initial target slice includes: The centroid of the connected region containing the target neural tube on the initial target slice is taken as the center point of the target neural tube on the initial target slice.

5. The neural tube marking method according to claim 1, characterized in that, The step of extracting the target neural tube center point from each target slice (excluding the starting target slice) layer by layer according to the standard parameters, following the order from the starting target slice to the ending target slice, includes: Step A: Take the next layer of the target slice after the initial target slice as the current slice to be analyzed; Step B: Extract connected components from the current slice to be analyzed, so as to extract all connected components on the current slice to be analyzed; Step C: For each connected component on the current slice to be analyzed, determine whether the connected component meets the recognition requirements of the target neural tube according to the standard parameters. If so, the connected component is taken as the target connected component of the current slice to be analyzed. Step D: Determine whether the number of target connected components in the current slice to be analyzed is one; If yes, proceed to step E; otherwise, proceed to step F. Step E: Take the centroid of the target connected region as the center point of the target neural tube on the current slice to be analyzed, and continue to execute step F; Step F: Determine whether the current slice to be analyzed is the termination target slice; If not, proceed to step G; Step G: Take the next layer of the target slice to be analyzed as the new current slice to be analyzed, and return to step B.

6. The neural tube marking method according to claim 5, characterized in that, The step of determining whether each connected component on the current slice to be analyzed meets the recognition requirements of the target neural tube based on the standard parameters includes: For each connected component on the current slice to be analyzed: Obtain the identification parameters and centroid of the connected component, wherein the identification parameters include at least one of area, mean gray value, and roundness; Determine whether the difference between each parameter item in the identification parameters of the connected component and the corresponding parameter item in the standard parameters is within the corresponding preset error range, and whether the distance between the centroid of the connected component and the center point of the previous target neural tube is less than a first preset distance threshold or whether the distance between the centroid of the connected component and the sample point closest to the current slice to be analyzed is less than a second preset distance threshold. If so, the connected component is determined to meet the recognition requirements of the target neural tube.

7. The neural tube marking method according to claim 1, characterized in that, The step of obtaining the centerline of the target neural canal based on all the center points of the target neural canal includes: A first preset algorithm is used to select target neural tube center points that meet the first preset conditions from all the target neural tube center points as candidate target neural tube center points; The second preset algorithm is used to select the candidate target neural tube center points that meet the second preset conditions from all the candidate target neural tube center points as the final target neural tube center points; Based on all the center points of the final target neural tube, the centerline of the target neural tube is obtained.

8. The neural tube marking method according to claim 7, characterized in that, The step of using a first preset algorithm to select target neural tube center points that meet the first preset conditions from all the target neural tube center points as candidate target neural tube center points includes: For each target neural tube center point, the sample point closest to the target slice containing that neural tube center point is identified as the target sample point. Determine whether the difference between the coordinate value of the center point of the target neural tube on the first coordinate axis parallel to the extension direction of the target neural tube and the coordinate value of the center point of the target neural tube on the first coordinate axis on the target slice where the target sample point is located is within a first preset range; If not, then the center point of the target neural tube shall be taken as the candidate center point of the target neural tube; If so, determine whether the target neural tube center point meets the following conditions: the difference between the coordinate value of the target neural tube center point on the second coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the second coordinate axis on the target slice where the target sample point is located is within a second preset range, and the difference between the coordinate value of the target neural tube center point on the third coordinate axis perpendicular to the first coordinate axis and the coordinate value of the target neural tube center point on the third coordinate axis on the target slice where the target sample point is located is within a third preset range; If so, then the center point of the target neural tube is taken as the candidate center point of the target neural tube; If not, then delete the center point of the target neural tube.

9. The neural tube marking method according to claim 7, characterized in that, The step of using a second preset algorithm to select candidate target neural tube center points that meet the second preset conditions as the final target neural tube center points includes: Based on the location information of the center point of each candidate target neural tube, a spatial curve is fitted to obtain the corresponding spatial curve; For each candidate target neural tube center point, determine whether the distance between the candidate target neural tube center point and the spatial curve is less than a third preset distance threshold. If so, the candidate target neural tube center point is taken as the final target neural tube center point; otherwise, the candidate target neural tube center point is deleted.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, which, when executed by the processor, implements the neural tube labeling method according to any one of claims 1 to 9.

11. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the neural tube marking method according to any one of claims 1 to 9.

Images