CN116650109A - Method and system for generating pedicle screw implantation path - Google Patents

Abstract

A method and system for generating pedicle screw placement path includes segmenting vertebral body in CT medical image by vertebral body segmentation neural network model to obtain vertebral body Mask; based on the minimum or optimal outsourcing cuboid of the vertebral Mask, the original CT medical image area of the corresponding vertebral body of the patient is used as the input of a path optimization neural network model, and a left pedicle screw tail point and a right pedicle screw tail point and a midpoint heat map meeting the conditions are calculated; acquiring a screw feeding point of a pedicle screw and pedicle screw parameters; based on the optimal candidate path of the pedicle screws and the pedicle screw parameters, the left pedicle screw and the right pedicle screw are placed in the vertebral body. Therefore, the invention simplifies the algorithm by calculating the tail point and the middle point of the pedicle screw and then regenerating the nail feeding point.

Description

Method and system for generating pedicle screw implantation path

Technical Field

The invention relates to the technical field of surgical robots based on medical image processing, in particular to a method and a system for generating a pedicle screw placement path applied to a spinal surgical robot.

Background

Pedicle screws play an important role in applications such as internal fixation in spinal surgery, intervertebral disc fusion and the like, can effectively fix vertebral bodies, and have obvious clinical advantages in treatment of spinal diseases, so that the pedicle screws are widely used in spinal surgery.

The vast majority of traditional vertebral arch nail placement paths are manually made by doctors, or are manually made based on preoperative CT images, or are made on site through multiple X-ray fluoroscopy during operation, and the operation is complex and time-consuming.

There are also some automatic planning methods at present, such as a pedicle screw channel automatic planning system based on a Cone Beam CT (CBCT) image related to chinese patent publication No. CN113781496a, which includes a segmentation planning neural network module and a feature extraction module, where the segmentation planning neural network module is used to calculate a feature point heat map of a pedicle screw channel and a CBCT spine image segmentation map according to the CBCT spine image; and the feature extraction module is used for calculating the feature value of the pedicle screw channel according to the feature point heat map and the CBCT spine image segmentation map.

However, when the path planning is performed in the prior art, the planning neural network module performs path planning (namely, obtaining the position of the tail point) and pedicle screw size selection by dividing the feature point heat map of the centrum module, the nail feeding point and the middle point, and the algorithm is very complex.

Disclosure of Invention

In order to solve the technical problems, the invention provides a method and a system for generating a pedicle screw insertion path, which are used for calculating a pedicle screw insertion path channel, a pedicle screw length, a pedicle screw diameter and the like based on CT images shot by an empirical scheme of previous pedicle screw insertion operation by adopting an artificial intelligent deep learning technology training technology.

In order to achieve the above purpose, the technical scheme of the invention is as follows:

a method of generating a pedicle screw insertion path, comprising:

step S1: acquiring CT medical images of the vertebration of a patient, and segmenting all vertebration bodies in the CT medical images by adopting a cone segmentation neural network model to obtain corresponding cone Mask of each cone and naming of each cone;

step S2: determining the vertebral bodies of the left and right pedicle screws to be placed in each vertebral body, and based on the minimum outsourcing cuboid or the optimized outsourcing cuboid generated by the vertebral body Mask, taking the minimum outsourcing cuboid or the optimized outsourcing cuboid corresponding to the original CT medical image area of the vertebral body of the patient as the input of a path optimized neural network model, and calculating to obtain a tail point heat map of the left and right pedicle screws and a middle point heat map of the pedicle screws meeting the conditions; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is placed, and the pedicle midpoint is the position near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time; the regression algorithm module takes outsourced cuboids generated by a plurality of previous vertebral body masks as input, takes the middle point of the vertebral pedicle screw which is completely put in the outsourced cuboids and the tail point of the vertebral pedicle screw as output training data sets and verification data sets; the optimized outsourcing cuboid is obtained by extending a preset distance towards at least one surface of the minimum outsourcing cuboid; the path optimization neural network model is a full convolution neural network SCNet or GP-UNET model;

step S3: acquiring heat map values of tail points and midpoints of all the pedicle screws, judging and selecting the tail points and midpoints of the pedicle screws with the heat map values exceeding a preset threshold as candidate positions;

step S4: selecting a candidate position with the maximum tail point heat map value as a pedicle screw tail point, selecting a candidate position with the maximum midpoint heat map value as a pedicle screw midpoint, forming a connecting line between the pedicle screw tail point position and the pedicle screw midpoint position, extending the connecting line from the pedicle point, and taking a point where the extending line intersects with the vertebral body Mask as a pedicle screw feeding point position; the distance from the pedicle screw feeding point position to the pedicle screw tail point position is the length of the pedicle screw, the center line determined from the pedicle screw feeding point position to the pedicle screw tail point position is taken as a normal vector, the plane where the pedicle screw midpoint is located is taken as a normal plane, a circle with the radius continuously increasing is formed in the normal plane by taking the pedicle screw midpoint as the center, the radius when the circle intersects with the vertebral body Mask is marked as r, and the diameter d of the pedicle screw is determined by taking the radius; wherein the diameter d of the pedicle screw is less than 2*r;

step S5: based on the screw feeding point of the pedicle screw, the middle point of the pedicle screw, the tail point of the pedicle screw, the length of the pedicle screw and the diameter of the pedicle screw, the left pedicle screw and the right pedicle screw are embedded in the vertebral body.

Further, the surface corresponding to the pedicle screw feeding direction is taken as a surface A, the surface A is expanded outwards by a preset distance Y to form an optimized outsourcing cuboid, the remaining five surfaces are kept unchanged, and the area of the original CT image corresponding to the optimized outsourcing cuboid is the input of the path optimization neural network model.

Further, the predetermined distance Y is 1cm.

Further, the heat map values of the tail point candidate position and the middle point candidate position are in a value range of [0,1], and the preset threshold value of the heat map values is more than or equal to 0.2.

Further, the cone segmentation neural network model is a VNET or 3DUNET convolutional neural network.

Further, the path optimization method is an exhaustive method, a Dijkstra or a Markov algorithm.

Further, the pedicle screw diameter d=0.9x2xr2, or d=2 x r2-5mm.

Further, the X% is 90%.

Further, the path optimization neural network model is a full convolutional neural network SCNet model, and the training steps comprise:

first, a step of labeling training output data

Marking paths of a plurality of left and right pedicle screws passing through pedicle positions of the vertebral bodies in the past on a CT image, and marking tail points of the pedicle screws and midpoints of pedicles through which the central lines of the pedicle screws pass; at this time, four points are marked on each cone, namely a left tail point and a middle point, and a right tail point and a middle point; each point represents a spatial coordinate (x, y, z); the Mask of each cone and the cone name corresponding to each cone are obtained by dividing all cones in the CT medical image by adopting the cone segmentation neural network model;

second, input data for training is determined

The minimum wrapping cuboid or the optimized wrapping cuboid generated based on the cone Mask is used as the input of the full convolution neural network SCNet model corresponding to the original CT medical image area of the cone of the patient;

third, output data of training is determined

(1) Newly creating two cuboids with the same size as the minimum enveloping cuboid or the optimized enveloping cuboid generated by each cone Mask, marking the cuboids as a tail point cuboid and a middle point cuboid, and initializing the gray values of all points to be zero; taking two tail point coordinates in a label on a CT image area in the tail point cuboid, changing the gray value of the position corresponding to the tail point coordinates into 1, and changing the gray value of the position of the middle point coordinates into 1 in the middle point cuboid; then, smoothing operation is performed on the gray values for all coordinates of all cuboids, gaussian smoothing can be used,

where i=0, 1 denotes two kinds of heat maps, x is a position on a rectangular parallelepiped,for the coordinates of the tail/midpoint of the marker, σ is the size of the Gaussian kernel, +.>The distance between two points is defined, and gamma is a weight coefficient for determining the maximum value after corresponding smoothing;

(2) the tail point heat map and the middle point heat map which are generated after smoothing and output as the full convolution neural network SCNet model;

and finally, substituting the input and the corresponding output of the plurality of full convolutional neural network SCNet models into the full convolutional neural network SCNet models for training and verification so as to generate a trained full convolutional neural network SCNet model.

In order to achieve the above object, a further technical solution of the present invention is as follows:

a system employing the above method of generating a pedicle screw insertion path, comprising:

the extraction module is used for obtaining CT medical images of the spine of a patient through a vertebral body segmentation neural network model trained by an artificial intelligent deep learning technology, and segmenting all vertebral bodies in the CT medical images by adopting the vertebral body segmentation neural network model to obtain a corresponding vertebral body Mask of each vertebral body and naming of each vertebral body;

the input module is used for determining the vertebral bodies of the left pedicle screw and the right pedicle screw which are required to be placed in each vertebral body, inputting an original CT medical image area corresponding to the vertebral body of a patient on the basis of a minimum outsourcing cuboid or an optimized outsourcing cuboid generated by the vertebral body Mask as a path optimizing neural network model, and calculating to obtain a tail point heat map of the left pedicle screw and the right pedicle screw and a middle point heat map of the pedicle screw which meet the conditions; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is placed, and the pedicle midpoint is the position near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time; the regression algorithm module takes outsourced cuboids generated by a plurality of previous vertebral body masks as input, takes the middle point of the vertebral pedicle screw which is completely put in the outsourced cuboids and the tail point of the vertebral pedicle screw as output training data sets and verification data sets; the optimized outsourcing cuboid is obtained by extending a preset distance towards at least one surface of the minimum outsourcing cuboid;

the data processing module is used for acquiring heat map values of tail points and middle points of all the pedicle screws, judging and selecting the tail points and the middle points of the pedicle screws with the heat map values exceeding a preset threshold as candidate positions;

the optimal path acquisition module selects a candidate position with the largest tail point heat map value as a pedicle screw tail point, selects the candidate position with the largest midpoint heat map value as a pedicle screw midpoint, and forms a connecting line with the pedicle screw tail point position and the pedicle screw midpoint position, wherein the connecting line extends from a pedicle point, and a point where the extending line intersects with the vertebral body Mask is used as a pedicle screw feeding point position; the distance from the pedicle screw feeding point position to the pedicle screw tail point position is the length of the pedicle screw, the center line determined from the pedicle screw feeding point position to the pedicle screw tail point position is taken as a normal vector, the plane where the pedicle screw midpoint is located is taken as a normal plane, a circle with the radius continuously increasing is formed in the normal plane by taking the pedicle screw midpoint as the center, the radius when the circle intersects with the vertebral body Mask is marked as r, and the diameter d of the pedicle screw is determined by taking the radius; wherein the diameter d of the pedicle screw is less than 2*r;

the insertion module is used for inserting the left pedicle screw and the right pedicle screw in the vertebral body based on the screw feeding point of the pedicle screw, the middle point of the pedicle screw, the tail point of the pedicle screw, the length of the pedicle screw and the diameter of the pedicle screw.

As can be seen from the technical scheme, the invention provides a method and a system for generating a pedicle screw implantation path, which have the following beneficial technical effects compared with the prior art:

when planning the path, the method regenerates the screw feeding point by calculating the tail point and the middle point of the pedicle screw, the method does not need to directly calculate the screw feeding point, but automatically generates the screw feeding point and the selection of the size of the pedicle screw according to the screw placing path of the pedicle screw, and the algorithm is simplified.

Drawings

FIG. 1 is a flow chart of a method of generating a pedicle screw insertion path in accordance with an embodiment of the invention

FIG. 2 is a schematic view of a vertebral Mask according to an embodiment of the present invention

Fig. 3 is a schematic view of an area of an original CT image corresponding to an optimal outsourcing cuboid of a cone Mask according to an embodiment of the present invention; wherein, six faces of Right, left, analysis, posterior, superior and Informater respectively represent Right, left, front, back, upper and lower of human body

FIG. 4 is a schematic diagram showing a midpoint and heat thereof in an embodiment of the present invention

FIG. 5 is a schematic diagram of the tail point and heat thereof in an embodiment of the present invention

FIG. 6 is a schematic view showing the planned placement of two pedicle screws on the left and right sides of a single vertebral body in an embodiment of the invention

Detailed Description

The following describes embodiments of the present invention in further detail with reference to FIGS. 1-6.

Referring to fig. 1, fig. 1 is a flow chart of a method for generating a pedicle screw insertion path in accordance with an embodiment of the invention. As shown in fig. 1, the method comprises the following specific steps:

step S1: and acquiring CT medical images of the vertebration of the patient, and segmenting all the vertebration in the CT medical images by adopting a cone segmentation neural network model to obtain a cone Mask corresponding to each cone and naming of each cone.

The above steps utilize artificial intelligence deep learning technology, and the vertebral body segmentation neural network model can use VNET convolutional neural network to segment all vertebral bodies in the CT medical image, obtain a vertebral body Mask, and obtain the naming of each vertebral body (such as lumbar vertebra L1, lumbar vertebra L2 and/or thoracic vertebra T12).

It is clear to those skilled in the art that the VNET convolutional neural network is a relatively mature 3D medical image segmentation artificial intelligence method, and a segmentation model is trained and learned by using a coding, decoding and jump connection network structure in the VNET and some iterative optimization methods through a previously marked cone data set, so that multi-label segmentation of cones is realized. (e.g., as disclosed in Milletari, faudo, naspair Navab, and selected-Ahmad ahmadi. "V-net: fully convolutional neural networks for volumetric medical image segment." 2016fourth international conference on 3D vision (3 DV). Ieee, 2016).

Referring to fig. 6, fig. 6 is a schematic view showing the planned insertion effect of two pedicle screws on the left and right of a single vertebral body in an embodiment of the invention. As shown in fig. 6, in general, two pedicle screws can be placed in each vertebral body, and the left and right markers can be distinguished directly according to the left and right relationship on the image without using different marks. Wherein, when the surgeon performs the nail-placing operation, three position points are very important, namely a nail-feeding point of the pedicle screw, a pedicle screw tail point and a pedicle midpoint; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is driven in, and the pedicle midpoint is the point near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time.

It should be noted that, in the embodiment of the present invention, the pedicle screw insertion path (i.e., the screw insertion point) and the parameters (e.g., the length or the diameter d, etc.) of the pedicle screw are generated by calculating the thermal map of the tail point and the pedicle midpoint of the pedicle screw, combining the vertebral body Mask, and determining the screw insertion point by using the optimal path method, and by using the thermal map of the tail point and the pedicle midpoint.

When the heat map of the tail point and the middle point of the pedicle screw is calculated, a path optimization neural network model is needed, and the path optimization neural network model can be a full convolution neural network SCNet model or a GP-UNET model. Preferably, a full convolutional neural network SCNet model can be adopted, that is, each vertebral body has a full convolutional neural network SCNet model, the full convolutional neural network SCNet model is obtained by taking the smallest outsourced cuboid of a plurality of previous vertebral body masks as input and taking the pedicle midpoint heat map and the pedicle screw tail heat map of the pedicle screw which are completely put into the model as output training data and verification data; specifically, the method may include the steps of:

first, a step of labeling training output data

Marking paths of a plurality of left and right pedicle screws passing through pedicle positions of the vertebral bodies in the past on a CT image, and marking tail points of the pedicle screws and midpoints of pedicles through which the central lines of the pedicle screws pass; at this time, four points are marked on each cone, namely a left tail point and a middle point, and a right tail point and a middle point; each point represents a spatial coordinate (x, y, z); the Mask of each vertebral body and the corresponding vertebral body name of each vertebral body are obtained by dividing all vertebral bodies in the CT medical image through the vertebral body division neural network model.

Second, input data for training is determined

The minimum wrapping cuboid or the optimized wrapping cuboid generated based on the cone Mask is used as the input of the full convolution neural network SCNet model corresponding to the original CT medical image area of the cone of the patient.

Third, output data of training is determined

(1) Newly creating two cuboids with the same size as the minimum enveloping cuboid or the optimized enveloping cuboid generated by each cone Mask, marking the cuboids as a tail point cuboid and a middle point cuboid, and initializing the gray values of all points to be zero; taking two tail point coordinates in a label on a CT image area in the tail point cuboid, changing the gray value of the position corresponding to the tail point coordinates into 1, and changing the gray value of the position of the middle point coordinates into 1 in the middle point cuboid; then, smoothing operation is performed on the gray values for all coordinates of all cuboids, gaussian smoothing can be used,

where i=0, 1 denotes two kinds of heat maps, x is a position on a rectangular parallelepiped,for the coordinates of the tail/midpoint of the marker, σ is the size of the Gaussian kernel, +.>And gamma is a weight coefficient for determining the corresponding maximum value after smoothing for the distance between the two points.

(2) And generating a tail point heat map and a middle point heat map which are output as the full convolution neural network SCNet model after smoothing.

And finally, substituting the input and the corresponding output of the plurality of full convolutional neural network SCNet models into the full convolutional neural network SCNet models for training and verification so as to generate a trained full convolutional neural network SCNet model.

After the training of the full convolution neural network SCNet model is completed, the planning of the path (namely the position of the nail feeding point) and the selection of the size of the pedicle screw can be carried out according to the vertebral body segmentation neural network model by segmenting the characteristic point heat map of the vertebral body module, the tail point and the middle point, and the operation of vertebral arch nail placement is carried out.

That is, given a new patient CT image to be placed with pedicle screws, through the divided cone Mask, framing the corresponding position (the framing method is the same as the optimal cuboid in fig. 3), and through the training of the full convolution neural network SCNet model reasoning, the tail point heat map and the midpoint heat map can be calculated at the same time.

In an embodiment of the invention, the input to the fully convolutional neural network SCNet model is generated based on a cone Mask for each cone (as described above, for example, the cone Mask is calculated using the VNET convolutional neural network model).

Step S2 may then be performed.

Referring to fig. 2 and fig. 3, fig. 2 is a schematic diagram of a cone Mask according to an embodiment of the present invention, and fig. 3 is a schematic diagram of an area of an original CT image corresponding to an optimized outsourcing cuboid of the cone Mask according to an embodiment of the present invention.

Step S2: determining the vertebral bodies of the left and right pedicle screws to be placed in each vertebral body, and based on the minimum outsourcing cuboid or the optimized outsourcing cuboid generated by the vertebral body Mask, taking the minimum outsourcing cuboid or the optimized outsourcing cuboid corresponding to the original CT medical image area of the vertebral body of the patient as the input of a path optimized neural network model, and calculating to obtain a tail point heat map of the left and right pedicle screws and a middle point heat map of the pedicle screws meeting the conditions; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is placed, and the pedicle midpoint is the position near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time; the regression algorithm module takes outsourced cuboids generated by a plurality of previous vertebral body masks as input, takes the middle point of the vertebral pedicle screw which is completely put in the outsourced cuboids and the tail point of the vertebral pedicle screw as output training data sets and verification data sets; the optimized outsourcing cuboid is obtained by extending a preset distance towards at least one surface of the minimum outsourcing cuboid.

As shown in fig. 3, the optimized wrapping cuboid includes six sides (Right, left, front, rear, up, down sides of the human body, respectively), that is, english may be expressed as (Right, left, analyte, posterior, superior, informator is abbreviated as A, R, L, I, S, P).

Preferably, the surface a can be extended outwards by a predetermined distance, for example, 1cm, and the remaining five surfaces remain unchanged, so as to form a new cuboid, and the area of the original CT image corresponding to the cuboid is the input feature acquisition area of the full convolutional neural network SCNet model. Step S3: and acquiring heat map values of tail points and midpoints of the pedicle screws, and judging and selecting the tail points and midpoints of the pedicle screws, of which the heat map values exceed a preset threshold, as candidate positions.

Referring to fig. 4 and 5, fig. 4 shows a midpoint and a corresponding generated thermal diagram of an embodiment of the present invention, and fig. 5 shows a tail point and a corresponding generated thermal diagram of an embodiment of the present invention. After the tail point heat map and the middle point heat map are generated, an optimal path method can be used for determining a nail placing path and determining the parameters of the pedicle screws.

Step S4: selecting a candidate position with the maximum tail point heat map value as a pedicle screw tail point, selecting a candidate position with the maximum midpoint heat map value as a pedicle screw midpoint, forming a connecting line between the pedicle screw tail point position and the pedicle screw midpoint position, extending the connecting line from the pedicle point, and taking a point where the extending line intersects with the vertebral body Mask as a pedicle screw feeding point position; the distance from the pedicle screw feeding point position to the pedicle screw tail point position is the length of the pedicle screw, the center line determined from the pedicle screw feeding point position to the pedicle screw tail point position is taken as a normal vector, the plane where the pedicle screw midpoint is located is taken as a normal plane, a circle with the radius continuously increasing is formed in the normal plane by taking the pedicle screw midpoint as the center, the radius when the circle intersects with the vertebral body Mask is marked as r, and the diameter d of the pedicle screw is determined by taking the radius; wherein the diameter d of the pedicle screw is less than 2*r.

Step S5: based on the screw feeding point of the pedicle screw, the middle point of the pedicle screw, the tail point of the pedicle screw, the length of the pedicle screw and the diameter of the pedicle screw, the left pedicle screw and the right pedicle screw are embedded in the vertebral body.

Referring to fig. 6, fig. 6 is a schematic view showing the planned insertion effect of two pedicle screws on the left and right of a single vertebral body in an embodiment of the invention.

In summary, the method simplifies the algorithm by calculating the tail point and the middle point of the pedicle screw and then regenerating the screw feeding point, and calculates the insertion path channel, the pedicle screw length, the diameter and the like of the pedicle screw according to the optimal principle of the simple algorithm by adopting the artificial intelligent deep learning technology training technology based on the CT image shot by adopting the empirical scheme of the previous pedicle screw insertion operation.

The foregoing description is only of the preferred embodiments of the present invention, and the embodiments are not intended to limit the scope of the invention, so that all changes made in the equivalent structures of the present invention described in the specification and the drawings are included in the scope of the invention.

Claims (10)

1. A method of generating a pedicle screw insertion path, comprising:

step S1: acquiring CT medical images of the vertebration of a patient, and segmenting all vertebration bodies in the CT medical images by adopting a cone segmentation neural network model to obtain corresponding cone Mask of each cone and naming of each cone;

step S2: determining the vertebral bodies of the left and right pedicle screws to be placed in each vertebral body, and based on the minimum outsourcing cuboid or the optimized outsourcing cuboid generated by the vertebral body Mask, taking the minimum outsourcing cuboid or the optimized outsourcing cuboid corresponding to the original CT medical image area of the vertebral body of the patient as the input of a path optimized neural network model, and calculating to obtain a tail point heat map of the left and right pedicle screws and a middle point heat map of the pedicle screws meeting the conditions; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is placed, and the pedicle midpoint is the position near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time; the regression algorithm module takes outsourced cuboids generated by a plurality of previous vertebral body masks as input, takes the middle point of the vertebral pedicle screw which is completely put in the outsourced cuboids and the tail point of the vertebral pedicle screw as output training data sets and verification data sets; the optimized outsourcing cuboid is obtained by extending a preset distance towards at least one surface of the minimum outsourcing cuboid;

step S3: acquiring heat map values of tail points and midpoints of all the pedicle screws, judging and selecting the tail points and midpoints of the pedicle screws with the heat map values exceeding a preset threshold as candidate positions;

step S4: selecting a candidate position with the maximum tail point heat map value as a pedicle screw tail point, selecting a candidate position with the maximum midpoint heat map value as a pedicle screw midpoint, forming a connecting line between the pedicle screw tail point position and the pedicle screw midpoint position, extending the connecting line from the pedicle point, and taking a point where the extending line intersects with the vertebral body Mask as a pedicle screw feeding point position; the distance from the screw point of the pedicle screw to the position of the pedicle screw tail point is the length of the pedicle screw, the center line determined from the screw point of the pedicle screw to the position of the pedicle screw tail point is taken as a normal vector, the plane where the midpoint of the pedicle screw is positioned is taken as a normal plane, a circle with the radius continuously increased is formed in the normal plane by taking the midpoint of the pedicle screw as the center, the radius when the circle intersects with the vertebral body Mask is recorded as r, and the diameter d of the pedicle screw is determined according to the radius; wherein the diameter d of the pedicle screw is less than 2*r;

step S5: based on the screw feeding point of the pedicle screw, the middle point of the pedicle screw, the tail point of the pedicle screw, the length of the pedicle screw and the diameter of the pedicle screw, the left pedicle screw and the right pedicle screw are embedded in the vertebral body.

2. The method for generating a pedicle screw insertion path according to claim 1, wherein a plane corresponding to a direction of insertion of the pedicle screw is taken as a plane a, the smallest outer-wrapped cuboid of the vertebral body Mask in step S2 is expanded outwards by a predetermined distance Y to form an optimized outer-wrapped cuboid, the remaining five planes remain unchanged, and an area of an original CT image corresponding to the optimized outer-wrapped cuboid is an input of the path optimization neural network model.

3. The method of creating a pedicle screw insertion path as claimed in claim 2, wherein the predetermined distance Y is 0.5cm-2.0cm.

4. The method of generating a pedicle screw placement path as claimed in claim 1, wherein the thermal map values of the tail point candidate position and the midpoint candidate position range from [0,1], the predetermined threshold value of the thermal map values being 0.2 or more.

5. The method of generating a pedicle screw insertion path as claimed in claim 1, wherein the vertebral body segmentation neural network model is a VNET or 3DUNET convolutional neural network.

6. The method of generating a pedicle screw placement path as claimed in claim 1, wherein the path optimizing neural network model is a fully convolutional neural network SCNet model or a GP-UNET model.

7. The method of generating a pedicle screw insertion path as claimed in claim 1, wherein the pedicle screw has a diameter d=0.9x2 x r, or d= 2*r-5mm.

8. The method of creating a pedicle screw insertion path as claimed in claim 1, wherein said x% is 90%.

9. The method of generating a pedicle screw insertion path as claimed in claim 1, wherein the path optimizing neural network model is a full convolutional neural network SCNet model, the training step comprising:

first, a step of labeling training output data

Marking paths of a plurality of left and right pedicle screws passing through pedicle positions of the vertebral bodies in the past on a CT image, and marking tail points of the pedicle screws and midpoints of pedicles through which the central lines of the pedicle screws pass; at this time, four points are marked on each cone, namely a left tail point and a middle point, and a right tail point and a middle point; each point represents a spatial coordinate (x, y, z); the Mask of each cone and the cone name corresponding to each cone are obtained by dividing all cones in the CT medical image by adopting the cone segmentation neural network model;

second, input data for training is determined

The minimum wrapping cuboid or the optimized wrapping cuboid generated based on the cone Mask is used as the input of the full convolution neural network SCNet model corresponding to the original CT medical image area of the cone of the patient;

third, output data of training is determined

(1) Newly creating two cuboids with the same size as the minimum enveloping cuboid or the optimized enveloping cuboid generated by each cone Mask, marking the cuboids as a tail point cuboid and a middle point cuboid, and initializing the gray values of all points to be zero; taking two tail point coordinates in a label on a CT image area in the tail point cuboid, changing the gray value of the position corresponding to the tail point coordinates into 1, and changing the gray value of the position of the middle point coordinates into 1 in the middle point cuboid; then, smoothing operation is performed on the gray values for all coordinates of all cuboids, gaussian smoothing can be used,

where i=0, 1 denotes two kinds of heat maps, x is a position on a rectangular parallelepiped,for the coordinates of the tail/midpoint of the marker, σ is the size of the Gaussian kernel, +.>The distance between two points is defined, and gamma is a weight coefficient for determining the maximum value after corresponding smoothing;

(2) the tail point heat map and the middle point heat map which are generated after smoothing and output as the full convolution neural network SCNet model;

and finally, substituting the obtained inputs and corresponding outputs of the path optimization neural network models into the path optimization neural network models for training and verification so as to generate a trained path optimization neural network model.

10. A system employing the method of generating a pedicle screw insertion path as claimed in claims 1-9, comprising:

the extraction module is used for obtaining CT medical images of the spine of a patient through a vertebral body segmentation neural network model trained by an artificial intelligent deep learning technology, and segmenting all vertebral bodies in the CT medical images by adopting the vertebral body segmentation neural network model to obtain a corresponding vertebral body Mask of each vertebral body and naming of each vertebral body;

the input module is used for determining the vertebral bodies of the left pedicle screw and the right pedicle screw which are required to be placed in each vertebral body, inputting an original CT medical image area corresponding to the vertebral body of a patient on the basis of a minimum outsourcing cuboid or an optimized outsourcing cuboid generated by the vertebral body Mask as a path optimizing neural network model, and calculating to obtain a tail point heat map of the left pedicle screw and the right pedicle screw and a middle point heat map of the pedicle screw which meet the conditions; the pedicle screw tail point is the position of the nail tail point after the pedicle screw is placed, and the pedicle midpoint is the position near the center of the pedicle of the anatomical position and on the central line of the pedicle screw at the same time; the regression algorithm module takes outsourced cuboids generated by a plurality of previous vertebral body masks as input, takes the middle point of the vertebral pedicle screw which is completely put in the outsourced cuboids and the tail point of the vertebral pedicle screw as output training data sets and verification data sets; the optimized outsourcing cuboid is obtained by extending a preset distance towards at least one surface of the minimum outsourcing cuboid;

the data processing module is used for acquiring heat map values of tail points and middle points of all the pedicle screws, judging and selecting the tail points and the middle points of the pedicle screws with the heat map values exceeding a preset threshold as candidate positions;

the optimal path acquisition module selects a candidate position with the largest tail point heat map value as a pedicle screw tail point, selects the candidate position with the largest midpoint heat map value as a pedicle screw midpoint, and forms a connecting line with the pedicle screw tail point position and the pedicle screw midpoint position, wherein the connecting line extends from a pedicle point, and a point where the extending line intersects with the vertebral body Mask is used as a pedicle screw feeding point position; the distance from the pedicle screw feeding point position to the pedicle screw tail point position is the length of the pedicle screw, the center line determined from the pedicle screw feeding point position to the pedicle screw tail point position is taken as a normal vector, the plane where the pedicle screw midpoint is located is taken as a normal plane, a circle with the radius continuously increasing is formed in the normal plane by taking the pedicle screw midpoint as the center, the radius when the circle intersects with the vertebral body Mask is marked as r, and the diameter d of the pedicle screw is determined by taking the radius; wherein the diameter d of the pedicle screw is less than 2*r;

the insertion module is used for inserting the left pedicle screw and the right pedicle screw in the vertebral body based on the screw feeding point of the pedicle screw, the middle point of the pedicle screw, the tail point of the pedicle screw, the length of the pedicle screw and the diameter of the pedicle screw.