CN117017484A - Automatic planning method for pedicle screw channel, electronic equipment and storage medium - Google Patents
Automatic planning method for pedicle screw channel, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117017484A CN117017484A CN202310988157.9A CN202310988157A CN117017484A CN 117017484 A CN117017484 A CN 117017484A CN 202310988157 A CN202310988157 A CN 202310988157A CN 117017484 A CN117017484 A CN 117017484A
- Authority
- CN
- China
- Prior art keywords
- point
- bone structure
- pedicle screw
- pedicle
- coordinate point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 72
- 230000011218 segmentation Effects 0.000 claims abstract description 56
- 239000013598 vector Substances 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 13
- 230000005484 gravity Effects 0.000 claims description 12
- 206010034701 Peroneal nerve palsy Diseases 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 210000000115 thoracic cavity Anatomy 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 210000003484 anatomy Anatomy 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008439 repair process Effects 0.000 description 9
- 230000002980 postoperative effect Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002513 implantation Methods 0.000 description 2
- 206010002091 Anaesthesia Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 206010029174 Nerve compression Diseases 0.000 description 1
- 241000283984 Rodentia Species 0.000 description 1
- 230000037005 anaesthesia Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003412 degenerative effect Effects 0.000 description 1
- 239000000645 desinfectant Substances 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000002594 fluoroscopy Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 208000029761 vertebral disease Diseases 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/101—Computer-aided simulation of surgical operations
- A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an automatic planning method, device, electronic equipment and storage medium for a bone structure screw channel, wherein the method is characterized in that the vertebral body end plate plane of a single bone structure is fitted through the sub-structure segmentation result of the single bone structure, and the pedicle screw channel of the single bone structure is planned according to the sub-structure segmentation result and the fitting result of the vertebral body end plate plane.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an automatic planning method and device for a pedicle screw channel, electronic equipment and a storage medium.
Background
Pedicle screws are an internal fixation device for the spine, and can be beaten to the front vertebral body through the back of the pedicle, so that the pedicle screws have stronger fixation effect on the whole spine. In lumbar vertebra operation, the pedicle screw can be used for treating the unstable spine or nerve compression caused by lumbar vertebra slippage, degenerative lumbar vertebra disease, fracture and the like. Pedicle screw technology has been widely used in spinal surgery due to its superiority in spinal tri-column fixation biomechanics. Percutaneous pedicle screw endoprosthesis is a minimally invasive intraspinal fixation procedure that involves the insertion of a pedicle screw rod system through a hole in the skin under image guidance. Its advantages are less wound, less hemorrhage, short operation time and quick recovery.
The specific procedure for pedicle screw implantation is generally as follows:
1) Under anesthesia, the patient is supine or prone on an operating table and the surgical segment is determined using a C-arm machine perspective.
2) Marking the skin, cleaning the operation part with disinfectant, and spreading sterile towel.
3) The cortex at the needle insertion point is bitten by rongeur, the needle insertion point and the duct are prepared by an opening device, and the Kirschner wire is inserted.
4) And (5) a C-arm machine is used for perspective confirmation of the position of the Kirschner wire, and standard screws are implanted. The rest 3 screws are implanted in the same way.
5) The connecting rod and the screw cap are put in and screwed down for fixation. The position and stability of the fixation system is confirmed again by fluoroscopy.
6) And (5) suturing the incision, wrapping the wound and ending the operation.
The planning of the screw path of the pedicle screw is a core step in the pedicle screw implantation operation, and directly influences the stability, safety and effect of the screw. The nail path planning needs to consider the factors such as the nail feeding point, the nail feeding angle, the nail feeding depth and the like, and adjusts according to the anatomical structures and physiological curves of different parts. Doctors can improve the accuracy and reliability of the nail path planning by means of technologies such as perspective, CT navigation or robot assistance. Planning the pedicle screw channel before the operation can improve the accuracy and safety of screw placement and reduce the occurrence of complications. Therefore, the lumbar pedicle screw planning method with high precision and less time consumption is provided, and has great significance in clinical medicine.
In the prior art, the operation mode mainly depends on the understanding of an operator on anatomical knowledge and the proficiency of operation of surgical instruments, and has low accuracy and high surgical repair rate.
Disclosure of Invention
The invention aims to overcome the technical defects and provide an automatic planning method, device, electronic equipment and storage medium for a pedicle screw channel, so as to solve the technical problems that an operation mode in the related art mainly depends on understanding of an operator on anatomical knowledge and proficiency of operation of surgical instruments, and is low in accuracy and high in surgical repair rate.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
according to a first aspect of the present invention, there is provided a pedicle screw channel automatic planning method comprising:
step 1: acquiring CT images of a single-section bone structure, wherein the single-section bone structure is any one of lumbar vertebra, thoracic vertebra and cervical vertebra;
step 2: obtaining a substructure segmentation result of the single-segment bone structure according to the CT image;
step 3: fitting the plane of the vertebral endplate of the single-section bone structure;
step 4: and planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral body endplate plane.
Preferably, the obtaining a sub-structure segmentation result of the single-segment bone structure according to the CT image specifically includes:
and inputting the CT image of the single-segment bone structure into a pre-trained subdivision model to obtain a substructure segmentation result of the single-segment bone structure.
Preferably, the subdivision model is trained according to the following method, including:
establishing a 3D full convolution neural network model for finely dividing lumbar anatomy;
acquiring CT images of a single-section bone structure and CT images of the single-section bone structure with a segmentation label, and carrying out coordinate transformation on the two CT images to obtain two three-dimensional matrixes, wherein the matrix format is (x, y, z);
respectively expanding two three-dimensional matrixes by one dimension to obtain two four-dimensional matrixes, wherein each four-dimensional matrix is in the format of (1, x, y, z), and then superposing the two four-dimensional matrixes on the 0 th dimension to obtain a superposed four-dimensional matrix (2, x, y, z);
and carrying out interpolation and normalization processing on the superimposed four-dimensional matrix, taking the matrix subjected to interpolation and normalization processing as the input of the 3D full convolution neural network model, and training the 3D full convolution neural network model to obtain the subdivision model.
Preferably, if the single-node bone structure is lumbar, the sub-structure segmentation result includes: vertebral body, pedicle, lamina, transverse process, inferior articular process, spinous process, superior articular process; in said step 3, fitting the vertebral endplate planes of the single-segment bone structure comprises:
step 3-1: interpolation is carried out on the cone images in the sub-structure segmentation result, voxel spacing is enlarged, and then the cone images are converted into a three-dimensional matrix;
step 3-2: performing multiple smoothing treatment on the cone image after interpolation in the step 3-1 to obtain a coordinate point set of points on the surface of the cone image;
step 3-3: dividing the coordinate point set obtained in the step 3-2 into two coordinate point sets according to the z-axis coordinates of the centrum points of the vertebral body;
step 3-4: and respectively carrying out plane fitting on the two coordinate point sets, and obtaining normal vectors of two endplate planes while obtaining two endplates of the vertebral body by fitting.
Preferably, in step 4, planning the pedicle screw channel of the single-segment bone structure according to the sub-structure segmentation result and the fitting result of the vertebral endplate plane includes:
step 4-1: acquiring the barycenter coordinates of the vertebral bodies and the barycenter coordinates of the pedicles in the substructure segmentation result;
step 4-2: acquiring the center of gravity of the left pedicle and the center of gravity of the right pedicle, and connecting the center point coordinates of the left pedicle and the right pedicle;
step 4-3: adding the normal vectors of the two endplate planes obtained in the step 3-4 to obtain a vector sum;
step 4-4: calculating coordinates of a straight line passing through the midpoint and a straight line passing through the vector and the direction, and the straight line hanging down from the midpoint;
step 4-5: connecting the midpoint with the foot drop and extending a connecting line;
step 4-6: determining an end point of the connecting line, defining the end point as a far end point, wherein the distance from the far end point to the foot drop is in a preset proportional relationship with the distance from the foot drop to the middle point;
step 4-7: and determining the connection line of the far point and the center of gravity of the left pedicle as a first pedicle screw channel, and determining the connection line of the far point and the center of gravity of the right pedicle as a second pedicle screw channel.
Preferably, the method further comprises:
step 4-8: taking the left pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector of the first pedicle screw channel direction to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-9: repeating the steps 4-8 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw outlet point;
step 4-10: taking the left pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a first pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-11: repeating the steps 4-10 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw entry point.
Preferably, the method further comprises:
step 4-12: taking the right pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector in the direction of the second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-13: repeating the steps 4-12 until reaching the boundary of the vertebral body, wherein the point is the outlet point of the second pedicle screw;
step 4-14: taking the right pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-15: repeating the steps 4-14 until reaching the boundary of the vertebral body, wherein the point is the second pedicle screw entry point.
According to a second aspect of the present invention, there is provided an automatic pedicle screw passage planning apparatus comprising:
the acquisition module is used for acquiring CT images of a single-section bone structure, wherein the single-section bone structure is any one of lumbar vertebra, thoracic vertebra and cervical vertebra;
the method is also used for obtaining a substructure segmentation result of the single-section bone structure according to the CT image;
the fitting module is used for fitting the vertebral endplate plane of the single-section bone structure;
and the planning module is used for planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral endplate plane.
According to a third aspect of the present invention, there is provided an electronic device comprising:
the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the method when executing the program stored in the memory.
According to a fourth aspect of the present invention there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-described method.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
according to the method, compared with the technical scheme in the prior art, the intelligent planning is carried out on the paths of the pedicle screws in the pedicle screw fixation process, the workload of doctors is reduced, errors caused by manual planning are reduced, the operation accuracy is improved, and the postoperative repair rate is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.
Drawings
FIG. 1 is a flow chart illustrating a method of automatically planning a pedicle screw passage in accordance with an exemplary embodiment;
fig. 2 is a schematic diagram of a model structure of an nnUNet 3D network model shown according to an exemplary embodiment;
FIG. 3 is a diagram illustrating the effects of sub-structure partitioning of a subdivision model in accordance with an exemplary embodiment;
FIG. 4 is a schematic diagram showing barycentric coordinates of a vertebral body and barycentric coordinates effects of a pedicle, according to an example embodiment;
FIG. 5 is a graph illustrating a set of surface points of a vertebral body according to an exemplary embodiment;
FIG. 6 is an effect diagram after a single endplate plane fit, according to an exemplary embodiment;
FIG. 7 is a schematic view of a foot drop position shown according to an exemplary embodiment;
FIGS. 8A and 8B are schematic illustrations of the effect of an automatic planning method for pedicle screw passages, according to an example embodiment;
FIG. 9 is a schematic block diagram illustrating an automatic pedicle screw channel planning apparatus in accordance with an exemplary embodiment;
fig. 10 is a schematic block diagram of an electronic device, as shown in an exemplary embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As described in the foregoing background art, there is a technical problem in the related art that the surgical mode mainly depends on understanding of the anatomical knowledge by the operator and the proficiency of the operation of the surgical instrument, and the accuracy is not high and the surgical repair rate is high.
In order to effectively solve the problems in the related art, the invention provides an automatic planning method, an automatic planning device, electronic equipment and a storage medium for a pedicle screw channel, and the automatic planning method, the device, the electronic equipment and the storage medium are specifically described below.
Example 1
FIG. 1 is a flow chart illustrating a method of automatically planning a pedicle screw passage, according to an exemplary embodiment, comprising:
step S1: acquiring CT images of a single-section bone structure, wherein the single-section bone structure is any one of lumbar vertebra, thoracic vertebra and cervical vertebra;
step S2: obtaining a substructure segmentation result of the single-segment bone structure according to the CT image;
step S3: fitting the plane of the vertebral endplate of the single-section bone structure;
step S4: and planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral body endplate plane.
It should be noted that, in the technical solution provided in this embodiment, in specific practice, the device is operated in a controller of the medical apparatus, or the device is loaded and operated in an electronic device connected to the controller, and the controller of the medical apparatus executes a corresponding method by calling a program stored in the electronic device.
It can be appreciated that, the technical scheme provided in this embodiment, through the substructure segmentation result of the single-section bone structure, and fit the vertebral body endplate plane of the single-section bone structure, according to the substructure segmentation result and the fit result of the vertebral body endplate plane, plan the pedicle screw channel of the single-section bone structure, realized the automatic planning of pedicle screw channel, compare prior art's technical scheme, the technical scheme that this embodiment provided, in pedicle screw fixation operation, carry out intelligent planning to the route of pedicle screw, reduce doctor's work load, reduced the error that relies on the manual planning to bring entirely, improved the operation accuracy, reduced postoperative repair rate.
In specific practice, the sub-structure segmentation result of the single-segment bone structure is obtained according to the CT image, specifically:
inputting the CT image of the single-section bone structure into a pre-trained subdivision model to obtain a substructure segmentation result of the single-section bone structure; the subdivision model is trained according to the following method, and comprises the following steps:
establishing a 3D full convolution neural network model for finely segmenting the lumbar anatomy (the model structure of the nnUNet 3D network model can be a nnUNet 3D network model is shown in figure 2);
acquiring CT images of a single-section bone structure (which can be lumbar CT volume data with the size of 512 multiplied by N, wherein N represents the layer number of the CT volume data, 512 multiplied by 512 represents the size of each layer of CT data), and carrying out coordinate transformation on the two CT images to obtain two three-dimensional matrixes with the matrix format of (x, y, z);
respectively expanding two three-dimensional matrixes by one dimension to obtain two four-dimensional matrixes, wherein each four-dimensional matrix is in the format of (1, x, y, z), and then superposing the two four-dimensional matrixes on the 0 th dimension to obtain a superposed four-dimensional matrix (2, x, y, z);
and carrying out interpolation and normalization processing on the superimposed four-dimensional matrix, taking the matrix subjected to interpolation and normalization processing as the input of the 3D full convolution neural network model, and training the 3D full convolution neural network model to obtain the subdivision model.
It will be appreciated that the interpolation is used to change the size of the image, and in the nnUNet 3D network model, the image is trained in the form of a patch, so that it is required to ensure that the size of the image can be divided by the cut patch.
Normalization is a conventional method in the neural network training process, and aims to enable the training effect of the neural network to be better, namely, the neural network can be converged more quickly by normalization without sinking into saddle points to achieve local optimal rather than global optimal solution
Referring to fig. 3, if the single-node bone structure is lumbar, the sub-structure segmentation result includes: a vertebral body A, a vertebral pedicle B, an upper articular process C, a transverse process D, a vertebral lamina E, a lower articular process F and a spinous process G;
in said step 3, fitting the vertebral endplate planes of the single-segment bone structure comprises:
step 3-1: interpolation is carried out on the cone images in the sub-structure segmentation result, voxel spacing is enlarged, and then the cone images are converted into a three-dimensional matrix;
step 3-2: carrying out multiple smoothing treatment on the cone image after interpolation in the step 3-1 to obtain a coordinate point set of points on the surface of the cone image (multiple smoothing operation can rapidly obtain a surface point set by means of vtkmatrixtohomogeneous transform of a VTK library), wherein the effect of the cone surface point set is shown in figure 5;
step 3-3: dividing the coordinate point set obtained in the step 3-2 into two coordinate point sets according to the z-axis coordinates of the centrum points of the vertebral body;
step 3-4: and respectively carrying out plane fitting on the two coordinate point sets, and obtaining normal vectors of two endplate planes while fitting to obtain two endplates of the vertebral body (an effect diagram of a single endplate plane after fitting is shown in fig. 6).
In specific practice, the pedicle screw in clinical operation needs to be parallel to the upper end plate as much as possible, but because the upper end plate is sometimes irregular in shape, only the upper end plate is subjected to plane fitting, so that nail channel head-up is caused, and the technical scheme provided by the embodiment carries out plane fitting on the upper end plate and the lower end plate, and can improve the accuracy of final screw channel planning.
In specific practice, in the step 4, planning the pedicle screw channel of the single-segment bone structure according to the sub-structure segmentation result and the fitting result of the vertebral body endplate plane includes:
step 4-1: acquiring the barycentric coordinates of the vertebral bodies and the barycentric coordinates of the pedicles in the substructure segmentation result (as shown in fig. 4, the barycentric coordinates can be realized by means of the sitk.LabelShapes statistics imageFilter () of a SimpleITK library);
step 4-2: acquiring the center of gravity of the left pedicle and the center of gravity of the right pedicle, and connecting the center point coordinates of the left pedicle and the right pedicle;
step 4-3: adding the normal vectors of the two endplate planes obtained in the step 3-4 to obtain a vector sum;
step 4-4: calculating coordinates of a straight line passing through the midpoint and a straight line passing through the vector and the direction, and the two perpendicular feet (a perpendicular foot position schematic diagram is shown in fig. 7);
step 4-5: connecting the midpoint with the foot drop and extending a connecting line;
step 4-6: determining an end point of the connecting line, defining the end point as a far end point, wherein the distance from the far end point to the foot drop and the distance from the foot drop to the middle point are in a preset proportional relationship (the values of the proportional relationship are different for lumbar vertebrae of different sections);
step 4-7: and determining the connection line of the far point and the center of gravity of the left pedicle as a first pedicle screw channel, and determining the connection line of the far point and the center of gravity of the right pedicle as a second pedicle screw channel.
Step 4-8: taking the left pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector of the first pedicle screw channel direction to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-9: repeating the steps 4-8 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw outlet point.
Step 4-10: taking the left pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a first pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-11: repeating the steps 4-10 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw entry point.
Step 4-12: taking the right pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector in the direction of the second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-13: repeating the steps 4-12 until reaching the boundary of the vertebral body, wherein the point is the outlet point of the second pedicle screw.
Step 4-14: taking the right pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-15: repeating the steps 4-14 until reaching the boundary of the vertebral body, wherein the point is the second pedicle screw entry point.
Finally, the effect of the automatic planning of the pedicle screw channel is shown in fig. 8A and 8B.
In summary, the technical scheme provided by this embodiment, through the substructure segmentation result of single section bone structure to the vertebral body endplate plane of fitting single section bone structure, according to the substructure segmentation result and the planar fitting result of vertebral body endplate, plan the pedicle screw passageway of single section bone structure, realized pedicle screw passageway automatic planning, compare prior art's technical scheme, the technical scheme that this embodiment provided, in pedicle screw fixation operation in-process, carry out intelligent planning to the route of pedicle screw, reduce doctor's work load, reduced the error that relies on artifical planning to bring entirely, improved the operation rate of accuracy, reduced postoperative repair rate.
Example two
Fig. 9 is a schematic block diagram of an automatic pedicle screw channel planning apparatus 100, as shown in fig. 9, the apparatus 100 comprising:
an acquisition module 101, configured to acquire a CT image of a single-segment bone structure, where the single-segment bone structure is any one of a lumbar vertebra, a thoracic vertebra, and a cervical vertebra;
the method is also used for obtaining a substructure segmentation result of the single-section bone structure according to the CT image;
a fitting module 102 for fitting a vertebral endplate plane of a single bone structure;
and the planning module 103 is used for planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral endplate plane.
It should be noted that, in the technical solution provided in this embodiment, in specific practice, the device is operated in a controller of the medical apparatus, or the device is loaded and operated in an electronic device connected to the controller, and the controller of the medical apparatus executes a corresponding method by calling a program stored in the electronic device.
The specific implementation manner and the beneficial effects of each module are described in the above embodiments, and this embodiment is not repeated.
It can be appreciated that, the technical scheme provided in this embodiment, through the substructure segmentation result of the single-section bone structure, and fit the vertebral body endplate plane of the single-section bone structure, according to the substructure segmentation result and the fit result of the vertebral body endplate plane, plan the pedicle screw channel of the single-section bone structure, realized the automatic planning of pedicle screw channel, compare prior art's technical scheme, the technical scheme that this embodiment provided, in pedicle screw fixation operation, carry out intelligent planning to the route of pedicle screw, reduce doctor's work load, reduced the error that relies on the manual planning to bring entirely, improved the operation accuracy, reduced postoperative repair rate.
Example III
Referring to fig. 10, an electronic device according to an exemplary embodiment is shown, comprising:
a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 complete communication with each other through the communication bus 704;
a memory 703 for storing a computer program;
the processor 701 is configured to implement the above-described method when executing the program stored in the memory.
It can be appreciated that, the technical scheme provided in this embodiment, through the substructure segmentation result of the single-section bone structure, and fit the vertebral body endplate plane of the single-section bone structure, according to the substructure segmentation result and the fit result of the vertebral body endplate plane, plan the pedicle screw channel of the single-section bone structure, realized the automatic planning of pedicle screw channel, compare prior art's technical scheme, the technical scheme that this embodiment provided, in pedicle screw fixation operation, carry out intelligent planning to the route of pedicle screw, reduce doctor's work load, reduced the error that relies on the manual planning to bring entirely, improved the operation accuracy, reduced postoperative repair rate.
Example IV
A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-described method is shown according to an exemplary embodiment.
It can be appreciated that, the technical scheme provided in this embodiment, through the substructure segmentation result of the single-section bone structure, and fit the vertebral body endplate plane of the single-section bone structure, according to the substructure segmentation result and the fit result of the vertebral body endplate plane, plan the pedicle screw channel of the single-section bone structure, realized the automatic planning of pedicle screw channel, compare prior art's technical scheme, the technical scheme that this embodiment provided, in pedicle screw fixation operation, carry out intelligent planning to the route of pedicle screw, reduce doctor's work load, reduced the error that relies on the manual planning to bring entirely, improved the operation accuracy, reduced postoperative repair rate.
Of course, those skilled in the art will appreciate that implementing all or part of the above-described methods may be implemented by a computer program for instructing relevant hardware (e.g., a processor, a controller, etc.), where the program may be stored in a computer-readable storage medium, and where the program may include the steps of the above-described method embodiments when executed. The storage medium may be a memory, a magnetic disk, an optical disk, or the like.
The above-described embodiments of the present invention do not limit the scope of the present invention. Any other corresponding changes and modifications made in accordance with the technical idea of the present invention shall be included in the scope of the claims of the present invention.
Claims (10)
1. An automatic planning method for a pedicle screw channel, comprising the steps of:
step 1: acquiring CT images of a single-section bone structure, wherein the single-section bone structure is any one of lumbar vertebra, thoracic vertebra and cervical vertebra;
step 2: obtaining a substructure segmentation result of the single-segment bone structure according to the CT image;
step 3: fitting the plane of the vertebral endplate of the single-section bone structure;
step 4: and planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral body endplate plane.
2. The method according to claim 1, wherein the obtaining the sub-structure segmentation result of the single-segment bone structure according to the CT image specifically comprises:
and inputting the CT image of the single-segment bone structure into a pre-trained subdivision model to obtain a substructure segmentation result of the single-segment bone structure.
3. The method of claim 2, wherein the subdivision model is trained in accordance with the following method, including:
establishing a 3D full convolution neural network model for finely dividing lumbar anatomy;
acquiring CT images of a single-section bone structure and CT images of the single-section bone structure with a segmentation label, and carrying out coordinate transformation on the two CT images to obtain two three-dimensional matrixes, wherein the matrix format is (x, y, z);
respectively expanding two three-dimensional matrixes by one dimension to obtain two four-dimensional matrixes, wherein each four-dimensional matrix is in the format of (1, x, y, z), and then superposing the two four-dimensional matrixes on the 0 th dimension to obtain a superposed four-dimensional matrix (2, x, y, z);
and carrying out interpolation and normalization processing on the superimposed four-dimensional matrix, taking the matrix subjected to interpolation and normalization processing as the input of the 3D full convolution neural network model, and training the 3D full convolution neural network model to obtain the subdivision model.
4. The method of claim 1, wherein if the single-node bone structure is lumbar, the sub-structure segmentation result comprises: vertebral body, pedicle, lamina, transverse process, inferior articular process, spinous process, superior articular process; in said step 3, fitting the vertebral endplate planes of the single-segment bone structure comprises:
step 3-1: interpolation is carried out on the cone images in the sub-structure segmentation result, voxel spacing is enlarged, and then the cone images are converted into a three-dimensional matrix;
step 3-2: performing multiple smoothing treatment on the cone image after interpolation in the step 3-1 to obtain a coordinate point set of points on the surface of the cone image;
step 3-3: dividing the coordinate point set obtained in the step 3-2 into two coordinate point sets according to the z-axis coordinates of the centrum points of the vertebral body;
step 3-4: and respectively carrying out plane fitting on the two coordinate point sets, and obtaining normal vectors of two endplate planes while obtaining two endplates of the vertebral body by fitting.
5. The method according to claim 4, wherein in step 4, planning pedicle screw passages of a single-segment bone structure based on the sub-structure segmentation result and the fitting result of the vertebral endplate planes comprises:
step 4-1: acquiring the barycenter coordinates of the vertebral bodies and the barycenter coordinates of the pedicles in the substructure segmentation result;
step 4-2: acquiring the center of gravity of the left pedicle and the center of gravity of the right pedicle, and connecting the center point coordinates of the left pedicle and the right pedicle;
step 4-3: adding the normal vectors of the two endplate planes obtained in the step 3-4 to obtain a vector sum;
step 4-4: calculating coordinates of a straight line passing through the midpoint and a straight line passing through the vector and the direction, and the straight line hanging down from the midpoint;
step 4-5: connecting the midpoint with the foot drop and extending a connecting line;
step 4-6: determining an end point of the connecting line, defining the end point as a far end point, wherein the distance from the far end point to the foot drop is in a preset proportional relationship with the distance from the foot drop to the middle point;
step 4-7: and determining the connection line of the far point and the center of gravity of the left pedicle as a first pedicle screw channel, and determining the connection line of the far point and the center of gravity of the right pedicle as a second pedicle screw channel.
6. The method as recited in claim 5, further comprising:
step 4-8: taking the left pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector of the first pedicle screw channel direction to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-9: repeating the steps 4-8 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw outlet point;
step 4-10: taking the left pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a first pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-11: repeating the steps 4-10 until reaching the boundary of the vertebral body, wherein the point is the first pedicle screw entry point.
7. The method as recited in claim 6, further comprising:
step 4-12: taking the right pedicle as an origin, subtracting the unit vector from the origin coordinate by using the unit vector in the direction of the second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-13: repeating the steps 4-12 until reaching the boundary of the vertebral body, wherein the point is the outlet point of the second pedicle screw;
step 4-14: taking the right pedicle as an origin, adding a unit vector to the origin coordinate by using a unit vector in the direction of a second pedicle screw channel to obtain a new coordinate point, rounding the new coordinate point, checking the pixel value of the current new coordinate point in the original segmentation, if the pixel value is not 0, indicating that the current new coordinate point does not reach the cone boundary, and if the pixel value is 0, reaching the cone boundary;
step 4-15: repeating the steps 4-14 until reaching the boundary of the vertebral body, wherein the point is the second pedicle screw entry point.
8. An automatic planning device for pedicle screw passages, comprising:
the acquisition module is used for acquiring CT images of a single-section bone structure, wherein the single-section bone structure is any one of lumbar vertebra, thoracic vertebra and cervical vertebra;
the method is also used for obtaining a substructure segmentation result of the single-section bone structure according to the CT image;
the fitting module is used for fitting the vertebral endplate plane of the single-section bone structure;
and the planning module is used for planning pedicle screw channels of the single-section bone structure according to the substructure segmentation result and the fitting result of the vertebral endplate plane.
9. An electronic device, comprising:
the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 7 when executing a program stored on a memory.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988157.9A CN117017484A (en) | 2023-08-07 | 2023-08-07 | Automatic planning method for pedicle screw channel, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988157.9A CN117017484A (en) | 2023-08-07 | 2023-08-07 | Automatic planning method for pedicle screw channel, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117017484A true CN117017484A (en) | 2023-11-10 |
Family
ID=88632964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310988157.9A Pending CN117017484A (en) | 2023-08-07 | 2023-08-07 | Automatic planning method for pedicle screw channel, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117017484A (en) |
-
2023
- 2023-08-07 CN CN202310988157.9A patent/CN117017484A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10869722B2 (en) | Method and fixture for guided pedicle screw placement | |
| US20080177203A1 (en) | Surgical navigation planning system and method for placement of percutaneous instrumentation and implants | |
| AU2014209244B2 (en) | A system and process of utilizing image data to place a member | |
| US20220202498A1 (en) | System and method for surgical planning | |
| US9122670B2 (en) | Method for determining articular bone deformity resection using motion patterns | |
| CN104644258A (en) | Individuation minimal invasive vertebral pedicle screw entering navigation template and preparation method thereof | |
| Tu et al. | Three-dimensional–printed individualized guiding templates for surgical correction of severe kyphoscoliosis secondary to ankylosing spondylitis: outcomes of 9 cases | |
| US9826919B2 (en) | Construction of a non-imaged view of an object using acquired images | |
| US20200155236A1 (en) | Systems and methods for customized spine guide using two-dimensional imaging | |
| Knez et al. | Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes | |
| WO2021217714A1 (en) | Surgical guide plate, three-dimensional model and manufacturing and construction method, computer, and storage medium | |
| CN107157579A (en) | A kind of pedicle screw is implanted into paths planning method | |
| US20220183760A1 (en) | Systems and methods for generating a three-dimensional model of a joint from two-dimensional images | |
| CN111356405A (en) | Method for verifying hard tissue location using implant imaging | |
| WO2022267838A1 (en) | Spinal surgery robot system for screw placement operation | |
| EP4049609A1 (en) | Cross-modality planning using feature detection | |
| CN111728689A (en) | Pelvic fracture posterior ring minimally invasive stabilization system guide plate | |
| CN117017484A (en) | Automatic planning method for pedicle screw channel, electronic equipment and storage medium | |
| CN213075888U (en) | Pelvic fracture posterior ring minimally invasive stabilization system guide plate | |
| US20220354511A1 (en) | Three-dimensional (3d) bone-protecting drill guide device and systems and methods of manufacturing and using device | |
| CN210158690U (en) | Individualized cervical vertebra pedicle of vertebral arch screw is navigation template device step by step | |
| US20240138917A1 (en) | Apparatus for simulating medical procedure performing cervical artificial disc surgery and method thereof | |
| Nayak et al. | Significance of Prediction Techniques in Spinal Fusion Surgery | |
| US20220346968A1 (en) | Method for Planning an Orthopedic Procedure | |
| US20230310013A1 (en) | Apparatus, system, and method for patient-specific instrumentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |