CN117893694A - Atlantoaxial dislocation treatment scheme recommendation method and system - Google Patents
Atlantoaxial dislocation treatment scheme recommendation method and system Download PDFInfo
- Publication number
- CN117893694A CN117893694A CN202410294860.4A CN202410294860A CN117893694A CN 117893694 A CN117893694 A CN 117893694A CN 202410294860 A CN202410294860 A CN 202410294860A CN 117893694 A CN117893694 A CN 117893694A
- Authority
- CN
- China
- Prior art keywords
- atlas
- vector
- articular surface
- plane
- anterior
- 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.)
- Granted
Links
- 238000011282 treatment Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 47
- 239000013598 vector Substances 0.000 claims description 156
- 238000012549 training Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000006073 displacement reaction Methods 0.000 description 12
- 230000006872 improvement Effects 0.000 description 8
- 210000002632 atlanto-axial joint Anatomy 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 210000003625 skull Anatomy 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000002695 general anesthesia Methods 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003041 ligament Anatomy 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000011269 treatment regimen Methods 0.000 description 2
- 206010002091 Anaesthesia Diseases 0.000 description 1
- 208000032170 Congenital Abnormalities Diseases 0.000 description 1
- 206010010356 Congenital anomaly Diseases 0.000 description 1
- 206010061619 Deformity Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 206010061223 Ligament injury Diseases 0.000 description 1
- 206010037714 Quadriplegia Diseases 0.000 description 1
- 208000004756 Respiratory Insufficiency Diseases 0.000 description 1
- 230000037005 anaesthesia Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000001099 axilla Anatomy 0.000 description 1
- 210000004439 collateral ligament Anatomy 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000001767 medulla oblongata Anatomy 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 201000004193 respiratory failure Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
Landscapes
- Prostheses (AREA)
Abstract
The invention relates to a method and a system for recommending a treatment scheme of atlantoaxial dislocation, belongs to the technical field of medical information processing, and solves the problem of low decision efficiency and accuracy of the treatment scheme in the prior art. The method comprises the following steps: acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model; calculating characteristic parameters of the patient to be recommended based on the key points; inputting the characteristic parameters into a trained treatment scheme recommendation model to obtain a treatment scheme recommended for the patient to be recommended. A fast and accurate treatment plan recommendation is achieved.
Description
Technical Field
The invention relates to the technical field of medical information processing, in particular to a method and a system for recommending a treatment scheme of atlantoaxial dislocation.
Background
The dislocation of the atlantoaxial refers to the instability of the atlantoaxial caused by trauma, inflammation, congenital factors or idiopathic causes, the relative position of the atlantoaxial is changed, and the loss of normal anatomical relationship may lead to the compression of medulla oblongata and cervical spinal marrow, and the death of the patient due to quadriplegia and even respiratory failure. Due to its disability and high mortality, it is particularly important to diagnose, evaluate and receive appropriate therapeutic measures in time. How to evaluate the relative position of the atlantoaxial directly influences the selection of diagnosis and treatment decisions of the atlantoaxial dislocation.
Researchers at home and abroad propose various methods for describing the relative positions of atlantoaxial and typing, and commonly used methods include field typing, hawkins typing, greenberg typing, wang's typing, TOI typing and the like.
Fielding and Hawkins typing mainly include: type I: most commonly, the dislocation is not caused by rotation (pure rotation type) with displacement in the front-back direction, ADI is less than or equal to 3mm, and the atlantoaxial transverse ligament is not damaged, so that the atlantoaxial rotation movement range is normal. Type II: rotary dislocation is accompanied by anterior atlas displacement, ADI of about 3-5mm, possibly accompanied by collateral ligament injury. The lateral mass on one side is shifted, while the corresponding lateral mass is unchanged, and the atlantoaxial movement exceeds the normal range. Type III: the serious displacement occurs, ADI is more than or equal to 5mm, the transverse ligament and the atlantoaxial lateral articulation (the secondary important structure for limiting dislocation) are damaged, lateral masses at both sides are migrated, only one side is more obvious, and rotary dislocation is formed. Atlantoaxial movement is beyond normal range. Type IV: at least, posterior atlas shift, accompanied by incomplete dentate processes such as dentate fracture, may shift only one lateral mass. X-ray flats can have difficulty identifying changes, especially side-lying tablets, which are less readily determinable. The opening position sheet can display that the lateral mass is forwards and leans to the midline, the spinous process is biased to one side, and the opening position can also display that the injured joint parts of the necks 1-3 are overlapped and locked. Although the parting considers the size of ADI and the displacement of atlantoaxial in different directions, quantitative indexes of displacement, such as the size of the distance of lateral displacement, the size of rotation angle, the degree of displacement of lateral mass joints and the like, are not described in all directions, and the parting basis is difficult to be converted into quantitative data for comparison. And the typing is not related to treatment decision, the treatment method under the same typing is still more controversial, and the practicability of the method is limited.
Greenberg et al propose a treatment decision-related typing that classifies atlantoaxial dislocation into a renaturable type and a non-renaturable type depending on whether or not it is reset after distraction. The Wang's typing was proposed by the professor team Wang Chao, wang Shenglin, and the method is also divided into four types: the I type is that the atlantoaxial self-reposition person can be observed on the X-ray which extends beyond the lateral position of the flexion, and the reposition is purely fixed by the posterior approach; type II is that the patient can not reset by himself when the patient is over extended and bent, but can be reset under the traction of general anesthesia skull, and the reset is simply fixed by posterior approach; III is that the general anesthesia skull can not be reset under traction, and the anterior osteotomy is followed by posterior fixation; type IV is the case of bone fusion, where the anterior approach cuts bone and the posterior approach is fixed. TOI typing is similar to Wang's typing, and is also combined with X-ray and CT, and judges whether an anterior operation is required according to the skull traction result. Since the most important differentiation basis of such typing is further determined according to feedback after traction treatment, since the grasping and implementation of traction resetting technology has a difference between different doctors (such as drilling position, traction weight, traction time, anesthesia or not), the typing has a large uncertainty between the reconfigurability and the difficulty in reconfigurability, the uncertainty is influenced by subjective factors of the doctor technology, objective evaluation effect is difficult to achieve, different doctors may give different diagnosis results, so that deviation of treatment decisions is large, proper treatment schemes of patients cannot be quickly given, and treatment of patients is affected.
Disclosure of Invention
In view of the above analysis, the embodiments of the present invention aim to provide a method and a system for recommending an atlantoaxial dislocation treatment plan, which are used for solving the problem of low decision efficiency and accuracy of the existing treatment plan.
In one aspect, embodiments of the present invention provide a method for recommending a treatment regimen for atlantoaxial dislocation, comprising the steps of:
acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model;
calculating characteristic parameters of the patient to be recommended based on the key points;
inputting the characteristic parameters into a trained treatment scheme recommendation model to obtain a treatment scheme recommended for the patient to be recommended.
Based on the further improvement of the method, the treatment scheme recommendation model is trained by the following modes:
acquiring an atlantoaxial three-dimensional model and a treatment scheme of a sample patient, and identifying key points based on the atlantoaxial three-dimensional model; calculating characteristic parameters of each sample patient based on the key points; taking characteristic parameters of a sample patient as input data, and taking a treatment scheme as a label to construct a training sample set;
and constructing a neural network model, and training the constructed neural network model based on the training sample set to obtain a trained treatment scheme recommendation model.
Based on the further improvement of the method, generating the characteristic parameters of the patient to be recommended based on the key points comprises the following steps:
calculating a joint surface vector, a centrum axis vector and a plane where a lateral mass joint surface is located based on the key points;
and calculating to obtain characteristic parameters of the patient to be recommended based on the joint surface vector, the axial vector of the vertebral body and the lateral mass joint surface.
Based on the further improvement of the method, the key points comprise: an atlas anterior-posterior lower Fang Zhongdian, an atlas anterior-arch Fang Zhongdian, an atlas anterior-arch posterior-upper midpoint, an atlas right-side articular surface anterior-most point, an atlas left-side articular surface anterior-most point, an atlas right-side articular surface medial-most point, an atlas right-side articular surface lateral-most point, an atlas left-side articular surface medial-most point, an atlas left-side articular surface lateral-most point, an atlas odontopathy or odontopathy anterior-superior midpoint, an atlas odontopathy or odontopathy posterior-superior midpoint, an atlas anterior-lower Fang Zhongdian, an atlas left-side articular surface anterior-most point, an atlas right-side articular surface anterior-most point, an atlas left-side articular surface medial-most point, an atlas right-side articular surface medial-most point and an atlas right-side articular surface lateral-most point.
Based on a further improvement of the above method, the joint surface orientation comprises: atlanto-odontoid articular surface vector, right side block articular surface vector, and left side block articular surface vector;
calculating a joint face vector based on the keypoints, comprising:
the atlas and odontoid joint surface vector is calculated based on the anterior-posterior lower atlas arch Fang Zhongdian, the posterior-superior midpoint of the anterior-posterior arch of the atlas, the anterior-superior Fang Zhongdian of the dentate or the dentate cross section of the atlas and the anterior-inferior midpoint of the atlas;
calculating a right block articular surface vector based on a forwardmost point of a right articular surface of the epistropheus and a forwardmost point of a right articular surface of the atlas;
the left block articular surface vector is calculated based on the anterior most point of the left articular surface of the epistropheus and the anterior most point of the left articular surface of the atlas.
Based on the further improvement of the method, the plane of the lateral mass joint surface comprises: the plane of the right atlas articular surface, the plane of the right atlas axial articular surface, the plane of the left atlas articular surface and the plane of the left atlas axial articular surface;
calculating a plane of the lateral mass joint surface based on the key points, including:
construction of the first plane equation A 1R x+B 1R y+C 1R z+D 1R =0, solving the first plane equation based on the most anterior point of the right articular surface of the atlas, the most medial point of the right articular surface of the atlas and the most lateral point of the right articular surface of the atlas to obtain a plane in which the right atlas articular surface is located; wherein A is 1R 、B 1R 、C 1R And D 1R Are equation parameters;
construction of a second plane equation A 2R x+B 2R y+C 2R z+D 2R =0, solving the second plane equation based on the most anterior point of the right articular surface of the pivot, the most medial point of the right articular surface of the pivot and the most lateral point of the right articular surface of the pivot to obtain a plane in which the right block pivot articular surface is located; wherein A is 2R 、B 2R 、C 2R And D 2R Are equation parameters;
construction of the third plane equation A 1L x+B 1L y+C 1L z+D 1L =0, based on the anterior-most point of the left articular surface of the atlas, the medial-most point of the left articular surface of the atlas, and the atlasSolving the third plane equation by using the outermost point of the left articular surface of the vertebra to obtain a plane of the left atlas articular surface; wherein A is 1L 、B 1L 、C 1L And D 1L Are equation parameters;
construction of fourth plane equation A 2L x+B 2L y+C 2L z+D 2L =0, solving the fourth plane equation based on the most anterior point of the left articular surface of the pivot, the most medial point of the left articular surface of the pivot, and the most lateral point of the left articular surface of the pivot to obtain a plane in which the left block pivot articular surface is located; wherein A is 2L 、B 2L 、C 2L And D 2L Are equation parameters.
Based on a further improvement of the above method, the axial amount of the vertebral body comprises: axial amount of atlas、/>、/>And axial amount of the pivotes->、/>、/>；
Calculating an axial amount of the vertebral body based on the keypoints, comprising:
calculating vector from midpoint of anterior lower back of atlas to midpoint of anterior upper back of atlasObtaining Z-axis vector of atlas->；
Calculating the midpoint of the posterior lower part of the anterior arch of the atlas to the midpoint of the anterior part of the anterior arch of the atlas(Vector)Calculate->And->Is the vector of the X axis of the atlas +.>；
Calculation ofAnd->Is the vector of the normal vector of the atlas>；
Calculating the vector from the anterior-inferior midpoint of the centrum of the dentate or the anterior-superior midpoint of the dentate or the dentate cross-section of the dentateObtain the Z-axis vector of the pivotes>；
Calculating the vector from the front upper midpoint of the dentate or the dentate cross section to the rear upper midpoint of the dentate or the dentate cross sectionCalculate->And->The normal vector of (2) gives the X-axis vector of the pivot +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculate->And->The normal vector of (2) gets the Y-axis vector of the pivot +.>。
Based on a further improvement of the above method, the characteristic parameters include:
the atlanto-odontoid joint surface vector length, the atlanto-odontoid joint surface deflection angle, the right block joint surface vector length, the left block joint surface vector length, the atlas axis vector and the axis vector included angle of the axis vector of the axis, the right block axis joint surface included angle from the plane of the right block atlas joint surface to the plane of the right block atlas joint surface, the left block axis joint surface included angle from the plane of the left block atlas joint surface to the plane of the left block atlas joint surface, the right block deflection angle and the left block deflection angle.
Based on a further improvement of the method, the right block deflection angle comprises a right block cross section deflection angle, a right block coronal plane deflection angle and a right block sagittal plane deflection angle;
the right block yaw angle is calculated in the following manner:
calculating the projection of the right block joint surface vector on the axial vector of the pivot;
according to the formulaCalculating the right block joint plane vector +.>Projection on the XY plane of the axial vector of the said pivot +.>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the XZ plane of the axial vector of the pivot>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the YZ plane of the axial vector of the pivot>；
Computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the cross section of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the crown surface of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining a sagittal plane deflection angle of the right block;
wherein,representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto a projection plane.
In another aspect, an embodiment of the present invention provides a treatment plan recommendation system for atlantoaxial dislocation, including the following modules:
the key point identification module is used for acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model;
the characteristic parameter calculation module is used for calculating characteristic parameters of the patient to be recommended based on the key points;
and the recommending module is used for inputting the characteristic parameters into a trained treatment scheme recommending model to obtain a treatment scheme recommended for the patient to be recommended.
Compared with the prior art, the method has the advantages that the key points are identified on the basis of the atlantoaxial three-dimensional model, and then the characteristic parameters of a patient are calculated, so that the change of the atlantoaxial relative position is objectively and comprehensively quantified, then the recommended treatment scheme for the patient can be obtained on the basis of the trained treatment scheme recommendation model according to the characteristic parameters of the patient to be recommended, so that a more proper treatment scheme is quickly and accurately recommended for the patient, and the dispute of different diagnosis and treatment decisions under the same classification condition is overcome.
In the invention, the technical schemes can be mutually combined to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, like reference numerals being used to designate like parts throughout the drawings;
FIG. 1 is a flow chart of a method of treatment recommendation for atlantoaxial dislocation according to an embodiment of the present invention;
FIG. 2 is a schematic view of the angles of the planes of the articular surfaces of the lateral mass under normal conditions in accordance with an embodiment of the present invention;
FIG. 3 is a schematic view of the angles of the planes of the articular surfaces of the lateral mass in the case of a disease in accordance with an embodiment of the present invention;
FIG. 4 is a block diagram of a treatment recommendation system for atlantoaxial dislocation according to an embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and together with the description serve to explain the principles of the invention, and are not intended to limit the scope of the invention.
In one embodiment of the present invention, a method for recommending a treatment regimen for atlantoaxial dislocation is disclosed, as shown in fig. 1, comprising the steps of:
s1, acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points based on the atlantoaxial three-dimensional model;
s2, calculating characteristic parameters of the patient to be recommended based on the key points;
s3, inputting the characteristic parameters into a trained treatment scheme recommendation model to obtain a treatment scheme recommended for the patient to be recommended.
It should be noted that the characteristic parameters are used to characterize the displacement at each key location of the atlantoaxial.
In implementation, a three-dimensional model obtained by segmenting an atlantoaxial three-dimensional CT image of a patient to be recommended by adopting a manual segmentation or deep learning segmentation algorithm can be adopted.
Compared with the prior art, the atlantoaxial dislocation treatment scheme recommendation method provided by the embodiment identifies key points on the basis of the atlantoaxial three-dimensional model so as to calculate the characteristic parameters of a patient, thereby objectively and comprehensively quantifying the change of the atlantoaxial relative position, and then obtaining the treatment scheme recommended for the patient based on the trained treatment scheme recommendation model according to the characteristic parameters of the patient to be recommended, thereby rapidly and accurately recommending a more suitable treatment scheme for the patient, and overcoming the disputes of different diagnosis and treatment decisions under the same classification condition.
It should be noted that the key points of the atlantoaxial are required to meet the following requirements: (1) practicality: a vector or a coordinate system for evaluating the relative position relationship of the atlantoaxial can be constructed; (2) versatility: the method can be stably appeared on the three-dimensional reconstruction of the atlantoaxial of normal people and most of atlantoaxial disease patients, and the key points which appear in normal patients and cannot be marked in atlantoaxial deformity patients are avoided; (3) consistency: the key points are easy to understand and label, the difference between different labels is small, and the consistency is strong. (4) easy detection: the method is designed on edges such as edges and corners of the three-dimensional model as far as possible, and is easy to detect by a training algorithm.
Based on these requirements, the present invention defines the following key points on the atlas (C1) and the axis (C2) including:
an atlas anterior-posterior inferior midpoint P1, an atlas anterior-anterior midpoint P2, an atlas anterior-posterior superior midpoint P3, an atlas right-side articular surface anterior-anterior point P4, an atlas left-side articular surface anterior-most point P5, an atlas right-side articular surface medial-most point P6, an atlas right-side articular surface lateral-most point P7, an atlas left-side articular surface medial-most point P8, an atlas left-side articular surface lateral-most point P9, an atlas odontopathy or odontopathy anterior-superior midpoint P10, an atlas odontopathy or odontopathy posterior-superior midpoint P11, an atlas anterior-inferior midpoint P12, an atlas left-side articular surface anterior-most point P13, an atlas right-side articular surface anterior-most point P14, an atlas left-side articular surface medial-most point P15, an atlas left-side articular surface lateral-most point P16, an atlas right-side articular surface medial-most point P17 and an atlas right-side articular surface lateral-most point P18.
The atlantoaxial position variation ranges of P1-P5 and P10-P14 are smaller, and the atlantoaxial position variation ranges can be used for constructing vectors and planes of joint surfaces, and other key points are only used for constructing the planes of joint surfaces due to larger position variation.
In the case of occipital atlas, the three-dimensional reconstruction model has no complete anterior-posterior superior structure, and at this time, P3 is marked at the midpoint of the anterior-posterior superior cross section. In cases of 2 nd and 3 rd cervical vertebra insufficiency, the three-dimensional reconstruction model has no complete anterior and inferior structures of the vertebral body, and at the moment, P12 is marked at the midpoint of the anterior and inferior cross section of the vertebral body.
In the implementation, the deep learning model can be trained to supervise and learn the standard data on the basis of manual standard, so that the automatic detection of the key points is finally realized. For the patient to be recommended, the coordinate of the key point can be automatically detected and obtained by inputting the coordinate into a trained deep learning model. The key point coordinates may also be extracted manually.
After obtaining the key points, generating characteristic parameters of the patient to be recommended based on the key points, wherein the characteristic parameters comprise:
s21, calculating a joint surface vector, a centrum axis vector and a plane where a lateral mass joint surface is located based on the key points;
and S22, calculating to obtain characteristic parameters of the patient to be recommended based on the joint surface vector, the axial vector of the vertebral body and the lateral mass joint surface.
The joint surface vector is a vector formed by key points on the relative joint surfaces of the atlas and the axis, and is used for representing the relative position change of three joints between the atlas and the axis. For example, in the case of an atlantoaxial anatomical site, the positions of key points corresponding to the articular surfaces of the atlas and the axis in the atlantoaxial and left lateral mass joints are close to each other, and in the case of an atlantoaxial dislocation, displacement occurs at least at two points corresponding to one articular surface, and a vector formed by the displacement is used as a feature describing the relative position of the atlantoaxial.
Specifically, the joint surface area includes: atlantoodontoid joint face volumeRight block joint plane vector +.>And left side block joint aspect +.>；
Computing a joint face vector based on the keypoints, comprising:
the surface mount of the atlas odontoid joint is calculated based on the anterior-posterior lower midpoint P1 of the atlas anterior-posterior upper midpoint P3 of the atlas anterior-posterior, the anterior-superior midpoint P10 of the odontoid or odontoid cross section and the anterior-inferior midpoint P12 of the atlas；
Calculating the right block joint surface vector based on the anterior most point P14 of the right articular surface of the centrum and the anterior most point P4 of the right articular surface of the atlas；
Calculating the left block joint surface vector based on the anterior most point P13 of the left articular surface of the pivoteum and the anterior most point P5 of the left articular surface of the atlas。
When in implementation, firstly, the midpoint A of the upper and lower key points of the atlas tooth joint surface (namely the midpoint P1 at the back lower part of the atlas anterior arch and the midpoint P3 at the back upper part of the atlas anterior arch) is calculated; then calculating the vertical projection point D of the connection line of the upper limit key point in front of the dentate or the front upper midpoint P10 of the dentate section and the front lower midpoint P12 of the dentate body, wherein the vector from the point D to the point A is the atlantoodontoid joint surface area。
The vector from the anterior point P14 of the right articular surface of the dentate axis to the anterior point P4 of the right articular surface of the atlas is the right block joint surface vector。
Anterior-most point P13 of the left articular surface of the epistropheus to anterior-most point of the left articular surface of the atlasThe vector of the square point P5 is the left block joint surface vector。
The centrum axis vector is the axial amount of the Cartesian coordinate system inside each of the atlas and the axis. The included angle of the axial vector of the normal atlantoaxial is smaller, the relative position of the atlantoaxial after dislocation is changed, and the included angle of the axial vector is changed, so that the included angle is used as the characteristic of the relative position of the atlantoaxial.
Specifically, the axial amount of the vertebral body includes: axial amount of atlas、/>、/>And axial amount of the pivotes->、/>、/>；
Calculating an axial amount of the vertebral body based on the keypoints, comprising:
calculating vector from midpoint P1 of anterior lower part of atlas anterior arch to midpoint P3 of anterior upper part of atlas anterior archObtaining Z-axis vector of atlas->；
Calculating vector from anterior-lower midpoint P1 of anterior arch of atlas to anterior-middle midpoint P2 of anterior arch of atlasCalculate->Andis the vector of the X axis of the atlas +.>；
Calculation ofAnd->Is the vector of the normal vector of the atlas>；
Calculating the vector from the anterior-inferior midpoint P12 of the centrum of the dentate or the anterior-superior midpoint P10 of the dentate or the dentate fractureObtain the Z-axis vector of the pivotes>；
Calculating the vector from the anterior-superior midpoint P10 of the dentate or dentate cross-section to the posterior-superior midpoint P11 of the dentate or dentate cross-sectionCalculate->And->The normal vector of (2) gives the X-axis vector of the pivot +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculate->And->The normal vector of (2) gets the Y-axis vector of the pivot +.>。
The axis vector is a unit vector. Vector of Z axis (cephalad-caudal axis) of atlasUpward direction, X-axis (lateral-lateral axis) vector +.>Direction right, Y-axis (back-front axis) vector +.>The direction is backward. Z-axis (cephalad-caudal axis) vector of the pivotex>Upward direction, X-axis (lateral-lateral axis) vector +.>Direction right, Y-axis (back-front axis) vector +.>The direction is backward.
The plane of the lateral mass articular surface refers to the plane of the left and right lateral joints of the atlantoaxial, and as shown in fig. 2, the rotation angle from the plane of the lateral mass articular surface to the plane of the lateral mass atlantoaxial articular surface is a positive value under normal conditions. The rotation angle from the plane of the lateral mass articular surface to the plane of the lateral mass atlas articular surface in the case of dislocation may become smaller or even negative, as shown in fig. 3, and thus the relative position of the atlantoaxial lateral mass articular surface is characterized by the angle between the lateral mass atlas articular surface and the articular surface.
Specifically, the plane of the lateral mass articular surface comprises: plane M of right atlas articular surface 1R Plane M of right block pivot joint surface 2R Atlas of left side blockPlane M of the node surface 1L And a plane M in which the joint surface of the left lateral mass is located 2L ；
Calculating a plane of the lateral mass joint surface based on the key points, including:
construction of the first plane equation A 1R x+B 1R y+C 1R z+D 1R =0, solving the first plane equation based on the anterior most point P4 of the right articular surface of the atlas, the medial most point P6 of the right articular surface of the atlas and the lateral most point P7 of the right articular surface of the atlas to obtain a plane in which the right atlas articular surface is located; wherein A is 1R 、B 1R 、C 1R And D 1R Are equation parameters;
construction of a second plane equation A 2R x+B 2R y+C 2R z+D 2R =0, solving the second plane equation based on the most anterior point P14 of the right articular surface of the right pivot, the most medial point P17 of the right articular surface of the pivot, and the most lateral point P18 of the right articular surface of the pivot to obtain a plane in which the right block of the articular surface of the pivot is located; wherein A is 2R 、B 2R 、C 2R And D 2R Are equation parameters;
construction of the third plane equation A 1L x+B 1L y+C 1L z+D 1L =0, solving the third plane equation based on the anterior most point P5 of the left articular surface of the atlas, the medial most point P8 of the left articular surface of the atlas and the lateral most point P9 of the left articular surface of the atlas to obtain a plane in which the left atlas articular surface is located; wherein A is 1L 、B 1L 、C 1L And D 1L Are equation parameters;
construction of fourth plane equation A 2L x+B 2L y+C 2L z+D 2L =0, solving the fourth plane equation based on the most anterior point P13 of the left articular surface of the pivot, the most medial point P15 of the left articular surface of the pivot, and the most lateral point P16 of the left articular surface of the pivot to obtain a plane in which the left block of the pivot is located; wherein A is 2L 、B 2L 、C 2L And D 2L Are equation parameters.
When the method is implemented, corresponding key point coordinates are brought into corresponding plane equations to solve equation parameters, and the corresponding plane equations are obtained.
Firstly, calculating the planes of the joint surface vector, the centrum axial vector and the lateral mass joint surface based on key points, and then calculating the characteristic parameters of a patient to be recommended according to the joint surface vector, the centrum axial vector and the lateral mass joint surface, so that the atlantoaxial position characteristics are comprehensively and objectively extracted, and a basis is provided for accurately evaluating the atlantoaxial relative position relation and recommending a proper treatment scheme.
Specifically, the characteristic parameters include: atlantoodontoid joint face volumeLength of atlanto-odontoid articular surface deflection angle, right side block articular surface vector +.>Length, left side block articulation aspect +.>The length, the included angle of the axial vector of the atlas and the axial vector of the axis, the included angle from the plane of the right atlas articular surface to the plane of the right atlas articular surface, the included angle from the plane of the left atlas articular surface to the plane of the left atlas articular surface, the right atlas deflection angle and the left atlas deflection angle.
Wherein the atlantoodontoid joint surface areaIs used to characterize the atlas gap. The deflection angle of the atlantoodontoid articular surface is the vector of the atlantoodontoid articular surface +.>Included angle with the lateral-lateral axis vector of the axilla. Right block articular surface vector +.>Length, left side block articulation aspect +.>The length is used for representing the sliding distance of the foremost key point of the atlas lateral mass.
It is to be noted that, the included angle between the axial quantity of the atlas and the axial quantity of the axis, namely, the included angle between the X-axis vector of the atlas and the X-axis vector of the axis, the included angle between the Y-axis vector of the atlas and the Y-axis vector of the axis, and the included angle between the Z-axis vector of the atlas and the Z-axis vector of the axis.
The included angle from the plane of the right atlantoaxial joint surface to the plane of the right atlantoaxial joint surface and the included angle from the plane of the left atlantoaxial joint surface to the plane of the left atlantoaxial joint surface are used for representing the relative positions of the atlantoaxial side atlantoaxial joint surfaces.
Specifically, the right block deflection angle includes a right block cross section deflection angle, a right block coronal plane deflection angle, and a right block sagittal plane deflection angle;
the right block yaw angle is calculated in the following manner:
calculating the projection of the right block joint surface vector on the axial vector of the pivot;
according to the formulaCalculating the right block joint plane vector +.>Projection on the XY plane of the axial vector of the said pivot +.>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the XZ plane of the axial vector of the pivot>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the YZ plane of the axial vector of the pivot>；
Computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the cross section of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the crown surface of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining a sagittal plane deflection angle of the right block;
wherein,representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto a projection plane.
Likewise, the left block deflection angle includes a left block cross-sectional deflection angle, a left block coronal deflection angle, and a left block sagittal deflection angle;
the left block yaw angle is calculated in the following manner:
calculating a projection of the left block joint surface vector onto an axial vector of an axis;
according to the formulaCalculating the left block joint surface area +.>Projection on the XY plane of the axial vector of the said pivot +.>；
According to the formulaCalculating the left block joint surface area +.>Projection on the XZ plane of the axial vector of the pivot>；
According to the formulaCalculating the left block joint surface area +.>Projection on the YZ plane of the axial vector of the pivot>；
Computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the cross section of the left block;
computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the left block crown surface;
computing projectionsAxial amount with the axis of the Axis->Obtaining a left block sagittal plane deflection angle;
wherein,represents the axial amount of the left block joint surface amount in the axial direction of the pivotes +.>Projection onto; />Represents the axial amount of the left block joint surface amount in the axial direction of the pivotes +.>Projection onto; />Represents the axial amount of the left block joint surface amount in the axial direction of the pivotes +.>Projection onto a projection plane.
The deflection of the anterior key points of the atlas relative to the axial measurement direction of the axis is evaluated through the deflection angle, so that the position of the atlas relative to the whole axis is characterized.
The invention starts from the displacement of a plurality of key positions of the atlantoaxial, and establishes a system and index for evaluating the relative positions of the atlantoaxial with comprehensive, objective and high digitization.
After the characteristic parameters corresponding to the patient to be recommended are obtained, the characteristic parameters are input into a trained treatment scheme recommendation model to obtain a treatment scheme recommended for the patient to be recommended.
Specifically, the following method is adopted for training to obtain a treatment scheme recommendation model:
acquiring an atlantoaxial three-dimensional model and a treatment scheme of a sample patient, and identifying key points based on the atlantoaxial three-dimensional model; calculating characteristic parameters of each sample patient based on the key points; taking characteristic parameters of a sample patient as input data, and taking a treatment scheme as a label to construct a training sample set;
and constructing a neural network model, and training the constructed neural network model based on the training sample set to obtain a trained treatment scheme recommendation model.
It should be noted that the sample patient is a patient who recovered or significantly improved after treatment. The atlantoaxial three-dimensional model of the sample patient is obtained as the atlantoaxial three-dimensional model before treatment. The treatment scheme comprises: the treatment scheme of atlantoaxial dislocation comprises conservative treatment (i.e. no operation), simple posterior fixation after body position reset, simple posterior fixation after reset under general anesthesia skull traction, fixation after loosening operation between posterior joints, and posterior fixation after anterior osteotomy.
The atlantoaxial three-dimensional model of each sample patient is identified to obtain key points, the characteristic parameters of each sample patient are calculated based on the key points, and the specific process refers to the process of calculating the characteristic parameters of the patient to be recommended. Taking a characteristic parameter of a sample patient as input, and constructing a training sample for the label by the treatment scheme, thereby constructing a training sample set.
And then constructing a neural network model, for example, a multi-layer perceptron can be adopted, and training the constructed neural network model based on the constructed training sample set to obtain a trained treatment scheme recommendation model. The displacement size, the severity and the characteristics of dislocation can be comprehensively and accurately represented through the characteristic parameters, so that the dislocation treatment device corresponds to a treatment scheme.
For the patient to be recommended, through the treatment scheme recommendation model, a proper treatment scheme can be associated according to the specific objective condition of dislocation, so that a doctor can conveniently and rapidly diagnose and treat.
In one embodiment of the present invention, a treatment recommendation system for atlantoaxial dislocation is disclosed, as shown in fig. 4, comprising the following modules:
the key point identification module is used for acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model;
the characteristic parameter calculation module is used for calculating characteristic parameters of the patient to be recommended based on the key points;
and the recommending module is used for inputting the characteristic parameters into a trained treatment scheme recommending model to obtain a treatment scheme recommended for the patient to be recommended.
The method embodiment and the system embodiment are based on the same principle, and the related parts can be mutually referred to and can achieve the same technical effect. The specific implementation process refers to the foregoing embodiment, and will not be described herein.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A method of recommended treatment for atlantoaxial dislocation, comprising the steps of:
acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model;
calculating characteristic parameters of the patient to be recommended based on the key points;
inputting the characteristic parameters into a trained treatment scheme recommendation model to obtain a treatment scheme recommended for the patient to be recommended.
2. The method of claim 1, wherein the treatment recommendation model is trained by:
acquiring an atlantoaxial three-dimensional model and a treatment scheme of a sample patient, and identifying key points based on the atlantoaxial three-dimensional model; calculating characteristic parameters of each sample patient based on the key points; taking characteristic parameters of a sample patient as input data, and taking a treatment scheme as a label to construct a training sample set;
and constructing a neural network model, and training the constructed neural network model based on the training sample set to obtain a trained treatment scheme recommendation model.
3. The method of claim 1, wherein generating parameters of the patient to be recommended based on the keypoints comprises:
calculating a joint surface vector, a centrum axis vector and a plane where a lateral mass joint surface is located based on the key points;
and calculating to obtain characteristic parameters of the patient to be recommended based on the joint surface vector, the axial vector of the vertebral body and the lateral mass joint surface.
4. The method of claim 3, wherein the key points comprise: an atlas anterior-posterior lower Fang Zhongdian, an atlas anterior-arch Fang Zhongdian, an atlas anterior-arch posterior-upper midpoint, an atlas right-side articular surface anterior-most point, an atlas left-side articular surface anterior-most point, an atlas right-side articular surface medial-most point, an atlas right-side articular surface lateral-most point, an atlas left-side articular surface medial-most point, an atlas left-side articular surface lateral-most point, an atlas odontopathy or odontopathy anterior-superior midpoint, an atlas odontopathy or odontopathy posterior-superior midpoint, an atlas anterior-lower Fang Zhongdian, an atlas left-side articular surface anterior-most point, an atlas right-side articular surface anterior-most point, an atlas left-side articular surface medial-most point, an atlas right-side articular surface medial-most point and an atlas right-side articular surface lateral-most point.
5. The method of claim 4, wherein the joint surface mount comprises: atlanto-odontoid articular surface vector, right side block articular surface vector, and left side block articular surface vector;
calculating a joint face vector based on the keypoints, comprising:
the atlas and odontoid joint surface vector is calculated based on the anterior-posterior lower atlas arch Fang Zhongdian, the posterior-superior midpoint of the anterior-posterior arch of the atlas, the anterior-superior Fang Zhongdian of the dentate or the dentate cross section of the atlas and the anterior-inferior midpoint of the atlas;
calculating a right block articular surface vector based on a forwardmost point of a right articular surface of the epistropheus and a forwardmost point of a right articular surface of the atlas;
the left block articular surface vector is calculated based on the anterior most point of the left articular surface of the epistropheus and the anterior most point of the left articular surface of the atlas.
6. The method of claim 4, wherein the plane of the lateral mass articular surface comprises: the plane of the right atlas articular surface, the plane of the right atlas axial articular surface, the plane of the left atlas articular surface and the plane of the left atlas axial articular surface;
calculating a plane of the lateral mass joint surface based on the key points, including:
construction of the first plane equation A 1R x+B 1R y+C 1R z+D 1R =0, based on atlas right jointSolving the first plane equation by using a forefront point of the plane, an innermost point of the right articular surface of the atlas and an outermost point of the right articular surface of the atlas to obtain a plane where the right atlas articular surface is located; wherein A is 1R 、B 1R 、C 1R And D 1R Are equation parameters;
construction of a second plane equation A 2R x+B 2R y+C 2R z+D 2R =0, solving the second plane equation based on the most anterior point of the right articular surface of the pivot, the most medial point of the right articular surface of the pivot and the most lateral point of the right articular surface of the pivot to obtain a plane in which the right block pivot articular surface is located; wherein A is 2R 、B 2R 、C 2R And D 2R Are equation parameters;
construction of the third plane equation A 1L x+B 1L y+C 1L z+D 1L =0, solving the third plane equation based on the most anterior point of the left articular surface of the atlas, the most medial point of the left articular surface of the atlas and the most lateral point of the left articular surface of the atlas to obtain a plane in which the left atlas articular surface is located; wherein A is 1L 、B 1L 、C 1L And D 1L Are equation parameters;
construction of fourth plane equation A 2L x+B 2L y+C 2L z+D 2L =0, solving the fourth plane equation based on the most anterior point of the left articular surface of the pivot, the most medial point of the left articular surface of the pivot, and the most lateral point of the left articular surface of the pivot to obtain a plane in which the left block pivot articular surface is located; wherein A is 2L 、B 2L 、C 2L And D 2L Are equation parameters.
7. The method of claim 4, wherein the axial amount of the vertebral body comprises: axial amount of atlas、/>、/>And axial amount of the pivotes->、/>、/>；
Calculating an axial amount of the vertebral body based on the keypoints, comprising:
calculating vector from midpoint of anterior lower back of atlas to midpoint of anterior upper back of atlasObtaining Z-axis vector of atlas->；
Calculating vector from midpoint of anterior lower back of atlas to midpoint of anterior front of atlasCalculate->And->Is the vector of the X axis of the atlas +.>；
Calculation ofAnd->Atlas is obtained by normal vector of (2)Y-axis vector of vertebrae->；
Calculating the vector from the anterior-inferior midpoint of the centrum of the dentate or the anterior-superior midpoint of the dentate or the dentate cross-section of the dentateObtain the Z-axis vector of the pivotes>；
Calculating the vector from the front upper midpoint of the dentate or the dentate cross section to the rear upper midpoint of the dentate or the dentate cross sectionCalculate->And->The normal vector of (2) gives the X-axis vector of the pivot +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculate->And->The normal vector of (2) gets the Y-axis vector of the pivot +.>。
8. The method of claim 4, wherein the characteristic parameters comprise:
the atlanto-odontoid joint surface vector length, the atlanto-odontoid joint surface deflection angle, the right block joint surface vector length, the left block joint surface vector length, the atlas axis vector and the axis vector included angle of the axis vector of the axis, the right block axis joint surface included angle from the plane of the right block atlas joint surface to the plane of the right block atlas joint surface, the left block axis joint surface included angle from the plane of the left block atlas joint surface to the plane of the left block atlas joint surface, the right block deflection angle and the left block deflection angle.
9. The method of claim 8, wherein the right block deflection angle comprises a right block cross-sectional deflection angle, a right block coronal deflection angle, and a right block sagittal deflection angle;
the right block yaw angle is calculated in the following manner:
calculating the projection of the right block joint surface vector on the axial vector of the pivot;
according to the formulaCalculating the right block joint plane vector +.>Projection on the XY plane of the axial vector of the said pivot +.>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the XZ plane of the axial vector of the pivot>；
According to the formulaCalculating the right block joint plane vector +.>Projection on the YZ plane of the axial vector of the pivot>；
Computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the cross section of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining the deflection angle of the crown surface of the right block;
computing projectionsAxial amount with the axis of the Axis->Obtaining a sagittal plane deflection angle of the right block;
wherein,representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto; />Representing the axial amount of the right block joint surface vector in the axis of the pivot>Projection onto a projection plane.
10. An atlantoaxial dislocation treatment protocol recommendation system, comprising the following modules:
the key point identification module is used for acquiring an atlantoaxial three-dimensional model of a patient to be recommended, and identifying key points of the atlantoaxial based on the atlantoaxial three-dimensional model;
the characteristic parameter calculation module is used for calculating characteristic parameters of the patient to be recommended based on the key points;
and the recommending module is used for inputting the characteristic parameters into a trained treatment scheme recommending model to obtain a treatment scheme recommended for the patient to be recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410294860.4A CN117893694B (en) | 2024-03-15 | 2024-03-15 | Atlantoaxial dislocation treatment scheme recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410294860.4A CN117893694B (en) | 2024-03-15 | 2024-03-15 | Atlantoaxial dislocation treatment scheme recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117893694A true CN117893694A (en) | 2024-04-16 |
| CN117893694B CN117893694B (en) | 2024-06-18 |
Family
ID=90649285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410294860.4A Active CN117893694B (en) | 2024-03-15 | 2024-03-15 | Atlantoaxial dislocation treatment scheme recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893694B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2263470C1 (en) * | 2004-03-15 | 2005-11-10 | Сидор Марьян Владимирович | Method for predicting dislocation of axis' odontoid process |
| CN112837828A (en) * | 2020-02-21 | 2021-05-25 | 上海联影智能医疗科技有限公司 | System, apparatus and method for automated healthcare services |
| WO2021114622A1 (en) * | 2020-06-08 | 2021-06-17 | 平安科技（深圳）有限公司 | Spinal-column curvature measurement method, apparatus, computer device, and storage medium |
| WO2021189971A1 (en) * | 2020-10-26 | 2021-09-30 | 平安科技（深圳）有限公司 | Medical plan recommendation system and method based on knowledge graph representation learning |
| CN113647939A (en) * | 2021-08-26 | 2021-11-16 | 复旦大学 | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases |
| CN115222937A (en) * | 2022-07-21 | 2022-10-21 | 北京深睿博联科技有限责任公司 | Method and device for detecting scoliosis |
| CN116452499A (en) * | 2023-03-03 | 2023-07-18 | 山东大学 | Lumbar vertebra instability and slipping diagnosis system based on Unet network |
| KR102597931B1 (en) * | 2022-07-20 | 2023-11-06 | 주식회사 십일리터 | Method for image analyzing about luxating patella |
-
2024
- 2024-03-15 CN CN202410294860.4A patent/CN117893694B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2263470C1 (en) * | 2004-03-15 | 2005-11-10 | Сидор Марьян Владимирович | Method for predicting dislocation of axis' odontoid process |
| CN112837828A (en) * | 2020-02-21 | 2021-05-25 | 上海联影智能医疗科技有限公司 | System, apparatus and method for automated healthcare services |
| WO2021114622A1 (en) * | 2020-06-08 | 2021-06-17 | 平安科技（深圳）有限公司 | Spinal-column curvature measurement method, apparatus, computer device, and storage medium |
| WO2021189971A1 (en) * | 2020-10-26 | 2021-09-30 | 平安科技（深圳）有限公司 | Medical plan recommendation system and method based on knowledge graph representation learning |
| CN113647939A (en) * | 2021-08-26 | 2021-11-16 | 复旦大学 | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases |
| KR102597931B1 (en) * | 2022-07-20 | 2023-11-06 | 주식회사 십일리터 | Method for image analyzing about luxating patella |
| CN115222937A (en) * | 2022-07-21 | 2022-10-21 | 北京深睿博联科技有限责任公司 | Method and device for detecting scoliosis |
| CN116452499A (en) * | 2023-03-03 | 2023-07-18 | 山东大学 | Lumbar vertebra instability and slipping diagnosis system based on Unet network |
Non-Patent Citations (1)
| Title |
|---|
| YASUTAKA OKITA 等: "Automatic evaluation of atlantoaxial subluxation in rheumatoid arthritis by a deep learning model", ARTHRITIS RESEARCH & THERAPY, vol. 25, no. 181, 25 September 2023 (2023-09-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117893694B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11798688B2 (en) | Systems and methods for simulating spine and skeletal system pathologies | |
| AU2018342606B2 (en) | Systems and methods for simulating spine and skeletal system pathologies | |
| US11207135B2 (en) | Systems and methods for modeling spines and treating spines based on spine models | |
| CN108320288B (en) | Data processing method for idiopathic scoliosis image | |
| US20130085723A1 (en) | Method for determining articular bone deformity resection using motion patterns | |
| Casaroli et al. | What do we know about the biomechanics of the sacroiliac joint and of sacropelvic fixation? A literature review | |
| Du et al. | Radiological and clinical differences between Tinavi orthopedic robot and O-arm navigation system in thoracolumbar screw implantation for reconstruction of spinal stability | |
| Lehman et al. | Do intraoperative radiographs in scoliosis surgery reflect radiographic result? | |
| Golubovsky et al. | Development of a novel in vitro cadaveric model for analysis of biomechanics and surgical treatment of Bertolotti syndrome | |
| Kim et al. | Vertebral body rotation in patients with lumbar degenerative scoliosis: surgical implication for oblique lumbar interbody fusion | |
| Scher | Unilateral locked facet in cervical spine injuries | |
| CN117893694B (en) | Atlantoaxial dislocation treatment scheme recommendation method and system | |
| Chu et al. | Dynamic magnetic resonance imaging in assessing lung function in adolescent idiopathic scoliosis: a pilot study of comparison before and after posterior spinal fusion | |
| CN208404987U (en) | A kind of humerus model of 3D printing | |
| US20110054851A1 (en) | Method for detecting information relevant for the characterization of joint movements | |
| Van Roy et al. | Left-right asymmetries and other common anatomical variants of the first cervical vertebra: Part 1: Left-right asymmetries in C1 vertebrae | |
| Lovecchio et al. | The impact of preoperative supine radiographs on surgical strategy in adult spinal deformity | |
| Godzik et al. | Impact of dual-headed pedicle screws on the biomechanics of lumbosacral junction multirod constructs | |
| US20200090815A1 (en) | A system and method for selecting a patient population for spinal repair using a measurable outcome predictive metric of the spine | |
| Dong et al. | Prediction of accuracy and screw size by pedicle anatomic parameters and screws in idiopathic scoliosis with freehand screw placement based on machine learning | |
| Purcell | Sex differences in the femur and acetabulum: biomechanical analysis with forensic significance | |
| Wuthrich | Statistical Shape and Intensity Modeling of the Sacrum | |
| Swee | Leveraging Population Data Towards a Computational Pipeline for Spinal Orthopaedic Planning | |
| Knapik | Evaluation of the Impact of Lumbar Spine Morphology on Loading with the Application of Biomedical Image-Based Computational Modeling | |
| Ramesh et al. | Image-based detection of point of insertion for pedicle screw implants |
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 | ||
| GR01 | Patent grant |