Spinal osteotomy pathway planning device, method and system

Abstract

This invention discloses a spinal osteotomy path planning device, method, and system, belonging to the field of medical device technology. The spinal osteotomy planning device is capable of planning the osteotomy path for spinal osteotomy surgery, specifically including: an identification module, an acquisition module, and a determination module. The identification module is used to identify feature points of at least two vertebrae based on a spinal scan image of the target object. The acquisition module is used to obtain the size of the lesion based on a pathological image of the target object. The determination module is used to determine the osteotomy area on the vertebrae to be osteotomized based on the feature points and the size of the lesion.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a spinal osteotomy path planning device, method, and system. Background Technology

[0002] Spinal osteotomy is a treatment method for specific spinal diseases. It alters the shape of the spine by removing a portion of the vertebral body bone to achieve a therapeutic effect. For example, ossification of the posterior longitudinal ligament requires osteotomy of the vertebral body at the site of the calcified ligament.

[0003] With the development and innovation of medical device technology, surgical robots have been put into clinical application. They plan surgical pathways based on the patient's pathological and physiological characteristics and perform surgery according to the planned pathways. The use of surgical robots has improved the stability and accuracy of surgical procedures.

[0004] However, few related technologies involve the use of intelligent systems for surgical planning in the field of spinal osteotomy. Therefore, it is necessary to develop surgical planning systems for spinal osteotomy. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the deficiency of the prior art in that it is impossible to realize surgical path planning for spinal osteotomy surgery, and to provide a spinal osteotomy path planning device, method and system.

[0006] The present invention solves the above-mentioned technical problems through the following technical solution:

[0007] In a first aspect, the present invention provides a spinal osteotomy planning device, the device comprising:

[0008] The recognition module is used to identify feature points of at least two vertebrae based on spinal scan images of the target object.

[0009] The acquisition module is used to acquire the size of the lesion based on the pathological image of the target object;

[0010] The determination module is used to determine the osteotomy area on the vertebral body to be osteotomized based on the feature points and the size of the lesion.

[0011] In one embodiment, the osteotomy region includes two perpendicularly distributed sagittal planes, transverse planes, and anterior edge planes; the determining module includes:

[0012] A construction unit is used to construct the longitudinal plane of the target object based on the feature points of the at least two vertebrae;

[0013] The first determining unit is configured to determine the sagittal plane based on the longitudinal plane and the physiological characteristics of the vertebral body to be osteotomized; and / or

[0014] The second determining unit is configured to determine the cross-section based on the longitudinal axis plane and the feature points; and / or

[0015] The third determining unit is used to determine the leading edge surface based on the longitudinal axis plane and the size of the lesion.

[0016] In one embodiment, the first determining unit includes:

[0017] The first acquisition subunit is used to acquire a target image from the tomographic scan image of the vertebra to be osteotomized based on the pedicle thickness.

[0018] A first determining subunit is used to determine the sagittal plane in the target image based on the positional relationship between the conical foramen and the osteotomy restriction area, wherein the sagittal plane is parallel to the longitudinal plane.

[0019] In one embodiment, the feature points include a first feature point and a second feature point distributed vertically along the vertebral body, and the second determining unit includes:

[0020] The second determining subunit is used to determine the first normal based on the projections of the first feature point and the second feature point onto the longitudinal plane;

[0021] The third determining subunit is used to determine a first cross-section that is perpendicular to the first normal and passes through the first feature point, and a second cross-section that is perpendicular to the first normal and passes through the second feature point.

[0022] In one embodiment, the feature point further includes a third feature point located axially between the first feature point and the second feature point, and the third determining unit includes:

[0023] The fourth determining subunit is used to determine the second normal based on the longitudinal plane and the first normal;

[0024] The fifth determining subunit is used to determine the leading edge surface based on the third feature point and the thickness of the lesion, wherein the leading edge surface is perpendicular to the second normal.

[0025] In one embodiment, the recognition module is specifically used to recognize the feature points based on the spinal scan image of the target object using a pre-trained first recognition model.

[0026] In one embodiment, the acquisition module is specifically used to acquire the size of the lesion based on the pathological image using a pre-trained second recognition model.

[0027] Secondly, a method for planning spinal osteotomy is provided, the method comprising:

[0028] Identify feature points of at least two vertebrae based on spinal scan images of the target object;

[0029] The size of the lesion is obtained from the pathological image of the target object;

[0030] The osteotomy area is determined on the vertebral body to be osteotomized based on the feature points and the size of the lesion.

[0031] Thirdly, a spinal osteotomy planning system is provided, the system comprising the osteotomy planning device provided in the first aspect above.

[0032] Fourthly, a spinal osteotomy operating system is provided, the operating system comprising:

[0033] The processor includes the spinal osteotomy planning system provided in the third aspect above.

[0034] An execution component, controlled by the processor, performs osteotomy operations according to the osteotomy area determined by the spinal osteotomy planning system.

[0035] The positive and progressive effects of this invention are as follows:

[0036] The spinal osteotomy planning device provided in this invention plans the osteotomy path quantitatively based on the spinal image and lesion size of the target object. This ensures the controllability of spinal osteotomy surgery, reduces human error, and lays the technical foundation for surgical robot solutions in the field of spinal osteotomy. Attached Figure Description

[0037] Figure 1 This is a block diagram illustrating a spinal osteotomy planning device according to an exemplary embodiment;

[0038] Figure 2 This is a diagram showing the distribution of feature points on a vertebral body according to an exemplary embodiment;

[0039] Figure 3 This is a feature point distribution diagram of different vertebrae on a segment of the spine, according to an exemplary embodiment.

[0040] Figure 4 This is a block diagram illustrating a determining module according to an exemplary embodiment;

[0041] Figure 5 This is a schematic cross-sectional view of a vertebral body according to an exemplary embodiment;

[0042] Figure 6 This is a block diagram illustrating a first determining unit according to an exemplary embodiment;

[0043] Figure 7 This is a block diagram illustrating a second determining unit according to an exemplary embodiment;

[0044] Figure 8This is a block diagram illustrating a third determining unit according to an exemplary embodiment;

[0045] Figure 9 This is an image of a lesion area shown according to an exemplary embodiment;

[0046] Figure 10 This is a flowchart of a spinal osteotomy planning method implemented according to an exemplary embodiment. Detailed Implementation

[0047] The present invention will be further illustrated by way of embodiments below, but the present invention is not limited to the scope of the embodiments described herein.

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. Unless otherwise defined, the technical or scientific terms used in this invention should be understood in their ordinary sense by one of ordinary skill in the art to which this invention pertains. The terms "a" or "an" and similar words used in this specification and claims do not indicate a limitation of quantity, but rather indicate the presence of at least one. Unless otherwise stated, the terms "comprising" or "including" and similar words mean that the elements or objects preceding "comprising" or "including" encompass the elements or objects listed following "comprising" or "including" and their equivalents, and do not exclude other elements or objects. The terms "connected" or "linked" and similar words are not limited to physical or mechanical connections, and can include electrical connections, whether direct or indirect.

[0050] The singular forms “a,” “the,” and “the” used in this specification and claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0051] Furthermore, in the examples provided in this embodiment of the invention, the directions such as "front," "back," "up," and "down" are all based on the human body. For example, the direction in which the human body faces is "front," the direction of the human body's back is "back," the head is "up," and the feet are "down." Moreover, "longitudinal" refers to the direction in which the human spine extends, and "transverse" refers to the direction perpendicular to "longitudinal."

[0052] Example 1

[0053] In a first aspect, embodiments of the present invention provide a spinal osteotomy planning device. Figure 1 This is a block diagram illustrating a spinal osteotomy planning device according to an exemplary embodiment. Figure 1 As shown, the spinal osteotomy planning device includes an identification module 100, an acquisition module 200, and a determination module 300.

[0054] The recognition module 100 is used to identify feature points of at least two vertebrae based on the spinal scan image of the target object.

[0055] In one embodiment, the recognition module 100 is specifically used to recognize the feature points based on a spinal scan image of the target object using a pre-trained first recognition model. The spinal scan image is a tomographic image containing the entire spine or parts of the vertebrae, such as a CT image. The first recognition model can be a deep learning model, obtained through iterative training based on several tomographic scan image data containing the human spine.

[0056] Optionally, the vertebral body to be osteotomized in the target object is the same vertebral body region contained in the image used when training the first recognition model. For example, if the spinal scan image of the target object is a cervical spine image, then an image containing the cervical vertebral body is used as training data when training the first recognition model. In this way, the recognition accuracy of the recognition module 100 is improved.

[0057] Feature points characterize the physiological morphology of the vertebral body. Figure 2 This is a diagram illustrating the distribution of feature points on a vertebral body according to an exemplary embodiment. For example... Figure 2 As shown, the recognition module 100 identifies nine feature points, including those characterizing the protruding structure of the vertebral body. In this embodiment of the invention, for a single vertebral body, the recognition module 100 identifies at least a first feature point P4, a second feature point P9, and a third feature point P8. The first feature point P4 is the anterior center point of the upper edge of the vertebral body, the second feature point P9 is the anterior center point of the lower edge of the vertebral body, and the third feature point P8 is the anterior center point of the vertebral body.

[0058] The recognition module 100 identifies feature points of at least two vertebrae. Figure 3 This is a distribution map of feature points of different vertebrae on a segment of the spine, according to an exemplary embodiment. For example... Figure 3 As shown, the recognition module 100 identifies feature points of each vertebra on a segment of the spine. By recognizing feature points on at least two vertebrae, the recognition module 100 constructs the longitudinal plane of the target object, thus providing reliable reference coordinates for accurately planning the osteotomy path. The details of constructing the longitudinal plane will be explained in subsequent steps.

[0059] Continue to refer to Figure 1 The acquisition module 200 is used to acquire the size of the lesion based on the pathological image of the target object. Taking ossification of the posterior longitudinal ligament as an example, the lesion is located in the posterior cervical ligament, and a visual pathological image of the lesion site can be acquired through medical imaging technology (such as X-ray image acquisition technology). In one embodiment, the acquisition module 200 is specifically used to acquire the size of the lesion based on the pathological image using a pre-trained second recognition model. The training data of the second recognition model is the same as the type of lesion.

[0060] The determination module 300 is used to determine the osteotomy area on the vertebral body to be osteotomized based on the feature points and the size of the lesion.

[0061] In one embodiment, the osteotomy region includes two perpendicularly distributed sagittal planes, transverse planes, and anterior planes. Figure 4 This is a block diagram illustrating a determining module according to an exemplary embodiment. Figure 4 As shown, the determining module 300 includes a construction unit 310, and the determining module 300 also includes a first determining unit 320, a second determining unit 330 and / or a third determining unit 340.

[0062] The construction unit 310 is used to construct the longitudinal plane 510 of the target object based on the feature points of the at least two vertebral segments. Combined with... Figure 3 As shown, optionally, the construction unit 310 uses the least squares method to fit the longitudinal axis surface 510 based on the feature points of at least two vertebral segments. The longitudinal axis surface 510 represents the longitudinal center plane of the target object. In this embodiment of the invention, constructing the longitudinal axis surface using the feature points of at least two vertebral segments avoids the pose deviation of the target object and improves the accuracy of the longitudinal axis surface 510.

[0063] The first determining unit 320 is used to determine the sagittal plane based on the longitudinal plane and the physiological characteristics of the vertebral body to be osteotomized. The sagittal plane consists of two side surfaces parallel to the longitudinal plane in the osteotomy region. Figure 5 This is a schematic cross-sectional view of a vertebral body according to an exemplary embodiment. Figure 5 As shown, the sagittal plane 520 includes a first sagittal plane 521 and a second sagittal plane 522 located on both sides of the longitudinal plane 510.

[0064] In one example Figure 6 This is a block diagram illustrating a first determining unit according to an exemplary embodiment, such as... Figure 6As shown, the first determining unit 320 includes a first acquiring subunit 321 and a first determining subunit 322. The first acquiring subunit 321 is used to acquire a target image from the tomographic scan images of the vertebral body to be osteotomized, based on the pedicle thickness. The pedicle is a component of the intervertebral foramen, and its thickness varies at different locations along the longitudinal direction of the vertebral body. Therefore, the pedicle thickness differs in different tomographic scan images. The first acquiring subunit 321 uses the tomographic scan image with the thickest pedicle as the target image.

[0065] The first determining subunit 322 is used to determine the sagittal plane in the target image based on the positional relationship between the conical foramen and the osteotomy restriction region. Combined with Figure 5 The osteotomy restriction area is the left arterial foramen 541 and the right arterial foramen 542 located below the conical foramen. When determining the sagittal plane, the first determining subunit 322 needs to consider the relative positions of the conical foramen and the arterial foramen. Taking the determination of the first sagittal plane 521 as an example, a section parallel to the left edge of the conical foramen on the longitudinal axis plane 510 is determined. If this section does not intersect with the left arterial foramen 541 on the left side, then this section is determined as the first sagittal plane 521 (e.g., Figure 5 (As shown). If the cut plane intersects with the left arterial foramen 541, the first sagittal plane 521 is determined based on the right edge of the left arterial foramen 541 to ensure that the first sagittal plane 521 does not intersect with the left arterial foramen. This method ensures that the planned sagittal plane will not damage other tissues, thus protecting the patient's safety.

[0066] Continue to refer to Figure 4 The second determining unit 330 in the determining module 300 is used to determine the cross-section based on the longitudinal axis plane and the feature points. The cross-section consists of two planes perpendicular to the longitudinal axis plane in the osteotomy region. Figure 7 This is a block diagram illustrating a second determining unit according to an exemplary embodiment. Figure 7 As shown, the second determining unit 330 includes a second determining subunit 331 and a third determining subunit 332.

[0067] The second determining subunit 331 is used to determine the first normal direction based on the projections of the first feature point P4 and the second feature point P9 onto the vertical axis plane. The first normal direction is parallel to the line connecting the projection points of the first feature point P4 and the second feature point P9 onto the vertical axis plane, and the direction of the first normal direction is upward.

[0068] The third determining subunit 332 is used to determine a first cross-section that is perpendicular to the first normal and passes through the first feature point P4, and a second cross-section that is perpendicular to the first normal and passes through the second feature point P9.

[0069] Continue to refer to Figure 4 The third determining unit 340 in the determining module 300 is used to determine the leading edge surface based on the longitudinal axis plane and the size of the lesion. Figure 8 This is a block diagram illustrating a third determining unit according to an exemplary embodiment, such as... Figure 8 As shown, the third determining unit 340 includes a fourth determining subunit 341 and a fifth determining subunit 342.

[0070] The fourth determining subunit 341 is used to determine the second normal based on the longitudinal plane and the first normal. Optionally, the second normal is the cross product of the first normal and the longitudinal plane normal. Based on this, a three-dimensional coordinate space is constructed using the first normal, the second normal, and the longitudinal plane normal, which serves as the reference coordinate for the osteotomy region.

[0071] The fifth determining subunit 342 is used to determine the leading edge surface based on the third feature point and the thickness of the lesion, the leading edge surface being perpendicular to the second normal. Figure 9 It is an image of a lesion area shown according to an exemplary embodiment, and Figure 9 The orientation shown is a cross-section parallel to the longitudinal axis. Optionally, in conjunction with... Figure 9 The thickness d of the lesion region is obtained through image recognition. The fifth determining subunit 342 is used to determine a reference plane 901 perpendicular to the second normal based on the third feature point P8, and then determine the plane 902 located at a distance d behind the reference plane 901 as the anterior edge surface 902. This anterior edge surface 902 is equivalent to the bottom surface of the groove formed by the osteotomy region on the vertebral body.

[0072] In summary, the spinal osteotomy planning device provided in this invention quantitatively plans the osteotomy path based on the spinal image and lesion size of the target object. This ensures the controllability of spinal osteotomy surgery, reduces human error, and lays a technical foundation for surgical robot solutions in the field of spinal osteotomy.

[0073] Example 2

[0074] Secondly, embodiments of the present invention provide a method for planning spinal osteotomy. Figure 10 This is a flowchart of a spinal osteotomy planning method implemented according to an exemplary embodiment. For example... Figure 10 As shown, the method includes:

[0075] Step S101: Identify feature points of at least two vertebrae based on the spinal scan image of the target object.

[0076] Step S102: Obtain the size of the lesion based on the pathological image of the target object.

[0077] Step S103: Determine the osteotomy area on the vertebral body to be osteotomized based on the feature points and the size of the lesion.

[0078] In one embodiment, the osteotomy region includes two perpendicularly distributed sagittal planes, transverse planes, and anterior margins; step S103 includes:

[0079] The longitudinal plane of the target object is constructed based on the feature points of the at least two vertebral segments;

[0080] The sagittal plane is determined based on the longitudinal plane and the physiological characteristics of the vertebral body to be osteotomized; and / or

[0081] The cross-section is determined based on the longitudinal plane and the feature points; and / or

[0082] The leading edge surface is determined based on the longitudinal plane and the size of the lesion.

[0083] In one embodiment, determining the sagittal plane based on the longitudinal plane and the physiological characteristics of the vertebral body to be osteotomized includes:

[0084] The target image is obtained from the tomographic scan of the vertebral body to be osteotomized based on the pedicle thickness.

[0085] The sagittal plane is determined in the target image based on the positional relationship between the conical foramen and the osteotomy restriction area, and the sagittal plane is parallel to the longitudinal axis plane.

[0086] In one embodiment, the feature points include a first feature point and a second feature point distributed vertically along the vertebral body, and determining the cross-section based on the longitudinal plane and the feature points includes:

[0087] The first normal is determined based on the projections of the first feature point and the second feature point onto the longitudinal plane.

[0088] Determine a first cross-section that is perpendicular to the first normal and passes through the first feature point, and a second cross-section that is perpendicular to the first normal and passes through the second feature point.

[0089] In one embodiment, the feature point further includes a third feature point located axially between the first feature point and the second feature point, and the determination of the anterior edge surface based on the longitudinal plane and the size of the lesion includes:

[0090] The second normal is determined based on the longitudinal plane and the first normal.

[0091] The leading edge surface is determined based on the third feature point and the thickness of the lesion, and the leading edge surface is perpendicular to the second normal.

[0092] In one embodiment, step S101 includes identifying the feature points based on a spinal scan image of the target object using a pre-trained first recognition model.

[0093] In one embodiment, step S102 includes obtaining the size of the lesion based on the pathological image using a pre-trained second recognition model.

[0094] In summary, the spinal osteotomy planning method provided by this invention quantitatively plans the osteotomy path based on the spinal image and lesion size of the target object. This ensures the controllability of spinal osteotomy surgery, reduces human error, and lays a technical foundation for surgical robot solutions in the field of spinal osteotomy.

[0095] Example 3

[0096] Thirdly, embodiments of the present invention provide a spinal osteotomy planning system, the system including the osteotomy planning device provided in Embodiment 2 above. Optionally, this system is used in conjunction with a physician diagnostic system to formulate a spinal osteotomy surgical plan. Optionally, this system is used in conjunction with a surgical operating system to provide osteotomy path planning for the surgical operating system.

[0097] The spinal osteotomy planning system provided in this invention quantitatively plans the osteotomy path based on the spinal image and lesion size of the target patient. This ensures the controllability of spinal osteotomy surgery, reduces human error, and lays the technical foundation for robotic surgical solutions in the field of spinal osteotomy.

[0098] Example 4

[0099] Fourthly, embodiments of the present invention provide a spinal osteotomy operating system, the operating system comprising: a processor and an execution component. The processor includes the spinal osteotomy planning system provided in Embodiment 3 above. The execution component is used to perform osteotomy operations under the control of the processor according to the osteotomy area determined by the spinal osteotomy planning system.

[0100] The spinal osteotomy operating system provided in this invention quantitatively plans the osteotomy path based on the spinal image and lesion size of the target object. This ensures the controllability of spinal osteotomy surgery, reduces human error, and realizes a robotic surgical solution in the field of spinal osteotomy.

[0101] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. A spinal osteotomy planning device, comprising: The device comprises: an identification module configured to identify feature points of at least two vertebrae based on a spine scan image of a target object; an acquisition module configured to acquire a size of a lesion based on a pathological image of the target object; a determination module configured to determine a bone cutting region on a vertebra to be cut based on the feature points and the size of the lesion; and the bone cutting region comprises sagittal planes, transverse planes and leading edge planes which are vertically distributed in pairs; the determination module comprises: a construction unit configured to construct a longitudinal axis plane of the target object based on the feature points of the at least two vertebrae; a first determination unit configured to determine the sagittal planes based on the longitudinal axis plane and physiological characteristics of the vertebra to be cut; and / or a second determination unit configured to determine the transverse planes based on the longitudinal axis plane and the feature points; and / or a third determination unit configured to determine the leading edge planes based on the longitudinal axis plane and the size of the lesion.

2. The apparatus of claim 1, wherein, The first determination unit comprises: a first acquisition sub-unit configured to acquire a target image in a tomographic scan image of the vertebra to be cut based on a pedicle thickness; a first determination sub-unit configured to determine the sagittal planes based on a position relationship between a cone hole and a bone cutting limit region in the target image, the sagittal planes being parallel to the longitudinal axis plane.

3. The apparatus of claim 1, wherein, The feature points comprise first feature points and second feature points which are distributed upward and downward along the vertebrae; the second determination unit comprises: a second determination sub-unit configured to determine a first normal based on projections of the first feature points and the second feature points on the longitudinal axis plane; a third determination sub-unit configured to determine a first transverse plane which is perpendicular to the first normal and passes through the first feature points, and a second transverse plane which is perpendicular to the first normal and passes through the second feature points.

4. The apparatus of claim 3, wherein, The feature points further comprise third feature points which are located between the first feature points and the second feature points in an axial direction; the third determination unit comprises: a fourth determination sub-unit configured to determine a second normal based on the longitudinal axis plane and the first normal; a fifth determination sub-unit configured to determine the leading edge planes based on the third feature points and a thickness of the lesion, the leading edge planes being perpendicular to the second normal.

5. The apparatus of any one of claims 1-4, wherein, The identification module is specifically configured to identify the feature points based on the spine scan image of the target object by using a pre-trained first identification model.

6. The apparatus of any one of claims 1-4, wherein, The acquisition module is specifically configured to acquire the size of the lesion based on the pathological image by using a pre-trained second identification model.

7. A spinal osteotomy planning method, characterized by, The method comprises: identifying feature points of at least two vertebrae based on a spine scan image of a target object; acquiring a size of a lesion based on a pathological image of the target object; determining a bone cutting region on a vertebra to be cut based on the feature points and the size of the lesion; and the bone cutting region comprises sagittal planes, transverse planes and leading edge planes which are vertically distributed in pairs; the step of determining the bone cutting region on the vertebra to be cut based on the feature points and the size of the lesion comprises: constructing a longitudinal axis plane of the target object based on the feature points of the at least two vertebrae; determining the sagittal planes based on the longitudinal axis plane and physiological characteristics of the vertebra to be cut; and / or determining the transverse planes based on the longitudinal axis plane and the feature points; and / or The leading edge surface is determined based on the longitudinal axis surface and a size of the lesion.

8. A spinal osteotomy planning system, comprising: The system comprises the osteotomy planning device of any one of claims 1-6.

9. A spinal osteotomy procedure system, comprising: The operating system comprises: a processor comprising the spinal osteotomy planning system of claim 8, an execution component for performing an osteotomy operation according to the osteotomy region determined by the spinal osteotomy planning system under control of the processor.

Images