CN117745989A - Nerve root blocking target injection path planning method and system based on vertebral canal structure - Google Patents
Nerve root blocking target injection path planning method and system based on vertebral canal structure Download PDFInfo
- Publication number
- CN117745989A CN117745989A CN202410190519.4A CN202410190519A CN117745989A CN 117745989 A CN117745989 A CN 117745989A CN 202410190519 A CN202410190519 A CN 202410190519A CN 117745989 A CN117745989 A CN 117745989A
- Authority
- CN
- China
- Prior art keywords
- image
- blocked
- injection path
- nerve root
- blocking target
- 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
- 230000000903 blocking effect Effects 0.000 title claims abstract description 161
- 238000002347 injection Methods 0.000 title claims abstract description 154
- 239000007924 injection Substances 0.000 title claims abstract description 154
- 210000005036 nerve Anatomy 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013439 planning Methods 0.000 title claims abstract description 36
- 230000009466 transformation Effects 0.000 claims abstract description 31
- 238000012937 correction Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 230000001537 neural effect Effects 0.000 claims description 31
- 239000013598 vector Substances 0.000 claims description 31
- 210000000988 bone and bone Anatomy 0.000 claims description 21
- 238000010146 3D printing Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000002591 computed tomography Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 210000001519 tissue Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 210000000273 spinal nerve root Anatomy 0.000 description 2
- 238000000844 transformation Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000932 sedative agent Substances 0.000 description 1
- 230000001624 sedative effect Effects 0.000 description 1
- 210000002330 subarachnoid space Anatomy 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a nerve root blocking target injection path planning method and system based on a vertebral canal structure, wherein the method comprises the following steps: acquiring a vertebra cross-sectional image of an object to be blocked, and denoising the cross-sectional image to obtain a denoised cross-sectional image; adjusting window parameters of the denoising cross-section image to obtain a window parameter optimized image, and constructing a geometric transformation model of the window parameter optimized image; registering the window parameter optimization images to obtain registered images, constructing a three-dimensional vertebral canal model of the object to be blocked, and determining an injection path of an expected nerve root blocking target point of the object to be blocked; blocking the object to be blocked, recording the blocking current path of the object to be blocked, calculating the path coincidence coefficient of the target expected nerve root blocking target injection path and the blocking current path, constructing a target error correction instruction of the object to be blocked, and executing the accurate blocking of the object to be blocked based on the target error correction instruction. The invention can improve the accuracy of automatic error correction of the positioning abnormality of the vertebral canal blocking system.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a neural root blocking target injection path planning method and system based on a vertebral canal structure.
Background
The vertebral canal blocking system is a blocking method for blocking the spinal nerve root by injecting local blocking medicine into a specific cavity gap in the vertebral canal of a human body, such as subarachnoid space or epidural space, so that the blocking effect is generated in the area dominated by the spinal nerve root, and the safety, efficiency and comfort of blocking operation can be improved by automatic error correction of abnormal positioning of the vertebral canal blocking system.
The existing automatic error correction for the positioning abnormality of the vertebral canal blocking system is mainly realized by installing a sensor on injection equipment, and the sensor is used for tracking the position and the direction of the sensor in real time to identify the deviation between the position information of the current blocking cannula and the target position information, and the method has the defect that the injection deviation is too large to correct in time easily due to the fact that a guiding route is not arranged in the blocking injection process due to the complexity of the vertebral canal structure, so that the automatic error correction for the positioning abnormality of the blocking system is not accurate enough.
Disclosure of Invention
The invention provides a neural root blocking target injection path planning method and system based on a vertebral canal structure, and mainly aims to improve the accuracy of automatic error correction of positioning abnormality of a vertebral canal blocking system.
In order to achieve the above object, the present invention provides a neural root blocking target injection path planning method based on a spinal canal structure, including:
acquiring a vertebra cross-sectional image of an object to be blocked, and denoising the vertebra cross-sectional image to obtain a vertebra denoising cross-sectional image;
adjusting window parameters of the vertebra denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
constructing a nerve root blocking target point of the three-dimensional vertebral canal model, determining a nerve root blocking target point coordinate of an object to be blocked based on the nerve root blocking target point, and determining an expected nerve root blocking target point injection path of the object to be blocked based on the nerve root blocking target point, the nerve root blocking target point coordinate and the vertebral canal characteristics;
Based on the expected nerve root blocking target injection path, performing simulated target injection on a 3D printing model of an object to be blocked, recording a current simulated target injection path of the 3D printing model of the object to be blocked, calculating a path coincidence coefficient of the current simulated target injection path and the expected nerve root blocking target injection path, and constructing a target error correction instruction based on the path coincidence coefficient to ensure that the error of the current simulated target injection path and the expected nerve root blocking target injection path is zero.
Optionally, the acquiring a cross-sectional image of the spine of the object to be retarded includes:
determining a scanning constraint condition of an object to be blocked based on a CT monitoring environment;
constraining the object to be blocked based on the scanning constraint condition to obtain a constrained object to be blocked;
adjusting equipment parameters of CT scanning equipment corresponding to the CT monitoring environment;
and acquiring cross-sectional images of the object to be blocked by using the CT scanning equipment based on the equipment parameters.
Optionally, denoising the spine cross-sectional image to obtain a spine denoising cross-sectional image, including:
marking neighborhood pixel points of the image pixel points corresponding to the spine cross-section image;
Calculating the space weight of the neighborhood pixel points;
calculating the value range weights of the image pixel points and the neighborhood pixel points;
identifying a target pixel value of the neighborhood pixel point based on the spatial weight and the value range weight;
and denoising the cross-sectional image of the vertebra based on the target pixel value to obtain a denoising cross-sectional image of the vertebra.
Optionally, the calculating the spatial weight of the neighborhood pixel includes:
constructing an exponential function of the neighborhood pixel points;
based on the exponential function, the spatial weight of the neighborhood pixel point is calculated by using the following formula:
wherein,(P, Q) represents the spatial weight of the neighborhood pixel, a represents the Euclidean distance between the neighborhood pixel corresponding to the image pixel P and the neighborhood pixel Q,/and>representing an exponential function, exp represents an exponential operation.
Optionally, the extracting the image feature points of the window parameter optimization image includes:
performing scale division on the window parameter optimization image to obtain a multi-scale image;
identifying extreme points of the multi-scale image;
positioning initial feature points of the multi-scale image based on the extreme points;
calculating local feature descriptors of the initial feature points;
And screening the image feature points in the initial feature points based on the local feature descriptors.
Optionally, the matching the image feature points to obtain matching feature points includes:
identifying feature descriptor vectors of the local feature descriptors corresponding to the image feature points;
calculating a distance metric of the feature descriptor vector;
and matching the image feature points based on the distance measurement to obtain matching feature points.
Optionally, the calculating the distance measure of the feature descriptor sub-vector includes:
calculating a distance metric of the feature descriptor sub-vector using the formula:
wherein,distance metric, k1[ i ] representing feature descriptor sub-vector k1 and feature descriptor sub-vector k2]Feature descriptor vectors k1, k2[ i ] representing the ith dimension]The feature descriptor sub-vector k2 representing the i-th dimension, sum represents the sum of the squares of the feature descriptor sub-vector differences for each dimension.
Optionally, the constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image includes:
extracting a bone structure of an object to be blocked based on the registration image;
registering the bone structure with a preset standard bone structure to obtain a registered bone structure;
Extracting a spinal canal region in the registered bone structure;
and carrying out three-dimensional reconstruction on the vertebral canal area to obtain a three-dimensional vertebral canal model of the object to be blocked.
Optionally, the determining the injection path of the desired nerve root blocking target of the object to be blocked based on the nerve root blocking target, the nerve root blocking target coordinates and the spinal canal feature includes:
marking a feasible target injection path of the object to be blocked based on the nerve root blocking target and the nerve root blocking target coordinates;
identifying an influence coefficient of the spinal canal feature on the feasible target injection path;
calculating path feasible weights of the feasible target injection paths based on the influence coefficients;
and determining an injection path of a desired nerve root blocking target of the object to be blocked based on the path feasible weight.
In order to solve the above problems, the present invention further provides a nerve root blocking target injection path planning system based on a spinal canal structure, the system comprising:
the image acquisition module of the object to be blocked is used for acquiring a cross-sectional image of the vertebra of the object to be blocked, denoising the cross-sectional image of the vertebra, and obtaining a denoising cross-sectional image of the vertebra;
The image registration analysis module is used for adjusting window parameters of the spine denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
the vertebral canal model construction module is used for registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
the nerve root blocking target injection path determining module is used for constructing a nerve root blocking target of the three-dimensional vertebral canal model, determining the coordinate of the nerve root blocking target of the object to be blocked based on the nerve root blocking target, and determining the expected nerve root blocking target injection path of the object to be blocked based on the nerve root blocking target, the coordinate of the nerve root blocking target and the vertebral canal characteristics;
the nerve root blocking target point injection path error correction module is used for carrying out simulated target point injection on the basis of the expected nerve root blocking target point injection path, recording the current simulated target point injection path of the 3D printing model of the object to be blocked, calculating the path coincidence coefficient of the current simulated target point injection path and the expected nerve root blocking target point injection path, and constructing a target point error correction instruction on the basis of the path coincidence coefficient to ensure that the error of the current simulated target point injection path and the expected nerve root blocking target point injection path is zero.
The cross-sectional images of the object to be blocked acquired based on the CT monitoring environment can be processed through a preset sequence and angles so as to better display each part of the vertebral canal; optionally, in the embodiment of the invention, the cross-sectional image is denoised to obtain a denoised cross-sectional image so as to display the tissue structure more clearly; the embodiment of the invention can be used in computer vision applications such as image matching, target recognition, image retrieval and the like by extracting the image characteristic points of the window parameter optimization image, and further, the embodiment of the invention can provide a data basis for image matching in the later stage by matching the image characteristic points to obtain the matching characteristic points; further, the embodiment of the invention registers the window parameter optimization image based on the geometric transformation model to obtain a registration image, which can ensure consistency of image space, and provide a data basis for modeling of later-stage images. Therefore, the neural root blocking target injection path planning method and system based on the vertebral canal structure can improve the accuracy of automatic error correction of the positioning abnormality of the vertebral canal blocking system.
Drawings
Fig. 1 is a schematic flow chart of a neural root block target injection path planning method based on a spinal canal structure according to an embodiment of the present invention;
fig. 2 is a functional block diagram of a neural root-blocking target injection path planning system based on a spinal canal structure according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device of a neural root-blocking target injection path planning system based on a spinal canal structure according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a nerve root blocking target injection path planning method based on a vertebral canal structure. The main execution body of the neural root blocking target injection path planning method based on the vertebral canal structure comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the neural root blocking target injection path planning method based on the spinal canal architecture can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a neural root blocking target injection path planning method based on a spinal canal structure according to an embodiment of the invention is shown. In this embodiment, the neural root blocking target injection path planning method based on the spinal canal structure includes:
s1, acquiring a cross-sectional image of a vertebra of an object to be blocked, and denoising the cross-sectional image of the vertebra to obtain a denoising cross-sectional image of the vertebra.
In the embodiment of the present invention, the CT monitoring environment refers to an environment for performing CT detection on the object to be blocked, for example, an environment such as a CT scanning device and a CT scanning environment.
Further, the embodiment of the invention acquires the cross-sectional images of the spine of the object to be retarded based on the CT monitoring environment through special sequences and angles so as to better display various parts of the spinal canal. Wherein the spinal cross-sectional image refers to a plurality of cross-sectional images acquired using an X-ray generator and detector of a CT scanner rotated about an object to be blocked.
As an embodiment of the present invention, the acquiring the cross-sectional image of the object to be blocked based on the CT monitoring environment includes: determining scanning constraint conditions of the object to be blocked based on the CT monitoring environment; constraining the object to be blocked based on the scanning constraint condition to obtain a constrained object to be blocked; adjusting equipment parameters of CT scanning equipment corresponding to the CT monitoring environment; and acquiring cross-sectional images of the object to be blocked by using the CT scanning equipment based on the equipment parameters.
Wherein the scanning constraint condition refers to a condition of performing CT scanning on the object to be blocked, for example, a constraint condition that sedative or blocking is needed when removing a metal object on the object, a child or an object to be blocked which cannot be kept still, the constraint object to be blocked refers to an object to be blocked which accords with the scanning constraint condition, and the equipment parameter refers to a parameter related to performing CT scanning on the object to be blocked, for example, a parameter such as a scanning range, a layer thickness, a reconstruction interval, and the like.
Optionally, the embodiment of the invention obtains the denoised spine cross-sectional image by denoising the spine cross-sectional image so as to more clearly display the tissue structure. The denoising spine cross-sectional image refers to an image obtained by removing noise from the spine cross-sectional image.
Optionally, as an embodiment of the present invention, the denoising the spine cross-sectional image to obtain a spine denoising cross-sectional image includes: marking neighborhood pixel points of the image pixel points corresponding to the spine cross-section image; calculating the space weight of the neighborhood pixel points; calculating the value range weights of the image pixel points and the neighborhood pixel points; identifying a target pixel value of the neighborhood pixel point based on the spatial weight and the value range weight; and denoising the cross-sectional image of the vertebra based on the target pixel value to obtain a denoising cross-sectional image of the vertebra.
The neighborhood pixel points are set with the image pixel points as the center and all adjacent pixel points in a preset range, the space weight refers to the influence degree of the neighborhood pixel points on other pixel points in an image processing algorithm, and the value range weight refers to the weight for determining the relation between the neighborhood pixel points according to the numerical value (such as gray value or color value) of the pixel points in the image processing. The value range weights may measure the similarity or difference between pixel points based on their intensity, color, or other attributes.
Optionally, as an optional embodiment of the present invention, the calculating the spatial weight of the neighborhood pixel includes: constructing an exponential function of the neighborhood pixel points; based on the exponential function, the spatial weight of the neighborhood pixel point is calculated by using the following formula:
wherein,(P, Q) represents the spatial weight of the neighborhood pixel, a represents the Euclidean distance between the neighborhood pixel corresponding to the image pixel P and the neighborhood pixel Q,/and>representing an exponential function, exp represents an exponential operation.
S2, adjusting window parameters of the vertebra denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points.
According to the embodiment of the invention, the window parameters of the denoising cross-section image are adjusted to obtain the window parameter optimized image, so that different tissues in the image are distinct in hierarchy and easy to identify. Wherein, the window parameters refer to window width and window level of the vertebra denoising cross-section image.
Optionally, the embodiment of the invention can be used in computer vision applications such as image matching, target recognition, image retrieval and the like by extracting the image characteristic points of the window parameter optimization image. Wherein, the image characteristic points refer to points with significant changes in the image.
Optionally, as an embodiment of the present invention, the extracting the image feature point of the window parameter optimization image includes: performing scale division on the window parameter optimization image to obtain a multi-scale image; identifying extreme points of the multi-scale image; positioning initial feature points of the multi-scale image based on the extreme points; calculating local feature descriptors of the initial feature points; and screening the image feature points in the initial feature points based on the local feature descriptors.
Wherein the multi-scale image refers to applying a gaussian filter to the window parameter optimized image to generate a series of images with different scales, the extreme points refer to regions with significant changes in the image, such as edges, corner points, etc., and the local feature descriptors refer to feature vectors used in computer vision to describe local regions in the image. The method is used for representing image information around key points, has scale invariance and robustness, and can be used for tasks such as image matching, target recognition, image retrieval and the like.
Furthermore, the embodiment of the invention can provide a data basis for image matching in the later stage by matching the image characteristic points to obtain the matching characteristic points. The matching feature points refer to feature points after the image feature points are matched one by one.
Further, as an embodiment of the present invention, the matching the image feature points to obtain matching feature points includes: identifying feature descriptor vectors of the local feature descriptors corresponding to the image feature points; calculating a distance metric of the feature descriptor vector; and matching the image feature points based on the distance measurement to obtain matching feature points.
Wherein the feature descriptor vector refers to a numerical vector for describing an image or a local area in the image. It is generated by counting and encoding image information of an area around a key point, and the distance measure refers to a method for measuring the degree of similarity or difference between two vectors.
Optionally, as an optional embodiment of the present invention, the calculating a distance metric of the feature descriptor sub-vector includes: calculating a distance metric of the feature descriptor sub-vector using the formula:
Wherein,distance metric, k1[ i ] representing feature descriptor sub-vector k1 and feature descriptor sub-vector k2]Feature descriptor vectors k1, k2[ i ] representing the ith dimension]The feature descriptor sub-vector k2 representing the i-th dimension, sum represents the sum of the squares of the feature descriptor sub-vector differences for each dimension.
In the embodiment of the invention, the geometric transformation model refers to a model which performs geometric transformation on an image to be transformed so as to realize the aims of alignment, splicing or correction of the image. Wherein the geometric transformation model may initialize an initial geometric transformation model, such as an affine transformation model or a perspective transformation model, by matching feature points. Some specific pairs of feature points may be selected for the estimation of the initial model, e.g. three non-collinear point pairs for the estimation of affine transformations, or four non-coplanar point pairs for the estimation of perspective transformations, the parameters of the geometric transformation model are optimized using an optimization algorithm (e.g. RANSAC, least squares, etc.) to fit most all matching pairs of feature points. In the optimization process, a group of interior points are selected to calculate errors, and model parameters are updated until a certain iteration number or convergence condition is reached.
And S3, registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model.
According to the embodiment of the invention, the window parameter optimization images are registered based on the geometric transformation model, and the consistency of image space can be ensured by obtaining the registered images, so that a data basis is provided for modeling of the images in the later stage. The registration image refers to an image after alignment, stitching or correction of the image is achieved. In detail, the registering of the window parameter optimized image involves establishing a pixel-level correspondence using the geometric transformation model, and adjusting an intensity distribution of the image for registration using an optimization algorithm (e.g., nearest neighbor interpolation, bilinear interpolation, etc.).
Further, the embodiment of the invention constructs the three-dimensional vertebral canal model of the object to be blocked based on the registration image, so that the vertebral canal structure of the object to be blocked can be recognized more intuitively. The three-dimensional vertebral canal model refers to a three-dimensional structure model of the vertebral canal of the object to be blocked.
As an embodiment of the present invention, the constructing the three-dimensional vertebral canal model of the object to be blocked based on the registration image includes: extracting a bone structure of the object to be blocked based on the registration image; registering the bone structure with a preset standard bone structure to obtain a registered bone structure; extracting a spinal canal region in the registered bone structure; and carrying out three-dimensional reconstruction on the vertebral canal area to obtain a three-dimensional vertebral canal model of the object to be blocked.
Wherein the bone structure refers to the structure of the bone of the object to be blocked, such as vertebrae, vertebral canal and the like, the registering bone structure refers to the bone after the alignment and matching of the bone structure, and the registering method can use rigid body transformation based on characteristic point matching or more complex non-rigid body transformation method, and the vertebral canal region refers to the region related to the vertebral canal of the object to be blocked.
Optionally, as an optional embodiment of the present invention, the three-dimensional reconstruction is performed on the vertebral canal area, so that the three-dimensional vertebral canal model of the object to be blocked may be obtained by converting the two-dimensional image data into the three-dimensional vertebral canal model through a three-dimensional reconstruction algorithm (such as voxelization, curved surface reconstruction, etc.).
In the embodiment of the present invention, the characteristic of the vertebral canal refers to the characteristic attribute of the vertebral canal of the object to be blocked, such as the characteristic attribute of curvature, bone thickness, etc.
S4, constructing a nerve root blocking target point of the three-dimensional vertebral canal model, determining a nerve root blocking target point coordinate of an object to be blocked based on the nerve root blocking target point, and determining an expected nerve root blocking target point injection path of the object to be blocked based on the nerve root blocking target point, the nerve root blocking target point coordinate and the vertebral canal characteristics.
In the embodiment of the invention, the nerve root blocking target point refers to coordinates in a three-dimensional space. The nerve root blocking target point coordinates refer to position coordinates of the object to be blocked, which is required to be blocked.
Optionally, the embodiment of the invention determines the injection path of the expected nerve root blocking target point of the object to be blocked based on the nerve root blocking target point and the nerve root blocking target point coordinate, and can provide an accurate route for blocking injection in the later stage, thereby improving the blocking control of the object to be blocked. The injection path of the desired nerve root blocking target point refers to an ideal injection path for blocking injection of the object to be blocked.
Further, as an optional embodiment of the present invention, the determining the desired nerve root blocking target injection path of the object to be blocked based on the nerve root blocking target, the nerve root blocking target coordinates, and the spinal canal feature includes: marking a feasible target injection path of the object to be blocked based on the nerve root blocking target and the nerve root blocking target coordinates; identifying an influence coefficient of the spinal canal feature on the feasible target injection path; calculating path feasible weights of the feasible target injection paths based on the influence coefficients; and determining an injection path of a desired nerve root blocking target of the object to be blocked based on the path feasible weight.
The feasible target injection path refers to a target injection path capable of blocking the object to be blocked, the influence coefficient refers to the influence degree of the vertebral canal feature on the feasible target injection path, and the path feasible weight refers to the executable degree of the feasible target injection path.
S5, performing simulated target point injection on the 3D printing model of the object to be blocked based on the expected nerve root blocking target point injection path, recording the current simulated target point injection path of the 3D printing model of the object to be blocked, calculating the path coincidence coefficient of the current simulated target point injection path and the expected nerve root blocking target point injection path, and constructing a target point error correction instruction based on the path coincidence coefficient to ensure that the error of the current simulated target point injection path and the expected nerve root blocking target point injection path is zero.
According to the embodiment of the invention, based on the injection path of the target point of the expected nerve root blocking, the 3D printing model of the object to be blocked is blocked, and the current simulation target point injection path of the 3D printing model of the object to be blocked is recorded so as to observe the blocking path in real time and timely identify the abnormality. The current simulation target injection path refers to a path state recorded in real time in a blocking process of the 3D printing model of the object to be blocked. Recording the current simulated target injection path of the 3D printing model of the object to be blocked can detect the blocking path in real time by installing a sensor on blocking equipment.
Optionally, the embodiment of the invention can identify whether the current simulated target injection path accords with the guiding route by calculating the path superposition coefficient of the expected nerve root blocking target injection path and the current simulated target injection path, thereby providing basis for performing path error correction in later stage. The path coincidence coefficient refers to the path coincidence degree of the injection path of the expected nerve root blocking target and the injection path of the current simulation target. The path overlap coefficient may be identified by path overlapping the desired nerve root blocking target injection path with the current simulated target injection path.
In the embodiment of the invention, the target point error correction instruction refers to an instruction for enabling the current simulated target point injection path to be overlapped with the expected nerve root blocking target point injection path, such as an instruction for adjusting the cannula position, the cannula depth and the like.
Further, according to the embodiment of the invention, the accurate blocking of the object to be blocked can be effectively controlled based on the target error correction instruction.
The embodiment of the invention acquires the spine cross-section image of the object to be blocked based on the CT monitoring environment, and can better display each part of the vertebral canal through a special sequence and angle; optionally, in the embodiment of the invention, the cross-sectional image of the vertebra is denoised to obtain the cross-sectional image of the vertebra denoised so as to display the tissue structure more clearly; the embodiment of the invention can be used in computer vision applications such as image matching, target recognition, image retrieval and the like by extracting the image characteristic points of the window parameter optimization image, and further, the embodiment of the invention can provide a data basis for image matching in the later stage by matching the image characteristic points to obtain the matching characteristic points; further, the embodiment of the invention registers the window parameter optimization image based on the geometric transformation model to obtain a registration image, which can ensure consistency of image space, and provide a data basis for modeling of later-stage images. Therefore, the neural root blocking target injection path planning method based on the vertebral canal structure can improve the accuracy of automatic error correction of the positioning abnormality of the vertebral canal blocking system.
Fig. 2 is a functional block diagram of a neural root-blocking target injection path planning system based on a spinal canal structure according to an embodiment of the present invention.
The nerve root blocking target injection path planning system 200 based on the spinal canal structure of the present invention may be installed in an electronic device. Depending on the implementation function, the neural root blocking target injection path planning system 200 based on the spinal canal structure may include an object to be blocked image acquisition module 201, an image registration analysis module 202, a spinal canal model construction module 203, a neural root blocking target injection path determination module 204, and a neural root blocking target injection path correction module 205. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the image acquisition module 201 for an object to be blocked is configured to acquire a cross-sectional image of a vertebra of the object to be blocked, and denoise the cross-sectional image of the vertebra to obtain a denoised cross-sectional image of the vertebra;
the image registration analysis module 202 is configured to adjust a window parameter of the vertebra denoising cross-section image to obtain a window parameter optimized image, extract image feature points of the window parameter optimized image, match the image feature points to obtain matching feature points, and construct a geometric transformation model of the window parameter optimized image based on the matching feature points;
The vertebral canal model construction module 203 is configured to register the window parameter optimization image based on the geometric transformation model to obtain a registration image, construct a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identify a vertebral canal feature of the object to be blocked based on the three-dimensional vertebral canal model;
the nerve root blocking target injection path determining module 204 is configured to construct a nerve root blocking target of the three-dimensional spinal canal model, determine a nerve root blocking target coordinate of an object to be blocked based on the nerve root blocking target, and determine an expected nerve root blocking target injection path of the object to be blocked based on the nerve root blocking target, the nerve root blocking target coordinate and the spinal canal feature;
the nerve root blocking target injection path correction module 205 is configured to perform simulated target injection on the basis of the desired nerve root blocking target injection path, perform simulated target injection on a 3D printing model of the object to be blocked, record a current simulated target injection path of the 3D printing model of the object to be blocked, calculate a path coincidence coefficient of the current simulated target injection path and the desired nerve root blocking target injection path, and construct a target correction instruction based on the path coincidence coefficient, so as to ensure that an error between the current simulated target injection path and the desired nerve root blocking target injection path is zero.
In detail, each module in the neural root blocking target injection path planning system 200 based on the spinal canal structure in the embodiment of the present invention adopts the same technical means as the neural root blocking target injection path planning method based on the spinal canal structure in the drawings, and can produce the same technical effects, which are not described herein.
The embodiment of the invention provides electronic equipment for realizing a nerve root blocking target injection path planning method based on a vertebral canal structure.
Referring to fig. 3, the electronic device may include a processor 30, a memory 31, a communication bus 32, and a communication interface 33, and may further include a computer program stored in the memory 31 and executable on the processor 30, such as a nerve root blocking target injection path planning method program based on spinal canal architecture.
The processor may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing Unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and the like. The processor is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory (e.g., executing a nerve root blocking target injection path planning program based on a spinal canal structure, etc.), and calling data stored in the memory.
The memory includes at least one type of readable storage medium including flash memory, removable hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory may also include both internal storage units and external storage devices of the electronic device. The memory can be used for storing application software installed in the electronic equipment and various data, such as codes based on nerve root blocking target injection path planning programs based on spinal canal construction, and the like, and can be used for temporarily storing data which are output or are to be output.
The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory and at least one processor or the like.
The communication interface is used for communication between the electronic equipment and other equipment, and comprises a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
For example, although not shown, the electronic device may further include a power source (such as a battery) for powering the respective components, and preferably, the power source may be logically connected to the at least one processor through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The neural root-blocking target injection path planning program stored by the memory in the electronic device and based on the spinal canal architecture is a combination of a plurality of instructions, and when running in the processor, the neural root-blocking target injection path planning program can realize:
acquiring a vertebra cross-sectional image of an object to be blocked, and denoising the vertebra cross-sectional image to obtain a vertebra denoising cross-sectional image;
adjusting window parameters of the vertebra denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
constructing a nerve root blocking target point of the three-dimensional vertebral canal model, determining a nerve root blocking target point coordinate of an object to be blocked based on the nerve root blocking target point, and determining an expected nerve root blocking target point injection path of the object to be blocked based on the nerve root blocking target point, the nerve root blocking target point coordinate and the vertebral canal characteristics;
Based on the expected nerve root blocking target injection path, performing simulated target injection on a 3D printing model of an object to be blocked, recording a current simulated target injection path of the 3D printing model of the object to be blocked, calculating a path coincidence coefficient of the current simulated target injection path and the expected nerve root blocking target injection path, and constructing a target error correction instruction based on the path coincidence coefficient to ensure that the error of the current simulated target injection path and the expected nerve root blocking target injection path is zero.
Specifically, the specific implementation method of the above instruction by the processor may refer to descriptions of related steps in the corresponding embodiment of the drawings, which are not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring a vertebra cross-sectional image of an object to be blocked, and denoising the vertebra cross-sectional image to obtain a vertebra denoising cross-sectional image;
adjusting window parameters of the vertebra denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
constructing a nerve root blocking target point of the three-dimensional vertebral canal model, determining a nerve root blocking target point coordinate of an object to be blocked based on the nerve root blocking target point, and determining an expected nerve root blocking target point injection path of the object to be blocked based on the nerve root blocking target point, the nerve root blocking target point coordinate and the vertebral canal characteristics;
Based on the expected nerve root blocking target injection path, performing simulated target injection on a 3D printing model of an object to be blocked, recording a current simulated target injection path of the 3D printing model of the object to be blocked, calculating a path coincidence coefficient of the current simulated target injection path and the expected nerve root blocking target injection path, and constructing a target error correction instruction based on the path coincidence coefficient to ensure that the error of the current simulated target injection path and the expected nerve root blocking target injection path is zero.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems as set forth in the system claims may also be implemented by means of one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A neural root block target injection path planning method based on a spinal canal structure, which is characterized by comprising the following steps:
acquiring a vertebra cross-sectional image of an object to be blocked, and denoising the vertebra cross-sectional image to obtain a vertebra denoising cross-sectional image;
adjusting window parameters of the vertebra denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
Registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
constructing a nerve root blocking target point of the three-dimensional vertebral canal model, determining a nerve root blocking target point coordinate of an object to be blocked based on the nerve root blocking target point, and determining an expected nerve root blocking target point injection path of the object to be blocked based on the nerve root blocking target point, the nerve root blocking target point coordinate and the vertebral canal characteristics;
based on the expected nerve root blocking target injection path, performing simulated target injection on a 3D printing model of an object to be blocked, recording a current simulated target injection path of the 3D printing model of the object to be blocked, calculating a path coincidence coefficient of the current simulated target injection path and the expected nerve root blocking target injection path, and constructing a target error correction instruction based on the path coincidence coefficient to ensure that the error of the current simulated target injection path and the expected nerve root blocking target injection path is zero.
2. The neural root-blocking target injection path planning method based on spinal canal architecture of claim 1, wherein the acquiring a spinal cross-sectional image of the object to be blocked comprises:
Determining a scanning constraint condition of an object to be blocked based on a CT monitoring environment;
constraining the object to be blocked based on the scanning constraint condition to obtain a constrained object to be blocked;
adjusting equipment parameters of CT scanning equipment corresponding to the CT monitoring environment;
and acquiring cross-sectional images of the object to be blocked by using the CT scanning equipment based on the equipment parameters.
3. The spinal canal architecture-based nerve root block target injection path planning method according to claim 1, wherein denoising the spinal cross-sectional image to obtain a spinal denoising cross-sectional image comprises:
marking neighborhood pixel points of the image pixel points corresponding to the spine cross-section image;
calculating the space weight of the neighborhood pixel points;
calculating the value range weights of the image pixel points and the neighborhood pixel points;
identifying a target pixel value of the neighborhood pixel point based on the spatial weight and the value range weight;
and denoising the cross-sectional image of the vertebra based on the target pixel value to obtain a denoising cross-sectional image of the vertebra.
4. The neural root-blocking target injection path planning method based on spinal canal architecture of claim 3, wherein the calculating the spatial weight of the neighborhood pixel comprises:
Constructing an exponential function of the neighborhood pixel points;
based on the exponential function, the spatial weight of the neighborhood pixel point is calculated by using the following formula:
；
wherein,(P, Q) represents the spatial weight of the neighborhood pixel, a represents the Euclidean distance between the neighborhood pixel corresponding to the image pixel P and the neighborhood pixel Q,/and>representing an exponential function, exp represents an exponential operation.
5. The neural root-blocking target injection path planning method based on spinal canal architecture of claim 1, wherein the extracting the image feature points of the window parameter optimization image comprises:
performing scale division on the window parameter optimization image to obtain a multi-scale image;
identifying extreme points of the multi-scale image;
positioning initial feature points of the multi-scale image based on the extreme points;
calculating local feature descriptors of the initial feature points;
and screening the image feature points in the initial feature points based on the local feature descriptors.
6. The neural root block target injection path planning method based on the spinal canal structure according to claim 1, wherein the matching the image feature points to obtain matching feature points comprises:
Identifying feature descriptor vectors of the local feature descriptors corresponding to the image feature points;
calculating a distance metric of the feature descriptor vector;
and matching the image feature points based on the distance measurement to obtain matching feature points.
7. The neural root-block target injection path planning method of claim 6, wherein the computing the distance metric of the feature descriptor vector comprises:
calculating a distance metric of the feature descriptor sub-vector using the formula:
；
wherein,distance metric, k1[ i ] representing feature descriptor sub-vector k1 and feature descriptor sub-vector k2]Feature descriptor vectors k1, k2[ i ] representing the ith dimension]The feature descriptor sub-vector k2 representing the i-th dimension, sum represents the sum of the squares of the feature descriptor sub-vector differences for each dimension.
8. The neural root-blocking target injection path planning method based on spinal canal architecture of claim 1, wherein constructing a three-dimensional spinal canal model of an object to be blocked based on the registered image comprises:
extracting a bone structure of an object to be blocked based on the registration image;
registering the bone structure with a preset standard bone structure to obtain a registered bone structure;
Extracting a spinal canal region in the registered bone structure;
and carrying out three-dimensional reconstruction on the vertebral canal area to obtain a three-dimensional vertebral canal model of the object to be blocked.
9. The neural root-blocking target injection path planning method based on spinal canal architecture of claim 1, wherein the determining a desired neural root-blocking target injection path for a subject to be blocked based on the neural root-blocking target, the neural root-blocking target coordinates, and the spinal canal features comprises:
marking a feasible target injection path of the object to be blocked based on the nerve root blocking target and the nerve root blocking target coordinates;
identifying an influence coefficient of the spinal canal feature on the feasible target injection path;
calculating path feasible weights of the feasible target injection paths based on the influence coefficients;
and determining an injection path of a desired nerve root blocking target of the object to be blocked based on the path feasible weight.
10. A spinal canal architecture-based nerve root blocking target injection path planning system for performing the spinal canal architecture-based nerve root blocking target injection path planning method of any one of claims 1-9, the system comprising:
The image acquisition module of the object to be blocked is used for acquiring a cross-sectional image of the vertebra of the object to be blocked, denoising the cross-sectional image of the vertebra, and obtaining a denoising cross-sectional image of the vertebra;
the image registration analysis module is used for adjusting window parameters of the spine denoising cross-section image to obtain a window parameter optimized image, extracting image feature points of the window parameter optimized image, matching the image feature points to obtain matching feature points, and constructing a geometric transformation model of the window parameter optimized image based on the matching feature points;
the vertebral canal model construction module is used for registering the window parameter optimization image based on the geometric transformation model to obtain a registration image, constructing a three-dimensional vertebral canal model of the object to be blocked based on the registration image, and identifying the vertebral canal characteristics of the object to be blocked based on the three-dimensional vertebral canal model;
the nerve root blocking target injection path determining module is used for constructing a nerve root blocking target of the three-dimensional vertebral canal model, determining the coordinate of the nerve root blocking target of the object to be blocked based on the nerve root blocking target, and determining the expected nerve root blocking target injection path of the object to be blocked based on the nerve root blocking target, the coordinate of the nerve root blocking target and the vertebral canal characteristics;
The nerve root blocking target point injection path error correction module is used for carrying out simulated target point injection on the basis of the expected nerve root blocking target point injection path, recording the current simulated target point injection path of the 3D printing model of the object to be blocked, calculating the path coincidence coefficient of the current simulated target point injection path and the expected nerve root blocking target point injection path, and constructing a target point error correction instruction on the basis of the path coincidence coefficient to ensure that the error of the current simulated target point injection path and the expected nerve root blocking target point injection path is zero.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190519.4A CN117745989B (en) | 2024-02-21 | Nerve root blocking target injection path planning method and system based on vertebral canal structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190519.4A CN117745989B (en) | 2024-02-21 | Nerve root blocking target injection path planning method and system based on vertebral canal structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117745989A true CN117745989A (en) | 2024-03-22 |
| CN117745989B CN117745989B (en) | 2024-05-14 |
Family
ID=
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108784839A (en) * | 2018-06-20 | 2018-11-13 | 王�忠 | A kind of auxiliary robot device of peripheral blockade and intraspinal tube nerve block |
| CN111132626A (en) * | 2017-07-17 | 2020-05-08 | 沃雅戈治疗公司 | Trajectory array guidance system |
| US20210161612A1 (en) * | 2019-12-03 | 2021-06-03 | Mediview Xr, Inc. | Holographic augmented reality ultrasound needle guide for insertion for percutaneous surgical procedures |
| CN115252075A (en) * | 2022-07-22 | 2022-11-01 | 上海卓昕医疗科技有限公司 | Real-time navigation system and method |
| CN116531089A (en) * | 2023-07-06 | 2023-08-04 | 中国人民解放军中部战区总医院 | Image-enhancement-based blocking anesthesia ultrasonic guidance data processing method |
| CN117413060A (en) * | 2021-08-02 | 2024-01-16 | 海思智财控股有限公司 | Augmented reality system for real space navigation and surgical system using the same |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111132626A (en) * | 2017-07-17 | 2020-05-08 | 沃雅戈治疗公司 | Trajectory array guidance system |
| CN108784839A (en) * | 2018-06-20 | 2018-11-13 | 王�忠 | A kind of auxiliary robot device of peripheral blockade and intraspinal tube nerve block |
| US20210161612A1 (en) * | 2019-12-03 | 2021-06-03 | Mediview Xr, Inc. | Holographic augmented reality ultrasound needle guide for insertion for percutaneous surgical procedures |
| CN117413060A (en) * | 2021-08-02 | 2024-01-16 | 海思智财控股有限公司 | Augmented reality system for real space navigation and surgical system using the same |
| CN115252075A (en) * | 2022-07-22 | 2022-11-01 | 上海卓昕医疗科技有限公司 | Real-time navigation system and method |
| CN116531089A (en) * | 2023-07-06 | 2023-08-04 | 中国人民解放军中部战区总医院 | Image-enhancement-based blocking anesthesia ultrasonic guidance data processing method |
Non-Patent Citations (3)
| Title |
|---|
| TANG, WW 等: "A 3D multi-modal intelligent intervention system using electromagnetic navigation for real-time positioning and ultrasound images: a prospective randomized controlled trial", ANNALS OF TRANSLATIONAL MEDICINE, 13 June 2022 (2022-06-13) * |
| 袁嫕 等: "B型超声辅助定位L5-S1间隙用于老年髋部骨折患者椎管内麻醉", 中华骨与关节外科杂志, 15 November 2023 (2023-11-15) * |
| 钟家雷: "超声引导下骶孔精准穿刺技术及数字化三维模型构建在骶神经调控术中的应用研究", 中国博士学位论文全文数据库 医药卫生科技辑, 15 September 2023 (2023-09-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20110085716A1 (en) | System and method for verifying registration accuracy in digital medical images | |
| US20120027277A1 (en) | Interactive iterative closest point algorithm for organ segmentation | |
| CN112382359B (en) | Patient registration method and device, electronic equipment and computer readable medium | |
| KR102328198B1 (en) | Method and apparatus for measuring volume of organ using artificial neural network | |
| CN108549906A (en) | Radiotherapy hooks target method for registering images and device | |
| EP4156096A1 (en) | Method, device and system for automated processing of medical images to output alerts for detected dissimilarities | |
| CN114663463A (en) | Method, system, device, electronic device and storage medium for measuring joint mobility | |
| Kamencay et al. | Improved feature point algorithm for 3D point cloud registration | |
| CN114360043B (en) | Model parameter calibration method, sight tracking method, device, medium and equipment | |
| Tang et al. | Retinal image registration based on robust non-rigid point matching method | |
| CN113782159A (en) | Medical image marking point matching method and device, electronic equipment and storage medium | |
| CN113724328A (en) | Hip joint key point detection method and system | |
| CN113822323A (en) | Brain scanning image identification processing method, device, equipment and storage medium | |
| CN111784660B (en) | Method and system for analyzing frontal face degree of face image | |
| CN111553969B (en) | Texture mapping method, medium, terminal and device based on gradient domain | |
| CN112258647A (en) | Map reconstruction method and device, computer readable medium and electronic device | |
| CN117745989B (en) | Nerve root blocking target injection path planning method and system based on vertebral canal structure | |
| CN113610746A (en) | Image processing method and device, computer equipment and storage medium | |
| Belhaoua et al. | Accuracy analysis of an augmented reality system | |
| CN116439691A (en) | Joint activity detection method based on artificial intelligence and related equipment | |
| CN116797545A (en) | Scoliosis detection method, computer equipment and storage medium | |
| CN117745989A (en) | Nerve root blocking target injection path planning method and system based on vertebral canal structure | |
| CN116258752A (en) | Registration method, registration apparatus, electronic device, and computer-readable storage medium | |
| CN112365959A (en) | Method and device for modifying annotation of three-dimensional image | |
| CN111223139A (en) | Target positioning method and terminal equipment |
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 |