CN112509022A - Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image - Google Patents
Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image Download PDFInfo
- Publication number
- CN112509022A CN112509022A CN202011490366.3A CN202011490366A CN112509022A CN 112509022 A CN112509022 A CN 112509022A CN 202011490366 A CN202011490366 A CN 202011490366A CN 112509022 A CN112509022 A CN 112509022A
- Authority
- CN
- China
- Prior art keywords
- image
- ray
- contour
- drr
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 210000003484 anatomy Anatomy 0.000 claims abstract description 3
- 230000001419 dependent effect Effects 0.000 claims abstract description 3
- 238000012545 processing Methods 0.000 claims abstract description 3
- 238000005070 sampling Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 210000000988 bone and bone Anatomy 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000000205 computational method Methods 0.000 claims 1
- 238000005094 computer simulation Methods 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000009877 rendering Methods 0.000 abstract 1
- 210000000689 upper leg Anatomy 0.000 description 4
- 238000001356 surgical procedure Methods 0.000 description 2
- 208000008924 Femoral Fractures Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 208000020089 femoral neck fracture Diseases 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004197 pelvis Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002673 radiosurgery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/38—Registration of image sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for registering a pre-operative three-dimensional image and an intra-operative perspective image without a calibration object, which comprises the following steps: 1) establishing a simulated reality anatomy and frequency-dependent system noise model M; 2) rendering CT/MRI data to generate three-dimensional volume data, adding anatomical noise and frequency noise to a DRR image to generate more vivid image data similar to an X-ray film, and extracting a skeleton outline; 3) in an operation, an X-Ray machine acquires two X-Ray perspective images at different angles; 4) generating N DRR images according to the operation requirement to obtain a pose coordinate P of each image; 5) processing image data generated by a DRR algorithm, then selecting an interested area without a fracture part, and extracting a contour; 6) extracting the contour line of the real X-Ray according to the same method; 7) and accurately registering the preoperative three-dimensional image and the X-Ray perspective image based on the characteristics related to the contour line and the characteristic point, and outputting the accurately registered image. The method can improve the registration precision and lead the operation navigation operation to be more visual.
Description
Technical Field
The invention relates to a calibration-object-free registration method of a preoperative three-dimensional image and an intraoperative perspective image, in particular to a medical image registration method for a medical robot-assisted operation navigation process.
Background
Currently, in the navigation and positioning process of a common medical robot-assisted surgery, such as a femoral neck fracture surgery, a traditional method is to implant a calibration object on a femur or a pelvis to establish a mapping relationship between a robot coordinate system and a surgical space coordinate system, and perform surgical path planning and positioning on the basis. The method can greatly increase the accuracy of femoral fracture reduction, but also increases the risks of trauma and infection to patients.
One method is a radiosurgery method and system using image navigation of a 2D/3D image registration algorithm that uses a layered and iterative 2D/3D registration algorithm to solve for transformation parameters of the inner and outer layers. The disadvantages of this registration algorithm are lower accuracy and slower speed. The other method is an algorithm and a system for registering MRI and X-Ray images by using a DRR technology, and is characterized in that an MRI image is extracted and segmented, and a DRR is generated from the segmented image for registration.
The shape descriptor is widely applied to the existing shape matching algorithm, the relationship between the angle information and the arc length and the chord length of the contour segment represents the boundary information of the contour segment, and the distance relationship between the sampling point and the centroid point represents the region information of the contour segment, so that the shape of the contour segment can be completely and quantitatively described, the shape of the contour can be more comprehensively described, and the description capacity is remarkably improved.
The invention applies the shape descriptor method to the non-calibration object registration process of the preoperative three-dimensional image and the intraoperative perspective image, and can improve the registration precision and speed.
Disclosure of Invention
The invention provides a calibration-object-free registration method of a preoperative three-dimensional image and an intraoperative perspective image, which can be applied to a surgical operation navigation system and has the advantages of simple operation, high speed and high accuracy.
In order to achieve the above purpose, the method for registration of a preoperative three-dimensional image and an intraoperative perspective image without a calibration object comprises the following steps:
1) firstly, a real-simulated anatomical and frequency-dependent system noise (including quantum noise) model M is designed by utilizing a human body model:
2) before an operation starts, a series of three-dimensional images are obtained through CT or MRI, N DRR images are generated at intervals of preset degrees from 0 degrees in the visual angle direction of a coronal position, a sagittal position or a transverse position according to the operation requirement, and corresponding pose parameters P are obtained; where P is (θ X, θ Y, θ Z, X, Y, Z), θ X, θ Y, θ Z denote the rotation direction, and X, Y, Z denotes the translation amount in each direction in the coordinate system;
3) in the operation process, an X-Ray machine on the C-shaped arm acquires X-Ray perspective images at different angles;
4) applying a model M to the DRR image i, adding anatomical noise and frequency-related noise, performing two-dimensional Gaussian weighted normalization processing on each pixel on the perspective image, subtracting a Gaussian weighted mean value from the original gray value of each pixel, and dividing the value by the Gaussian weighted mean square error to obtain a normalized gray value of the pixel;
5) correcting the gray difference between the DRR image i and the X-Ray transmission image by adopting a linear histogram matching algorithm, selecting a region with the gray value larger than the gray average value of the projection image for histogram matching, and eliminating the influence of background pixels on a histogram;
6) performing edge detection on the DRR image i and the X-Ray by using a canny operator in OpenCV3.4.0, then respectively performing contour extraction by using findContours (), comparing the contour and the histogram similarity of the transmission images, if the two groups of images are matched, acquiring the pose parameters of the X-Ray transmission images, and entering the next step; otherwise, extracting information of the DRR image i +1, and returning to the step 4);
7) performing contour correlation and point registration to accurately register the preoperative three-dimensional image and the X-Ray perspective image, outputting the accurately registered image, and completing the non-calibration object registration of the preoperative three-dimensional image and the intraoperative perspective image;
in the step 2), N DRR images are generated at preset degrees of 1 degree or 2 degrees from 0 degrees according to the three-dimensional images provided by CT/MRI;
in the step 3), at least two X-Ray perspective images are acquired by the X-Ray machine on the C-shaped arm.
In the step 1) and the step 6), the contour matching correlation is used as a registration algorithm for similarity measurement, and a contour matching similarity evaluation method comprises the following steps:
1) shape descriptor: for a given contour segment S, sampling the pixel points thereof, as shown in fig. 3, first sampling to obtain a sampling point Pi＝(xi,yi) (i ═ 1,2, …, N), where N is the number of sampling points of the profile segment, the centroid point G of the segment is first calculated, and then the farthest distance point f is found for each sampling pointPiBy calculating the sampling point PiDistance to all other sample points, furthest distance point fPi；
Function DS(Pi) The shape descriptor for each sample point is calculated as:
in the formula: di is the normalized distance of the centroid point G of sample point Pi, normalized by the distance between Pi and fPi; α i is represented by
And
the resulting angle values, normalized by pi; cRi denotes the ratio of chord length chorLeni to arc length radLeni, and the function DS (Pi) has 3 components all in the interval [0,1]The inner dimension is unchanged; after the shape descriptor of each sampling point is obtained, each profileThe shape descriptor SD (S) of the segment S can be represented by the combination of equation (1):
in the formula, SD (S) is a 3 XN dimensional matrix;
wherein each column represents the shape descriptor D of the ith sampling point on the profile segmentS(Pi)；
Each row represents distance information, angle information and radian information of the contour segment;
template matching can be carried out after the shape descriptor of the complete contour segment is obtained;
representing the matching relation of the two contour segments through the similarity between the shape descriptors;
the shape descriptors are expressed in a matrix, the matrix correlation coefficients of the shape descriptors and the matrix correlation coefficients can reflect the degree of closeness of the relationship, and can represent the matching degree of different contour segments, and the correlation coefficients between the shape descriptors and the matrix correlation coefficients are called the matching coefficients of the contours;
2) evaluation criteria: in the contour matching process, firstly, the contours of the interested areas of the DRR image and the X-Ray image are extracted, and then the matching result is obtained according to the standards of 50% -IoU and 20% -IoU.
Preferably, a healthy bone edge contour must be taken in both the DRR image and the X-Ray image.
Further, noise such as medical anatomy and frequency is added to each generated DRR image to simulate a real X-Ray film.
Furthermore, image preprocessing is carried out on the simulated X-Ray image, including brightness and contrast improvement, so that the femur edge contour of the DRR image can be improved to be more real.
Further, a doctor or a training person with a certain medical background is required to operate the selected region of interest; selecting edge points of the outline which must be representative; matching of points we consider matching to be unsuccessful if the resulting rotation or translation matrix is too large.
Drawings
FIG. 1 is a schematic view of the present invention illustrating the digital projection reconstruction of preoperative CT or MRI images from different view angles;
FIG. 2 is a pencil beam entering a voxel in a first posterior-anterior (PA) slice of a CT data set;
FIG. 3 is a profile segment shape descriptor schematic;
FIG. 4 is a schematic flow chart of the present invention;
fig. 5 is a femoral binary image profile extracted from X-Ray and DRR pictures, respectively.
Detailed description of the preferred embodiment
The present invention will be described in detail below with reference to the drawings and examples, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1 to 5, the present invention provides a method for registration of a pre-operative three-dimensional image and an intraoperative perspective image without a calibration object, taking a femur as an example, and specifically comprises the following steps:
1) the general signal-to-noise ratio of the femoral part of the X-Ray image is obtained through experiments.
2) Before the operation is started, a series of three-dimensional images are obtained by CT or MRI, and the three-dimensional images are positioned in the view angle direction of the coronal position, the sagittal position or the transverse position according to the operation requirement; generating N DRR images at intervals of preset degrees from 0 degrees according to a three-dimensional image provided by CT or MRI, and acquiring corresponding pose parameters P as shown in figure 1; wherein the predetermined degree is preferably 1 ° or 2 °.
3) Adding noise to each image so as to extract the contour of the edge of the femur;
adding a noise function: DRRp + s ═ DRRp + scatter;
where DRRPp + s is the principal DRR with linear dispersion added (experimental measurements) and scatter is the beam scattering parameter;
a pose parameter formula: p ═ θ X, θ Y, θ Z, X, Y, Z;
in the formula, θ x, θ y, and θ z denote rotation directions, and X, Y, Z denotes translation amounts in the respective directions of the coordinate system.
4) In an operation, an X-Ray machine on a C-shaped arm acquires two X-Ray perspective images at different angles; the two perspective images are angled as perpendicularly as possible and the result is more desirable.
5) And correcting the gray difference between the DRR image i and the X-Ray transmission image by adopting a linear histogram matching algorithm, and selecting a region with the gray value larger than the gray average value of the projection image for histogram matching to eliminate the influence of background pixels on the histogram.
6) Performing edge detection on the DRR image i and the X-Ray by using a canny operator in OpenCV3.4.0, then respectively performing contour extraction by using findContours (), as shown in figures 5(a) and (b), performing contour comparison on the transmission images, and if the contour matching values of the two groups of images are greater than a given threshold value, acquiring pose parameters of the X-Ray transmission images, recording and entering the next step; otherwise, extracting information of the DRR image i +1, and returning to the step 5);
7) and (5) respectively extracting shift angular points of the two DRR images and the X-Ray image which are successfully matched in the outlines, as shown in the images (c) and (d), and performing angular point matching to obtain an angular point matching matrix.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (4)
1. A method for registering a pre-operative three-dimensional image and an intra-operative perspective image without a calibration object is characterized by comprising the following steps:
1) firstly, designing a simulated real anatomy and frequency-dependent system noise (including quantum noise) model M by utilizing a human body model;
2) before an operation is started, a series of three-dimensional images are obtained through CT or MRI, N DRR images can be generated at intervals of preset degrees from 0 degrees in the view angle direction of a coronal position, a sagittal position or a transverse position according to the operation requirement according to the three-dimensional images provided by CT or MRI, and corresponding pose parameters P are obtained: p is (θ X, θ Y, θ Z, X, Y, Z), θ X, θ Y, θ Z denote rotation directions, and X, Y, Z denotes translation amounts in each direction in the coordinate system;
3) in the operation process, an X-Ray machine on the C-shaped arm acquires X-Ray perspective images at different angles;
4) applying a model M to the DRR image i, adding anatomical noise and frequency-related noise, performing two-dimensional Gaussian weighted normalization processing on each pixel on the perspective image, subtracting a Gaussian weighted mean value from the original gray value of each pixel, and dividing the value by the Gaussian weighted mean square error to obtain a normalized gray value of the pixel;
adding a noise function: DRRp + s ═ DRRp + scatter;
5) correcting the gray difference between the DRR image i and the X-Ray transmission image by adopting a linear histogram matching algorithm, selecting a region with the gray value larger than the gray average value of the projection image for histogram matching, and eliminating the influence of background pixels on a histogram;
6) performing edge detection on the DRR image i and the X-Ray by using a canny operator in OpenCV3.4.0, then respectively performing contour extraction by using findContours (), comparing the contour and the histogram similarity of the transmission images, if the two groups of images are matched, acquiring the pose parameters of the X-Ray transmission images, and entering the next step; otherwise, extracting information of the DRR image i +1, and returning to the step 4);
7) outputting the accurately registered image to finish the non-calibration object registration of the preoperative three-dimensional image and the intraoperative perspective image;
in the step 2), N DRR images are generated at preset degrees of 1 degree or 2 degrees from 0 degrees according to the three-dimensional images provided by CT/MRI;
in the step 3), at least two X-Ray perspective images are acquired by the X-Ray machine on the C-shaped arm.
2. The method of claim 1, wherein the method comprises the steps of: there must be a computational method or model that simulates the signal-to-noise ratio of the real X-Ray picture.
3. The method of claim 1, wherein the method comprises the steps of: in the step 1) and the step 6), the contour matching correlation is used as a registration algorithm for similarity measurement, and the contour matching similarity evaluation method comprises the following steps:
1) shape descriptor: for a given contour segment S, sampling the pixel points thereof, as shown in fig. 3, first sampling to obtain a sampling point Pi＝(xi,yi) (i ═ 1,2, …, N), where N is the number of sampling points of the profile segment, the centroid point G of the segment is first calculated, and then the farthest distance point f is found for each sampling pointPiBy calculating the sampling point PiDistance to all other sample points, furthest distance point fPi；
Function DS(Pi) The shape descriptor for each sample point is calculated as:
in the formula: diIs a sampling point PiNormalized distance of centroid point G, from PiAnd fPiThe distance between them; alpha is alphaiIs shown by
And
the resulting angle values, normalized by pi; cRiRepresenting chord length chord leniAnd arc length radLeniRatio of (D), function DS(Pi)3 components are all in the interval [0,1 ]]The inner dimension is unchanged; after obtaining the shape descriptor of each sampling point, the shape descriptor SD (S) of each contour segment S can be represented by the combination of equation (1):
in the formula, SD (S) is a 3 XN dimensional matrix;
wherein each column represents the shape descriptor D of the ith sampling point on the profile segmentS(Pi)；
Each row represents distance information, angle information and radian information of the contour segment;
template matching can be carried out after the shape descriptor of the complete contour segment is obtained;
representing the matching relation of the two contour segments through the similarity between the shape descriptors;
the shape descriptors are expressed in a matrix, the matrix correlation coefficients of the shape descriptors and the matrix correlation coefficients can reflect the degree of closeness of the relationship, and can represent the matching degree of different contour segments, and the correlation coefficients between the shape descriptors and the matrix correlation coefficients are called the matching coefficients of the contours;
2) evaluation criteria: in the contour matching process, firstly, the contours of the interested areas of the DRR image and the X-Ray image are extracted, and then the matching result is obtained according to the standards of 50% -IoU and 20% -IoU.
4. The method of claim 1, wherein the method comprises the steps of: a healthy bone edge contour must be taken in the DRR image and the X-Ray image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490366.3A CN112509022A (en) | 2020-12-17 | 2020-12-17 | Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490366.3A CN112509022A (en) | 2020-12-17 | 2020-12-17 | Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112509022A true CN112509022A (en) | 2021-03-16 |
Family
ID=74972949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011490366.3A Pending CN112509022A (en) | 2020-12-17 | 2020-12-17 | Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112509022A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450396A (en) * | 2021-06-17 | 2021-09-28 | 北京理工大学 | Three-dimensional/two-dimensional image registration method and device based on bone features |
| CN113570648A (en) * | 2021-07-30 | 2021-10-29 | 武汉联影智融医疗科技有限公司 | Multi-bone image registration method, electronic device and medical navigation system |
| CN113723417A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Image matching method, device and equipment based on single view and storage medium |
| CN114399503A (en) * | 2022-03-24 | 2022-04-26 | 武汉大学 | Medical image processing method, device, terminal and storage medium |
| CN116728420A (en) * | 2023-08-11 | 2023-09-12 | 苏州安博医疗科技有限公司 | Mechanical arm regulation and control method and system for spinal surgery |
| WO2023240912A1 (en) * | 2022-06-14 | 2023-12-21 | 中国人民解放军总医院第一医学中心 | Image registration method and system for femoral neck fracture surgery navigation |
| WO2024016248A1 (en) * | 2022-07-21 | 2024-01-25 | 中国人民解放军总医院第一医学中心 | Image registration system and method for femoral surgery |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2831458A1 (en) * | 2009-02-25 | 2010-09-02 | Zimmer, Inc. | Customized orthopaedic implants and related methods |
| US20130051647A1 (en) * | 2011-08-23 | 2013-02-28 | Siemens Corporation | Automatic Initialization for 2D/3D Registration |
| US20130094745A1 (en) * | 2011-09-28 | 2013-04-18 | Siemens Corporation | Non-rigid 2d/3d registration of coronary artery models with live fluoroscopy images |
| KR20140120157A (en) * | 2013-04-02 | 2014-10-13 | 연세대학교 산학협력단 | Radiopaque Hemisphere Shape Maker Based Registration Method of Radiopaque 3D Maker for Cardiovascular Diagnosis and Procedure Guiding Image |
| CN105976372A (en) * | 2016-05-05 | 2016-09-28 | 北京天智航医疗科技股份有限公司 | Non-calibration object registering method for pre-operation three-dimensional images and intra-operative perspective images |
| CN108770373A (en) * | 2015-10-13 | 2018-11-06 | 医科达有限公司 | It is generated according to the pseudo- CT of MR data using feature regression model |
| US20190000564A1 (en) * | 2015-12-30 | 2019-01-03 | The Johns Hopkins University | System and method for medical imaging |
| CN111429491A (en) * | 2020-03-11 | 2020-07-17 | 上海嘉奥信息科技发展有限公司 | Spine preoperative three-dimensional image and intraoperative two-dimensional image registration method and system |
-
2020
- 2020-12-17 CN CN202011490366.3A patent/CN112509022A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2831458A1 (en) * | 2009-02-25 | 2010-09-02 | Zimmer, Inc. | Customized orthopaedic implants and related methods |
| US20130051647A1 (en) * | 2011-08-23 | 2013-02-28 | Siemens Corporation | Automatic Initialization for 2D/3D Registration |
| US20130094745A1 (en) * | 2011-09-28 | 2013-04-18 | Siemens Corporation | Non-rigid 2d/3d registration of coronary artery models with live fluoroscopy images |
| KR20140120157A (en) * | 2013-04-02 | 2014-10-13 | 연세대학교 산학협력단 | Radiopaque Hemisphere Shape Maker Based Registration Method of Radiopaque 3D Maker for Cardiovascular Diagnosis and Procedure Guiding Image |
| CN108770373A (en) * | 2015-10-13 | 2018-11-06 | 医科达有限公司 | It is generated according to the pseudo- CT of MR data using feature regression model |
| US20190000564A1 (en) * | 2015-12-30 | 2019-01-03 | The Johns Hopkins University | System and method for medical imaging |
| CN105976372A (en) * | 2016-05-05 | 2016-09-28 | 北京天智航医疗科技股份有限公司 | Non-calibration object registering method for pre-operation three-dimensional images and intra-operative perspective images |
| CN111429491A (en) * | 2020-03-11 | 2020-07-17 | 上海嘉奥信息科技发展有限公司 | Spine preoperative three-dimensional image and intraoperative two-dimensional image registration method and system |
Non-Patent Citations (4)
| Title |
|---|
| DANIELB.RUSSAKOFF 等: "Fast Generation of Digitally Reconstructed Radiographs Using Attenuation Fields With Application to 2D-3D Image Registration", IEEE TRANSACTIONS ON MEDICAL IMAGING, vol. 24, no. 11, 30 November 2005 (2005-11-30), pages 1447 - 1453, XP001240921, DOI: 10.1109/TMI.2005.856749 * |
| 左俊彦;张建国;钟涛;: "基于Canny检测的股骨边缘轮廓连接算法", 山东大学学报(工学版), no. 03, 20 June 2015 (2015-06-20) * |
| 汪国彬: "形状描述与匹配研究", 信息科技辑, no. 03, 15 March 2016 (2016-03-15), pages 1 - 44 * |
| 钟涛;张建国;左俊彦;: "基于Harris角点检测的图像配准新算法", 中国医学影像学杂志, no. 10, 25 October 2015 (2015-10-25) * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450396A (en) * | 2021-06-17 | 2021-09-28 | 北京理工大学 | Three-dimensional/two-dimensional image registration method and device based on bone features |
| CN113570648A (en) * | 2021-07-30 | 2021-10-29 | 武汉联影智融医疗科技有限公司 | Multi-bone image registration method, electronic device and medical navigation system |
| CN113570648B (en) * | 2021-07-30 | 2023-09-26 | 武汉联影智融医疗科技有限公司 | Multi-skeleton image registration method, electronic device and medical navigation system |
| CN113723417A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Image matching method, device and equipment based on single view and storage medium |
| CN113723417B (en) * | 2021-08-31 | 2024-04-12 | 深圳平安智慧医健科技有限公司 | Single view-based image matching method, device, equipment and storage medium |
| CN114399503A (en) * | 2022-03-24 | 2022-04-26 | 武汉大学 | Medical image processing method, device, terminal and storage medium |
| WO2023240912A1 (en) * | 2022-06-14 | 2023-12-21 | 中国人民解放军总医院第一医学中心 | Image registration method and system for femoral neck fracture surgery navigation |
| WO2024016248A1 (en) * | 2022-07-21 | 2024-01-25 | 中国人民解放军总医院第一医学中心 | Image registration system and method for femoral surgery |
| CN116728420A (en) * | 2023-08-11 | 2023-09-12 | 苏州安博医疗科技有限公司 | Mechanical arm regulation and control method and system for spinal surgery |
| CN116728420B (en) * | 2023-08-11 | 2023-11-03 | 苏州安博医疗科技有限公司 | Mechanical arm regulation and control method and system for spinal surgery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112509022A (en) | Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image | |
| CN108765417B (en) | Femur X-ray film generating system and method based on deep learning and digital reconstruction radiographic image | |
| US6747646B2 (en) | System and method for fusing three-dimensional shape data on distorted images without correcting for distortion | |
| CN106934821B (en) | Conical beam CT and CT image registration method based on ICP algorithm and B spline | |
| US9240046B2 (en) | Method and system to assist 2D-3D image registration | |
| JP6404310B2 (en) | Planning system and method for surgical correction of abnormal bone | |
| AU2020101836A4 (en) | A method for generating femoral x-ray films based on deep learning and digital reconstruction of radiological image | |
| Tomazevic et al. | 3-D/2-D registration by integrating 2-D information in 3-D | |
| EP2849630B1 (en) | Virtual fiducial markers | |
| EP2056255B1 (en) | Method for reconstruction of a three-dimensional model of an osteo-articular structure | |
| CN106485695A (en) | Medical image Graph Cut dividing method based on statistical shape model | |
| Zhang et al. | 3-D reconstruction of the spine from biplanar radiographs based on contour matching using the hough transform | |
| Kurazume et al. | 3D reconstruction of a femoral shape using a parametric model and two 2D fluoroscopic images | |
| Baka et al. | Statistical shape model-based femur kinematics from biplane fluoroscopy | |
| Hacihaliloglu et al. | Statistical shape model to 3D ultrasound registration for spine interventions using enhanced local phase features | |
| Alam et al. | Medical image registration: Classification, applications and issues | |
| Guéziec et al. | Providing visual information to validate 2-D to 3-D registration | |
| CN114261095A (en) | AI-based orthopedic 3D printing method and device | |
| Goswami et al. | 3D modeling of X-ray images: a review | |
| CN112308764A (en) | Image registration method and device | |
| CN116363181A (en) | Feature-based CT image and ultrasonic image liver registration method | |
| Messmer et al. | Volumetric model determination of the tibia based on 2D radiographs using a 2D/3D database | |
| CN106875376A (en) | The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model | |
| Varghese et al. | Segmentation and three dimensional visualization of mandible using active contour and visualization toolkit in craniofacial computed tomography images | |
| Dong et al. | Automatic extraction of proximal femur contours from calibrated X‐ray images using 3D statistical models: an in vitro study |
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 |