CN108154525A - A kind of matched bone fragments joining method of feature based - Google Patents
A kind of matched bone fragments joining method of feature based Download PDFInfo
- Publication number
- CN108154525A CN108154525A CN201711165008.3A CN201711165008A CN108154525A CN 108154525 A CN108154525 A CN 108154525A CN 201711165008 A CN201711165008 A CN 201711165008A CN 108154525 A CN108154525 A CN 108154525A
- Authority
- CN
- China
- Prior art keywords
- point
- model
- bone fragments
- transformation matrix
- feature
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of matched bone fragments joining method of feature based, by the way that being registrated from the three-dimensional bone fragments model of medicine image reconstruction, preoperative guidance is provided for fracture of mandible reparation.This method comprises the following steps：1）Import three-dimensional bone fragments model, the plane of disruption of manual extraction fragment model；2）Based on 3D SIFT algorithms, the key point on the bone fragments model plane of disruption is extracted；3）Point of use feature histogram FPFH algorithms are key point construction feature description of extraction；4）Key point and corresponding description based on extraction establish two bone fragments models（It is referred to as model subject to registration, object module）Initial correspondence；5）Optimize initial correspondence using improved ICP algorithm, obtain final transformation matrix；6）Transformation matrix obtained in the previous step is acted in model subject to registration, obtains the splicing result of two bone fragments models.Method flow is as shown in Figure 1.
Description
Technical field
The present invention relates to computer graphicals and Computer Aided Surgery digital prototype technology field, relate generally to a kind of base
In the bone fragments joining method of characteristic matching
Background technology
At the beginning of eighties of last century 90, domestic and foreign scholars start computer technology such as computer graphics, virtual reality
Technology etc. is applied in craniomaxillofacial surgery, and the direction for making traditional craniomaxillofacial surgery to digitlization, minimally invasiveization is developed, and as doctor
The important developing direction in one, field.Cranium maxillofacial zones include many important blood vessels and nerve fiber, and take into account face
Beauty, these reasons all propose higher requirement to the accuracy of cranium maxillofacial zones operation.Traditional modus operandi mainly according to
By the personal surgical experience of doctor, cause operating time longer, wound is larger caused by patient.Therefore for cranium jaw face
The computer assisted surgery planning at position is always to digitize the popular research field of surgery.
Patent of the present invention is directed to the reset of cranium maxillofacial fracture wound, and design is a kind of to be based on threedimensional model feature extraction and three
The bone fragments recovery technique of registration technique is tieed up, for doctor to be assisted to carry out pre-operative surgical planning, formulates rational operation plan,
So as to reduce secondary injury of the surgical procedure to patient, the success rate of operation is improved.
Show that fracture of mandible case accounts for the 25%- of craniofacial injury case sum according to domestic and international relevant statistics
28%, account for the 55%-72% of Maxillofacial fracture case sum.Therefore, patent of the present invention is to the fracture of mandible reparation of cranium maxillofacial zones
There are important application value and wide application prospect.
Invention content
It is an object of the invention to：Using relevant computer technology, by damage Lu Jaw faces, provided to be easiest to
Preoperative planning and designing method, auxiliary doctor formulate pre-operative surgical scheme.
The technical solution adopted by the present invention is as follows：
A kind of matched bone fragments joining method of feature based, technical solution are as follows：
1) from the three-dimensional bone fragments model of reconstruction, manual extraction plane of disruption region；Threedimensional model used in the present invention is rebuild
In the CT image datas of patient.
2) to extraction plane of disruption region, based on 3D-SIFT feature extraction algorithms, the characteristic point of the region of fracture is extracted；
Traditional 3D-SIFT feature extraction algorithms, the principle of selected characteristic point is the larger data point of Selection Model mean curvature, this
Further improvement has been done traditional algorithm in invention, by the way that minimum curvature threshold is set to remove the smaller candidate of model mean curvature
Key point to obtain the characteristic point of key position, improves registration accuracy and efficiency；Mainly include three steps：
2.1）For three-dimension modeling scale space and gaussian pyramid；
2.2）Find the characteristic point that contrast is low in candidate characteristic point and removal scale space；
2.3）By setting minimum curvature threshold, the smaller candidate key point of model mean curvature, remaining candidate feature point are removed
The key feature points as obtained.
3）To extract each characteristic point, calculating and establishing quick point feature histogram FPFH descriptions, process is established
It is as follows：
3.1）For each characteristic point p, formula is utilized（1）Calculate the triple between it and it all neighbor points（F1, f2,
f3）, all triples are then built into histogram with statistical namely calculate the feature histogram SPFH of the simplification of point p；
（1）
3.2）For each point p in the neighborhood of piIts neighbor point is inquired, and calculates each piThe SPFH values of point, use neighbor point
piSPFH values calculate the FPFH values of query point p, specific calculation is shown in formula（2）
（2）
4）The corresponding FPFH Feature Descriptors of characteristic point and characteristic point based on extraction, establish two bone fragments models（Point
Also known as it is source model and object module）Between correspondence point pair；
The present invention using two ways establishes feature correspondence, and one kind is directly to inquire, and one to be that loop iteration is looked into optimal.Directly
Connect search algorithm accuracy height；But time complexity is also high, causes efficiency relatively low.Loop iteration looks into the main thought of best practice
It is to find optimal correspondence by constantly reducing the distance between model point set difference, is using final registration effect to lead
To an algorithm.The present invention combines the advantages of the two algorithms, establishes the preliminary correspondence before two models.By straight
Inquiry is connect, excludes the weaker characteristic point of a part of feature, best practice is then looked into based on loop iteration for residue character point again and is built
Vertical correspondence, to ensure accuracy, and improves efficiency.Algorithm steps are as follows：
4.1）S characteristic point is randomly choosed in the characteristic point of model subject to registration, this s characteristic point will ensure them between any two
Distance be more than setting a threshold value；
4.2）For each point S in s characteristic point of selectioni, in the feature description subspace of target model features point,
Select k Neighbor Points, k values be 10, randomly selected from 10 points one as with point SiCorresponding relationship point, in this way
Just constitute s corresponding relationship points pair；
4.3）According to s obtained correspondence point pair, transformation matrix T is calculated, and use two models by the method for SVD
Between range error function value assess specifically converting, if recycled better than last time, replace transformation matrix, otherwise,
Retain the transformation matrix T in last time cycle；
4.4）Three above step is repeated until reaching maximum cycle；In each cycle, only store current cycle and obtain
Transformation matrix and the optimal value in the transformation matrix that is stored in last cycle, i.e., so that the distance between two models accidentally
The smaller transformation matrix T of difference function values.
5）Optimize initial correspondence using improved ICP algorithm, obtain final transformation matrix；
In order to advanced optimize registration result, the present invention is to improving iteration with regard to proximal method（ICP）, for advanced optimizing registration
As a result, to obtain more preferably transformation matrix；Step is as follows：
5.1）According to arest neighbors selection algorithm structure point pair：For band registration model MiIn each point, in target input model T
The point nearest from it is searched out, forms a correspondence point pair, two points is finally found out and concentrates all corresponding points pair.This hair
It is bright in order to improve the anti-noise ability of ICP algorithm, when the distance between closest approach and query point be less than set threshold value when, just composition
One correspondence point pair；
5.2）According to the correspondence point that previous step is calculated to set, the spin moment of rigid transformation between two models is calculated
Battle array R and translation vector t；
5.3）According to obtained spin matrix and translation vector R, t, by MiIt is converted to obtain new model Mi+1；Later, it is traditional
Method is by calculating Mi+1With MiThe distance between quadratic sum, using the absolute value of the difference of square distance sum twice in succession as whether
Convergent foundation, to determine whether stopping iteration.The error that end condition is set as between model twice in succession by the present invention becomes
The absolute value Epsilon of rate, wherein Epsilon=| (Ec-Ec-1)/Ec-1|, EcIt is the corresponding points between two models to error
The sum of, the efficiency of algorithm is improved with this；
5.4）Above step is repeated, the maximum iteration until restraining or reaching setting preserves transformation matrix.
6）Transformation matrix is acted on into model subject to registration, obtains the result after two model splicings；
By the reuse to above-mentioned steps, the splicing result of multiple fragment models can be obtained, is realized due to trauma fracture
The proper reset of caused fragment model.
In conclusion by adopting the above-described technical solution, the beneficial effects of the invention are as follows：
1. by three-dimensional feature extractive technique and three-dimensional registration technology, the splicing reparation of multiple bone fragments models is realized, is allowed
Doctor has preliminary scheme to the recovery position of bone fragments in the preoperative, preoperative guidance is provided for doctor, when shortening operation with this
Between, it reduces in operation to the secondary injury of patient, there is very wide application prospect and important in fracture of mandible reparation
Application value.
Description of the drawings
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein：
Fig. 1 bone fragments model and the plane of disruption of extraction
The SPFH feature histograms of Fig. 2 characteristic points
The bone fragments model of Fig. 3 an example different visual angles
The split-join model of Fig. 3 fragment models of Fig. 4 different visual angles
The part lower jaw bone fragments model of Fig. 5 first case different visual angles
The splicing repairing model of Fig. 5 fragment models of Fig. 6 different visual angles
The part lower jaw bone fragments model of Fig. 7 second case different visual angles
The splicing repairing model of Fig. 7 fragment models of Fig. 8 different visual angles
The complete fracture of mandible model of Fig. 9 third example different visual angles
The splicing repairing model of Fig. 9 fragment models of Figure 10 different visual angles
Specific embodiment
All features or disclosed all methods disclosed in this specification or in the process the step of, in addition to mutually exclusive
Feature and/or step other than, can combine in any way.The present invention is explained with reference to Fig. 1-Figure 10：
A kind of matched bone fragments joining method of feature based, Fig. 1 are this technology overall flow figure；Detailed step is as follows：
1) from the three-dimensional bone fragments model of reconstruction, manual extraction plane of disruption region.Threedimensional model used in the present invention is rebuild
In the CT image datas of patient.As shown in Fig. 2, the left side is the two lower jaw bone chip models imported, the right is respectively at two
The plane of disruption region extracted on model；
2) to extraction plane of disruption region, based on 3D-SIFT feature extraction algorithms, the characteristic point of the region of fracture is extracted, such as Fig. 3 institutes
Show, the left side is the fragment model imported, and the right is the display in the characteristic point of the fragment model extraction；
3) to extract each characteristic point, calculating and establishing quick point feature histogram FPFH descriptions；Fig. 4 show one
The SPFH feature histograms of a characteristic point；
4) characteristic point based on extraction and the corresponding FPFH Feature Descriptors of characteristic point, establish two bone fragments models（Point
Also known as it is source model and object module）Between correspondence point pair；
5) in order to further optimize registration result, the present invention is to known iteration with regard to proximal method（ICP）It is improved, is used
In advanced optimizing registration result, to obtain more preferably transformation matrix；
6) transformation matrix is acted on into model subject to registration, obtains the result after two model splicings；
It is to show result of the present invention by three groups of data below：
Fig. 5, Fig. 7, Fig. 9 be experiment three groups of data, three groups of bone fragments models
Fig. 6, Fig. 8, Figure 10 are to obtain the experimental result of three groups of data based on above-mentioned steps.Three groups of description of test are based on the region of fracture
Splicing repair mode reconstruction can be carried out successfully to common fracture of mandible case.
Claims (5)
1. a kind of disclosure of the invention matched bone fragments joining method of feature based, by the preoperative to each two fragment mould
It is registrated between type, the final splicing for realizing whole fracture fragments models generates preoperative repair of fractured bones scheme, when shortening operation
Between, reduce the long secondary injury brought to patient of operating time；It is characterized in that, the method comprises the following steps：
1）Import three-dimensional bone fragments model, the plane of disruption of manual extraction fragment model；
2）Based on 3D-SIFT algorithms, the key point on the bone fragments model plane of disruption is extracted；
3）Point of use feature histogram FPFH algorithms are key point construction feature description of extraction；
4）Key point and corresponding description based on extraction establish two bone fragments models（Be referred to as model subject to registration,
Object module）Initial correspondence；
5）Optimize initial correspondence using improved ICP algorithm, obtain final transformation matrix；
6）Transformation matrix obtained in the previous step is acted in model subject to registration, obtains the splicing result of two bone fragments models.
2. the matched bone fragments joining method of a kind of feature based according to claim 1, spy are, the step
Rapid 2）It comprises the following steps：
2.1）For three-dimension modeling scale space and gaussian pyramid；
2.2）Calculate the characteristic point that contrast is low in candidate characteristic point and removal scale space；
2.3）By setting minimum curvature threshold, the smaller candidate key point of model mean curvature, remaining candidate feature point are removed
The key feature points as obtained.
3. the matched bone fragments joining method of a kind of feature based according to claim 1, spy are, the step
Rapid 3）It comprises the following steps：
3.1）For each characteristic point p of extraction, its simplification feature histogram SPFH is calculated；
3.2）For each point p in the neighborhood of piIts neighbor point is inquired, and calculates each piThe SPFH values of point, use neighbor point
piSPFH values calculate the FPFH values of query point p.
4. the matched bone fragments joining method of a kind of feature based according to claim 1, spy are, the step
Rapid 4）It comprises the following steps：
4.1）S characteristic point is randomly choosed in the characteristic point of model subject to registration, this s characteristic point will ensure them between any two
Distance be more than setting a threshold value；
4.2）For each point S in s characteristic point of selectioni, in the feature description subspace of target model features point,
Select k Neighbor Points, k values be 10, randomly selected from this 10 points one as with point SiCorresponding relationship point, this
Sample just constitutes s corresponding relationship points pair；
4.3）According to s obtained correspondence point pair, transformation matrix T is calculated, and use two models by the method for SVD
Between range error function value assess specifically converting, if recycled better than last time, replace transformation matrix, otherwise,
Retain the transformation matrix T in last time cycle；
4.4）Three above step is repeated until reaching maximum cycle；In each cycle, only store current cycle and obtain
Transformation matrix and the optimal value in the transformation matrix that is stored in last cycle, i.e., so that the distance between two models accidentally
The smaller transformation matrix T of difference function values.
5. the matched bone fragments joining method of a kind of feature based according to claim 1, spy are, the step
Rapid 5）It comprises the following steps：
5.1）According to arest neighbors selection algorithm structure point pair：For model M subject to registrationiIn each point, in target input model T
The point nearest from it is searched out, forms a correspondence point pair, two points is finally found out and concentrates all corresponding points pair；This hair
It is bright in order to improve the anti-noise ability of ICP algorithm, when the distance between closest approach and query point be less than set threshold value when, just composition
One correspondence point pair；
5.2）According to the correspondence point that previous step is calculated to set, the spin moment of rigid transformation between two models is calculated
Battle array R and translation vector t；
5.3）According to obtained spin matrix and translation vector R, t, by MiIt is converted to obtain new model Mi+1；Calculate continuous two
The absolute value Epsilon of error rate between secondary model, wherein Epsilon=| (Ec-Ec-1)/Ec-1|, EcIt is two models
Between corresponding points to the sum of error, and in this, as whether convergent foundation, to determine whether stop iteration；
5.4）Above step is repeated, until restraining or reaching the maximum iteration set by us, preserves transformation matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711165008.3A CN108154525B (en) | 2017-11-21 | 2017-11-21 | Bone fragment splicing method based on feature matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711165008.3A CN108154525B (en) | 2017-11-21 | 2017-11-21 | Bone fragment splicing method based on feature matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108154525A true CN108154525A (en) | 2018-06-12 |
| CN108154525B CN108154525B (en) | 2022-06-07 |
Family
ID=62468947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711165008.3A Active CN108154525B (en) | 2017-11-21 | 2017-11-21 | Bone fragment splicing method based on feature matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108154525B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035311A (en) * | 2018-07-11 | 2018-12-18 | 大连理工大学 | A kind of curved bone fracture autoregistration and internal fixation steel plate pre-bending modeling method |
| CN110009562A (en) * | 2019-01-24 | 2019-07-12 | 北京航空航天大学 | A method of comminuted fracture threedimensional model is spliced using template |
| CN110415361A (en) * | 2019-07-26 | 2019-11-05 | 北京罗森博特科技有限公司 | It is broken object joining method and device |
| CN111383353A (en) * | 2020-04-01 | 2020-07-07 | 大连理工大学 | Fractured bone model registration method based on Gaussian mixture model and contour descriptor |
| CN112884653A (en) * | 2021-03-01 | 2021-06-01 | 西北大学 | Broken terracotta warriors fragment splicing method and system based on fracture surface information |
| CN113409301A (en) * | 2021-07-12 | 2021-09-17 | 上海精劢医疗科技有限公司 | Point cloud segmentation-based femoral neck registration method, system and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030300A (en) * | 2007-02-08 | 2007-09-05 | 深圳大学 | Method for matching depth image |
| CN103337065A (en) * | 2013-05-22 | 2013-10-02 | 西安电子科技大学 | Non-rigid registering method of mouse three-dimensional CT image |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| CN104463953A (en) * | 2014-11-11 | 2015-03-25 | 西北工业大学 | Three-dimensional reconstruction method based on inertial measurement unit and RGB-D sensor |
| CN105447908A (en) * | 2015-12-04 | 2016-03-30 | 山东山大华天软件有限公司 | Dentition model generation method based on oral cavity scanning data and CBCT (Cone Beam Computed Tomography) data |
| CN105974386A (en) * | 2016-05-05 | 2016-09-28 | 乐山师范学院 | Multistatic radar multi-target imaging positioning method |
| CN106056053A (en) * | 2016-05-23 | 2016-10-26 | 西安电子科技大学 | Human posture recognition method based on skeleton feature point extraction |
| CN106296693A (en) * | 2016-08-12 | 2017-01-04 | 浙江工业大学 | Based on 3D point cloud FPFH feature real-time three-dimensional space-location method |
| CN106407985A (en) * | 2016-08-26 | 2017-02-15 | 中国电子科技集团公司第三十八研究所 | Three-dimensional human head point cloud feature extraction method and device thereof |
| CN106963489A (en) * | 2017-05-12 | 2017-07-21 | 常州工程职业技术学院 | A kind of individuation femoral fracture reset model construction method |
| CN107123161A (en) * | 2017-06-14 | 2017-09-01 | 西南交通大学 | A kind of the whole network three-dimensional rebuilding method of contact net zero based on NARF and FPFH |
-
2017
- 2017-11-21 CN CN201711165008.3A patent/CN108154525B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030300A (en) * | 2007-02-08 | 2007-09-05 | 深圳大学 | Method for matching depth image |
| CN103337065A (en) * | 2013-05-22 | 2013-10-02 | 西安电子科技大学 | Non-rigid registering method of mouse three-dimensional CT image |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| CN104463953A (en) * | 2014-11-11 | 2015-03-25 | 西北工业大学 | Three-dimensional reconstruction method based on inertial measurement unit and RGB-D sensor |
| CN105447908A (en) * | 2015-12-04 | 2016-03-30 | 山东山大华天软件有限公司 | Dentition model generation method based on oral cavity scanning data and CBCT (Cone Beam Computed Tomography) data |
| CN105974386A (en) * | 2016-05-05 | 2016-09-28 | 乐山师范学院 | Multistatic radar multi-target imaging positioning method |
| CN106056053A (en) * | 2016-05-23 | 2016-10-26 | 西安电子科技大学 | Human posture recognition method based on skeleton feature point extraction |
| CN106296693A (en) * | 2016-08-12 | 2017-01-04 | 浙江工业大学 | Based on 3D point cloud FPFH feature real-time three-dimensional space-location method |
| CN106407985A (en) * | 2016-08-26 | 2017-02-15 | 中国电子科技集团公司第三十八研究所 | Three-dimensional human head point cloud feature extraction method and device thereof |
| CN106963489A (en) * | 2017-05-12 | 2017-07-21 | 常州工程职业技术学院 | A kind of individuation femoral fracture reset model construction method |
| CN107123161A (en) * | 2017-06-14 | 2017-09-01 | 西南交通大学 | A kind of the whole network three-dimensional rebuilding method of contact net zero based on NARF and FPFH |
Non-Patent Citations (9)
| Title |
|---|
| LUWEN QIU 等: "An Automatic Registration Algorithm for 3D Maxillofacial Model", 《3D RESEARCH》 * |
| 刘斌: "股骨头坏死与骨折计算机辅助手术技术研究", 《万方数据》 * |
| 周朗明 等: "旋转平台点云数据的配准方法", 《测绘学报》 * |
| 杨旭静 等: "考虑位移约束的功能梯度结构ICM拓扑优化方法", 《湖南大学学报(自然科学版)》 * |
| 洪菁 等: "基于模糊粗糙集的瓦斯涌出量预测模型的研究", 《微计算机信息》 * |
| 翟优 等: "自适应对比度阈值SIFT算法研究", 《计算机测量与控制》 * |
| 许万林: "大规模层次图集的可视化研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 谢颖: "基于三维激光扫描的粮仓储量测量中点云数据处理技术的研究", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
| 鲁俊: "基于kinect三维人体重建中配准算法的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035311A (en) * | 2018-07-11 | 2018-12-18 | 大连理工大学 | A kind of curved bone fracture autoregistration and internal fixation steel plate pre-bending modeling method |
| CN109035311B (en) * | 2018-07-11 | 2021-10-01 | 大连理工大学 | Automatic registration and internal fixation steel plate pre-bending modeling method for curved bone fracture |
| CN110009562A (en) * | 2019-01-24 | 2019-07-12 | 北京航空航天大学 | A method of comminuted fracture threedimensional model is spliced using template |
| CN110415361A (en) * | 2019-07-26 | 2019-11-05 | 北京罗森博特科技有限公司 | It is broken object joining method and device |
| CN110415361B (en) * | 2019-07-26 | 2020-05-15 | 北京罗森博特科技有限公司 | Method and device for splicing broken objects |
| CN111383353A (en) * | 2020-04-01 | 2020-07-07 | 大连理工大学 | Fractured bone model registration method based on Gaussian mixture model and contour descriptor |
| CN111383353B (en) * | 2020-04-01 | 2023-05-23 | 大连理工大学 | Fractured bone model registration method based on Gaussian mixture model and contour descriptor |
| CN112884653A (en) * | 2021-03-01 | 2021-06-01 | 西北大学 | Broken terracotta warriors fragment splicing method and system based on fracture surface information |
| CN113409301A (en) * | 2021-07-12 | 2021-09-17 | 上海精劢医疗科技有限公司 | Point cloud segmentation-based femoral neck registration method, system and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108154525B (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108154525A (en) | A kind of matched bone fragments joining method of feature based | |
| CN110214341A (en) | The method for rebuilding skull | |
| JP2014097220A (en) | Surgical operation support device | |
| CN105147341B (en) | Three-dimensional model reconstructing method for keeping fracture line of jaw bone | |
| CN109378068A (en) | A kind of method for automatically evaluating and system of Therapeutic Effects of Nasopharyngeal | |
| JP7329603B2 (en) | Method and apparatus for generating virtual internal fixture based on image reduction | |
| WO2015142291A1 (en) | Computer-aided planning of craniomaxillofacial and orthopedic surgery | |
| Wagner et al. | Development and first clinical application of automated virtual reconstruction of unilateral midface defects | |
| WO2023236367A1 (en) | Planning method and apparatus for tibia osteotomy intelligent navigation system | |
| Vlachopoulos et al. | Computer-assisted planning and patient-specific guides for the treatment of midshaft clavicle malunions | |
| CN110378941A (en) | A kind of Rigid Registration method obtaining Middle face Occluded target reference data | |
| CN113409301A (en) | Point cloud segmentation-based femoral neck registration method, system and medium | |
| WO2023000560A1 (en) | Reduction trajectory automatic planning method for parallel fracture surgical robot | |
| Moolenaar et al. | Computer-assisted preoperative planning of bone fracture fixation surgery: A state-of-the-art review | |
| CN112184720A (en) | Method and system for segmenting rectus muscle and optic nerve of CT image | |
| Lu et al. | Preoperative virtual reduction planning algorithm of fractured pelvis based on adaptive templates | |
| CN117598781A (en) | Path planning method and device for vertebral plate decompression robot | |
| Gong et al. | Reduction of multi-fragment fractures of the distal radius using atlas-based 2D/3D registration | |
| KR101692442B1 (en) | Method and apparatus for automated pedicle screw placement planning for safe spinal fusion surgery | |
| Jiménez-Delgado et al. | Virtual Reality Environment for the Validation of Bone Fracture Reduction Processes. | |
| CN103110438A (en) | Distraction maintenance device for small incision for posterior minimally invasive screw fixation for vertebral column of patient | |
| CN110766666A (en) | Skeleton fault outline large sample library generation method based on region segmentation and GAN model | |
| Li et al. | Automatic laminectomy cutting plane planning based on artificial intelligence in robot assisted laminectomy surgery | |
| CN118402867B (en) | Bone surface registration guide device, bone surface registration apparatus, and storage medium | |
| Zeng et al. | A bidirectional framework for fracture simulation and deformation-based restoration prediction in pelvic fracture surgical planning |
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 | ||
| GR01 | Patent grant |