CN107578434A - VR rendering intents and system based on 3D point cloud rapid registering - Google Patents
VR rendering intents and system based on 3D point cloud rapid registering Download PDFInfo
- Publication number
- CN107578434A CN107578434A CN201710739259.1A CN201710739259A CN107578434A CN 107578434 A CN107578434 A CN 107578434A CN 201710739259 A CN201710739259 A CN 201710739259A CN 107578434 A CN107578434 A CN 107578434A
- Authority
- CN
- China
- Prior art keywords
- registration
- image
- point cloud
- data
- subject
- 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
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of VR rendering intents and system based on 3D point cloud rapid registering, this method is:Load two groups of image datas subject to registration;Two group image data are respectively labeled as to refer to image and floating image;3D reconstructions are carried out to loaded data, obtain corresponding 3D point cloud data;Critical point detection is done to two groups of cloud datas using ISS algorithms, and builds crucial point feature and describes operator;Registration is carried out to cloud data using ICP algorithm, obtains transformation matrix T;Transformation matrix T is acted on floating image, renders output registration result;Utilize VR device downloads registration structure and display output rendering result scene.The system includes:Including VR engines, processor, the client of VR equipment and for the modeling of the image sequence subject to registration of input, registration, and the registration structure scene rendered is output to client-server end.After result after registration is rendered output by the present invention via VR equipment so that doctor being capable of effective observation anatomical structure more directly perceived and Pathological Information.
Description
Technical field
The present invention relates to field of medical images, more particularly, to a kind of VR rendering intents based on 3D point cloud rapid registering and
System.
Background technology
With the continuous development of science and technology, medical imaging technology also achieves huge advance, and various new imaging devices are continuous
Emerge, such as:Computerized tomography imaging (CT), magnetic resonance imaging (MRI), digital subtraction angiography (DSA), positron emission break
Layer imaging (PET) etc..Different imaging techniques has its advantage and weak point, can win currently without any imaging technique
Appoint imaging and inspection to all organ-tissues of human body, but can be by images such as registration, fusions between different imaging techniques at
Reason means are had complementary advantages, and then aid in doctor to improve rate of correct diagnosis.
Virtual reality (Virtual Reality, VR) combines computer graphics, computer simulation technique, sensor
The multidisciplinary technology such as technology creates a virtual three-dimensional world in Multi information space, provides the user on the spot in person immerse
Sense, presents a kind of brand-new man-machine interaction means, helps to inspire and conceives, has and immerse, interact, conceiving three big characteristics.
However, during traditional diagosis diagnosis, doctor needs to face bidimensional image sequence, is passed through by the clinic of itself long term accumulation
Test to judge to diagnose, this mode is not directly perceived and diagnostic result varies with each individual sometimes.In addition, different imaging device outputs
Image information is also variant, such as:For CT mainly based on skeletal survey, MRI is mainly preferable to brain, muscle, soft-tissue imaging effect,
PET then belongs to functional metabolism imaging, and equally has certain radioactivity with CT.Therefore, in order to preferably find and position
Focus, the image data registration fusion to same mode/anomalous mode state is needed in actual applications in order to which doctor preferably diagnoses.It is existing
Some medical science registration techniques are all based on greatly two-dimensional image sequence and need to apply substantial amounts of image preprocessing means, on the one hand increase
Added the working strength another aspect registration result of diagosis doctor to be still bidimensional image, based on this result reconstruct again come
3D models can lose many information, for the situation in complicated or overlapping region, easily generation wrong diagnosis and escape.
Also, in terms of display, conventional meanses are checked by the medical image browser installed on PC, PC is supported at present
Interactive mode be mainly mouse, keyboard and touch-screen, be difficult to meet to require in the case of some are complicated special.At this moment VR
It is powerful to render function and distinctive interactive meanses and just use, it can more effectively help doctor's diagosis to diagnose.
The content of the invention
The purpose of the present invention is exactly to solve the above problems, there is provided a kind of VR sides of rendering based on 3D point cloud rapid registering
Method and system, it is treated registration data progress 3D modeling and obtains its cloud data, after registration Algorithm registration, via VR equipment
Registration result is rendered into output, auxiliary doctor effective observation anatomical structure more directly perceived and Pathological Information.
In order to solve the above technical problems, the invention provides a kind of VR rendering intents based on 3D point cloud rapid registering, should
Method is:Load two groups of image datas subject to registration;Two group image data are respectively labeled as to refer to image and floating image;It is right
Loaded data carry out 3D reconstructions, obtain corresponding 3D point cloud data;Key point inspection is done to two groups of cloud datas using ISS algorithms
Survey, and build crucial point feature and describe operator;Registration is carried out to cloud data using ICP algorithm, obtains transformation matrix T;It will become
Change matrix T to act on floating image, render output registration result;Rendered using VR device downloads registration structure and display output
As a result scene.
Compared with prior art, technology provided by the invention reduces the working strength of doctor to a certain extent, also,
Doctor can more intuitively observe the anatomical structure of human body, and can observe its internal structure;Compared with traditional approach, using VR wash with watercolours
Dye output, its effect is more directly perceived, and interactivity is stronger, and operation is more convenient;
In VR rendering intents based on 3D point cloud rapid registering, two groups of image datas subject to registration are added by 3D Slicer
Carry.
In VR rendering intents based on 3D point cloud rapid registering, image data subject to registration is treated for same mode/anomalous mode state
Registering image data.
In VR rendering intents based on 3D point cloud rapid registering, the VR equipment is that VR heads show equipment.
For the system of the VR rendering intents based on 3D point cloud rapid registering, it includes:
Client, it includes VR engines, processor and the VR equipment for display, and VR equipment, which for example can be that VR heads are aobvious, to be set
It is standby;
Server end, it is used for the modeling of the image sequence subject to registration of input, registration, and the registration structure field that will have been rendered
Scape is output on client display device and shown.
Brief description of the drawings
Fig. 1 is the flow chart of the VR rendering intents based on 3D point cloud rapid registering.
Embodiment
In order that the technical means, the inventive features, the objects and the advantages of the present invention are easy to understand, tie below
Specific embodiment is closed, the present invention is expanded on further.
Embodiment:Referring to Fig. 1, the VR rendering intents based on 3D point cloud rapid registering, it includes obtaining with/anomalous mode state two dimension
Image data → carried out respectively to the image data got three-dimensional reconstruction obtains corresponding cloud data → to obtained point cloud
Data perform registration using point cloud registration algorithm and obtain the result scene of registration result → after registration is rendered during VR heads are aobvious.
From the foregoing it can be that after the result after registration is rendered output by method provided by the invention via VR equipment, make
Obtaining doctor being capable of effective observation anatomical structure more directly perceived and Pathological Information.
In VR rendering intents based on 3D point cloud rapid registering, with treating for 3D Slicer two groups of same mode/anomalous mode states of loading
Registering image data, it is respectively labeled as referring to image (Fixed Image) and floating image (Moving Image).
And loading data are carried out with 3D and is rebuild after obtaining corresponding 3D point cloud data, utilize ISS (Intrinsic Shape
Signatures) algorithm does key point (Keypoints) detection to two groups of cloud datas, to acquired key point construction feature
Operator is described.
In step of registration, using ICP (Iterative Closest Point) algorithms two groups of points are converged with conjunction execution and is matched somebody with somebody
Standard, and then registration transformation matrix T is obtained, registration transformation T is then to floating image, output renders registration result.
Finally show device downloads using such as VR heads and display output renders registration result scene.
System for preceding method includes:Client, the server end being connected with client, client are drawn including VR
Hold up, processor and the VR equipment formed for the aobvious equipment of such as VR heads of display, server end are used for the shadow subject to registration to input
As Series Modeling, registration, and the registration structure scene rendered is output on client display device and shown.
It will be understood by those skilled in the art that the respective embodiments described above are to realize the specific embodiment of the present invention,
And in actual applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (6)
1. a kind of VR rendering intents based on 3D point cloud rapid registering, it is characterised in that this method is:
Load two groups of image datas subject to registration;
Two group image data are respectively labeled as to refer to image and floating image;
3D reconstructions are carried out to loaded data, obtain corresponding 3D point cloud data;
Critical point detection is done to two groups of cloud datas using ISS algorithms, and builds crucial point feature and describes operator;
Registration is carried out to cloud data using ICP algorithm, obtains transformation matrix T;
Transformation matrix T is acted on floating image, renders output registration result;
Utilize VR device downloads registration structure and display output rendering result scene.
2. the VR rendering intents according to claim 1 based on 3D point cloud rapid registering, it is characterised in that two groups subject to registration
Image data loaded by 3D Slicer.
3. the VR rendering intents according to claim 1 based on 3D point cloud rapid registering, it is characterised in that shadow subject to registration
As the image data subject to registration that data are same mode/anomalous mode state.
4. the VR rendering intents according to claim 1 based on 3D point cloud rapid registering, it is characterised in that the VR equipment
Show equipment for VR heads.
5. a kind of system for being used for the VR rendering intents based on 3D point cloud rapid registering as described in claim 1-4 is any, its
It is characterised by, it includes:
Client, it includes VR engines, processor and the VR equipment for display;
Server end, it is used for the modeling of the image sequence subject to registration of input, registration, and the registration structure scene rendered is defeated
Go out to showing on client display device.
6. system according to claim 5, it is characterised in that the VR equipment is that VR heads show equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710739259.1A CN107578434A (en) | 2017-08-25 | 2017-08-25 | VR rendering intents and system based on 3D point cloud rapid registering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710739259.1A CN107578434A (en) | 2017-08-25 | 2017-08-25 | VR rendering intents and system based on 3D point cloud rapid registering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107578434A true CN107578434A (en) | 2018-01-12 |
Family
ID=61034827
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710739259.1A Pending CN107578434A (en) | 2017-08-25 | 2017-08-25 | VR rendering intents and system based on 3D point cloud rapid registering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107578434A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109269405A (en) * | 2018-09-05 | 2019-01-25 | 天目爱视(北京)科技有限公司 | A kind of quick 3D measurement and comparison method |
CN112967236A (en) * | 2018-12-29 | 2021-06-15 | 上海联影智能医疗科技有限公司 | Image registration method and device, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160071318A1 (en) * | 2014-09-10 | 2016-03-10 | Vangogh Imaging, Inc. | Real-Time Dynamic Three-Dimensional Adaptive Object Recognition and Model Reconstruction |
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 |
CN106846461A (en) * | 2016-12-30 | 2017-06-13 | 西安交通大学 | A kind of human body three-dimensional scan method |
CN106846386A (en) * | 2017-02-08 | 2017-06-13 | 南通大学 | 3D cranium method for registering images based on ROI and conformal geometric algebra property invariant |
CN106874700A (en) * | 2017-04-01 | 2017-06-20 | 上海术理智能科技有限公司 | Surgical simulation method, surgical simulation device and electronic equipment based on Web |
CN106890024A (en) * | 2016-12-29 | 2017-06-27 | 李岩 | A kind of preoperative servicing unit of liver neoplasm heating ablation operation |
-
2017
- 2017-08-25 CN CN201710739259.1A patent/CN107578434A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160071318A1 (en) * | 2014-09-10 | 2016-03-10 | Vangogh Imaging, Inc. | Real-Time Dynamic Three-Dimensional Adaptive Object Recognition and Model Reconstruction |
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 |
CN106890024A (en) * | 2016-12-29 | 2017-06-27 | 李岩 | A kind of preoperative servicing unit of liver neoplasm heating ablation operation |
CN106846461A (en) * | 2016-12-30 | 2017-06-13 | 西安交通大学 | A kind of human body three-dimensional scan method |
CN106846386A (en) * | 2017-02-08 | 2017-06-13 | 南通大学 | 3D cranium method for registering images based on ROI and conformal geometric algebra property invariant |
CN106874700A (en) * | 2017-04-01 | 2017-06-20 | 上海术理智能科技有限公司 | Surgical simulation method, surgical simulation device and electronic equipment based on Web |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109269405A (en) * | 2018-09-05 | 2019-01-25 | 天目爱视(北京)科技有限公司 | A kind of quick 3D measurement and comparison method |
CN109269405B (en) * | 2018-09-05 | 2019-10-22 | 天目爱视(北京)科技有限公司 | A kind of quick 3D measurement and comparison method |
CN112967236A (en) * | 2018-12-29 | 2021-06-15 | 上海联影智能医疗科技有限公司 | Image registration method and device, computer equipment and storage medium |
CN112967236B (en) * | 2018-12-29 | 2024-02-27 | 上海联影智能医疗科技有限公司 | Image registration method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AlZu’bi et al. | Parallel implementation for 3d medical volume fuzzy segmentation | |
US11132792B2 (en) | Cross domain medical image segmentation | |
JP6396310B2 (en) | Method and apparatus for displaying to a user a transition between a first rendering projection and a second rendering projection | |
US9471987B2 (en) | Automatic planning for medical imaging | |
Jiménez et al. | A Web platform for the interactive visualization and analysis of the 3D fractal dimension of MRI data | |
Shen et al. | A geometry-informed deep learning framework for ultra-sparse 3D tomographic image reconstruction | |
Gulo et al. | Techniques of medical image processing and analysis accelerated by high-performance computing: A systematic literature review | |
US10390726B2 (en) | System and method for next-generation MRI spine evaluation | |
CN110570483A (en) | scanning method, scanning device, computer equipment and storage medium | |
Behroozi et al. | Software tools for the analysis of functional magnetic resonance imaging | |
CN114596311B (en) | Blood vessel function evaluation method and blood vessel function evaluation device based on blood vessel image | |
CN108320314A (en) | A kind of image processing method and device based on the cross-section images of CT, Bone images display system | |
Zhao et al. | Medical images super resolution reconstruction based on residual network | |
CN107578434A (en) | VR rendering intents and system based on 3D point cloud rapid registering | |
US20220222812A1 (en) | Device and method for pneumonia detection based on deep learning | |
Khezrpour et al. | Automatic segmentation of the brain stroke lesions from MR flair scans using improved U-net framework | |
Hussain | ViPS: A novel visual processing system architecture for medical imaging | |
US10621720B2 (en) | Deformable registration of magnetic resonance and ultrasound images using biomechanical models | |
EP3300664B1 (en) | Reconstruction of flow data | |
Zhang et al. | MR and ultrasound cardiac image dynamic visualization and synchronization over Internet for distributed heart function diagnosis | |
EP4285828A1 (en) | Learned model generation method, machine learning system, program, and medical image processing device | |
JP5518970B2 (en) | Image display device | |
Upendra et al. | A supervised image registration approach for late gadolinium enhanced MRI and cine cardiac MRI using convolutional neural networks | |
CN113850794A (en) | Image processing method and device | |
CN104392487B (en) | Quick real-time reconstruction method based on dual-panel PET |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180112 |
|
WD01 | Invention patent application deemed withdrawn after publication |