CN110349254A - A kind of adaptive medical image three-dimensional rebuilding method towards C/S framework - Google Patents
A kind of adaptive medical image three-dimensional rebuilding method towards C/S framework Download PDFInfo
- Publication number
- CN110349254A CN110349254A CN201910623642.XA CN201910623642A CN110349254A CN 110349254 A CN110349254 A CN 110349254A CN 201910623642 A CN201910623642 A CN 201910623642A CN 110349254 A CN110349254 A CN 110349254A
- Authority
- CN
- China
- Prior art keywords
- layer
- client
- network
- medical image
- server
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present invention provides a kind of adaptive medical image three-dimensional rebuilding method towards C/S framework, is related to medical image three-dimensional reconstruction field.This method by the general three-dimensional method for reconstructing based on four layer architectures provide it is a kind of in client and server-side all include four-layer structure general three-dimensional method for reconstructing, it is remote transfer protocol layer respectively that four-layer structure is upper the bottom of from, pretreatment volume data layer, rebuilds reuse algorithm layer and rendering visual model layer, then it is realized by the adaptive reconstruction mode selection method based on decision tree dynamically according to operation platform, data volume, network classification, the difference of network speed, adaptively switches reconstruction mode.The present invention can unify current various types of medical image three-dimensional reconstruction mechanism, different operation platforms, different transmission networks, different medical image data amounts are adapted to based on the Medical Imaging System that this method is realized, and according to different operation real time status switching at runtime medical image three-dimensional reconstruction mechanism, strong flexibility.
Description
Technical field
The present invention relates to medical image three-dimensional reconstruction field more particularly to a kind of adaptive doctors towards C/S framework
Learn three-dimensional reconstruction method.
Background technique
Medical image imaging device continues to develop, and the accuracy and speed that image generates is higher and higher, and Polaroid result will
It generates mass data (200MB~2GB), these data all bring challenge to doctor and Image archiving equipment.Doctor's reading
Bidimensional image quantity is doubled and redoubled, and workload increases, and be easy to cause and fails to pinpoint a disease in diagnosis.Therefore, three-dimensional reconstruction is to doctor one new
Dimension is observed, from different angles, different scale removes observation lesion or histoorgan.Three-dimensional reconstruction not only intuitively shows
Doctor is as a result, also allow the operating point amount for alleviating diagosis, and bring to anaphase, auxiliary surgery planning, doctors and patients' exchange etc.
Great convenience.
Existing three-dimensional reconstruction functional module is all integrated in PACS system or image workstation, as heart software package,
Lung function software package etc., these three-dimensional rebuilding methods are all based on local image data and run.With cloud computing, Internet of Things etc.
The fast development of technology, remote image technology (Tele-radiology) promote the development of the technologies such as remote medical consultation with specialists, long-range diagosis;
Simultaneously as mobile network's speed is promoted and mobile device performance improves, portable medical is also fast-developing, doctor also not only office
Limit is not also diagnosed in diagosis room, clinician only with local Image-aided.Therefore, long-range three-dimensional reconstruction research
More and more attention has been paid to.
Three-dimensional reconstruction refers to the mathematical model established to three-dimension object and be suitble to computer representation and processing, is in computer ring
The basis of its property is handled it, operated and analyzed under border, and establishes the virtual of expression objective world in a computer
The key technology of reality.Medical image three-dimensional reconstruction is to study the two dimensional image tomography sequence obtained by various medical imaging devices
The 3-D geometric model of tissue or organ is constructed, and draws and shows on the computer screen.It is divided from computing mechanism, three
Dimension method for reconstructing can be divided into client rebuild, server-side rebuild and three kinds of hybrid reconstruction, as shown in Figure 1, it is shown that A, B, C tri-
Kind re-establishment mechanism (reconstruction mode): mechanism A, net client carries out three-dimensional reconstruction process outside, and passes through wide area network or movement
Net etc. interacts Three-dimension Reconstruction Model with the Web server of hospital services network, while the image number on Web server connection backstage
The transmitting of medical image data is carried out according to library;Mechanism B carries out three-dimensional reconstruction process at the Web server end of hospital services network,
The image database on the backstage of Web server connection simultaneously carries out the transmitting of medical image data, and passes through wide area network or movement
Net etc. interacts Three-dimension Reconstruction Model with outer net client;Mechanism C, the Web in net client and hospital services network takes outside
Business device both ends all carry out three-dimensional reconstruction process, but the three-dimensional reconstruction effect of the two is different, the Three-dimensional Gravity that Web server carries out
Building is the medical image based on original resolution, and the three-dimensional reconstruction that client carries out is the medical image based on resolution decreasing.
Above-mentioned several method cuts both ways, and the applicable ability under different running environment, different application scene has very
Big difference, as shown in table 1.
Table 1 is existing, and there are three types of re-establishment mechanism comparisons
In customer resource requirements, network speed demand, operation fluency, platform flexibility, data volume adaptability, client
Picture quality, mobile universality, user experience and UI demonstrate one's ability several aspects, have made respectively point to above-mentioned three kinds of re-establishment mechanisms
Analysis.Mechanism A is relatively low to network rate request, and operation fluency is good, and client picture quality display effect is good, the experience of user
Strong with system demonstration ability, other aspects compare poor.Mechanism B does not need too many customer resources, and cross-platform adaptability is good,
It is good to data volume adaptability, it can also be easily applied to mobile end equipment, other aspects compare poor.Mechanism C operation is smooth
Property it is relatively good, client quality is high, and user experience is good, but poor to data volume applicability, other aspect performances are general.It is existing
These methods cut both ways, lack it is a kind of can to the unified Modeling of these methods, and can according to actual motion scene from
Dynamic switching re-establishment mechanism.
The current systems such as PACS and image workstation all use client re-establishment mechanism (the reconstruction side Web including plug-in type
Formula), and the drafting of pure server-side, blend rendering and pure Web re-establishment mechanism are due to being limited to mobile terminal performance, UI demonstrates one's ability,
Network speed etc. influences and limitation, and products application is also in prototype conceptual phase at present.But as the technologies such as 5G, service architecture are sent out
Exhibition, based on urgent demands such as the online diagosis of existing actual clinical, remote diagnosis, the following online three-dimensional reconstruction will be obtained extensively
General application.How a kind of applicability extensive, cross-platform three-dimensional rebuilding method is proposed, and according to client's running environment and scene energy
Enough adaptive switching re-establishment mechanisms are current techniques difficult point and challenge.
Summary of the invention
It is a kind of towards C/S framework the technical problem to be solved by the present invention is in view of the above shortcomings of the prior art, provide
Adaptive medical image three-dimensional rebuilding method can be run in existing a variety of application platforms, and applicability is wider, can satisfy clinic
The demands such as online diagosis, remote diagnosis, solve conventional three-dimensional re-establishment mechanism defect
In order to solve the above technical problems, the technical solution used in the present invention is:
A kind of adaptive medical image three-dimensional rebuilding method towards C/S framework, the general three-dimensional weight including four layer architectures
Construction method and adaptive reconstruction mode selection method based on decision tree;
In client and server-side all include four-layer structure in the general three-dimensional method for reconstructing of four layer architecture, the bottom of from and
Upper is remote transfer protocol layer R1, pretreatment volume data layer R2, reconstruction reuse algorithm layer R3 and rendering visual model layer R4 respectively;
Remote transfer protocol layer is fixed for providing three-dimensional reconstruction communication transport protocols and data/control message contents semantic and format
Justice;Pretreatment volume data layer is for providing the processing of three-dimensional reconstruction body data interpolating, including thickness, pixel depth, sampling resolution;
It rebuilds reuse algorithm layer and is used to provide different three-dimensional reconstruction algorithm and reconstruction model output;Rendering visual model layer is for providing
The rendering visualization of three-dimensional reconstruction result and picture are shown;It is flexibly straight from bottom R1 according to different application scenarios and demand
It connects and jumps to any of the above one layer of R2, R3 or R4, simplify the layer at customer service both ends, form different application models, including following
Four kinds of modes:
(a) for remote transfer protocol layer, client and server can select HTTP, FTP, RMI, HTTPS agreement into
Row remote data transmission;For pre-processing volume data layer, client and server stores the medical image of DICOM format;
For rebuilding reuse algorithm layer and rendering visual model layer, since the mode is rebuild in client, so only client has
This double-layer structure, client carry out three-dimensional reconstruction to medical image using MPR, VR, SSD, MIP, MinIP, AvgIP algorithm, and
Threedimensional model is shown to the electronics in client using Medical Image Workstation or ActiveX, Applet, Flash plug-in card program
On the screen of equipment;
(b) for remote transfer protocol layer, client and server can select HTTP, AJAX, HTTPS, FTP, RMI to assist
View or technology carry out remote data transmission;For pre-process volume data layer, server-side be DICOM format medical image, and
Client is model file;For rebuilding reuse algorithm layer, since three-dimensional reconstruction process is carried out in server, so only taking
Business device has this layer of structure, and medical image is carried out Three-dimensional Gravity using iso-surface patch (Surface Rendering) algorithm in this layer
It builds;For rendering visual model layer, shown due to needing to carry out three-dimensional reconstruction in client, so only client has this layer
Server-side is rebuild the three-dimensional modeling data that reuse algorithm layer is rebuild and utilizes player plug-in unit in the electronics of client by structure, this layer
Browsing displaying is carried out on the screen of equipment;
(c) for remote transfer protocol layer, client and server can select HTTP, WebSocket, WebWork to assist
View or technology carry out remote data transmission;For pretreatment volume data layer and reuse algorithm layer is rebuild, since the mode is only
It is rebuild in server, so only server has this double-layer structure, server stores the medical image of DICOM format, then sharp
These medical images are carried out with volume drawing (Volume Rendering) or iso-surface patch (Surface Rendering) algorithm
Three-dimensional reconstruction;For rendering visual model layer, technology that client and server uses is different, client using HTML,
Canvas and WebGL technology, and server-side uses VTK, OpenGL technology;
(d) for remote transfer protocol layer, client and server can select AJAX, WebSocket, WebWork,
Http protocol or technology carry out remote data transmission;For pre-processing volume data layer, server storage is original resolution
DICOM medical image, and client storage be down-sampled resolution ratio DICOM medical image;For rebuilding reuse algorithm layer,
MPR, VR that client uses perhaps iso-surface patch (Surface Rendering) algorithm and server using VR or face
Draw (Surface Rendering) algorithm;For rendering visual model layer, client is serviced using WebGL technology
Device is using VTK, OpenGL technology;
Adaptive reconstruction mode selection method based on decision tree refers to based on the customized reconstruction process of user, dynamically root
According to operation platform, data volume, network classification, the difference of network speed, automatic switchover mode;Handoff procedure, which uses, is based on decision tree
Method, the attribute that the decision tree building process is related to include operation platform, data volume, network classification, network speed;Its
In, operation platform is divided into that PC is locally applied, PC Web application, plate are locally applied, plate Web application, smart phone are locally answered
It is applied with smart phone Web;Data volume is divided into two classes, i.e., the image number of plies is less than 200 layers and data volume is less than 100M, image bearing layer
Greater than 200 layers or data volume is greater than 100M;Network classification includes wide area network, local area network, wireless network, mobile network;Network speed is
The actual transmission speed of current network;Network speed is a dynamic parameter, and defining basis is two threshold parameters, a upper limit
One lower limit, different network types have different threshold values, these threshold values are set as needed;
Decision process is first since operation platform;Then judge data volume, weigh in terms of number and size two respectively
Amount;Current network type is checked later;It is last that corresponding reconstruction model is selected according to current dynamic network speed.
The decision tree, longitudinal includes four-layer structure, it is top-down be respectively operation platform, medical image data volume,
Network type and current network speed;From the point of view of laterally, client is divided into 6 kinds according to operation platform by first layer structure,
It is the local PC App, PC Web App, the local Pad App, Pad Web App, the local Phone App and Phone Web respectively
App;Then second layer structure judges the size of medical image data amount, and medical image is divided into two according to the size of data volume
Kind, one is the image numbers of plies less than 200 layers and data volume is less than 100M, and another kind is that the image number of plies is greater than 200 layers or data volume
Greater than 100M, every kind of client all respectively analyzes both of these case;Then third layer structure checks current network class
Type, for PC, network type includes wide area network, local area network and wireless network;For Pad and Phone, network type packet
Include mobile network and wireless network;The last layer structure selects corresponding reconstruction mode according to current dynamic network speed.
The beneficial effects of adopting the technical scheme are that provided by the invention towards the adaptive of C/S framework
Medical image three-dimensional rebuilding method can unify current various types of medical image three-dimensional reconstruction mechanism, be based on the party
The Medical Imaging System that method is realized have adapt to different operation platforms, different transmission network, different medical image data amounts energy
Power, and according to different operation real time status switching at runtime medical image three-dimensional reconstruction mechanism, strong flexibility.
Detailed description of the invention
Fig. 1 is that existing three-dimensional reconstruction mechanism divides schematic diagram;
Fig. 2 is the four-layer structure signal in the general three-dimensional method for reconstructing provided in an embodiment of the present invention based on layer architecture
Figure;
Fig. 3 is the application model schematic diagram provided in an embodiment of the present invention towards C/S framework;
Fig. 4 is that the different application form of the general three-dimensional method for reconstructing provided in an embodiment of the present invention based on layer architecture is shown
It is intended to;
Fig. 5 is the building structural schematic diagram of decision tree provided in an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
A kind of adaptive medical image three-dimensional rebuilding method towards C/S framework, the general three-dimensional weight including four layer architectures
Construction method and adaptive reconstruction mode selection method based on decision tree.
It in client and server-side all include four-layer structure in the general three-dimensional method for reconstructing of four layer architectures, as shown in Fig. 2,
Upper the bottom of from is remote transfer protocol layer, pretreatment volume data layer, reconstruction reuse algorithm layer and rendering visual model layer respectively.
Remote transfer protocol layer for provide three-dimensional reconstruction communication transport protocols and data/control message contents semantic and
Format definition, such as: WebSocket, HTTP, Socket, FTP.
It pre-processes volume data layer and the processing of three-dimensional reconstruction body data interpolating, including thickness, pixel depth, sampling resolution is provided
Rate, such as: image interpolation, image cutting, resampling.
It rebuilds reuse algorithm layer and different three-dimensional reconstruction algorithms is provided, such as surface rendering, volume drawing and reconstruction model are defeated
Out, such as: volume drawing, iso-surface patch, multiplanar reconstruction, maximum intensity projection.
It renders visual model layer and the rendering visualization of three-dimensional reconstruction result is provided, including visual model data are shown, GPU number
According to drafting or image data display technology mode, such as: various plug-in units, WebGL, Image Rendering Canvas.
From figure 2 it can be seen that according to different application scenarios and demand, from bottom R1 can leap to above appoint
Anticipate one layer of R2, R3 or R4, the applicable flexibility of implementation method.The present embodiment method is intended for client-server software architecture
(Client/Server, C/S) software application, therefore the general three-dimensional method for reconstructing of four layer architectures of the present embodiment is in client
It all include four layer architectures with server-side, application model is as shown in Figure 3.
According to different application scenarios and demand, the layer at customer service both ends be can simplify, and form different application models,
According to four layer architectures described in the present embodiment, the three-dimensional rebuilding method occurred at present can be divided into four kinds of typical cases as shown in Figure 4
Application model, including following four mode:
(a) for remote transfer protocol layer, client and server can select HTTP, FTP, RMI, HTTPS agreement into
Row remote data transmission;For pre-processing volume data layer, client and server stores the medical image of DICOM format;
For rebuilding reuse algorithm layer and rendering visual model layer, since the mode is rebuild in client, so only client has
This double-layer structure, client carry out three-dimensional reconstruction to medical image using MPR, VR, SSD, MIP, MinIP, AvgIP algorithm, and
Threedimensional model is shown to the electronics in client using Medical Image Workstation or ActiveX, Applet, Flash plug-in card program
On the screen of equipment;
(b) for remote transfer protocol layer, client and server can select HTTP, AJAX, HTTPS, FTP, RMI to assist
View or technology carry out remote data transmission;For pre-process volume data layer, server-side be DICOM format medical image, and
Client is model file;For rebuilding reuse algorithm layer, since three-dimensional reconstruction process is carried out in server, so only taking
Business device has this layer of structure, and medical image is carried out Three-dimensional Gravity using iso-surface patch (Surface Rendering) algorithm in this layer
It builds;For rendering visual model layer, shown due to needing to carry out three-dimensional reconstruction in client, so only client has this layer
Server-side is rebuild the three-dimensional modeling data that reuse algorithm layer is rebuild and utilizes player plug-in unit in the electronics of client by structure, this layer
Browsing displaying is carried out on the screen of equipment;
(c) for remote transfer protocol layer, client and server can select HTTP, WebSocket, WebWork to assist
View or technology carry out remote data transmission;For pretreatment volume data layer and reuse algorithm layer is rebuild, since the mode is only
It is rebuild in server, so only server has this double-layer structure, server stores the medical image of DICOM format, then sharp
These medical images are carried out with volume drawing (Volume Rendering) or iso-surface patch (Surface Rendering) algorithm
Three-dimensional reconstruction;For rendering visual model layer, technology that client and server uses is different, client using HTML,
Canvas and WebGL technology, and server-side uses VTK, OpenGL technology;
(d) for remote transfer protocol layer, client and server can select AJAX, WebSocket, WebWork,
Http protocol or technology carry out remote data transmission;For pre-processing volume data layer, server storage is original resolution
DICOM medical image, and client storage be down-sampled resolution ratio DICOM medical image;For rebuilding reuse algorithm layer,
MPR, VR that client uses perhaps iso-surface patch (Surface Rendering) algorithm and server using VR or face
Draw (Surface Rendering) algorithm;For rendering visual model layer, client is serviced using WebGL technology
Device is using VTK, OpenGL technology.
It can be seen from figure 4 that tri- kinds of A, B, C typical re-establishment mechanisms are (a), (c), (d) in Fig. 4 respectively in Fig. 1
Specific application form.Model data is pushed to client using after server Three-dimension Reconstruction Model by (b) quasi-mode in Fig. 4, benefit
It is browsed with player plug-in unit.The framework of this layering of the present embodiment can flexibly correspond to different application scenarios.
Based on above-mentioned C/S layered structure, the present embodiment proposes based on certainly tri- kinds of typical reconstruction process of A, B, C in Fig. 1
The adaptive reconstruction mode automatic selecting method of plan tree.In practical application, user can according to actual needs with above-mentioned layering knot
Structure, predefined many kinds reconstruction process.
Adaptive reconstruction mode selection method based on decision tree refers to based on the customized reconstruction process of user, dynamically root
According to network, operation platform, data volume, network classification, the difference of network speed, automatic switchover mode can be best to user
Usage experience, rather than it is fixed to a certain reconstruction process mode.
The process of the switching, which uses, is based on traditional decision-tree, and the attribute that the decision tree building process is related to includes fortune
Row platform, data volume, network classification, network speed.Wherein, operation platform is divided into that PC is locally applied, PC Web application, plate sheet
Ground application, plate Web application, smart phone is locally applied and smart phone Web is applied;Data volume is divided into two classes, i.e. image bearing layer
Number is less than 200 layers and data volume is less than 100M, image bearing layer is greater than 200 layers or data volume is greater than 100M;Network classification includes wide area
Net, local area network, wireless network, mobile network (cellular network);Network speed is the actual transmission speed of current network.The structure of decision tree
It is as shown in Figure 5 to build structure.
Decision process is first since operation platform;Then judge data volume, weigh in terms of number and size two respectively
Amount;Current network type is checked later;It is last that corresponding reconstruction model is selected according to current dynamic network speed.Network speed
It is a dynamic parameter, defining basis is two threshold parameters, and one lower limit of a upper limit, different network types has different
Threshold value, these threshold values set as needed.The present embodiment shares four class networks, and 8 threshold values, the threshold value of setting is respectively T1
=100K, T2=1M, T3=1M, T4=10M, T5=1M, T6=5M, T7=500K, T8=1M.
The decision tree, longitudinal includes four-layer structure, it is top-down be respectively operation platform, medical image data volume,
Network type and current network speed;From the point of view of laterally, client is divided into 6 kinds according to operation platform by first layer structure,
It is the local PC App, PC Web App, the local Pad App, Pad Web App, the local Phone App and Phone Web respectively
App;Then second layer structure judges the size of medical image data amount, and medical image is divided into two according to the size of data volume
Kind, one is the image numbers of plies less than 200 layers and data volume is less than 100M, and another kind is that the image number of plies is greater than 200 layers or data volume
Greater than 100M, every kind of client all respectively analyzes both of these case;Then third layer structure checks current network class
Type, for PC, network type includes wide area network, local area network and wireless network;For Pad and Phone, network type packet
Include mobile network and wireless network;The last layer structure selects corresponding reconstruction mould in Fig. 1 according to current dynamic network speed
Formula.
It is described in detail by taking the Liang Ge branch of decision tree in Fig. 5 as an example below.
First branch is that the local PC App uses wide area network to the image number of plies less than 200 layers and data volume is less than 100M
When medical image is operated, different reconstruction process is selected according to network speed.T1, T2 are wide area network network speed respectively
Bound, if network speed be less than T1, automatically select B reconstruction model;If network speed is greater than T1 and is less than T2, C reconstruction model is automatically selected;
If network speed is greater than T2, A reconstruction model is automatically selected.Similarly, the local PC App is less than the image number of plies using local area network and wireless network
The case where medical image of 200 layers and data volume less than 100M is operated is also to automatically select correspondence according to network speed speed in this way
Reconstruction model.
Second branch is that Pad Web App is greater than 200 layers to the image number of plies using mobile network or data volume is greater than 100M
Medical image when operated, different reconstruction process is selected according to network speed.T7, T8 are mobile network net respectively
The bound of speed automatically selects B reconstruction model if network speed is less than T7;If network speed is greater than T7 and is less than T8, automatically selects B and rebuild mould
Type;If network speed is greater than T8, C reconstruction model is automatically selected.Similarly, Pad Web App is greater than 200 to the image number of plies using wireless network
The case where layer or data volume are operated greater than the medical image of 100M be also automatically selected in this way according to network speed speed it is corresponding
Reconstruction model.
The case where other branches is also to automatically select corresponding reconstruction model according to network speed speed in this way.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify to technical solution documented by previous embodiment, or some or all of the technical features are equal
Replacement;And these are modified or replaceed, model defined by the claims in the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (2)
1. a kind of adaptive medical image three-dimensional rebuilding method towards C/S framework, it is characterised in that: this method includes four layer frames
The general three-dimensional method for reconstructing of structure and adaptive reconstruction mode selection method based on decision tree;
It in client and server-side all include four-layer structure in the general three-dimensional method for reconstructing of four layer architecture, from upper point of bottom
It is not remote transfer protocol layer R1, pretreatment volume data layer R2, rebuilds reuse algorithm layer R3 and rendering visual model layer R4;Remotely
Transmission protocol layer is for providing three-dimensional reconstruction communication transport protocols and data/control message contents semantic and format definition;In advance
Processing volume data layer is for providing the processing of three-dimensional reconstruction body data interpolating, including thickness, pixel depth, sampling resolution;It rebuilds
Reuse algorithm layer is used to provide different three-dimensional reconstruction algorithm and reconstruction model output;Rendering visual model layer is for providing three-dimensional
The rendering visualization of reconstructed results and picture are shown;According to different application scenarios and demand, flexibly directly jumped from bottom R1
To any of the above one layer of R2, R3 or R4, simplifies the layer at customer service both ends, form different application models, including following four
Mode:
(a) for remote transfer protocol layer, it is remote that client and server can select HTTP, FTP, RMI, HTTPS agreement to carry out
Number of passes is according to transmission;For pre-processing volume data layer, client and server stores the medical image of DICOM format;For
Rebuild reuse algorithm layer and rendering visual model layer, due to the mode be client rebuild, so only client have this two
Layer structure, client carries out three-dimensional reconstruction to medical image using MPR, VR, SSD, MIP, MinIP, AvgIP algorithm, and utilizes
Threedimensional model is shown the electronic equipment in client by Medical Image Workstation or ActiveX, Applet, Flash plug-in card program
Screen on;
(b) for remote transfer protocol layer, client and server can select HTTP, AJAX, HTTPS, FTP, RMI protocol or
Technology carries out remote data transmission;For pre-processing volume data layer, server-side be DICOM format medical image, and client
End is model file;For rebuilding reuse algorithm layer, since three-dimensional reconstruction process is carried out in server, so only server
There is this layer of structure, medical image is subjected to three-dimensional reconstruction using iso-surface patch algorithm in this layer;For rendering visual model layer, by
Three-dimensional reconstruction, which is carried out, in client in needs shows that, so only client has this layer of structure, server-side is rebuild field by this layer
The three-dimensional modeling data that scape algorithm layer is rebuild carries out browsing exhibition using player plug-in unit on the screen of the electronic equipment of client
Show;
(c) for remote transfer protocol layer, client and server can select HTTP, WebSocket, WebWork agreement or
Technology carries out remote data transmission;For pretreatment volume data layer and reuse algorithm layer is rebuild, since the mode is only to take
Business, which is thought highly of, builds, so only server has this double-layer structure, server stores the medical image of DICOM format, then utilizes body
It draws or iso-surface patch algorithm carries out three-dimensional reconstruction to these medical images;For rendering visual model layer, client and service
The technology that device uses is different, and client uses HTML, Canvas and WebGL technology, and server-side uses VTK, OpenGL
Technology;
(d) for remote transfer protocol layer, client and server can select AJAX, WebSocket, WebWork, HTTP to assist
View or technology carry out remote data transmission;For pre-processing volume data layer, that server stores is the DICOM doctor of original resolution
Learn image, and client storage be down-sampled resolution ratio DICOM medical image;For rebuilding reuse algorithm layer, client
MPR, VR of use perhaps iso-surface patch algorithm and server using VR or iso-surface patch algorithm;For rendering visual model
Layer, client is using WebGL technology, and server is using VTK, OpenGL technology;
Adaptive reconstruction mode selection method based on decision tree refers to based on the customized reconstruction process of user, dynamically according to fortune
Row platform, data volume, network classification, the difference of network speed, automatic switchover mode;Handoff procedure, which uses, is based on decision tree side
Method, the attribute that the decision tree building process is related to include operation platform, data volume, network classification, network speed;Wherein,
Operation platform be divided into that PC is locally applied, PC Web application, plate are locally applied, plate Web application, smart phone are locally applied and
Smart phone Web application;Data volume is divided into two classes, i.e., the image number of plies is less than 200 layers and data volume is less than 100M, image bearing layer is greater than
200 layers or data volume are greater than 100M;Network classification includes wide area network, local area network, wireless network, mobile network;Network speed is current
The actual transmission speed of network;Network speed is a dynamic parameter, and defining basis is two threshold parameters, one the upper limit one
Lower limit, different network types have different threshold values, these threshold values are set as needed;
Decision process is first since operation platform;Then judge data volume, measured in terms of number and size two respectively;It
After check current network type;It is last that corresponding reconstruction model is selected according to current dynamic network speed.
2. the adaptive medical image three-dimensional rebuilding method according to claim 1 towards C/S framework, it is characterised in that:
The decision tree, longitudinal includes four-layer structure, and top-down is operation platform, the data volume of medical image, network type respectively
With current network speed;From the point of view of laterally, client is divided into 6 kinds according to operation platform, is PC respectively by first layer structure
Local App, PC Web App, the local Pad App, Pad Web App, the local Phone App and Phone Web App;Then
Two-layer structure judges the size of medical image data amount, medical image is divided into two kinds according to the size of data volume, one is shadows
The picture number of plies is less than 200 layers and data volume is less than 100M, and another kind is that the image number of plies is greater than 200 layers or data volume is greater than 100M, often
Kind client all respectively analyzes both of these case;Then third layer structure checks current network type, and PC is come
It says, network type includes wide area network, local area network and wireless network;For Pad and Phone, network type include mobile network and
Wireless network;The last layer structure selects corresponding reconstruction mode according to current dynamic network speed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910623642.XA CN110349254B (en) | 2019-07-11 | 2019-07-11 | C/S architecture-oriented adaptive medical image three-dimensional reconstruction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910623642.XA CN110349254B (en) | 2019-07-11 | 2019-07-11 | C/S architecture-oriented adaptive medical image three-dimensional reconstruction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110349254A true CN110349254A (en) | 2019-10-18 |
CN110349254B CN110349254B (en) | 2022-12-06 |
Family
ID=68175871
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910623642.XA Active CN110349254B (en) | 2019-07-11 | 2019-07-11 | C/S architecture-oriented adaptive medical image three-dimensional reconstruction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110349254B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113808051A (en) * | 2021-09-26 | 2021-12-17 | 武汉联影生命科学仪器有限公司 | Multi-modal medical image reconstruction system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120084350A1 (en) * | 2010-10-05 | 2012-04-05 | Liang Xie | Adaptive distributed medical image viewing and manipulating systems |
CN102592310A (en) * | 2011-12-28 | 2012-07-18 | 中国人民解放军第四军医大学唐都医院 | Three-dimensional reconstruction method of image of mobile terminal for medical image teaching |
CN107835436A (en) * | 2017-09-25 | 2018-03-23 | 北京航空航天大学 | A kind of real-time virtual reality fusion live broadcast system and method based on WebGL |
-
2019
- 2019-07-11 CN CN201910623642.XA patent/CN110349254B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120084350A1 (en) * | 2010-10-05 | 2012-04-05 | Liang Xie | Adaptive distributed medical image viewing and manipulating systems |
CN102592310A (en) * | 2011-12-28 | 2012-07-18 | 中国人民解放军第四军医大学唐都医院 | Three-dimensional reconstruction method of image of mobile terminal for medical image teaching |
CN107835436A (en) * | 2017-09-25 | 2018-03-23 | 北京航空航天大学 | A kind of real-time virtual reality fusion live broadcast system and method based on WebGL |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113808051A (en) * | 2021-09-26 | 2021-12-17 | 武汉联影生命科学仪器有限公司 | Multi-modal medical image reconstruction system and method |
Also Published As
Publication number | Publication date |
---|---|
CN110349254B (en) | 2022-12-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10671255B2 (en) | Facilitating transitioning between viewing native 2D and reconstructed 3D medical images | |
Mwalongo et al. | State‐of‐the‐Art Report in Web‐based Visualization | |
CN103136785B (en) | For the implementation method of the human medical model three-dimension visible sysem of mobile terminal | |
Lin et al. | Visualization of indoor thermal environment on mobile devices based on augmented reality and computational fluid dynamics | |
CN101976458A (en) | Medical image three-dimensional visualization method applied to mobile handheld equipment | |
JP7083047B2 (en) | Medical image 4D visualization method and equipment | |
EP2084671A1 (en) | Method and system for delivering and interactively displaying three-dimensional graphics | |
Doellner et al. | Server-based rendering of large 3D scenes for mobile devices using G-buffer cube maps | |
Hachaj | Real time exploration and management of large medical volumetric datasets on small mobile devices—evaluation of remote volume rendering approach | |
CN110163959A (en) | A kind of medical image three-dimensional stereo reconstruction device and equipment | |
JP4203251B2 (en) | Volume rendering processing method, volume rendering processing system, computer and program | |
US20220346888A1 (en) | Device and system for multidimensional data visualization and interaction in an augmented reality virtual reality or mixed reality environment | |
CN113409333B (en) | Three-dimensional image cutting method and electronic equipment | |
CN110349254A (en) | A kind of adaptive medical image three-dimensional rebuilding method towards C/S framework | |
CN115080886A (en) | Three-dimensional medical model GLB file analysis and display method based on mobile terminal | |
CN113379929B (en) | Bone tissue repair virtual reality solution method based on physical simulation | |
Ji et al. | Research on telemedicine technology and implement based on Virtual Reality | |
CN114388145A (en) | Online inquiry method and device | |
Yin et al. | Remote three-dimensional reconstruction for medical images based on Browser/Server framework | |
Zhang et al. | Server-aided 3d dicom viewer for mobile platforms | |
Li et al. | R4: a client server architecture oriented open three dimensional reconstruction layered reference model for medical images | |
CN113096779A (en) | Medical image cloud image system based on distributed CT terminal | |
Pham et al. | Delivery and interactive processing of visual data for a cooperative telemedicine environment | |
CN116958392A (en) | Graphic image processing method, graphic image processing device and medical graphic image application system | |
Al-Saidi et al. | Distributed collaborative visualization using light field rendering |
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 |