CN108846896A - A kind of automatic molecule protein molecule body diagnostic system - Google Patents
A kind of automatic molecule protein molecule body diagnostic system Download PDFInfo
- Publication number
- CN108846896A CN108846896A CN201810697956.XA CN201810697956A CN108846896A CN 108846896 A CN108846896 A CN 108846896A CN 201810697956 A CN201810697956 A CN 201810697956A CN 108846896 A CN108846896 A CN 108846896A
- Authority
- CN
- China
- Prior art keywords
- point
- point cloud
- protein molecule
- protein
- module
- 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
Classifications
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/006—Inverse problem, transformation from projection-space into object-space, e.g. transform methods, back-projection, algebraic methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to medical diagnosis technical fields, disclose a kind of automatic molecule protein molecule body diagnostic system, and the automatic molecule protein molecule body diagnostic system includes：Protein detection module, DNA detection module, main control module, DNA sequencing module, cancer cell detection module, analysis expert module, data memory module, display module；The detection method of protein detection module includes the gray scale or texture features according to magnetic resonance or computer tomography voxel data, draws boundary contour and interior tissue edge line outside protein molecule body.The present invention can quick, accurate, low cost progress DNA sequencing by DNA sequencing module；The cancer cell that can easily detect in a short time in peripheral blood is capable of providing by cancer cell detection module simultaneously；More professional detection data can be analyzed by analysis expert module, ensure the reliability of testing result.
Description
Technical field
The invention belongs to medical diagnosis technical field more particularly to a kind of automatic molecule protein molecule body diagnosis systems
System.
Background technique
Currently, the prior art commonly used in the trade is such：
Molecular diagnosis refers to the structure or table using molecule protein molecule body method detection patient's body inhereditary material
The technology of diagnosis is made up to horizontal variation.Molecular diagnosis is the main method of predictive diagnosis, can both carry out individual inheritance
The diagnosis of disease, infectious diseases etc. can also carry out pre-natal diagnosis.It is relevant to disease various that molecular diagnosis is primarily referred to as coding
The genetic test of structural proteins, enzyme, antigen-antibody, immunological molecule.However, existing automatic molecule protein molecule body is examined
That there are DNA sequencing speed is slow, at high cost for disconnected system；The disadvantages of detecting cancer cell simultaneously consuming time is long.
Optical 3-dimensional imaging is a kind of emerging optical image technology, it passes through fused protein molecule body body surface measurement
Multi-angle optical signal, the anatomical structure of protein molecule body and tissue optical parameter information are based on accurate protein molecule
The position of targeting target and strength distributing information in optical transport Model Reconstruction living body protein molecule body in body tissue.Wherein,
The accurate description of optical transmission process and the accurate quick reconstruction of targeting target are optical 3-dimensional imagings in protein molecule body tissue
The basis that method is realized.Beijing University of Technology its patent application document " the multispectral autofluorescence tomography based on single-view at
As method for reconstructing " (application number 200810116818.4, applying date 2008.7.18, grant number ZL200810116818.4, authorization
Day 2010.6.2) in propose a kind of multispectral autofluorescence tomography rebuilding method based on single width view.The patent skill
Art is based on diffusion approximation equation, considers the nonuniformity characteristic of protein molecule body and the spectrum characteristic of autofluorescence light source, utilizes
In multiple spectral coverage fluorescence datas of single angle measurement, the position of targeting target and intensity distribution in protein molecule body body are rebuild
Information.But since diffusion approximation equation is only applicable to describe the optical transmission process in high scattering properties tissue, for low scattering
Characteristic and cavity tissue, its solving precision are very low.Therefore, the patented technology is for the albumen with a variety of scattering properties tissues
Matter molecule body solving precision is poor, is difficult accurately to obtain the position of targeting target and intensity distribution letter in protein molecule body body
Breath.Xian Electronics Science and Technology University is in its patent application document " optical 3-dimensional imaging based on protein molecule body tissue specificity
Method " (application number 201110148500.6, applying date 2011.6.2, grant number ZL201110148500.6, grant date
2013.4.3 a kind of optical 3-dimensional imaging method based on protein molecule body tissue specificity) is proposed.The patent is based on egg
White matter molecule body tissue specificity optical transport combined mathematics model and complete sparse regularization method establish objective function, using base
It is solved in the method for mixing and optimizing of task orientation, to realize the optical 3-dimensional imaging of targeting target in vivo, is solved existing
It cannot achieve in technology and standard carried out to the complex proteins molecule body with irregular anatomical structure and a variety of scattering properties tissues
The problem of really quickly optical 3-dimensional is imaged.However, in the light based on nonuniformity model and protein molecule body tissue specificity
It learns in three-D imaging method, the intracorporal histoorgan of protein molecule is accurately and effectively divided and the high quality number of grid
Being worth discrete is accurate building and the essential committed step for solving optical imagery model.Organ segmentation is a complexity, numerous
Trivial work needs professional software and human-computer interaction that could complete.The discrete software for not only needing profession of grid and human-computer interaction
It could complete, and also have difference for the discrete quality of different imaging requirements grids.Meanwhile there is also not for grid discrete
Controllable factor, which results in the discrete quality of grid on model solution and to rebuild the uncontrollable influence of bring.
Computer graphics data processing is related to multiple subjects, mainly includes：Object detection and recognition, edge extracting, feature
Extraction and three-dimensional reconstruction etc..Three-dimensional reconstruction is also based on the modeling technique of image, is just concerned at the beginning of birth,
This method only needs two frame adjacent images that can more accurately recover the three-dimensional space of matching characteristic point and camera in image
Relationship.In this process, the quantity of matching characteristic point directly determines the quality for the point cloud that three-dimensional reconstruction obtains, so that it is determined that
The quality of reconstruction model.
Common three-dimensional rebuilding method has three classes：(1) Stereo Vision.This method simulates human visual system to objective
The perceptive mode of three-dimension object the same scenery is imaged in different location using more than two cameras, further according to two frames
Disparity map between image, is converted to depth map, obtains the depth information of object.The geometrical model file that the method generates is logical
It is often smaller, it is easy to be used in virtual reality.But this method needs to overcome the problems, such as that object features are sparse, when texture is flat
When, there is large stretch of white space in the disparity map being calculated, the dense degree for putting cloud is very low.(2) motion structure method.To object
Body carry out the movement that point around any position in bat, rigid objects occurs between two field pictures be it is identical, by two frames
Several pairs of characteristic points are extracted between image and are matched, and the transformation matrix that object moves can be calculated, according to change
Changing matrix can determine that the positional relationship between two cameras can restore characteristic point in world coordinate system by pinhole imaging system principle
In coordinate.The method develops comparative maturity, the movement of camera can be calculated in the case where camera internal reference is demarcated, to sparse point
Cloud, which carries out processing, to be obtained compared with dense point cloud, and recovers more accurately threedimensional model.But it requires adjacent two interframe
Matching characteristic point quantity is more, therefore in the negligible amounts of the flat region available point of feature.(3) based on the side of depth image
Method.The point cloud of the object under Current camera coordinate system, adjacent two frame can be generated with depth map by the RGB figure of every frame image
Two groups of point clouds that RGBD figure generates are matched, and calculate the transformation matrix of two frame cameras, so that it may which two groups of point clouds are fused to generation
Boundary's coordinate system.The point cloud that the method is calculated is more accurate, and the dense degree for putting cloud is higher.But it needs depth camera
Assistance, and it is very sensitive to the precision of depth map, rebuild in scene on a large scale, the precision of depth camera is always limited, and
The precision of depth camera will be directly linked the precision of reconstruction point cloud.
In above method, the calculation amount that stereo vision method needs is smaller, but obtained in image texture flat site
There are white spaces for disparity map, therefore the dense degree of point cloud being calculated is very low；Motion structure method universality with higher,
Derivation history wherein comprising sparse cloud to dense point cloud, but the dense degree of the dense point cloud obtained still depends on figure
The dense degree of point cloud of the texture complexity degree of picture, the image flat for texture, acquisition is also relatively low；Based on depth image
Method for reconstructing precision is higher, and does not require the texture complexity degree of image, but this method is to the quick of depth camera precision
Sense degree is higher, not applicable at present to rebuild with a wide range of object dimensional.
In conclusion problem of the existing technology is：
Existing automatic molecule protein molecule body diagnostic system is slow to DNA sequencing speed, at high cost；It is thin to detect cancer simultaneously
Consuming time is long by born of the same parents.
Need to carry out that cumbersome organ segmentation and grid are discrete could obtain optical 3-dimensional imaging reconstruction knot in the prior art
Fruit.
Validity of the present invention improves Three-dimensional Gravity and lays foundations the method for the dense degree of cloud, is not limited to that specifically around clapping image sequence
Column, are not too dependent on the adjustment of parameter, can improve available point cloud in a relatively short period of time in the case where lower calculation amount
Dense degree, while the erroneous point cloud in origin cloud can be deleted, so that the point cloud obtained overcomes texture to a certain extent
Flat influence.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of automatic molecule protein molecule body diagnosis systems
System.
The invention is realized in this way a kind of automatic molecule protein molecule body diagnostic system, including：
Protein detection module, connect with main control module, for being detected by protein detection instrument to protein；Egg
White matter detector draws protein molecule body according to magnetic resonance or the gray scale or texture features of computer tomography voxel data
Outer boundary contour line and interior tissue edge line；Voxel data and label based on magnetic resonance or computed tomography reconstruction
Interior tissue edge line, construction inner boundary node be enriched with function；Consider the structural heterogeneity and light of protein molecule body tissue
Specificity is learned, light particle is described in protein molecule body using the adaptive optical transmission mathematical model based on mixing photon transport equation
In transmission process；In view of application advantage of the finite volume method on hexahedron voxel grid, using extension finite volume method pair
Adaptive optical transmits mathematical model and carries out numerical discretization and solution, establishes in Description and linearly closes between target and body surface measurement value
The system equation of system；Consider the sparsity of internal target distribution and the imperfection of body surface measurement data, establish based on it is sparse just
Then change the objective function of strategy and the fusion preliminary target positioning result of priori；Using suitable Optimization Method objective function,
Carry out accurate, the quick reconstruction of targeting target in protein molecule body body；
DNA detection module, connect with main control module, for being detected by DNA detector to DNA；
Main control module, with protein detection module, DNA detection module, DNA sequencing module, cancer cell detection module, expert
Analysis module, data memory module, display module connection, work normally for controlling modules；
DNA sequencing module, connect with main control module, for the DNA of detection to be sequenced；
Cancer cell detection module, connect with main control module, for detecting the cancer cell in peripheral blood；
Analysis expert module, connect with main control module, carries out for commenting on net by on-line expert to the data of detection
Line analysis；
Data memory module is connect with main control module, for storing the data information of detection；
Display module is connect with main control module, for showing the data information of detection.
Further, protein detection instrument, which detect to protein, further includes：
(1) after rebuilding, one group is obtained around image sequence is clapped, to every frame around bat image zooming-out object wheel by photographic equipment
Exterior feature, and 255 are set by the pixel value in contour area, the pixel value outside profile is set as 0, obtains a frame bianry image, is claimed
For effective coverage figure；Obtain the very low point cloud of a consistency, referred to as initial point cloud, at the same also obtain each frame camera relative to
The spin matrix R and translation vector t of world coordinate system, spin matrix and translation vector combine to form transformation matrix M；
(2) each point in initial point cloud is traversed, obtaining all the points in initial point cloud, value is most on three axis of x, y, z
Big value and minimum value, and the distance between maxima and minima difference on each axis is calculated, it is denoted as x_dis, y_dis, z_ respectively
Dis, respectively by this three range differences divided by 100, three obtained amount, referred to as the derivation scale of initial point cloud are denoted as x_
scalar,y_scalar,z_scalar；
(3) using a point in initial point cloud as source point, the positive negative direction along three directions of x, y, z respectively extends pair respectively
The derivation scale size calculated in step (2) is answered, a cuboid centered on source point, the length and width high score of the cuboid are obtained
Not Wei 2*x_scalar, 2*y_scalar, 2*z_scalar, the source point center toward extending 26 sides around cuboid altogether
To deriving a new point in each direction, take the normal vector of the new point identical as the normal vector of source point, and each derivation point
Record its source point；
(4) operation of derivation described in a step 4) is all carried out to each of initial point cloud point, will obtain a group
Raw point cloud, the quantity at this cloud midpoint are 26 times of initial point cloud quantity；
(5) to around the i-th frame image clapped in image sequence, its transformation matrix M being calculated in step (1) is taken outi,
By the point cloud of derivation obtained in step (4) according to transformation matrix MiIt transforms under corresponding camera coordinates system, and former according to projection
Reason will derive from each of point cloud back projection to accurate, the quick reconstruction procedures for carrying out targeting target in protein molecule body body
On the effective coverage figure of i-th frame of middle acquisition；
According to the step in (5), to the point in the inactive area projected in the i-th frame effective coverage figure, by it from derivation
It is deleted in point cloud, the point in effective coverage projected in the i-th frame effective coverage figure then retains；
To being performed both by above-mentioned steps (4) around each frame clapped in image sequence and deleting it from derivation point cloud, project
The operation then retained to the point in the effective coverage in the i-th frame effective coverage figure, by around projection and deleting derivation point cloud,
Three-dimensional reconstruction obtains the derivation point cloud for containing interior point；
The each derivation point obtained derived from point cloud is traversed, judges that each derivation point is interior point or exterior point, deletes
Fall be interior point derivation point cloud, reservation is the derivation point cloud of exterior point；The point cloud finally retained is to derive from primary available point cloud；
The quantity of statistics gained available point cloud, if dense degree reaches demand, this available point cloud is maximal end point cloud；If thick
Close degree is not up to demand, then using the available point cloud as initial point cloud, repeats the above steps (2) to current procedures, until obtaining
The available point cloud obtained meets consistency requirement.
Further, 26 directions group in step (3) using one of point in initial point cloud as source point to cuboid
It is raw to obtain new point, wherein the calculation formula newly put is：
Wherein, x_org, y_org, z_org are respectively that some in initial point cloud puts the coordinate on x, y, z axis, x_
Scalar, y_scalar, z_scalar are respectively the derivation scale in three directions of x, y, z being calculated,
The case where 3*3*3 that above formula is calculated new point coordinates in addition to source point increment of coordinate are (0,0,0), it will group
Bear 26 new point clouds described in step (3)；
In step (5), by the calculation formula of the camera coordinates system of derivation point Cloud transform to the i-th frame image：
(x_cami,y_cami,z_cami)=(x_world, y_world, z_world) * Ri|ti
Wherein, (x_world, y_world, z_world) is the coordinate for deriving from point cloud in world coordinate system, Ri, tiRespectively
For the spin matrix and translation vector of the i-th frame camera, by RiWith tiTransformation, the point cloud in world coordinate system has been gone to i-th
Under frame camera coordinates system, i.e. the coordinate of transformed cloud is (x_cam in the i-th frame camera coordinates systemi,y_cami,z_cami)；
Point cloud in camera coordinates system is subjected to back projection, each point is projected in the i-th frame effective coverage figure, projects position
The calculation formula set：
Wherein, f is camera focus, Cx、CyRespectively 0.5 times of image resolution ratio, u, the v being calculated are point projection
Position on to image, i.e., u row, v on image arrange corresponding location of pixels.
Further, the voxel-based physical model of building specifically includes：
The first step, using the registration software in multi-mode molecule imaging system, by magnetic resonance or computer tomography weight
The three-dimensional voxel Registration of Measuring Data built is drawn and outside labelled protein molecule body to being disclosed in digital mouse map with this
The boundary line of contour line and interior tissue；
Second step, the interior tissue boundary line based on three-dimensional voxel data and label, tectonic boundary node are enriched with function：
Wherein, j is voxel node；
ψjIt (r) is the inner boundary node enrichment function defined；
vjIt (r) is interpolation function；
It is symbolic measurement, is defined as node to the distance away from nearest Close edges：
Wherein, sign (r) is used to indicate the subordinate relation of point r Yu boundary Γ：Value is negative if putting inside region, in area
Overseas portion is then positive, and is then zero on boundary；
It is value of the symbolic measurement on voxel node j；
Protein molecule body is decomposed into multiple organs using the interior tissue boundary line of label as interface by third step
Intersection, and optical properties of tissue is assigned to corresponding organ, construct voxel-based optical 3-dimensional Imaging physics model.
Further, the building adaptive optical transmission mathematical model specifically includes：
Organ is divided into high scattering, sky according to the multiple organs and corresponding optical properties of tissue of decomposition by the first step
Chamber and its hetero-organization three classes, classification foundation are defined as：
Wherein, Ω is the solution domain that protein molecule body is constituted；ΩhsIt is high scattering tissue region；ΩvIt is cavity area；
ΩlsIt is other tissue regions；μ′sIt is tissue reduced scattering coefficient；ζ and χ is classification thresholds, be taken as respectively ζ=10 and χ=
0.2mm-1；
Second step comprehensively considers accuracy and computation complexity, and it is suitable that different types of tissue is adaptive selected
Optical transport model is described；Wherein, transmission process of the light in high scattering tissue is described using diffusion approximation equation, using certainly
The transmission process of light in the cavities is described by space optical transmission equation, and simplifies ball harmonic approximation equation using three ranks and describes light
Transmission process in its hetero-organization；
Third step, by constructing the boundary coupling condition of physical quantity between different optical transport models, building adaptive optical is passed
Defeated mathematical model：
Wherein, φi(r) (i=1,2) is node luminous flux, and S (r) is the energy density of protein molecule bulk optics probe
Distribution, μa(r) and μaj(r) (j=1,2,3) is that protein molecule body absorbs relevant parameter, and D (r) is the diffusion of protein molecule body
Coefficient, βi(i=1,2) and α is SP3The factor is mismatched with DA equation by boundary, G (r ', r) is description radiation transfer theory concept
Transmission function, for describing diffused light from the transmission process in cavity tissue, B is the interface of scattering tissue and cavity, σ (r)
It is the indicator for describing solution point position, is：
High scattering and the photon transport equation of other scattering tissues are coupled using following formula:
Wherein, φ0(r) be diffusion approximation equation solution node luminous flux；
Using the photon transport equation of following formula coupling scattering tissue and cavity:
Wherein, q0It (r) is the graceful luminous flux of promise formed on cavity and scattering tissue interface.
Further, the fusion enrichment function is established system equation and is specifically included：
Using the voxel-based physical model of building as domain is solved, function is enriched with using the inner boundary node of fusion constructs
Finite volume method numerical discretization is carried out to the adaptive optical of building transmission mathematical model and is solved, establish description protein molecule
The system equation of linear relationship between internal target and body surface measurement value：
J=AS；
Wherein, A is sytem matrix, dependent on the distribution of three Protein-like chain body tissues in protein molecule body and accordingly
Optical property parameter；J is the emergent light flow rate of protein molecule body body surface acquisition；S is targeting target energy Density Distribution.
The automatic molecule protein molecule body diagnostic system fortune is realized another object of the present invention is to provide a kind of
The computer program of row method.
Another object of the present invention is to provide one kind equipped with the automatic molecule protein molecule body diagnostic system
Information data processing terminal.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the automatic molecule protein molecule body diagnostic system operation method.
The automatic molecule protein molecule body diagnosis system is installed another object of the present invention is to provide a kind of
The automatic molecule protein molecule body diagnostic device of system.
Advantages of the present invention and good effect are：
The present invention can quick, accurate, low cost progress DNA sequencing by DNA sequencing module；It is examined simultaneously by cancer cell
It surveys module and is capable of providing the cancer cell that can easily detect in a short time in peripheral blood；It can be more by analysis expert module
Analyzing detection data for profession, ensures the reliability of testing result.
The present invention directly on the voxel data of magnetic resonance or computed tomography reconstruction due to carrying out optical 3-dimensional weight
Build, overcome must carry out in the prior art organ segmentation and grid it is discrete could complete targeting target three-dimensional reconstruction the problem of,
It fundamentally avoids that cumbersome organ segmentation and grid are discrete, simplifies the reconstruction process of optical 3-dimensional imaging, realize standard
Really, efficiently, easy-to-use optical 3-dimensional imaging.
The present invention due to considering difference of the protein molecule body in terms of anatomical structure and optical properties of tissue simultaneously
Optical transport combined mathematics model is established, the optics based on single approximate equation or mixing photon transport equation in the prior art is overcome
The limitation in terms of reconstruction precision and efficiency of three-D imaging method, can be to irregular anatomical structure and a variety of scatterings
The targeting target of the complex proteins molecule body of characteristic tissue carries out accurate, fast imaging.
It is fixed as the preliminary target of priori using the testing result of magnetic resonance or computer tomography data in the present invention
Position as a result, limit the feasible zone range that system equation solves, overcome directly positioned and rebuild in the prior art it is inaccurate
True problem effectively realizes the accurate positionin of target and quantifies.
The present invention compares the method for obtaining point cloud based on stereoscopic vision：The method needs for obtaining point cloud based on stereoscopic vision mention
For the image sequence of texture complexity, there is no the region of disparity map not point in reconstruction process, reconstruction error is solved by disparity map and missed
The influence of difference.And the requirement that texture of the present invention to image be not excessive, only initial point cloud to be offered can be closer to really
The shape of object just can restore the most information of initial point cloud loss to a certain extent.
Compared to the method for obtaining point cloud based on motion structure：The point cloud of the method acquisition of point cloud is obtained based on motion structure
Quantity depends on the quantity that characteristic point pair is effectively matched between adjacent two frame, the sparse cloud taken to the derivation side of dense point cloud
The calculating of formula is complicated.And the quantity of derivation point cloud and the texture of image generated in the present invention does not contact directly, to initial point
Cloud does not require excessively, as long as being closer to real-world object, script can be made to put cloud by derivation mode and be distributed sparse place
Point cloud quantity increase, increase available point cloud quantity.
Compared to the method based on depth image：Method based on depth image needs to provide the depth map of every frame image, calculates
Method is higher to the susceptibility of the accuracy of depth map, and the matching between two clouds uses iterative algorithm, so that required calculating
Amount is very big, and there are many matrix operation, need to calculate on GPU.And method proposed by the present invention does not require depth map, with group
Raw point cloud filters out, and the quantity of calculative point is also being reduced, and calculating speed is speeded, and not needing to calculate on GPU can also have
Faster speed.
Detailed description of the invention
Fig. 1 is automatic molecule protein molecule body diagnostic system structure chart provided in an embodiment of the present invention.
In figure：1, protein detection module；2, DNA detection module；3, main control module；4, DNA sequencing module；5, cancer cell
Detection module；6, analysis expert module；7, data memory module；8, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
As shown in Figure 1, automatic molecule protein molecule body diagnostic system provided in an embodiment of the present invention, including：Albumen
Quality detection module 1, DNA detection module 2, main control module 3, DNA sequencing module 4, cancer cell detection module 5, analysis expert module
6, data memory module 7, display module 8.
Protein detection module 1 is connect with main control module 3, for being detected by protein detection instrument to protein；
DNA detection module 2 is connect with main control module 3, for being detected by DNA detector to DNA；
Main control module 3, with protein detection module 1, DNA detection module 2, DNA sequencing module 4, cancer cell detection module
5, analysis expert module 6, data memory module 7, display module 8 connect, and work normally for controlling modules；
DNA sequencing module 4 is connect with main control module 3, for the DNA of detection to be sequenced；
Cancer cell detection module 5 is connect with main control module 3, for detecting the cancer cell in peripheral blood；
Analysis expert module 6 is connect with main control module 3, is carried out for commenting on net by on-line expert to the data of detection
On-line analysis；
Data memory module 7 is connect with main control module 3, for storing the data information of detection；
Display module 8 is connect with main control module 3, for showing the data information of detection.
Below with reference to concrete analysis, the invention will be further described.
The detection method of protein detection module includes：1) according to magnetic resonance or the ash of computer tomography voxel data
Degree or texture features draw boundary contour and interior tissue edge line outside protein molecule body；Based on magnetic resonance or calculating
The voxel data of machine tomography rebuilding and the interior tissue edge line of label, construction inner boundary node are enriched with function；Consider egg
The structural heterogeneity and optical specificity of white matter molecule body tissue transmit number using the adaptive optical based on mixing photon transport equation
It learns model and describes transmission process of the light particle in protein molecule body；In view of finite volume method on hexahedron voxel grid
Application advantage carries out numerical discretization and solution to adaptive optical transmission mathematical model using extension finite volume method, establishes description
The system equation of linear relationship between internal target and body surface measurement value；Consider the sparsity and body surface measurement of internal target distribution
The imperfection of data establishes the objective function based on sparse Regularization Strategy and the fusion preliminary target positioning result of priori；It adopts
With suitable Optimization Method objective function, accurate, the quick reconstruction of targeting target in protein molecule body body is realized；
2) rebuild after, by photographic equipment obtain one group around clap image sequence, to every frame around clap image zooming-out contour of object,
And 255 are set by the pixel value in contour area, the pixel value outside profile is set as 0, a frame bianry image is obtained, is known as having
Imitate administrative division map；The very low point cloud of a consistency, referred to as initial point cloud are obtained, while also obtaining each frame camera relative to the world
The spin matrix R and translation vector t of coordinate system, spin matrix and translation vector combine to form transformation matrix M；
3) each point in initial point cloud is traversed, obtaining all the points in initial point cloud, value is most on three axis of x, y, z
Big value and minimum value, and the distance between maxima and minima difference on each axis is calculated, it is denoted as x_dis, y_dis, z_ respectively
Dis, respectively by this three range differences divided by 100, three obtained amount, referred to as the derivation scale of initial point cloud are denoted as x_
scalar,y_scalar,z_scalar；
4) using a point in initial point cloud as source point, the positive negative direction along three directions of x, y, z respectively extends pair respectively
The derivation scale size calculated in step 3) is answered, a cuboid centered on source point, the length and width high score of the cuboid are obtained
Not Wei 2*x_scalar, 2*y_scalar, 2*z_scalar, the source point center toward extending 26 sides around cuboid altogether
To deriving a new point in each direction, take the normal vector of the new point identical as the normal vector of source point, and each derivation point
Record its source point；
5) operation of derivation described in a step 4) is all carried out to each of initial point cloud point, will obtain a derivation
Point cloud, the quantity at this cloud midpoint is 26 times of initial point cloud quantity；
6) to around the i-th frame image clapped in image sequence, its transformation matrix M being calculated in step 2) is taken outi, will
Derivation point cloud is according to transformation matrix M obtained in step 5)iIt transforms under corresponding camera coordinates system, and will according to projection theory
On the effective coverage figure for deriving from the i-th frame that each of point cloud back projection obtains into step 1).
According to the step in 6), to the point in the inactive area projected in the i-th frame effective coverage figure, by it from deriving from point
It is deleted in cloud, the point in effective coverage projected in the i-th frame effective coverage figure then retains；
To around clap image sequence in each frame be performed both by above-mentioned steps 6) and by its from derive from point cloud in delete, project to
The operation that the point in effective coverage in i-th frame effective coverage figure then retains, by around projection and deleting, three derivation point cloud
Dimension rebuilds the derivation point cloud for obtaining and containing interior point；
The each derivation point obtained derived from point cloud is traversed, judges that each derivation point is interior point or exterior point, deletes
Fall be interior point derivation point cloud, reservation is the derivation point cloud of exterior point；The point cloud finally retained is to derive from primary available point cloud；
The quantity of statistics gained available point cloud, if dense degree reaches demand, this available point cloud is maximal end point cloud；If thick
Close degree is not up to demand, then using the available point cloud as initial point cloud, repetition is above-mentioned 3) to current procedures, until having for acquisition
Effect point cloud meets consistency requirement；
26 directions in step 4) using one of point in initial point cloud as source point to cuboid, which are derived from, to be obtained newly
Point, wherein the calculation formula newly put is：
Wherein, x_org, y_org, z_org are respectively that some in initial point cloud puts the coordinate on x, y, z axis, x_
Scalar, y_scalar, z_scalar are respectively the derivation scale in three directions of x, y, z being calculated,
The case where 3*3*3 that above formula is calculated new point coordinates in addition to source point increment of coordinate are (0,0,0), it will group
Bear 26 new point clouds described in step 4)；
In step 6), by the calculation formula of the camera coordinates system of derivation point Cloud transform to the i-th frame image：
(x_cami,y_cami,z_cami)=(x_world, y_world, z_world) * Ri|ti
Wherein, (x_world, y_world, z_world) is the coordinate for deriving from point cloud in world coordinate system, Ri, tiRespectively
For the spin matrix and translation vector of the i-th frame camera, by RiWith tiTransformation, the point cloud in world coordinate system has been gone to i-th
Under frame camera coordinates system, i.e. the coordinate of transformed cloud is (x_cam in the i-th frame camera coordinates systemi,y_cami,z_cami)；
Point cloud in camera coordinates system is subjected to back projection, each point is projected in the i-th frame effective coverage figure, projects position
The calculation formula set：
Wherein, f is camera focus, Cx、CyRespectively 0.5 times of image resolution ratio, u, the v being calculated are point projection
Position on to image, i.e., u row, v on image arrange corresponding location of pixels.
The voxel-based physical model of building specifically includes：
The first step, using the registration software in multi-mode molecule imaging system, by magnetic resonance or computer tomography weight
The three-dimensional voxel Registration of Measuring Data built is drawn and outside labelled protein molecule body to being disclosed in digital mouse map with this
The boundary line of contour line and interior tissue；
Second step, the interior tissue boundary line based on three-dimensional voxel data and label, tectonic boundary node are enriched with function：
Wherein, j is voxel node；
ψjIt (r) is the inner boundary node enrichment function defined；
vjIt (r) is interpolation function；
It is symbolic measurement, is defined as node to the distance away from nearest Close edges：
Wherein, sign (r) is used to indicate the subordinate relation of point r Yu boundary Γ：Value is negative if putting inside region, in area
Overseas portion is then positive, and is then zero on boundary；
It is value of the symbolic measurement on voxel node j；
Protein molecule body is decomposed into multiple organs using the interior tissue boundary line of label as interface by third step
Intersection, and optical properties of tissue is assigned to corresponding organ, construct voxel-based optical 3-dimensional Imaging physics model.
The building adaptive optical transmission mathematical model specifically includes：
Organ is divided into high scattering, sky according to the multiple organs and corresponding optical properties of tissue of decomposition by the first step
Chamber and its hetero-organization three classes, classification foundation are defined as：
Wherein, Ω is the solution domain that protein molecule body is constituted；ΩhsIt is high scattering tissue region；ΩvIt is cavity area；
ΩlsIt is other tissue regions；μ′sIt is tissue reduced scattering coefficient；ζ and χ is classification thresholds, be taken as respectively ζ=10 and χ=
0.2mm-1；
Second step comprehensively considers accuracy and computation complexity, and it is suitable that different types of tissue is adaptive selected
Optical transport model is described；Wherein, transmission process of the light in high scattering tissue is described using diffusion approximation equation, using certainly
The transmission process of light in the cavities is described by space optical transmission equation, and simplifies ball harmonic approximation equation using three ranks and describes light
Transmission process in its hetero-organization；
Third step, by constructing the boundary coupling condition of physical quantity between different optical transport models, building adaptive optical is passed
Defeated mathematical model：
Wherein, φi(r) (i=1,2) is node luminous flux, and S (r) is the energy density of protein molecule bulk optics probe
Distribution, μa(r) and μaj(r) (j=1,2,3) is that protein molecule body absorbs relevant parameter, and D (r) is the diffusion of protein molecule body
Coefficient, βi(i=1,2) and α is SP3The factor is mismatched with DA equation by boundary, G (r ', r) is description radiation transfer theory concept
Transmission function, for describing diffused light from the transmission process in cavity tissue, B is the interface of scattering tissue and cavity, σ (r)
It is the indicator for describing solution point position, is defined as：
High scattering and the photon transport equation of other scattering tissues are coupled using following formula:
Wherein, φ0(r) be diffusion approximation equation solution node luminous flux；
Using the photon transport equation of following formula coupling scattering tissue and cavity:
Wherein, q0It (r) is the graceful luminous flux of promise formed on cavity and scattering tissue interface.
The fusion enrichment function is established system equation and is specifically included：
Using the voxel-based physical model of building as domain is solved, function is enriched with using the inner boundary node of fusion constructs
Finite volume method numerical discretization is carried out to the adaptive optical of building transmission mathematical model and is solved, establish description protein molecule
The system equation of linear relationship between internal target and body surface measurement value：
J=AS；
Wherein, A is sytem matrix, dependent on the distribution of three Protein-like chain body tissues in protein molecule body and accordingly
Optical property parameter；J is the emergent light flow rate of protein molecule body body surface acquisition；S is targeting target energy Density Distribution.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of automatic molecule protein molecule body diagnostic system, which is characterized in that the automatic molecule protein molecule body
Learning diagnostic system includes：
Protein detection module, connect with main control module, for being detected by protein detection instrument to protein；Protein
Detector is drawn outside protein molecule body according to magnetic resonance or the gray scale or texture features of computer tomography voxel data
Boundary contour and interior tissue edge line；In voxel data and label based on magnetic resonance or computed tomography reconstruction
Portion's organization edge line, construction inner boundary node are enriched with function；Consider that structural heterogeneity and the optics of protein molecule body tissue are special
The opposite sex describes light particle in protein molecule body using the adaptive optical transmission mathematical model based on mixing photon transport equation
Transmission process；In view of application advantage of the finite volume method on hexahedron voxel grid, using extension finite volume method to adaptive
It answers optical transport mathematical model to carry out numerical discretization and solution, establishes in Description linear relationship between target and body surface measurement value
System equation；Consider the sparsity of internal target distribution and the imperfection of body surface measurement data, establishes and be based on sparse regularization
The objective function of strategy and the fusion preliminary target positioning result of priori；Using suitable Optimization Method objective function, carry out
Accurate, the quick reconstruction of targeting target in protein molecule body body；
Main control module is connect, for controlling with protein detection module, analysis expert module, data memory module, display module
Modules work normally；
Analysis expert module, connect with main control module, is divided online for commenting on net by on-line expert the data of detection
Analysis；
Data memory module is connect with main control module, for storing the data information of detection；
Display module is connect with main control module, for showing the data information of detection.
2. automatic molecule protein molecule body diagnostic system as described in claim 1, which is characterized in that the automatic molecule
Protein molecule body diagnostic system further comprises：
DNA detection module, connect with main control module, for being detected by DNA detector to DNA；
DNA sequencing module, connect with main control module, for the DNA of detection to be sequenced；
Cancer cell detection module, connect with main control module, for detecting the cancer cell in peripheral blood；
Protein detection instrument carries out detection to protein：
(1) after rebuilding, by one group of photographic equipment acquisition around image sequence is clapped, to every frame around bat image zooming-out contour of object, and
255 are set by the pixel value in contour area, the pixel value outside profile is set as 0, obtains a frame bianry image, referred to as effectively
Administrative division map；The very low point cloud of a consistency, referred to as initial point cloud are obtained, while also obtaining each frame camera and being sat relative to the world
The spin matrix R and translation vector t of system are marked, spin matrix and translation vector combine to form transformation matrix M；
(2) each point in initial point cloud is traversed, the maximum value of all the points value on three axis of x, y, z in initial point cloud is obtained
With minimum value, and the distance between maxima and minima difference on each axis is calculated, is denoted as x_dis, y_dis, z_dis respectively,
Respectively by this three range differences divided by 100, three obtained amount, referred to as the derivation scale of initial point cloud are denoted as x_scalar, y_
scalar,z_scalar；
(3) using a point in initial point cloud as source point, the positive negative direction along three directions of x, y, z respectively extends corresponding step respectively
Suddenly the derivation scale size calculated in (2), obtains a cuboid centered on source point, the length, width and height of the cuboid are respectively
2*x_scalar, 2*y_scalar, 2*z_scalar, the source point center toward extending 26 directions altogether around cuboid,
A new point is derived in each direction, takes the normal vector of the new point identical as the normal vector of source point, and each derivation point is remembered
Record its source point；
(4) operation of derivation described in a step 4) is all carried out to each of initial point cloud point, will obtain a derivation
Point cloud, the quantity at this cloud midpoint is 26 times of initial point cloud quantity；
(5) to around the i-th frame image clapped in image sequence, its transformation matrix M being calculated in step (1) is taken outi, will walk
Suddenly the point of derivation obtained in (4) cloud is according to transformation matrix MiIt transforms under corresponding camera coordinates system, and will according to projection theory
Each of point cloud back projection is derived to obtain into accurate, the quick reconstruction procedures for carrying out targeting target in protein molecule body body
On the effective coverage figure of the i-th frame obtained；
According to the step in (5), to the point in the inactive area projected in the i-th frame effective coverage figure, it is put into a cloud from derivation
Middle deletion, the point in effective coverage projected in the i-th frame effective coverage figure then retain；
To being performed both by above-mentioned steps (4) around each frame clapped in image sequence and deleting it from derivation point cloud, i-th is projected to
The operation that the point in effective coverage in the figure of frame effective coverage then retains, it is three-dimensional by around projection and deleting derivation point cloud
Rebuild the derivation point cloud for obtaining and containing interior point；
The each derivation point obtained derived from point cloud is traversed, judges that each derivation point is interior point or exterior point, deleting is
The derivation point cloud of interior point, reservation are the derivation point clouds of exterior point；The point cloud finally retained is to derive from primary available point cloud；
The quantity of statistics gained available point cloud, if dense degree reaches demand, this available point cloud is maximal end point cloud；If dense journey
Degree is not up to demand and repeats the above steps (2) to current procedures, until acquisition then using the available point cloud as initial point cloud
Available point cloud meets consistency requirement.
3. molecule protein molecule body diagnostic system as described in claim 1 automatic, which is characterized in that in step (3) with
One of point in initial point cloud, which is derived from as source point to 26 directions of cuboid, obtains new point, wherein the calculating newly put is public
Formula is：
Wherein, x_org, y_org, z_org are respectively that some in initial point cloud puts coordinate on x, y, z axis, x_scalar,
Y_scalar, z_scalar are respectively the derivation scale in three directions of x, y, z being calculated,
The case where 3*3*3 that above formula is calculated new point coordinates in addition to source point increment of coordinate are (0,0,0), it will derive
26 new point clouds described in step (3)；
In step (5), by the calculation formula of the camera coordinates system of derivation point Cloud transform to the i-th frame image：
(x_cami,y_cami,z_cami)=(x_world, y_world, z_world) * Ri|ti
Wherein, (x_world, y_world, z_world) is the coordinate for deriving from point cloud in world coordinate system, Ri, tiRespectively
The spin matrix and translation vector of i frame camera, by RiWith tiTransformation, the point cloud in world coordinate system has been gone into the i-th frame phase
Under machine coordinate system, i.e. the coordinate of transformed cloud is (x_cam in the i-th frame camera coordinates systemi,y_cami,z_cami)；
Point cloud in camera coordinates system is subjected to back projection, each point is projected in the i-th frame effective coverage figure, projected position
Calculation formula：
Wherein, f is camera focus, Cx、CyRespectively 0.5 times of image resolution ratio, u, the v being calculated are that the point projects to figure
As upper position, i.e., u row, v on image arrange corresponding location of pixels.
4. automatic molecule protein molecule body diagnostic system as described in claim 1, which is characterized in that the building is based on
The physical model of voxel specifically includes：
The first step is obtained magnetic resonance or computed tomography reconstruction using the registration software in multi-mode molecule imaging system
To three-dimensional voxel Registration of Measuring Data to being disclosed in digital mouse map, drawn with this and the external contouring of labelled protein molecule
The boundary line of line and interior tissue；
Second step, the interior tissue boundary line based on three-dimensional voxel data and label, tectonic boundary node are enriched with function：
Wherein, j is voxel node；
ψjIt (r) is the inner boundary node enrichment function defined；
vjIt (r) is interpolation function；
It is symbolic measurement, is defined as node to the distance away from nearest Close edges：
Wherein, sign (r) is used to indicate the subordinate relation of point r Yu boundary Γ：Value is negative if putting inside region, outside region
Portion is then positive, and is then zero on boundary；
It is value of the symbolic measurement on voxel node j；
Protein molecule body is decomposed into the intersection of multiple organs using the interior tissue boundary line of label as interface by third step,
And optical properties of tissue is assigned to corresponding organ, construct voxel-based optical 3-dimensional Imaging physics model.
5. automatic molecule protein molecule body diagnostic system as described in claim 1, which is characterized in that the building is adaptive
Optical transport mathematical model is answered to specifically include：
The first step, according to the multiple organs and corresponding optical properties of tissue of decomposition, by organ be divided into high scattering, cavity and
Its hetero-organization three classes, classification foundation are defined as：
Wherein, Ω is the solution domain that protein molecule body is constituted；ΩhsIt is high scattering tissue region；ΩvIt is cavity area；ΩlsIt is
Other tissue regions；μ′sIt is tissue reduced scattering coefficient；ζ and χ is classification thresholds, is taken as ζ=10 and χ=0.2mm respectively-1；
Second step comprehensively considers accuracy and computation complexity, and suitable light is adaptive selected to different types of tissue and passes
Defeated model is described；Wherein, transmission process of the light in high scattering tissue is described using diffusion approximation equation, using free sky
Between photon transport equation the transmission process of light in the cavities described, and simplify ball harmonic approximation equation using three ranks and describe light at it
Transmission process in hetero-organization；
Third step, by constructing the boundary coupling condition of physical quantity between different optical transport models, building adaptive optical transmits number
Learn model：
Wherein, φi(r) (i=1,2) is node luminous flux, and S (r) is the energy density distribution of protein molecule bulk optics probe,
μa(r) and μaj(r) (j=1,2,3) is that protein molecule body absorbs relevant parameter, and D (r) is protein molecule body diffusion coefficient,
βi(i=1,2) and α is SP3The factor is mismatched with DA equation by boundary, G (r ', r) is the transmitting letter for describing radiation transfer theory concept
Number, for describing diffused light from the transmission process in cavity tissue, B is the interface of scattering tissue and cavity, and σ (r) is description
The indicator of solution point position is：
High scattering and the photon transport equation of other scattering tissues are coupled using following formula:
Wherein, φ0(r) be diffusion approximation equation solution node luminous flux；
Using the photon transport equation of following formula coupling scattering tissue and cavity:
Wherein, q0It (r) is the graceful luminous flux of promise formed on cavity and scattering tissue interface.
6. automatic molecule protein molecule body diagnostic system as described in claim 1, which is characterized in that the fusion enrichment
Function is established system equation and is specifically included：
Using the voxel-based physical model of building as domain is solved, having for function is enriched with using the inner boundary node of fusion constructs
It limits volumetric method to carry out numerical discretization to the adaptive optical transmission mathematical model of building and solve, establish in description protein molecule body
The system equation of linear relationship between target and body surface measurement value：
J=AS；
Wherein, A is sytem matrix, dependent on the distribution of three Protein-like chain body tissues and corresponding light in protein molecule body
Learn characterisitic parameter；J is the emergent light flow rate of protein molecule body body surface acquisition；S is targeting target energy Density Distribution.
7. automatic molecule protein molecule body diagnostic system operation method described in a kind of realization claim 1~6 any one
Computer program.
8. a kind of information equipped with automatic molecule protein molecule body diagnostic system described in claim 1~6 any one
Data processing terminal.
9. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires automatic molecule protein molecule body diagnostic system operation method described in 1-6 any one.
10. a kind of automatic molecule protein for being equipped with automatic molecule protein molecule body diagnostic system described in claim 1
Matter molecule body diagnostic device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810697956.XA CN108846896A (en) | 2018-06-29 | 2018-06-29 | A kind of automatic molecule protein molecule body diagnostic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810697956.XA CN108846896A (en) | 2018-06-29 | 2018-06-29 | A kind of automatic molecule protein molecule body diagnostic system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108846896A true CN108846896A (en) | 2018-11-20 |
Family
ID=64200076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810697956.XA Pending CN108846896A (en) | 2018-06-29 | 2018-06-29 | A kind of automatic molecule protein molecule body diagnostic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108846896A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145338A (en) * | 2019-12-17 | 2020-05-12 | 桂林理工大学 | Chair model reconstruction method and system based on single-view RGB image |
| CN111833296A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection and verification system and method for bone marrow cell morphology |
| CN116800551A (en) * | 2023-08-29 | 2023-09-22 | 北京金泰康辰生物科技有限公司 | Online feedback system for molecular detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030207340A1 (en) * | 2002-05-01 | 2003-11-06 | Morre D. James | Sequences encoding human neoplastic marker |
| CN1695057A (en) * | 2002-09-12 | 2005-11-09 | 摩诺根公司 | Cell-based detection and differentiation of disease states |
| CN103109186A (en) * | 2010-06-30 | 2013-05-15 | 安派科生物医学科技有限公司 | Apparatus for disease detection |
| CN104919299A (en) * | 2012-10-03 | 2015-09-16 | 皇家飞利浦有限公司 | Combined sample examinations |
| CN105825547A (en) * | 2016-03-11 | 2016-08-03 | 西安电子科技大学 | Optical three-dimensional imaging method based on voxel and adaptive optical transmission model |
| CN106023303A (en) * | 2016-05-06 | 2016-10-12 | 西安电子科技大学 | Method for improving three-dimensional reconstruction point-clout density on the basis of contour validity |
-
2018
- 2018-06-29 CN CN201810697956.XA patent/CN108846896A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030207340A1 (en) * | 2002-05-01 | 2003-11-06 | Morre D. James | Sequences encoding human neoplastic marker |
| CN1695057A (en) * | 2002-09-12 | 2005-11-09 | 摩诺根公司 | Cell-based detection and differentiation of disease states |
| CN103109186A (en) * | 2010-06-30 | 2013-05-15 | 安派科生物医学科技有限公司 | Apparatus for disease detection |
| CN104919299A (en) * | 2012-10-03 | 2015-09-16 | 皇家飞利浦有限公司 | Combined sample examinations |
| CN105825547A (en) * | 2016-03-11 | 2016-08-03 | 西安电子科技大学 | Optical three-dimensional imaging method based on voxel and adaptive optical transmission model |
| CN106023303A (en) * | 2016-05-06 | 2016-10-12 | 西安电子科技大学 | Method for improving three-dimensional reconstruction point-clout density on the basis of contour validity |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145338A (en) * | 2019-12-17 | 2020-05-12 | 桂林理工大学 | Chair model reconstruction method and system based on single-view RGB image |
| CN111145338B (en) * | 2019-12-17 | 2023-09-26 | 桂林理工大学 | Chair model reconstruction method and system based on single-view RGB image |
| CN111833296A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection and verification system and method for bone marrow cell morphology |
| CN111833296B (en) * | 2020-05-25 | 2023-03-10 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection and verification system and method for bone marrow cell morphology |
| CN116800551A (en) * | 2023-08-29 | 2023-09-22 | 北京金泰康辰生物科技有限公司 | Online feedback system for molecular detection |
| CN116800551B (en) * | 2023-08-29 | 2023-12-22 | 北京金泰康辰生物科技有限公司 | Online feedback system for molecular detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ham et al. | Computer vision based 3D reconstruction: A review | |
| CN110490851B (en) | Mammary gland image segmentation method, device and system based on artificial intelligence | |
| CN109410188B (en) | System and method for segmenting medical images | |
| Stoyanov | Stereoscopic scene flow for robotic assisted minimally invasive surgery | |
| Liu et al. | Wound area measurement with 3D transformation and smartphone images | |
| CN105488804B (en) | Brain ASL, SPECT and the method and system of MRI image registration fusion Conjoint Analysis | |
| CN102753962A (en) | System and method for multimode three dimensional optical tomography based on specificity | |
| CN107667380A (en) | The method and system of scene parsing and Model Fusion while for endoscope and laparoscopic guidance | |
| CN109074639A (en) | Figure registration system and method in medical image system | |
| US20130170726A1 (en) | Registration of scanned objects obtained from different orientations | |
| CN108735279A (en) | A kind of virtual reality headstroke rehabilitation training of upper limbs system and control method | |
| CN106504321A (en) | Method using the method for photo or video reconstruction three-dimensional tooth mould and using RGBD image reconstructions three-dimensional tooth mould | |
| JP6304970B2 (en) | Image processing apparatus and image processing method | |
| CN103229210A (en) | Image registration apparatus | |
| CN108364290A (en) | Method, medium and the system that the image sequence of cyclical physiological activity is analyzed | |
| CN108846896A (en) | A kind of automatic molecule protein molecule body diagnostic system | |
| CN101947103B (en) | Optical bioluminescence tomography method | |
| US20240193764A1 (en) | Systems and methods for reconstruction of 3d images from ultrasound and camera images | |
| JP7023196B2 (en) | Inspection support equipment, methods and programs | |
| CN110993067A (en) | Medical image labeling system | |
| Abreu de Souza et al. | 3d multi-modality medical imaging: Combining anatomical and infrared thermal images for 3d reconstruction | |
| CN108876783B (en) | Image fusion method and system, medical equipment and image fusion terminal | |
| CN114049344A (en) | Image segmentation method, training method of model thereof, related device and electronic equipment | |
| Long et al. | A marching cubes algorithm: application for three-dimensional surface reconstruction based on endoscope and optical fiber | |
| CN111161371B (en) | Imaging system and method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |