CN110310323A - The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian - Google Patents
The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian Download PDFInfo
- Publication number
- CN110310323A CN110310323A CN201810242675.5A CN201810242675A CN110310323A CN 110310323 A CN110310323 A CN 110310323A CN 201810242675 A CN201810242675 A CN 201810242675A CN 110310323 A CN110310323 A CN 110310323A
- Authority
- CN
- China
- Prior art keywords
- vessel
- hessian matrix
- blood vessels
- dimensional gaussian
- blood vessel
- 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
- 239000011159 matrix material Substances 0.000 title claims abstract description 30
- 210000001210 retinal vessel Anatomy 0.000 title claims abstract description 14
- 238000000691 measurement method Methods 0.000 title claims abstract description 7
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 230000000877 morphologic effect Effects 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract 1
- 230000003287 optical effect Effects 0.000 description 9
- 230000002792 vascular Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- WMFYOYKPJLRMJI-UHFFFAOYSA-N Lercanidipine hydrochloride Chemical compound Cl.COC(=O)C1=C(C)NC(C)=C(C(=O)OC(C)(C)CN(C)CCC(C=2C=CC=CC=2)C=2C=CC=CC=2)C1C1=CC=CC([N+]([O-])=O)=C1 WMFYOYKPJLRMJI-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000007323 disproportionation reaction Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004256 retinal image Effects 0.000 description 1
- 230000004233 retinal vasculature Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration by non-spatial domain filtering
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The present invention provides a kind of retinal blood vessels caliber measurement methods being fitted based on Hessian matrix and dimensional Gaussian.This method realizes that process is: (1) using the method for Hessian matrix detection linear structure, dividing blood vessel network；(2) feature vector according to corresponding to the minimal eigenvalue of Hessian matrix tentatively obtains vessel directions；(3) it is tentatively extracted using center line of the morphologic thinning method to blood vessel；(4) according to vessel cross-sections grey value profile characteristic, vessel centerline and direction are corrected using dimensional Gaussian fitting, accurate vessel directions and position of center line is obtained and then measures blood vessels caliber.Compared with traditional blood vessels caliber measurement method, the present invention is successfully corrected initial vessel directions and vessel centerline using dimensional Gaussian fitting, blood vessels caliber measurement is carried out on the basis of obtaining accurate vessel directions and center line, measurement result has very high accuracy.
Description
Technical field
The invention belongs to technical field of image processing, are related to a kind of view being fitted based on Hessian matrix and dimensional Gaussian
Retinal vasculature Calibration method.It can be used for colored eye fundus image blood vessels caliber measurement.The accurate measurement of blood vessel is to all kinds of heart and brain
Vascular diseases early prevention and treatment have important clinical meaning.Eye fundus image analysis is played an important role.
Background technique
Optical fundus blood vessel and cardio-cerebrovascular have common anatomical physiology characteristic, therefore lesion occurs for optical fundus blood vessel not only
It is the direct performance of optical fundus blood vessel lesion itself, while is also the diagnosis basis of hypertension, diabetes and cardiovascular and cerebrovascular disease.
Oculist's manual measurement blood vessels caliber accuracy rate is high, but time-consuming larger, is not suitable for batch processing image, therefore in eye fundus image
Analysis field, for the generaI investigation of optical fundus blood vessel Calibration objectivity, accuracy, repeatability and batch eyeground, optical fundus blood vessel pipe
The quantitative analysis of diameter has become an important research contents.
Existing blood vessels caliber measurement method is divided into three categories.One kind is boundary intersection method, and the key of such method is to want quasi-
Vessel directions and vessel centerline, such as Yao Chang etc. really are obtained on the basis of two-value blood vessel, are proposed one kind and are known based on priori
The caliber method for automatic measurement of knowledge, the method are adopted on the basis of the direction of blood vessel pixel on combining skeleton and location information
With improved directed local contrast method, obtains the vessel borders coordinate of two sides in skeleton line vertical direction and then acquire blood vessel
Caliber.Second class is cross-sectional profiles method, changes approximate Gaussian curve across the pixel grey scale of blood vessel, therefore use Gaussian curve
The advantages of fitting blood vessel acquires blood vessels caliber, such method is can to fit accurate blood vessel center according to the grayscale information of blood vessel
Line, such as Lowell etc. are on the basis of the directional information based on retinal vessel is with being fitted across blood vessel pixel gray level, needle
The case where whether there is reflected light to vascular wall is fitted local vascular dimensional Gaussian curved measurement blood vessels caliber.Third class is to build
Vertical modelling establishes model measurement blood vessels caliber, such as Carmen appropriate etc. according to blood vessel feature and proposes a kind of utilization and determines
The Calibration method of the Hellman model of plan tree and multiresolution, according to using the Hellman function comprising 6 parameter presets
It is fitted three-dimensional vessel surface model, calculates blood vessels caliber.
Existing boundary intersection method exists due to vascular skeleton line drawing inaccuracy and influences blood vessels caliber and accurately measure at present
The problem of；Cross-sectional profiles method due to Gaussian curve can not Complete Convergence, so vessel borders can not be determined accurately, caliber is surveyed
Amount can have error；Some methods need setup parameter in model foundation method, can not achieve adaptive measuring, cannot reach it is complete from
The requirement of dynamicization.Therefore, it studies one kind accurately and the method for automatic measurement blood vessels caliber has become problem in the urgent need to address.
Summary of the invention
The purpose of the present invention is overcoming the above-mentioned deficiency of the prior art, propose a kind of based on Hessian matrix and two dimension
The retinal blood vessels caliber measurement method of Gauss curve fitting.This method takes full advantage of the gray feature of vessel cross-sections, by right
The optical fundus blood vessel direction tentatively extracted and centreline correction also overcome tradition and seek so that blood vessels caliber measurement is more accurate
The disadvantage of vessel centerline and direction inaccuracy.We it is bright to image measurement in the library REVIEW and with its disclosed in Calibration
Data comparison, comparing result show that context of methods can guarantee the accuracy of Calibration.Realize the technical side of the object of the invention
Case, including the following steps:
Step 1: matching filter is carried out to smoothed eye fundus image using the multi-scale filtering device based on Hessian matrix
Wave realizes the extraction of blood vessel network；
Step 2: vessel directions are sought according to the corresponding feature vector of the characteristic value of Hessian matrix；
Step 3: vessel centerline is extracted using morphologic thinning；
Step 4: according to vessel cross-sections gray distribution features, being fitted blood vessel using two-dimensional Gaussian function and correct blood vessel side
To and position of center line, finally seek retinal blood vessels caliber.
The present invention has the advantages that compared with prior art
1. the retinal blood vessels caliber of the eye fundus images such as, brightness disproportionation low to contrast of the invention can also be measured accurately.
2. the present invention is by the analysis to vessel cross-sections intensity profile, at the beginning of designing two-dimensional Gaussian function fitting blood vessel correction
Obtained vessel centerline and direction are walked, the disadvantage of vessel centerline and direction inaccuracy that conventional method obtains is overcome.
Detailed description of the invention
Fig. 1: flow chart of the invention.
Fig. 2: (a) original image, (b) blood vessel network extracts result
Fig. 3: the corresponding feature vector chart of the minimal eigenvalue of Hessian matrix on blood vessel
Fig. 4: vessel centerline is extracted using Mathematical Morphology Method
Fig. 5: center line and correction for direction schematic diagram
Fig. 6: vessel cross-sections grey value characteristics function
Fig. 7: it the vessel centerline and direction after correction and the vessel centerline before correction and direction comparison diagram: (a) corrects
Center line chart afterwards, (b) initial scaffold line chart, the vessel directions after (c) correcting, (d) initial vessel directions
Fig. 8: blood vessel center line chart: (a) vessel centerline, (b) vessel centerline is superimposed with green channel images
Fig. 9: blood vessels caliber instrumentation plan
Figure 10: retinal blood vessels caliber measures diagram
Specific embodiment
Flow chart of the invention is as shown in Figure 1, first using the multi-scale filtering device based on Hessian matrix to by flat
Sliding optical fundus blood vessel is enhanced, and realizes the extraction of blood vessel network.Then the minimal eigenvalue according to Hessian matrix is corresponding
Feature vector tentatively seeks vessel directions, tentatively extracts vessel centerline using morphologic thinning method, then by blood vessel cross
The distribution character of section gray value is analyzed, design two-dimensional Gaussian function fitting blood vessel and correct the vessel centerline tentatively obtained and
Direction obtains more accurate vessel centerline and direction.The pipe of blood vessel is finally acquired according to accurate vessel directions and center line
Diameter value.
1. being enhanced using the multi-scale filtering device based on Hessian matrix smoothed optical fundus blood vessel, realize
The extraction of blood vessel network；
It chooses image green channel and carries out subsequent processing.Eyeground figure is weakened using mathematic morphology smooth processing relevant operation first
The interference of pseudo- blood vessel feature as in, and using the comparison of the adaptive histogram equalization of contrast-limited enhancing eye fundus image
Degree and clarity then use the filtering of anisotropy coupling diffusion equation with wiping out background noise, finally with based on Hessian square
The multi-scale enhancement filter of battle array is filtered eye fundus image.The table of multi-scale enhancement filter based on Hessian matrix
It is as follows up to formula:
WhereinB is the scale factor for influencing D,M is under current scale
Hessian matrix norm value, i.e. M=| | H | |, a is the initial parameter that noise is eliminated.It include three main portions in formula (2)
Point: (1)Realize the enhancing to blood vessel；(2)Realize the multiple dimensioned judgement to blood vessel；(3)Realize the removal to noise.
Therefore, in order to describe the blood vessel of different scale, context of methods takes multi-scale enhancement side according to Scale-space theory
Formula enhances blood vessel.When optical fundus blood vessel passes through different iteration scale σ (smin< s < smax) when can obtain Z under different scales, right
In blood vessel, the only Z when scale factor is most matched with blood vessels calibersValue output is maximum, takes Z at each pointsMaximum value as working as
The blood vessel confidence level of preceding point:
Finally with iteration method by blood vessel binaryzation, and morphology post-processing is carried out, final vessel segmentation such as Fig. 2
(b) shown in.It is operated compared to traditional form, this paper algorithm sufficiently maintains the continuity of blood vessel, can accurately divide bleeding
It manages and preferable for the segmentation effect of capillary.
2. seeking vessel directions according to the corresponding feature vector of the characteristic value of Hessian matrix；
For eye fundus image, the present invention calculates the second dervative of image in the x direction and the y direction using Gaussian function to acquire
The element of Hessian matrix is constituted, i.e., carries out convolution using the second dervative of Gaussian function and image, constitutes Hessian matrix
Element it is as follows:
Wherein P (x, y) is original image, g (x, y；σ) be standard deviation be σ Gaussian function, by Gaussian function in X and Y
The second order in direction leads the Hessian matrix that the image slices vegetarian refreshments (x, y) obtained after convolution is carried out to original image are as follows:
The characteristic value that pixel (x, y) can be acquired according to H (x, y), is shown below:
The corresponding feature vector of characteristic value is vessel directions, is shown below:
It is 5 that the present invention, which chooses scale factor σ, can characterize view according to the characteristic value of Hessian matrix and feature vector
The characteristics of intensity of film image blood vessel and direction, chooses the corresponding feature vector of the lesser characteristic value of amplitude as the initial of blood vessel
Direction, as a result as shown in Figure 3.
3. extracting vessel centerline using Mathematical Morphology Method；
The present invention extracts vessel centerline using Mathematical Morphology Method, as a result as shown in Figure 4.
4. vessel directions and centreline correction based on dimensional Gaussian fitting
Vessel segment grey value profile is analyzed, vessel cross-sections direction grey scale pixel value is in dimensional gaussian distribution, blood
Tube hub line is distributed in the highest point of Gaussian curve, therefore is fitted using dimensional Gaussian to blood according to blood vessel gray-scale watermark
Tube hub line and direction are corrected.Common two-dimensional Gaussian function expression formula are as follows:
The directional information of blood vessel is not included in common two-dimensional Gaussian function, in order to fit vessel directions information, this hair
It is bright to propose that the two-dimensional Gaussian function comprising vessel directions information, mathematic(al) representation are as follows:
Wherein (x, y) is the center line coordinates before correction, (x0, y0) be correction after center line coordinates, θ be correction after
Vessel directions, σ are the mean square deviation of Gaussian function, and A is the peak value of Gaussian function, for the unknown parameter solution procedure of Gaussian function
It is as follows:
Firstly, to the logarithm side-draw of formula two and multiplying f, can obtain:
It enables
Then, it is assumed that contain i candidate pixel point altogether in vascular skeleton line image, wherein (xj, yj) it is in candidate pixel point
J-th of pixel coordinate, f (xj, yj) it is j-th point of gray value in the picture.Bring all candidate point pixels into two dimension
In Gauss model, and a, b, c, d, e are solved:
Finally, calculating center line coordinates and vessel directions according to the value for acquiring a, b, c, d, e:
(1) center line coordinates (x0, y0) solution are as follows:
(2) solution of vessel directions θ are as follows:
To point A (x on the skeleton line after morphologic thinningi, yi) direction and position of center line correction such as Fig. 5 institute
Show, wherein l is vessel bone stringing, and A point is the original point of skeleton line, is obtained using the multi-scale enhancement filter of Hessian matrix
Maximum output to A point responds direction, i.e. blood vessel initially moves towards, then the direction of point A and location information are inputted into dimensional Gaussian
After function, the characteristics of using the gray value in vessel cross-sections being in Gaussian Profile, direction and position of center line is carried out to point A and rectified
Just, the point B (x after being correctedi, yi) and its direction.Vessel cross-sections grey value characteristics function is as shown in fig. 6, wherein B is school
Blood vessel center point after just, the gray value of point B is the maximum value of vessel cross-sections after as can be seen from the figure correcting.
The present invention carries out Gauss curve fitting to blood vessel using above-mentioned 2 Gauss model parameters, the blood vessel center after being corrected
Line and direction, they are as shown in Figure 7 with vessel centerline before correction and direction comparison diagram.It can be seen from the figure that after correction
It improves significantly to vessel centerline trend and the practical trend of blood vessel meets and smoother (such as Fig. 7 (a) shown), after correction
Vessel directions more meet the practical trend (such as Fig. 7 (b) shown in) of blood vessel.
4. retinal blood vessels caliber measures
Blood vessels caliber is measured on the basis of vessel segmentation.Calibration includes three steps, first with morphologic thinning
Vessel bone stringing is obtained, is then carried out using directional information and location information of the two-dimensional Gaussian function to the initial point on skeleton line
Correction, obtains accurate vessel directions and position of center line, and vessel borders point is found in the last direction scanning along perpendicular to blood vessel,
Calculate the pixel level width that the distance between two boundary points obtain blood vessel.Vessel centerline result after dimensional Gaussian correction is as schemed
Shown in 8.
The boundary point of blood vessel is positioned in the vertical scan direction of blood vessel, each point and the angle of X-axis are one on center line
Important parameter.Fig. 9 is blood vessels caliber instrumentation plan, by 3.2 sections it is found that q is a point P on the line of centeriVessel directions
The angle for obtaining current point and X-axis is q, and dotted line is the edge of blood vessel in figure.In order to find the blood vessel side in blood vessel vertical direction
Boundary point Q1、Q2, with PiIt scans, looks for blood vessel two sides respectively along the direction vertical with blood vessel using 1 pixel as step-length for starting point
To the boundary point Q of blood vessel two sides1、Q2.Calculate Q1、Q2The Euclidean distance of two o'clock is P on vascular skeletoniCaliber at point, Figure 10
For Part portions blood vessels caliber instrumentation plan in retinal images.
Claims (4)
1. a kind of retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian, the method includes
The following steps:
Step 1: matched filtering is carried out to smoothed eye fundus image using the multi-scale filtering device based on Hessian matrix,
Realize the extraction of blood vessel network；
Step 2: vessel directions are sought according to the corresponding feature vector of the characteristic value of Hessian matrix；
Step 3: vessel centerline is extracted using morphologic thinning；
Step 4: according to vessel cross-sections gray distribution features, be fitted blood vessel using two-dimensional Gaussian function and correct vessel directions and
Position of center line finally seeks retinal blood vessels caliber.
2. the retinal blood vessels caliber measurement side according to claim 1 being fitted based on Hessian matrix and dimensional Gaussian
Method, which is characterized in that in step 1, choose green channel, Hessian is based on according to the linear design feature design in the part of blood vessel
The multi-scale filtering device of matrix enhances blood vessel, extracts blood vessel network using iteration method.
3. the retinal blood vessels caliber measurement side according to claim 1 being fitted based on Hessian matrix and dimensional Gaussian
Method, which is characterized in that in step 2, according to the property that Hessian matrix is made of second-order partial differential coefficient, utilize Hessian matrix
The corresponding feature vector of minimal eigenvalue seek vessel directions.
4. according to the right retinal vessel pipe according to claim 1 being fitted based on Hessian matrix and dimensional Gaussian
Diameter measurement method, which is characterized in that in step 4, the characteristics of according to vessel cross-sections gray value being in Gaussian Profile, using tentatively mentioning
The vessel directions and center line that vessel directions and center line the design two-dimensional Gaussian function fitting blood vessel taken and correction are tentatively extracted,
More accurate vessel directions and center line are obtained, it is last according to the direction acquired and center line computation blood vessels caliber value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810242675.5A CN110310323A (en) | 2018-03-20 | 2018-03-20 | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810242675.5A CN110310323A (en) | 2018-03-20 | 2018-03-20 | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110310323A true CN110310323A (en) | 2019-10-08 |
Family
ID=68073426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810242675.5A Pending CN110310323A (en) | 2018-03-20 | 2018-03-20 | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110310323A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111000563A (en) * | 2019-11-22 | 2020-04-14 | 北京理工大学 | Automatic measuring method and device for retinal artery and vein diameter ratio |
| CN112164020A (en) * | 2020-03-31 | 2021-01-01 | 苏州润迈德医疗科技有限公司 | Method, device, analysis system and storage medium for accurately extracting blood vessel center line |
| CN112837288A (en) * | 2021-02-01 | 2021-05-25 | 数坤（北京）网络科技有限公司 | Blood vessel centerline extraction method and device and readable storage medium |
| CN113344895A (en) * | 2021-06-23 | 2021-09-03 | 依未科技(北京)有限公司 | High-precision fundus blood vessel diameter measuring method, device, medium and equipment |
| CN113643353A (en) * | 2020-09-04 | 2021-11-12 | 深圳硅基智能科技有限公司 | Method for measuring enhanced resolution of blood vessel diameter of fundus image |
| WO2022120743A1 (en) * | 2020-12-10 | 2022-06-16 | 深圳先进技术研究院 | Geometric analysis method for cerebral vascular wall contour labeling |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819823A (en) * | 2012-01-12 | 2012-12-12 | 北京理工大学 | Method for tracking and extracting blood vessels from angiography image full-automatically |
| CN106651846A (en) * | 2016-12-20 | 2017-05-10 | 中南大学湘雅医院 | Method for segmenting vasa sanguinea retinae image |
| CN107644420A (en) * | 2017-08-31 | 2018-01-30 | 西北大学 | Blood-vessel image dividing method, MRI system based on central line pick-up |
-
2018
- 2018-03-20 CN CN201810242675.5A patent/CN110310323A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819823A (en) * | 2012-01-12 | 2012-12-12 | 北京理工大学 | Method for tracking and extracting blood vessels from angiography image full-automatically |
| CN106651846A (en) * | 2016-12-20 | 2017-05-10 | 中南大学湘雅医院 | Method for segmenting vasa sanguinea retinae image |
| CN107644420A (en) * | 2017-08-31 | 2018-01-30 | 西北大学 | Blood-vessel image dividing method, MRI system based on central line pick-up |
Non-Patent Citations (2)
| Title |
|---|
| 李绅: "MRA脑图像的血管中轴提取研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 肖志涛 等: "基于Hesse矩阵和多尺度分析的视网膜动静脉血管管径测量方法", 《电子与信息学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111000563A (en) * | 2019-11-22 | 2020-04-14 | 北京理工大学 | Automatic measuring method and device for retinal artery and vein diameter ratio |
| CN112164020A (en) * | 2020-03-31 | 2021-01-01 | 苏州润迈德医疗科技有限公司 | Method, device, analysis system and storage medium for accurately extracting blood vessel center line |
| CN112164020B (en) * | 2020-03-31 | 2024-01-23 | 苏州润迈德医疗科技有限公司 | Method, device, analysis system and storage medium for accurately extracting blood vessel center line |
| CN113643353A (en) * | 2020-09-04 | 2021-11-12 | 深圳硅基智能科技有限公司 | Method for measuring enhanced resolution of blood vessel diameter of fundus image |
| WO2022048171A1 (en) * | 2020-09-04 | 2022-03-10 | 深圳硅基智能科技有限公司 | Method and apparatus for measuring blood vessel diameter in fundus image |
| CN113643353B (en) * | 2020-09-04 | 2024-02-06 | 深圳硅基智能科技有限公司 | Measurement method for enhancing resolution of vascular caliber of fundus image |
| WO2022120743A1 (en) * | 2020-12-10 | 2022-06-16 | 深圳先进技术研究院 | Geometric analysis method for cerebral vascular wall contour labeling |
| CN112837288A (en) * | 2021-02-01 | 2021-05-25 | 数坤（北京）网络科技有限公司 | Blood vessel centerline extraction method and device and readable storage medium |
| CN113344895A (en) * | 2021-06-23 | 2021-09-03 | 依未科技(北京)有限公司 | High-precision fundus blood vessel diameter measuring method, device, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110310323A (en) | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian | |
| US8861817B2 (en) | Image processing apparatus, control method thereof, and computer program | |
| CN107169998B (en) | A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image | |
| Kovács et al. | A self-calibrating approach for the segmentation of retinal vessels by template matching and contour reconstruction | |
| CN106204555B (en) | A kind of optic disk localization method of combination Gbvs model and phase equalization | |
| CN102163326B (en) | Method for automatic computerized segmentation and analysis on thickness uniformity of intima media of carotid artery blood wall in sonographic image | |
| KR101121396B1 (en) | System and method for providing 2-dimensional ct image corresponding to 2-dimensional ultrasound image | |
| CN106651888B (en) | Colour eye fundus image optic cup dividing method based on multi-feature fusion | |
| CN102982542B (en) | Fundus image vascular segmentation method based on phase congruency | |
| WO2016194161A1 (en) | Ultrasonic diagnostic apparatus and image processing method | |
| CN108615239B (en) | Tongue image segmentation method based on threshold technology and gray level projection | |
| US9230331B2 (en) | Systems and methods for registration of ultrasound and CT images | |
| CN106709967B (en) | Endoscopic imaging algorithm and control system | |
| US20110196236A1 (en) | System and method of automated gestational age assessment of fetus | |
| CN108186051B (en) | Image processing method and system for automatically measuring double-apical-diameter length of fetus from ultrasonic image | |
| WO2012126070A1 (en) | Automatic volumetric analysis and 3d registration of cross sectional oct images of a stent in a body vessel | |
| WO2021208739A1 (en) | Method and apparatus for evaluating blood vessel in fundus color image, and computer device and medium | |
| CN109829942A (en) | A kind of automatic quantization method of eye fundus image retinal blood vessels caliber | |
| CN105205437B (en) | Side face detection method and device based on contouring head verifying | |
| CN108550145A (en) | A kind of SAR image method for evaluating quality and device | |
| CN104732520A (en) | Cardio-thoracic ratio measuring algorithm and system for chest digital image | |
| CN109087310A (en) | Dividing method, system, storage medium and the intelligent terminal of Meibomian gland texture region | |
| US9147250B2 (en) | System and method for automatic magnetic resonance volume composition and normalization | |
| CN108665474B (en) | B-COSFIRE-based retinal vessel segmentation method for fundus image | |
| CN106372593B (en) | Optic disk area positioning method based on vascular convergence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191008 |