CN105787924A - Method for measuring diameter of maximum choroid blood vessel based on image segmentation - Google Patents
Method for measuring diameter of maximum choroid blood vessel based on image segmentation Download PDFInfo
- Publication number
- CN105787924A CN105787924A CN201610066181.7A CN201610066181A CN105787924A CN 105787924 A CN105787924 A CN 105787924A CN 201610066181 A CN201610066181 A CN 201610066181A CN 105787924 A CN105787924 A CN 105787924A
- Authority
- CN
- China
- Prior art keywords
- image
- choroid
- blood vessel
- maximum
- diameter
- 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
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
-
- 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 invention discloses a method for measuring the diameter of the maximum choroid blood vessel based on image segmentation. The method comprises the following steps: firstly performing image pre-processing on a choroid in a SD-OCT retina image, then adopting the method of image segmentation to extract a region of interest and performing related calculation on the region, and finally outputting a measuring result. According to the invention, the method reduces measuring errors by making the obtained diameter of the choroid maximum blood vessel with an improved precision than the diameter obtained by manual measuring. The method, by using the simple and rapid image segmentation technology, increases accuracy and efficiency in measuring the diameter of the choroid blood vessel, and has great significance in facilitating successive choroid diseases analysis and improving doctor's working efficiency.
Description
Technical field
The present invention relates to a kind of measuring method, the survey of a kind of choroid maximum blood vessel diameter based on image segmentation
Metering method.
Background technology
Choroid layer is made up of substantial amounts of blood vessel, provides nutrition for layer of retina, in close relations with retinal disease.Train of thought
The abnormal changes such as film blood vessel dilatation, hyperemia, high-permeability can cause the fundus oculi disease that choroid is relevant, and choroid form is in clinic
On there is the auxiliary diagnosis status do not replaced, along with continuous intensification to fundus oculi disease understanding in recent years, increasingly by eye
The concern of section clinician.In recent years, due to choroidal artery in domain optical coherence tomography (SD-OCT) image appearance not
Complete the most unintelligible, the method for choroidal artery monitoring is limited, clinical often by the work lacking the detection of accurate objective quantitative
Tool, this quantitative approach is disadvantageous in that: retinal vessel is not that the radiation sample centered by optic disk of rule completely divides
Cloth, so being scanned the blood vessel in the range of concentric circles centered by optic disk, arises that the non-perpendicular survey to blood vessel diameter
Amount, causes error；.The most traditional target extract method is difficult to effectively provide choroidal artery region.Existing in order to overcome
The accuracy of the method existence measuring choroidal artery is the highest, is easily caused error, the invention provides a kind of accuracy high, energy
The method enough obtaining choroid maximum blood vessel diameter.
Summary of the invention
Object of the present invention is to provide the measuring method of a kind of choroid maximum blood vessel diameter based on image segmentation.
The measuring method technical solution of choroid maximum blood vessel diameter based on image segmentation comprises three modules: figure
As pretreatment module, image segmentation module and measurement result output module；Described image pre-processing module comprises choroid layer figure
As filtering and choroid layer image enhaucament；Described image segmentation module is used for utilizing image segmentation algorithm to carry out choroid layer point
Cut and the maximum blood vessel in choroid layer is split, then segmentation rear region numerical value being calculated；Described measurement is tied
Really output module is used for exporting measurement result.
Concrete measuring method comprises the steps of
Step 1, gather the cross-sectional view of blood vessel in the choroid layer of SD-OCT retinal images；
Step 2, input picture is carried out denoising；
Step 3, input picture is carried out enhancing process；
Step 4, input picture is carried out dividing processing；
The maximum angiosomes diameter obtained after step 5, calculating segmentation；
Step 6, output measurement result；
Described step 4 uses overall situation Otsu threshold method carry out image segmentation, after segmentation, obtain the image of binaryzation.
Rear area-of-interest diameter is cut in the point counting of falling into a trap of described step 5, irregularly shaped due to vessel cross-section, and we adopt
It is the maximum Ink vessel transfusing pixel number of zero with gray value in statistics bianry image, maximum blood vessel diameter, wherein S is
The area of big blood vessel, vessel area is multiplied by each pixel size gained by number of pixels.
Compared with prior art, its remarkable advantage is the present invention: present invention reduces manual measure error, have employed letter
Single quickly error image binaryzation extractive technique, improves measurement accuracy and the efficiency of choroidal artery diameter, to convenient
The operating efficiency of follow-up choroidal diseases analysis and raising doctor is significant.
Accompanying drawing explanation
Fig. 1 SD-OCT retinal images.
Fig. 2 choroid layer is extracted.
Bianry image after Fig. 3 segmentation.
Fig. 4 choroid layer maximum vessel graph
Detailed description of the invention
With reference to Fig. 1-4, further illustrate the present invention:
The measuring method of a kind of choroid maximum blood vessel diameter based on image segmentation, first obtains SD-OCT retinal map
As it is shown in figure 1, use the method for image segmentation to measure choroid the choroid layer of the SD-OCT retinal images obtained
Blood vessel diameter, including image pre-processing module, image segmentation module and measurement result output module；Wherein image pre-processing module
Comprise choroid layer image filtering and choroid layer image enhaucament；Image segmentation module is used for utilizing image segmentation algorithm to train of thought
Film layer is split, as in figure 2 it is shown, and the maximum blood vessel in choroid layer is split, as it is shown on figure 3, then to point
Cut rear region numerical value to calculate；Described measurement result output module is used for exporting measurement result.
Measuring method comprises the steps of
Step 1, gather the cross-sectional view of blood vessel in the choroid layer of SD-OCT retinal images；
Step 2, input picture is carried out denoising；
Step 3, input picture is carried out enhancing process；
Step 4, input picture is carried out dividing processing；
The maximum angiosomes diameter obtained after step 5, calculating segmentation；
Step 6, output measurement result；
Described step 4 uses overall situation Otsu threshold method carry out image segmentation, after segmentation, obtain the image of binaryzation.
Rear area-of-interest diameter is cut in the point counting of falling into a trap of described step 5, and using gray value in statistics bianry image is zero
Big Ink vessel transfusing pixel number, maximum blood vessel diameter, wherein S is maximum vessel area, and vessel area is by number of pixels
It is multiplied by each pixel size gained.
The method that the present invention is introduced reduces measure error, and obtained choroid layer maximum blood vessel diameter is than manually surveying
Accuracy of measurement is higher；Present invention employs simple and quick image Segmentation Technology, the measurement that improve choroidal artery diameter is accurate
Property and efficiency, choroidal diseases analysis that the other side continues after an action of the bowels and to improve the operating efficiency of doctor significant.
Claims (4)
1. the measuring method of a choroid maximum blood vessel diameter based on image segmentation, it is characterised in that: to SD-OCT view
The choroid layer of film image uses the method for image segmentation to measure choroid maximum blood vessel diameter, including Image semantic classification mould
Block, image segmentation module and measurement result output module.
The measuring method of choroid maximum blood vessel diameter based on image segmentation the most according to claim 1, its feature exists
In, described image pre-processing module comprises choroid layer image filtering and choroid layer image enhaucament；Described image is split
Module is used for using image segmentation algorithm to split choroid layer and splitting the maximum blood vessel in choroid layer,
Then the maximum angiosomes numerical value obtained after segmentation is calculated；Described measurement result output module is used for exporting measurement knot
Really；
Concrete measuring method comprises the steps of
Step 1, gather the cross-sectional view of blood vessel in the choroid layer of SD-OCT retinal images；
Step 2, input picture is carried out denoising；
Step 3, input picture is carried out enhancing process；
Step 4, input picture is carried out dividing processing；
The maximum angiosomes diameter obtained after step 5, calculating segmentation；
Step 6, output measurement result.
The method of measurement choroidal artery diameter the most according to claim 2, it is characterised in that: step 4 uses the overall situation
Otsu threshold method carries out image segmentation, obtains the image of binaryzation after segmentation.
The method of measurement choroidal artery diameter the most according to claim 2, it is characterised in that: step 5 point counting of falling into a trap is cut
After the maximum angiosomes diameter that obtains, using maximum Ink vessel transfusing gray value in statistics bianry image is the pixel number of zero,
According to formula:Trying to achieve, wherein S is vessel area, and it is big that vessel area is multiplied by each pixel by number of pixels
Little gained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066181.7A CN105787924A (en) | 2016-02-01 | 2016-02-01 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066181.7A CN105787924A (en) | 2016-02-01 | 2016-02-01 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105787924A true CN105787924A (en) | 2016-07-20 |
Family
ID=56402600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610066181.7A Pending CN105787924A (en) | 2016-02-01 | 2016-02-01 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105787924A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780347A (en) * | 2017-02-09 | 2017-05-31 | 浙江科技学院 | A kind of loquat early stage bruise discrimination method based on OCT image treatment |
| CN109886938A (en) * | 2019-01-29 | 2019-06-14 | 深圳市科曼医疗设备有限公司 | A kind of ultrasound image blood vessel diameter method for automatic measurement |
| JP2021167802A (en) * | 2020-04-10 | 2021-10-21 | 株式会社トプコン | Three-dimensional analysis using optical coherence tomography image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060159322A1 (en) * | 2004-09-09 | 2006-07-20 | Daniel Rinck | Method for segmentation of anatomical structures from 4D image data records |
| CN102999905A (en) * | 2012-11-15 | 2013-03-27 | 天津工业大学 | Automatic eye fundus image vessel detecting method based on PCNN (pulse coupled neural network) |
-
2016
- 2016-02-01 CN CN201610066181.7A patent/CN105787924A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060159322A1 (en) * | 2004-09-09 | 2006-07-20 | Daniel Rinck | Method for segmentation of anatomical structures from 4D image data records |
| CN102999905A (en) * | 2012-11-15 | 2013-03-27 | 天津工业大学 | Automatic eye fundus image vessel detecting method based on PCNN (pulse coupled neural network) |
Non-Patent Citations (3)
| Title |
|---|
| 孙洪涛等: "冠状动脉弹性参数测量的系统与方法", 《中国医学影像技术》 * |
| 李居朋: "眼底图像处理与分析中一些关键问题的研究", 《中国博士学位论文全文数据库》 * |
| 李春林: "冠脉造影图像的血管识别方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780347A (en) * | 2017-02-09 | 2017-05-31 | 浙江科技学院 | A kind of loquat early stage bruise discrimination method based on OCT image treatment |
| CN106780347B (en) * | 2017-02-09 | 2020-03-03 | 浙江科技学院 | Early loquat bruise identification method based on OCT image processing |
| CN109886938A (en) * | 2019-01-29 | 2019-06-14 | 深圳市科曼医疗设备有限公司 | A kind of ultrasound image blood vessel diameter method for automatic measurement |
| JP2021167802A (en) * | 2020-04-10 | 2021-10-21 | 株式会社トプコン | Three-dimensional analysis using optical coherence tomography image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110010219B (en) | Intelligent detection system and detection method for retinopathy by optical coherence tomography | |
| US9418423B2 (en) | Motion correction and normalization of features in optical coherence tomography | |
| CN109003299A (en) | A method of the calculating cerebral hemorrhage amount based on deep learning | |
| CN109727243A (en) | Breast ultrasound image recognition analysis method and system | |
| CN104545792B (en) | The arteriovenous retinal vessel optic disc localization method of eye fundus image | |
| WO2021208739A1 (en) | Method and apparatus for evaluating blood vessel in fundus color image, and computer device and medium | |
| CN109637660B (en) | Tongue diagnosis analysis method and system based on deep convolutional neural network | |
| CN104809480A (en) | Retinal vessel segmentation method of fundus image based on classification and regression tree and AdaBoost | |
| CN102136135A (en) | Method for extracting inner outline of cornea from optical coherence tomography image of anterior segment of eye and method for extracting inner outline of anterior chamber from optical coherence tomography image of anterior segment of eye | |
| KR102206621B1 (en) | Programs and applications for sarcopenia analysis using deep learning algorithms | |
| CN105787924A (en) | Method for measuring diameter of maximum choroid blood vessel based on image segmentation | |
| CN110310323A (en) | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian | |
| CN114830173A (en) | Method for determining the severity of skin disorders based on the percentage of human body surface area covered by lesions | |
| Mao et al. | Deep learning with skip connection attention for choroid layer segmentation in oct images | |
| Aruchamy et al. | Automated glaucoma screening in retinal fundus images | |
| Babu et al. | Relation networks for optic disc and fovea localization in retinal images | |
| EP3129955B1 (en) | Method for the analysis of image data representing a three-dimensional volume of biological tissue | |
| Rao et al. | Automated detection of diabetic retinopathy through image feature extraction | |
| Pham et al. | Deep learning algorithms to isolate and quantify the structures of the anterior segment in optical coherence tomography images | |
| EP3129956B1 (en) | Method for the analysis of image data representing a three-dimensional volume of biological tissue | |
| Aloudat et al. | Histogram analysis for automatic blood vessels detection: First step of IOP | |
| Archana et al. | Detection of abnormal blood vessels in diabetic retinopathy based on brightness variations in SDOCT retinal images | |
| Santhakumar et al. | A fast algorithm for optic disc segmentation in fundus images | |
| Rosidi et al. | Classification of cervical cells based on labeled colour intensity distribution | |
| Nugroho et al. | Detection of foveal avascular zone in colour retinal fundus images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160720 |
|
| RJ01 | Rejection of invention patent application after publication |