CN110956107A - Three-dimensional blood vessel type distinguishing method based on OCT (optical coherence tomography) scanning system - Google Patents
Three-dimensional blood vessel type distinguishing method based on OCT (optical coherence tomography) scanning system Download PDFInfo
- Publication number
- CN110956107A CN110956107A CN201911145891.9A CN201911145891A CN110956107A CN 110956107 A CN110956107 A CN 110956107A CN 201911145891 A CN201911145891 A CN 201911145891A CN 110956107 A CN110956107 A CN 110956107A
- Authority
- CN
- China
- Prior art keywords
- matrix
- blood vessel
- dimensional
- diameter
- scanning system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a three-dimensional blood vessel type distinguishing method based on an OCT (optical coherence tomography) scanning system, which comprises the steps of obtaining a three-dimensional stereo image group of a blood vessel in the time direction through the OCT scanning system; extracting a two-dimensional image corresponding to unit depth from the three-dimensional stereo image group, converting the two-dimensional image into a two-dimensional matrix, and forming the two-dimensional matrix and time corresponding to the two-dimensional matrix into a three-dimensional matrix T; carrying out noise reduction processing on the three-dimensional matrix T to obtain a matrix G; performing Fourier transform on the matrix G to convert the matrix G from a time domain space to a frequency domain space to obtain a matrix K; carrying out quantization processing on the matrix K through a parameter IR to obtain a matrix A, wherein an image represented by the matrix A is an artery distribution map; subtracting the matrix A from the matrix T to obtain a matrix B; performing convolution on the matrix B by taking a Gaussian function as a convolution kernel to obtain a matrix C; determining a vessel radial search direction; and obtaining the diameter of the blood vessel and obtaining a vein distribution diagram and a capillary distribution diagram by searching the radial search direction of the blood vessel. The method is mainly used for biological imaging.
Description
Technical Field
The invention relates to the technical field of medical detection, in particular to a three-dimensional blood vessel type distinguishing method based on an OCT (optical coherence tomography) scanning system.
Background
Before methods for automatically distinguishing blood vessel types are proposed, the blood vessel types are mainly judged by doctors or biological laboratory technicians according to self experiences. With the development of optical imaging technology, some methods for automatically distinguishing blood vessel types based on optical imaging are also continuously proposed. In 1982 and 1998, Akita et al and Jusephsky-Haw Yu et al set threshold values to distinguish the type of retinal vessels in the fundus according to the difference of the reflection light intensity of arteriovenous vessels. However, in some cases of single-wavelength illumination, the light intensity of more artery and vein regions is similar, which is not enough to distinguish the blood vessel types according to the light intensity difference. In 2007, zhanhoboshi et al, university of texas a & M, used a photoacoustic microscope to observe changes in hemoglobin oxygen saturation (SO2), and discriminated arteriovenous types from measured blood oxygen saturation. In 2007, Indian scientist Narasimhaiyer et al identified blood vessel types by structural and functional features of fundus retinal images at 570nm and 600nm wavelengths. Furthermore, single wavelength based imaging methods are also used to distinguish vessel types. In 2010 and 2011, the brain cortex blood vessel type recognition is realized by the blood vessel anatomical features and the light intensity distribution in single-wavelength LSCI (SW-LSCI) images of the Shanghai traffic university nerve engineering laboratory, Roento doctor and the like and the Huazhong science and technology university Von Neng cloud doctor in sequence. With the application and development of MRA and CT techniques, they are also used for three-dimensional vessel classification to distinguish head, lung and heart.
At present, two-dimensional blood vessel classification technologies mainly comprise a multi-wavelength artery and vein classification method and a single-wavelength blood vessel classification method, but the two methods are complex and are not beneficial to rapidly distinguishing the types of blood vessels.
Disclosure of Invention
The present invention is directed to a method for distinguishing three-dimensional blood vessel types based on an OCT scanning system, which solves one or more of the problems of the prior art, and provides at least one of the advantages.
The solution of the invention for solving the technical problem is as follows: a three-dimensional blood vessel type distinguishing method based on an OCT scanning system comprises the following steps:
step 1, performing continuous C scanning on a region where a blood vessel is located through an OCT (optical coherence tomography) scanning system to obtain a three-dimensional map group of the blood vessel in the time direction;
step 2, extracting a two-dimensional image corresponding to unit depth from the three-dimensional stereo image group, converting the two-dimensional image into a two-dimensional matrix, and forming the two-dimensional matrix and time corresponding to the two-dimensional matrix into a three-dimensional matrix T;
step 3, carrying out noise reduction processing on the three-dimensional matrix T to obtain a matrix G;
step 4, carrying out Fourier transform on the matrix G to convert the matrix G from a time domain space to a frequency domain space to obtain a matrix K;
step 5, carrying out quantization processing on the matrix K through a parameter IR to obtain a matrix A, wherein an image represented by the matrix A is an artery distribution map;
6, subtracting the matrix A from the matrix T to obtain a matrix B;
step 7, performing convolution on the matrix B by taking a Gaussian function as a convolution kernel to obtain a matrix C;
step 8, calculating a Hessian matrix H (x, y) of the matrix C;
step 9, calculating eigenvalues and corresponding eigenvectors of a Hessian matrix H (x, y), taking the included angle direction of the two eigenvectors as the direction of the blood vessel, and rotating by 90 degrees to obtain the radial search direction of the blood vessel;
step 10, obtaining the diameter of the blood vessel by searching the radial search direction of the blood vessel;
step 11, obtaining a vein distribution map and a capillary distribution map through the diameter of a blood vessel;
wherein the expression of the parameter IR is:
Further, in step 3, the noise reduction processing is eight-domain noise reduction processing.
Further, the eight-domain denoising specifically comprises: and (3) taking 3-by-3 windows with all values of 1 to convolute the matrix T in turn, and smoothing data by using Savitzky-Golay filtering operators for the eight neighborhoods in a single column in sequence along the time direction.
Further, in step 10, the method for determining the diameter of the blood vessel includes: performing blood vessel segmentation, then performing binarization, respectively starting to search blood vessel boundaries along the radial search direction and the opposite direction of the blood vessel, wherein the distance between adjacent blood vessel boundaries is the diameter of the blood vessel, and the diameter of the blood vessel is recorded as a first diameter; calculating gradient value change conditions along the radial search direction of the blood vessel and the opposite direction of the radial search direction of the blood vessel by adopting a gradient extreme value method, determining the edge of the blood vessel, wherein the gradient value of the edge of the blood vessel is increased from zero to gradient, the initial end and the termination end of the mutation are taken as two edge points of the blood vessel, the Euclidean distance between the two edge points is taken as the diameter of the blood vessel, and the diameter of the blood vessel is taken as a second diameter; the first diameter and the second diameter are averaged to obtain the vessel diameter.
Further, in step 11, the acquisition of the vein profile and the capillary profile includes: marking the blood vessels with the diameter of more than 15 mu m to obtain a vein distribution map, and marking the blood vessels with the diameter of less than or equal to 15 mu m to obtain a capillary distribution map.
The invention has the beneficial effects that: the three-dimensional map group is obtained by using an OCT scanning system, then the artery is separated out by using the difference of vibration signals, and then the vein and the capillary vessel are separated according to the difference between the diameters of the vein and the capillary vessel, so that the three-dimensional blood vessel types are distinguished with high precision.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the described drawings are only a part of the embodiments of the invention, not all embodiments, and that a person skilled in the art will be able to derive other designs and drawings from these drawings without the exercise of inventive effort.
Fig. 1 is a flow chart of steps of a three-dimensional blood vessel type distinguishing method based on an OCT scanning system.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as up, down, front, rear, left, right, etc., is the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of the description of the present invention, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the invention, if words such as "a number" or the like are used, the meaning is one or more, the meaning of a plurality is two or more, more than, less than, more than, etc. are understood as not including the number, and more than, less than, more than, etc. are understood as including the number.
In the description of the present invention, unless otherwise explicitly defined, terms such as setup, installation, connection, and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the terms in the present invention in combination with the detailed contents of the technical solutions.
Embodiment 1, referring to fig. 1, a three-dimensional blood vessel type distinguishing method based on an OCT scanning system includes:
step 1, performing continuous C scanning on a region where a blood vessel is located through an OCT (optical coherence tomography) scanning system to obtain a three-dimensional map group of the blood vessel in the time direction;
step 2, extracting a two-dimensional image corresponding to unit depth from the three-dimensional stereo image group, converting the two-dimensional image into a two-dimensional matrix, and forming the two-dimensional matrix and time corresponding to the two-dimensional matrix into a three-dimensional matrix T;
step 3, carrying out noise reduction processing on the three-dimensional matrix T to obtain a matrix G;
step 4, carrying out Fourier transform on the matrix G to convert the matrix G from a time domain space to a frequency domain space to obtain a matrix K;
step 5, carrying out quantization processing on the matrix K through a parameter IR to obtain a matrix A, wherein an image represented by the matrix A is an artery distribution map;
6, subtracting the matrix A from the matrix T to obtain a matrix B;
step 7, performing convolution on the matrix B by taking a Gaussian function as a convolution kernel to obtain a matrix C;
step 8, calculating a Hessian matrix H (x, y) of the matrix C;
step 9, calculating eigenvalues and corresponding eigenvectors of a Hessian matrix H (x, y), taking the included angle direction of the two eigenvectors as the direction of the blood vessel, and rotating by 90 degrees to obtain the radial search direction of the blood vessel;
step 10, obtaining the diameter of the blood vessel by searching the radial search direction of the blood vessel;
step 11, obtaining a vein distribution map and a capillary distribution map through the diameter of a blood vessel;
wherein the expression of the parameter IR is:
Wherein, in some optimized embodiments, in step 3, the denoising process is an eight-domain denoising process. The eight-field denoising treatment specifically comprises the following steps: and (3) taking 3-by-3 windows with all values of 1 to convolute the matrix T in turn, and smoothing data by using Savitzky-Golay filtering operators for the eight neighborhoods in a single column in sequence along the time direction. The Savitzky-Golay filter is a special low-pass filter, can be used for directly carrying out smooth denoising on data in a time domain, and has the characteristic of high fidelity of abnormal signals. The idea of this filter is to slide filter the data with a window width of 2m +1, and fit an nth order polynomial to the data within the window:
calculating expression of fitting polynomial P (x) based on least square principle, and substituting the horizontal coordinate of the central point in the window into P (x) to obtain function value P (x)0) The Savitzky-Golay filtering value at the point is sequentially and continuously slid from head to tail to complete the filtering of all data.
Since the vibration of the artery originates from the beating of the animal's heart, the I (upsilon) of the artery location is mainly distributed at a specific frequency f0(ii) a The veins and capillaries have no obvious and stable vibration signals, so that the I (upsilon) of the veins and capillaries are randomly distributed in the whole frequency domain. Based on the characteristics, the vibration noise at non-artery positions can be weakened through the parameter IR, so thatThe artery position is highlighted. Thereby obtaining an arterial map.
After obtaining the artery distribution map, it is necessary to distinguish veins and capillaries, and a gaussian function is used as a convolution kernel to reduce the interference of random noise, so as to obtain a matrix G, which is represented by T (x, y; s), that is:
T(x,y；s)＝T(x,y)*G(x,y；s)
wherein, is convolution symbol, variance is s2Is defined as:
in order to accurately calculate the blood vessel diameter, it is necessary to calculate the direction of the blood vessel first, and to use the vertical direction of the blood vessel direction as the search direction in the calculation of the blood vessel diameter. The invention adopts eigenvalue analysis based on Hessian matrix to calculate the direction of the blood vessel. The Hessian matrix of a two-dimensional image is a symmetric square matrix composed of second-order partial derivatives of a bivariate real-valued function, and is defined as:
respectively convolving the original image T (X, Y) by calculating first and second derivatives of the Gaussian kernel function in the X direction and the Y direction, and finally obtaining a Hessian matrix of the matrix C at the point (X, Y):
and calculating the eigenvalue of the Hessian matrix H (x, y) and the corresponding eigenvector, taking the included angle direction of the two eigenvectors as the direction of the blood vessel, and rotating by 90 degrees to obtain the radial search direction of the blood vessel. And obtaining the diameter of the blood vessel by searching the radial search direction of the blood vessel. The specific method comprises the following steps: performing blood vessel segmentation, then performing binarization, respectively starting to search blood vessel boundaries along the radial search direction and the opposite direction of the blood vessel, wherein the distance between adjacent blood vessel boundaries is the diameter of the blood vessel, and the diameter of the blood vessel is recorded as a first diameter; calculating gradient value change conditions along the radial search direction of the blood vessel and the opposite direction of the radial search direction of the blood vessel by adopting a gradient extreme value method, determining the edge of the blood vessel, wherein the gradient value of the edge of the blood vessel is increased from zero to gradient, the initial end and the termination end of the mutation are taken as two edge points of the blood vessel, the Euclidean distance between the two edge points is taken as the diameter of the blood vessel, and the diameter of the blood vessel is taken as a second diameter; the first diameter and the second diameter are averaged to obtain the vessel diameter. The method for segmenting the blood vessel includes but is not limited to: frangi algorithm based on Hessian matrix, algorithm based on PCA, matched filtering algorithm and adaptive contrast enhancement algorithm. By averaging the first diameter and the second diameter, the diameter of the blood vessel at a certain position can be determined more accurately, so that veins and capillaries can be better distinguished. Wherein the method of distinguishing between veins and capillaries is by comparing the diameters of veins and capillaries. Specifically, blood vessels with the diameter of more than 15 mu m are marked to obtain a vein distribution map, and blood vessels with the diameter of less than or equal to 15 mu m are marked to obtain a capillary distribution map.
The invention utilizes an OCT scanning system to obtain a three-dimensional map group, then separates out the artery by utilizing the difference of vibration signals, and separates the vein and the capillary vessel by the difference of the diameters of the vein and the capillary vessel, thereby realizing the high-precision distinguishing of the three-dimensional blood vessel types.
While the preferred embodiments of the present invention have been described in detail, it will be understood by those skilled in the art that the invention is not limited to the details of the embodiments shown, but is capable of various modifications and substitutions without departing from the spirit of the invention.
Claims (5)
1. A three-dimensional blood vessel type distinguishing method based on an OCT scanning system is characterized by comprising the following steps:
step 1, performing continuous C scanning on a region where a blood vessel is located through an OCT (optical coherence tomography) scanning system to obtain a three-dimensional map group of the blood vessel in the time direction;
step 2, extracting a two-dimensional image corresponding to unit depth from the three-dimensional stereo image group, converting the two-dimensional image into a two-dimensional matrix, and forming the two-dimensional matrix and time corresponding to the two-dimensional matrix into a three-dimensional matrix T;
step 3, carrying out noise reduction processing on the three-dimensional matrix T to obtain a matrix G;
step 4, carrying out Fourier transform on the matrix G to convert the matrix G from a time domain space to a frequency domain space to obtain a matrix K;
step 5, carrying out quantization processing on the matrix K through a parameter IR to obtain a matrix A, wherein an image represented by the matrix A is an artery distribution map;
6, subtracting the matrix A from the matrix T to obtain a matrix B;
step 7, performing convolution on the matrix B by taking a Gaussian function as a convolution kernel to obtain a matrix C;
step 8, calculating a Hessian matrix H (x, y) of the matrix C;
step 9, calculating eigenvalues and corresponding eigenvectors of a Hessian matrix H (x, y), taking the included angle direction of the two eigenvectors as the direction of the blood vessel, and rotating by 90 degrees to obtain the radial search direction of the blood vessel;
step 10, obtaining the diameter of the blood vessel by searching the radial search direction of the blood vessel;
step 11, obtaining a vein distribution map and a capillary distribution map through the diameter of a blood vessel;
wherein the expression of the parameter IR is:
2. The three-dimensional blood vessel type distinguishing method based on the OCT scanning system of claim 1, wherein in step 3, the noise reduction processing is eight-domain noise reduction processing.
3. The three-dimensional blood vessel type distinguishing method based on the OCT scanning system of claim 2, wherein the eight-domain noise reduction processing specifically comprises: and (3) taking 3-by-3 windows with all values of 1 to convolute the matrix T in turn, and smoothing data by using Savitzky-Golay filtering operators for the eight neighborhoods in a single column in sequence along the time direction.
4. The three-dimensional blood vessel type distinguishing method based on the OCT scanning system of claim 1, wherein in step 10, the method for determining the diameter of the blood vessel comprises: performing blood vessel segmentation, then performing binarization, respectively starting to search blood vessel boundaries along the radial search direction and the opposite direction of the blood vessel, wherein the distance between adjacent blood vessel boundaries is the diameter of the blood vessel, and the diameter of the blood vessel is recorded as a first diameter; calculating gradient value change conditions along the radial search direction of the blood vessel and the opposite direction of the radial search direction of the blood vessel by adopting a gradient extreme value method, determining the edge of the blood vessel, wherein the gradient value of the edge of the blood vessel is increased from zero to gradient, the initial end and the termination end of the mutation are taken as two edge points of the blood vessel, the Euclidean distance between the two edge points is taken as the diameter of the blood vessel, and the diameter of the blood vessel is taken as a second diameter; the first diameter and the second diameter are averaged to obtain the vessel diameter.
5. The method for distinguishing three-dimensional blood vessel types based on the OCT scanning system of claim 1, wherein in step 11, the obtaining manner of the vein profile and the capillary vessel profile comprises: marking the blood vessels with the diameter of more than 15 mu m to obtain a vein distribution map, and marking the blood vessels with the diameter of less than or equal to 15 mu m to obtain a capillary distribution map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911145891.9A CN110956107B (en) | 2019-11-21 | 2019-11-21 | Three-dimensional blood vessel type distinguishing method based on OCT scanning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911145891.9A CN110956107B (en) | 2019-11-21 | 2019-11-21 | Three-dimensional blood vessel type distinguishing method based on OCT scanning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110956107A true CN110956107A (en) | 2020-04-03 |
| CN110956107B CN110956107B (en) | 2023-05-30 |
Family
ID=69977864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911145891.9A Active CN110956107B (en) | 2019-11-21 | 2019-11-21 | Three-dimensional blood vessel type distinguishing method based on OCT scanning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956107B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681242A (en) * | 2020-08-14 | 2020-09-18 | 北京至真互联网技术有限公司 | Retinal vessel arteriovenous distinguishing method, device and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105188550A (en) * | 2013-03-12 | 2015-12-23 | 光学实验室成像公司 | Vascular data processing and image registration systems, methods, and apparatuses |
| CN107468234A (en) * | 2017-08-28 | 2017-12-15 | 佛山科学技术学院 | A kind of vascular flow projection chromatography 3-D imaging system and imaging method |
| CN107485383A (en) * | 2017-09-29 | 2017-12-19 | 佛山科学技术学院 | A kind of speckle blood flow imaging method and apparatus based on constituent analysis |
| CN107595250A (en) * | 2017-09-30 | 2018-01-19 | 浙江大学 | The blood flow imaging method and system of contrast is mixed with figure based on motion |
| US20180020909A1 (en) * | 2016-07-20 | 2018-01-25 | Oregon Health & Science University | Automated quantification of nonperfusion in the retina using optical coherence tomography angiography |
| CN108670239A (en) * | 2018-05-22 | 2018-10-19 | 浙江大学 | A kind of the three-dimensional flow imaging method and system in feature based space |
| CN109907731A (en) * | 2019-01-31 | 2019-06-21 | 浙江大学 | The three-dimensional flow angiographic method and system of optical coherence tomography based on feature space |
| CN110160440A (en) * | 2019-03-07 | 2019-08-23 | 佛山科学技术学院 | A kind of three-dimensional colour dynamic imaging device and method based on frequency domain OCT technology |
-
2019
- 2019-11-21 CN CN201911145891.9A patent/CN110956107B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105188550A (en) * | 2013-03-12 | 2015-12-23 | 光学实验室成像公司 | Vascular data processing and image registration systems, methods, and apparatuses |
| US20180020909A1 (en) * | 2016-07-20 | 2018-01-25 | Oregon Health & Science University | Automated quantification of nonperfusion in the retina using optical coherence tomography angiography |
| CN107468234A (en) * | 2017-08-28 | 2017-12-15 | 佛山科学技术学院 | A kind of vascular flow projection chromatography 3-D imaging system and imaging method |
| CN107485383A (en) * | 2017-09-29 | 2017-12-19 | 佛山科学技术学院 | A kind of speckle blood flow imaging method and apparatus based on constituent analysis |
| CN107595250A (en) * | 2017-09-30 | 2018-01-19 | 浙江大学 | The blood flow imaging method and system of contrast is mixed with figure based on motion |
| CN108670239A (en) * | 2018-05-22 | 2018-10-19 | 浙江大学 | A kind of the three-dimensional flow imaging method and system in feature based space |
| CN109907731A (en) * | 2019-01-31 | 2019-06-21 | 浙江大学 | The three-dimensional flow angiographic method and system of optical coherence tomography based on feature space |
| CN110160440A (en) * | 2019-03-07 | 2019-08-23 | 佛山科学技术学院 | A kind of three-dimensional colour dynamic imaging device and method based on frequency domain OCT technology |
Non-Patent Citations (2)
| Title |
|---|
| FULI ZHANG 等: "In vivo full-field functional optical hemocytometer", 《J. BIOPHOTONICS.》 * |
| RIWEI LIAO 等: "High-temporal-resolution, full-field optical angiography based on short time modulation depth for vascular occlusion tests", 《JOURNAL OF BIOMEDICAL OPTICS》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681242A (en) * | 2020-08-14 | 2020-09-18 | 北京至真互联网技术有限公司 | Retinal vessel arteriovenous distinguishing method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110956107B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akbar et al. | Arteriovenous ratio and papilledema based hybrid decision support system for detection and grading of hypertensive retinopathy | |
| Wu et al. | On the adaptive detection of blood vessels in retinal images | |
| Zhao et al. | Automated vessel segmentation using infinite perimeter active contour model with hybrid region information with application to retinal images | |
| CN111340789A (en) | Method, device, equipment and storage medium for identifying and quantifying eye fundus retinal blood vessels | |
| US9940722B2 (en) | Segmentation and identification of closed-contour features in images using graph theory and quasi-polar transform | |
| Rossant et al. | A morphological approach for vessel segmentation in eye fundus images, with quantitative evaluation | |
| Moghimirad et al. | Retinal vessel segmentation using a multi-scale medialness function | |
| ES2921974T3 (en) | Image processing method for the detection of glaucoma and associated software products | |
| KR102095723B1 (en) | Improvements in or relating to image processing | |
| Khan et al. | A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity | |
| Kafieh et al. | An accurate multimodal 3-D vessel segmentation method based on brightness variations on OCT layers and curvelet domain fundus image analysis | |
| Rehman et al. | Microscopic retinal blood vessels detection and segmentation using support vector machine and K‐nearest neighbors | |
| Amini et al. | Classification of medical image modeling methods: A review | |
| Liu et al. | A multiscale ray-shooting model for termination detection of tree-like structures in biomedical images | |
| Mukherjee et al. | Tree2tree2: Neuron tracing in 3d | |
| CN110956107A (en) | Three-dimensional blood vessel type distinguishing method based on OCT (optical coherence tomography) scanning system | |
| Morales et al. | Segmentation and analysis of retinal vascular tree from fundus images processing | |
| KR101601041B1 (en) | Pattern Classification Apparatus and Method for fMRI | |
| Bhattacharya et al. | A new approach to automated retinal vessel segmentation using multiscale analysis | |
| Li et al. | Automated retinal vessel segmentation using multiscale analysis and adaptive thresholding | |
| KR102223263B1 (en) | Method and Apparatus for Interpretation of Magnifying Endoscopy Images of Esophageal Cancer using Computer Aided Diagnostic System | |
| Singh et al. | Automatic detection of hard exudates shadow region within retinal layers of OCT images | |
| Hatanaka et al. | Artery and vein diameter ratio measurement based on improvement of arteries and veins segmentation on retinal images | |
| DelPozo‐Baños et al. | Localized component filtering for electroencephalogram artifact rejection | |
| CN112017132A (en) | Vein image enhancement method based on maximum curvature method and multi-scale Hessian matrix |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |