CN114305321A - Method and system for measuring thickness of retinal vessel wall - Google Patents
Method and system for measuring thickness of retinal vessel wall Download PDFInfo
- Publication number
- CN114305321A CN114305321A CN202210249162.3A CN202210249162A CN114305321A CN 114305321 A CN114305321 A CN 114305321A CN 202210249162 A CN202210249162 A CN 202210249162A CN 114305321 A CN114305321 A CN 114305321A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- vessel wall
- thickness
- infrared fundus
- 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
Images
Abstract
The application discloses a method and a system for measuring thickness of retinal vessel wall, wherein the method comprises the following steps: acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography; respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image; respectively carrying out optic disc labeling on the segmented infrared fundus image and the segmented registration image; overlapping the marked infrared fundus image and the marked registration image to obtain a blood vessel section in the ring; and measuring the thickness of the blood vessel wall of the blood vessel section, and obtaining the thickness of the retinal blood vessel wall based on the thickness of the blood vessel wall of the blood vessel section. The invasion that exists among the prior art is overcome to this application, has the damage, and asynchronous, non-simultaneous shortcoming has improved vascular wall thickness measurement result's accuracy, helps the doctor to judge retina blood vessel diameter, has practiced thrift doctor's time.
Description
Technical Field
The application belongs to the technical field of medical image processing, and particularly relates to a method and a system for measuring thickness of retinal vessel wall.
Background
Retinal blood vessels and the cardiovascular and cerebrovascular systems have common anatomical physiological characteristics, so that the change of the retinal blood vessel diameter (such as the stenosis of retinal artery and the dilation of retinal vein) is not only an important sign of the retinopathy, but also can become direct evidence of the vascular injury of cardiovascular and cerebrovascular diseases such as diabetes, hypertension and the like. In recent years, methods for detecting retinal blood vessels clinically include fluorescence angiography, fundus color photography, ophthalmoscope and the like, but most of the methods are indirect, asynchronous and even invasive, the accuracy and repeatability are low, and the methods are not suitable for being widely developed clinically, while an Optical Coherence Tomography (OCT) infrared fundus image includes the outer side of a blood vessel wall, an Optical Coherence Tomography (OCTA) blood vessel image includes the inner side of the blood vessel wall, and the information of the two images is complementary, so that the measurement of the thickness of the blood vessel wall is easier.
For example, the Chinese patent application number is: 201810668831.4 discloses a retinal vessel wall thickness measurement method based on image registration, including: acquiring a fundus color image and a fundus fluorescence radiography image; respectively preprocessing two images, segmenting blood vessels, denoising the blood vessels, extracting skeletonization of the blood vessels, detecting angular points and generating characteristic points; registering according to the angular point characteristics; performing optic disc labeling on the registered picture; the thickness of the vessel wall is measured. The disadvantages of this method are: firstly, two sides of a blood vessel in the fundus color image are formed in a reflecting mode and are not the real thickness of the blood vessel wall; secondly, the contrast agent has the problems of allergy, potential renal toxicity and the like; moreover, the fundus color image and the fundus fluorography image are acquired non-synchronously and non-simultaneously, which can be influenced by the head position, the eye position and even the pulsation of the blood vessel.
Disclosure of Invention
The application provides a method and a system for measuring thickness of a retinal vessel wall, and an optical coherence tomography infrared fundus image and a corresponding optical coherence tomography registration image which are simultaneously acquired by inputting the same eyeball overcome the defects of invasiveness, damage, asynchrony and non-simultaneity in the prior art for measuring the thickness of the retinal vessel wall.
In order to achieve the above object, the present application provides a method of measuring a thickness of a retinal vessel wall, comprising:
acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography;
respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image;
respectively carrying out optic disc labeling on the segmented infrared fundus image and the segmented registration image;
overlapping the marked infrared fundus image and the marked registration image to obtain a blood vessel section in the ring;
and measuring the thickness of the blood vessel wall of the blood vessel section, and obtaining the thickness of the retinal blood vessel wall based on the thickness of the blood vessel wall of the blood vessel section.
Optionally, the method for obtaining the registration image includes: and acquiring an optical coherence tomography blood vessel image, and covering the shallow optical coherence tomography blood vessel image on the infrared fundus image through blood vessel alignment to obtain a registration image.
Optionally, the infrared fundus image and the registration image are both from the same eyeball of the same person and acquired at the same eye position; the infrared fundus image and the registration image are consistent in width and height.
Optionally, the method for respectively performing blood vessel segmentation on the infrared fundus image and the registration image comprises:
and respectively carrying out vessel segmentation on the infrared fundus image and the registration image by adopting a Residual U-Net model and a mixed loss function consisting of cross entropy and DICE.
Optionally, the method for performing optic disc labeling on the segmented infrared fundus image and the segmented registration image respectively comprises: and acquiring the center of the optic disc and the diameter DD of the optic disc, and acquiring a circular ring formed by circles with diameters of 2DD and 3DD by taking the center of the optic disc as the center of a circle and the diameter DD of the optic disc as the reference.
Optionally, the method for measuring the thickness of the blood vessel wall of the blood vessel section comprises:
and obtaining a preset blood vessel section in the ring, counting the total number COUNT0 of the pixel points of the blood vessel wall of the blood vessel section, and calculating the thickness P of the retinal blood vessel wall according to the total number COUNT0 of the pixel points and the diameter DD of the optic disc.
Optionally, the calculation formula for measuring the thickness of the blood vessel wall of the blood vessel section is as follows:
P=COUNT0/0.5DD。
in another aspect, to achieve the above object, the present application provides a system for measuring thickness of a retinal vessel wall, including:
the device comprises an acquisition module, a segmentation module, a labeling module, an overlapping module and a measurement module;
the acquisition module is used for acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography;
the segmentation module is used for respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image;
the labeling module is used for respectively labeling the segmented infrared fundus image and the segmented registration image;
the overlapping module is used for overlapping the marked infrared fundus image and the marked registration image to obtain an annular blood vessel section;
the measuring module is used for measuring the thickness of the blood vessel wall of the blood vessel section, and the thickness of the retina blood vessel wall is obtained based on the thickness of the blood vessel wall of the blood vessel section.
The beneficial effect of this application does:
1. the application utilizes OCT infrared ray eye ground image and corresponding OCT registration image to measure the thickness of retinal vessel wall, has the advantages of no damage, non-invasiveness and no mydriasis, and has no problems of allergy, potential nephrotoxicity and the like brought by contrast agents.
And 2, the acquisition of the OCT infrared fundus image and the corresponding OCT registration image is synchronous at the same time, so that the influence of the pulsation of the head, the eye position and even the blood vessel is avoided due to the asynchronization in time and space.
And 3, the high resolution of the OCT can display the structural details of the blood vessel, and can accurately measure the inner diameter and the outer diameter of the blood vessel so as to obtain the thickness of the blood vessel wall.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for a person skilled in the art to obtain other drawings without any inventive exercise.
Fig. 1 is a schematic flowchart of a method for measuring thickness of a retinal vessel wall according to a first embodiment of the present application;
FIG. 2 is a schematic diagram of an OCT infrared fundus image according to the first embodiment of the present application;
fig. 3 is a schematic diagram of an OCT registration image according to the first embodiment of the present application;
FIG. 4 is a diagram illustrating a blood vessel segmentation result of an OCT infrared fundus image according to a first embodiment of the present application;
fig. 5 is a schematic view of a blood vessel segmentation result of an OCT registered image according to a first embodiment of the present application;
fig. 6 is a schematic diagram of an overlay image of a blood vessel in a retaining ring according to a first embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
The first embodiment is as follows:
as shown in fig. 1, a method for measuring thickness of retinal vessel wall according to an embodiment of the present application includes,
s1: based on Optical Coherence Tomography (OCT), an infrared fundus image and corresponding registration image are acquired, as shown in fig. 2-3:
specifically, the obtained registration image is obtained by obtaining an optical coherence tomography blood vessel image (OCTA), the OCT automatically aligns the blood vessel, and the shallow optical coherence tomography blood vessel image (OCTA) is covered on the OCT infrared fundus image to realize automatic registration.
Furthermore, the OCT infrared fundus image and the OCT registration image are used for measuring the thickness of the blood vessel wall, the method is a non-invasive, non-invasive and non-mydriasis method, the OCT infrared fundus image and the OCT registration image are simultaneously acquired under the same eyeball of the same patient, the width and the height of the two images are consistent, namely the pixel size is consistent, and manual image registration is not needed.
S2: the infrared fundus image and the registration image are respectively subjected to vessel segmentation, as shown in fig. 4-5:
specifically, the method for performing vessel segmentation on the infrared fundus image and the registration image respectively is to perform model development by using a labeled high-quality public data set (including Drive, Stare, HRF, chase db 1). To enlarge the training data set and reduce overfitting, the present application employs a block-based segmentation method. And in the training stage, the resolution of the input image is converted into 640-512 pixels, 180 image blocks with the size of 64-64 are generated for each image, wherein 80 image blocks are generated by adopting a sliding window method and are not overlapped and crossed with each other, and 100 random cropping is performed. Whereas only 80 non-overlapping image blocks are generated in the prediction phase. Vessel segmentation can be regarded as a semantic segmentation problem, so the application adopts a Residual U-Net model, and the loss function adopts a mixed loss function consisting of cross entropy and DICE. The prediction stage model outputs a blood vessel map with 640 x 512 pixels of resolution, and the size of the original image needs to be adjusted in proportion. In addition, gray value 0= black, representing the vessel wall; gray value 128= gray, representing blood flow; gray value 200= light gray, representing a circle; gray value 255= white, representing other areas.
S3: and (3) performing optic disc labeling on the segmented infrared fundus image and the segmented registration image respectively:
specifically, the method for performing optic disc labeling on the segmented infrared fundus image and the segmented registration image respectively comprises the following steps: an ophthalmic clinician artificially positions the center of the optic disc and the diameter DD of the optic disc according to clinical experience, and obtains a circular ring consisting of circles with diameters of 2DD and 3DD by taking the center of the optic disc as the center of a circle and the diameter DD of the optic disc as the reference.
S4: overlapping the marked infrared fundus image and the marked registration image to obtain an intra-annular blood vessel segment, as shown in fig. 6:
specifically, the infrared fundus image after the addition of the ring is overlapped with the registration image, the blood vessel section in the ring is reserved, and other blood vessel sections are deleted.
S5: measuring the thickness of the blood vessel wall of the blood vessel section, and obtaining the thickness of the retina blood vessel wall based on the thickness of the blood vessel wall of the blood vessel section:
specifically, the method for measuring the thickness of the vessel wall of the blood vessel section comprises the following steps: manually selecting a certain large blood vessel section (preset) in the ring by using a mouse, counting the total number of pixel points COUNT0 of the blood vessel wall of the blood vessel section, and calculating the thickness P of the retinal blood vessel wall according to the total number of pixel points COUNT0 and the diameter DD of the optic disc.
The specific process is as follows: manually selecting a certain point (preset) of a large blood vessel section in the ring by using a mouse as a probe mark point, taking the probe mark point as a center, and not repeatedly diffusing the probe mark point to pixel points with adjacent gray values of 0 (black) or 128 (gray), wherein the pixel points with the gray value of 0 are accumulated in the diffusion process (marked as COUNT 0) until no new non-repeated pixel points can be diffused. At this time, the value of the COUNT value COUNT0 is the total number of the pixel points of the blood vessel wall of the manually selected blood vessel section in the circular ring, the blood vessel wall thickness P of the blood vessel in the retina is calculated according to the total number of the pixel points COUNT0 and the diameter DD of the optic disc, and the calculation formula is as follows: p = COUNT0/0.5 DD.
Furthermore, the same large blood vessel section in the ring of the OCT infrared fundus image and the OCT registration image can be manually selected, a plurality of blood vessels in the positioning ring can be sequentially measured, and calculation can be repeated. In addition, the retinal vessel wall thickness is calculated according to the total number of the pixel points and the diameter DD of the optic disc, the efficiency is high, and the accuracy is high.
Example two:
the present application provides a system for measuring retinal vessel wall thickness, comprising,
the device comprises an acquisition module, a segmentation module, a labeling module, an overlapping module and a measurement module;
the acquisition module is used for acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography;
the segmentation module is used for respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image;
the labeling module is used for respectively labeling the optic disc of the segmented infrared fundus image and the segmented registration image;
the overlapping module is used for overlapping the marked infrared fundus image and the marked registration image to obtain a blood vessel section in the ring;
the measuring module is used for measuring the thickness of the blood vessel wall of the blood vessel section, and the thickness of the retina blood vessel wall is obtained based on the thickness of the blood vessel wall of the blood vessel section.
According to the method, one OCT infrared fundus image and one corresponding OCT registration image which are simultaneously acquired by the same eyeball are input, so that the defects of invasiveness, damage, asynchronism and non-synchronization in the prior art are overcome, and the method for measuring the thickness of the retinal vessel wall with high accuracy and high speed is provided; in addition, the thickness of a single blood vessel wall of the eye ground is calculated after the optic disc is marked, the accuracy of a measurement result of the thickness of the blood vessel wall is improved, a doctor can judge the diameter of a retina blood vessel, and the time of the doctor is saved.
The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims of the present application.
Claims (8)
1. A method of measuring retinal vessel wall thickness, comprising:
acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography;
respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image;
respectively carrying out optic disc labeling on the segmented infrared fundus image and the segmented registration image;
overlapping the marked infrared fundus image and the marked registration image to obtain a blood vessel section in the ring;
and measuring the thickness of the blood vessel wall of the blood vessel section, and obtaining the thickness of the retinal blood vessel wall based on the thickness of the blood vessel wall of the blood vessel section.
2. The method of measuring retinal vessel wall thickness of claim 1, wherein the method of obtaining the registration image is: and acquiring an optical coherence tomography blood vessel image, and covering the shallow optical coherence tomography blood vessel image on the infrared fundus image through blood vessel alignment to obtain a registration image.
3. The method of measuring retinal vessel wall thickness of claim 1 wherein the infrared fundus image and the registration image are both from the same eye of the same person and are acquired at the same eye location at the same time; the infrared fundus image and the registration image are consistent in width and height.
4. The method of measuring retinal vessel wall thickness according to claim 1, wherein the method of performing vessel segmentation on the infrared fundus image and the registration image, respectively, is:
and respectively carrying out vessel segmentation on the infrared fundus image and the registration image by adopting a Residual U-Net model and a mixed loss function consisting of cross entropy and DICE.
5. The method of measuring retinal vessel wall thickness of claim 4, wherein the method of performing optic disc labeling on the segmented infrared fundus image and the segmented registration image respectively is: and acquiring the center of the optic disc and the diameter DD of the optic disc, and acquiring a circular ring formed by circles with diameters of 2DD and 3DD by taking the center of the optic disc as the center of a circle and the diameter DD of the optic disc as the reference.
6. The method of measuring retinal vessel wall thickness of claim 5, wherein the method of measuring vessel wall thickness of the vessel segment is:
and obtaining a preset blood vessel section in the ring, counting the total number COUNT0 of the pixel points of the blood vessel wall of the blood vessel section, and calculating the thickness P of the retinal blood vessel wall according to the total number COUNT0 of the pixel points and the diameter DD of the optic disc.
7. The method of claim 6, wherein the vessel wall thickness of the vessel segment is measured by the formula:
P=COUNT0/0.5DD。
8. a system for measuring retinal vessel wall thickness, comprising:
the device comprises an acquisition module, a segmentation module, a labeling module, an overlapping module and a measurement module;
the acquisition module is used for acquiring an infrared fundus image and a corresponding registration image based on optical coherence tomography;
the segmentation module is used for respectively carrying out blood vessel segmentation on the infrared fundus image and the registration image;
the labeling module is used for respectively labeling the segmented infrared fundus image and the segmented registration image;
the overlapping module is used for overlapping the marked infrared fundus image and the marked registration image to obtain an annular blood vessel section;
the measuring module is used for measuring the thickness of the blood vessel wall of the blood vessel section, and the thickness of the retina blood vessel wall is obtained based on the thickness of the blood vessel wall of the blood vessel section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210249162.3A CN114305321A (en) | 2022-03-15 | 2022-03-15 | Method and system for measuring thickness of retinal vessel wall |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210249162.3A CN114305321A (en) | 2022-03-15 | 2022-03-15 | Method and system for measuring thickness of retinal vessel wall |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114305321A true CN114305321A (en) | 2022-04-12 |
Family
ID=81033417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210249162.3A Pending CN114305321A (en) | 2022-03-15 | 2022-03-15 | Method and system for measuring thickness of retinal vessel wall |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114305321A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114985283A (en) * | 2022-04-27 | 2022-09-02 | 韩山师范学院 | Tea leaf identification method based on multi-feature image identification technology |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103584868A (en) * | 2013-07-26 | 2014-02-19 | 童毓华 | Method for measuring retinal blood vessel diameter and thickness of vessel wall |
| EP3263018A1 (en) * | 2016-06-29 | 2018-01-03 | Koninklijke Philips N.V. | Devices and methods for stratification of patients for renal denervation based on intravascular pressure and wall thickness measurements |
| JP2018079208A (en) * | 2016-11-18 | 2018-05-24 | キヤノン株式会社 | Image processing device, image processing method, and program |
| CN108961334A (en) * | 2018-06-26 | 2018-12-07 | 电子科技大学 | A kind of retinal blood pipe thickness measurement method based on image registration |
| CN109448042A (en) * | 2018-10-17 | 2019-03-08 | 北京师范大学 | A method of vessel wall thickness is calculated using integral curve |
| WO2020122672A1 (en) * | 2018-12-13 | 2020-06-18 | 서울대학교병원 | Apparatus and method for automatically segmenting blood vessels by matching fp image and fag image |
| CN111493853A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Blood vessel parameter evaluation method and system for angiodermic diseases |
| CN113256646A (en) * | 2021-04-13 | 2021-08-13 | 浙江工业大学 | Cerebrovascular image segmentation method based on semi-supervised learning |
| CN113781381A (en) * | 2020-06-05 | 2021-12-10 | 中山大学中山眼科中心 | System for identifying chronic kidney disease image |
-
2022
- 2022-03-15 CN CN202210249162.3A patent/CN114305321A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103584868A (en) * | 2013-07-26 | 2014-02-19 | 童毓华 | Method for measuring retinal blood vessel diameter and thickness of vessel wall |
| EP3263018A1 (en) * | 2016-06-29 | 2018-01-03 | Koninklijke Philips N.V. | Devices and methods for stratification of patients for renal denervation based on intravascular pressure and wall thickness measurements |
| JP2018079208A (en) * | 2016-11-18 | 2018-05-24 | キヤノン株式会社 | Image processing device, image processing method, and program |
| CN108961334A (en) * | 2018-06-26 | 2018-12-07 | 电子科技大学 | A kind of retinal blood pipe thickness measurement method based on image registration |
| CN109448042A (en) * | 2018-10-17 | 2019-03-08 | 北京师范大学 | A method of vessel wall thickness is calculated using integral curve |
| WO2020122672A1 (en) * | 2018-12-13 | 2020-06-18 | 서울대학교병원 | Apparatus and method for automatically segmenting blood vessels by matching fp image and fag image |
| CN111493853A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Blood vessel parameter evaluation method and system for angiodermic diseases |
| CN113781381A (en) * | 2020-06-05 | 2021-12-10 | 中山大学中山眼科中心 | System for identifying chronic kidney disease image |
| CN113256646A (en) * | 2021-04-13 | 2021-08-13 | 浙江工业大学 | Cerebrovascular image segmentation method based on semi-supervised learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114985283A (en) * | 2022-04-27 | 2022-09-02 | 韩山师范学院 | Tea leaf identification method based on multi-feature image identification technology |
| CN114985283B (en) * | 2022-04-27 | 2024-03-29 | 韩山师范学院 | Tea leaf identification method based on multi-feature image identification technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Thompson et al. | A deep learning algorithm to quantify neuroretinal rim loss from optic disc photographs | |
| Trucco et al. | Validating retinal fundus image analysis algorithms: issues and a proposal | |
| Abràmoff et al. | Retinal imaging and image analysis | |
| Adam et al. | Quality and diagnostic utility of mydriatic smartphone photography: the smartphone ophthalmoscopy reliability trial | |
| Giancardo et al. | Textureless macula swelling detection with multiple retinal fundus images | |
| Sharma et al. | Comparison of automated analysis of Cirrus HD OCT spectral-domain optical coherence tomography with stereo photographs of the optic disc | |
| CN109784337A (en) | A kind of macular area recognition methods, device and computer readable storage medium | |
| US7147329B2 (en) | Method for judging changes in images of the eye or its component parts | |
| Chiba et al. | Association between optic nerve blood flow and objective examinations in glaucoma patients with generalized enlargement disc type | |
| EP2772185A1 (en) | Image processing apparatus and image processing method | |
| Wu et al. | Multivendor spectral-domain optical coherence tomography dataset, observer annotation performance evaluation, and standardized evaluation framework for intraretinal cystoid fluid segmentation | |
| US20210259546A1 (en) | Portable system for identifying potential cases of diabetic macular oedema using image processing and artificial intelligence | |
| Suero et al. | Locating the Optic Disc in Retinal Images Using Morphological Techniques. | |
| Abràmoff | Image processing | |
| CN111402184B (en) | Method and system for realizing remote fundus screening and health service | |
| CN114305321A (en) | Method and system for measuring thickness of retinal vessel wall | |
| CN111436905A (en) | Optical coherence tomography angiography method and device | |
| Spaide et al. | Using deep learning to automate Goldmann applanation tonometry readings | |
| Wu et al. | Retinal blood vessel width measured on color fundus photographs by image analysis | |
| CN113920077A (en) | Method for training fundus image segmentation model and arteriovenous segmentation method | |
| JP2006263127A (en) | Ocular fundus diagnostic imaging support system and ocular fundus diagnostic imaging support program | |
| WO2021117043A1 (en) | Automatic stenosis detection | |
| Hidalgo-Aguirre et al. | Automatic segmentation of the optic nerve head for deformation measurements in video rate optical coherence tomography | |
| Liu et al. | A curriculum learning-based fully automated system for quantification of the choroidal structure in highly myopic patients | |
| Miyagawa et al. | Automated measurements of human cone photoreceptor density in healthy and degenerative retina by region-based segmentation |
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 |