GB2591919A - Method and system for analyzing hypertensive retinal blood vessel change feature data - Google Patents
Method and system for analyzing hypertensive retinal blood vessel change feature data Download PDFInfo
- Publication number
- GB2591919A GB2591919A GB2104436.7A GB202104436A GB2591919A GB 2591919 A GB2591919 A GB 2591919A GB 202104436 A GB202104436 A GB 202104436A GB 2591919 A GB2591919 A GB 2591919A
- Authority
- GB
- United Kingdom
- Prior art keywords
- fundus image
- characteristic data
- fundus
- analyzing
- retinal vascular
- 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.)
- Withdrawn
Links
- 230000008859 change Effects 0.000 title claims abstract description 152
- 206010020772 Hypertension Diseases 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000001631 hypertensive effect Effects 0.000 title claims abstract description 22
- 210000001210 retinal vessel Anatomy 0.000 title abstract description 9
- 230000036541 health Effects 0.000 claims abstract description 48
- 230000036772 blood pressure Effects 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract description 37
- 210000001927 retinal artery Anatomy 0.000 claims abstract description 22
- 238000010191 image analysis Methods 0.000 claims abstract description 21
- 230000002792 vascular Effects 0.000 claims description 120
- 230000002207 retinal effect Effects 0.000 claims description 117
- 210000003733 optic disk Anatomy 0.000 claims description 90
- 210000004204 blood vessel Anatomy 0.000 claims description 79
- 230000000694 effects Effects 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000005259 measurement Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 16
- 230000005856 abnormality Effects 0.000 claims description 15
- 230000000877 morphologic effect Effects 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000000691 measurement method Methods 0.000 claims description 8
- 238000002560 therapeutic procedure Methods 0.000 abstract description 17
- 230000002265 prevention Effects 0.000 abstract description 9
- 230000001225 therapeutic effect Effects 0.000 abstract description 8
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000007246 mechanism Effects 0.000 abstract description 2
- 208000017667 Chronic Disease Diseases 0.000 abstract 1
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000005284 excitation Effects 0.000 abstract 1
- 206010025421 Macule Diseases 0.000 description 57
- 206010012601 diabetes mellitus Diseases 0.000 description 14
- 238000007405 data analysis Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 5
- 208000024172 Cardiovascular disease Diseases 0.000 description 4
- 208000017442 Retinal disease Diseases 0.000 description 4
- 206010038923 Retinopathy Diseases 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 206010002329 Aneurysm Diseases 0.000 description 3
- 229920000742 Cotton Polymers 0.000 description 3
- 206010012689 Diabetic retinopathy Diseases 0.000 description 3
- 208000009857 Microaneurysm Diseases 0.000 description 3
- 208000037111 Retinal Hemorrhage Diseases 0.000 description 3
- 210000001367 artery Anatomy 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 230000003143 atherosclerotic effect Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000004936 stimulating effect Effects 0.000 description 2
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- 206010063547 Diabetic macroangiopathy Diseases 0.000 description 1
- 208000031662 Noncommunicable disease Diseases 0.000 description 1
- 206010038926 Retinopathy hypertensive Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 238000002651 drug therapy Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 201000001948 hypertensive retinopathy Diseases 0.000 description 1
- 230000001976 improved effect Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013160 medical therapy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008816 organ damage Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000006496 vascular abnormality Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02007—Evaluating blood vessel condition, e.g. elasticity, compliance
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4887—Locating particular structures in or on the body
- A61B5/489—Blood vessels
-
- 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
-
- 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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Ophthalmology & Optometry (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Vascular Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The present invention relates to the fields of image analysis, health care service and data processing technologies, and provides a method for analyzing hypertensive retinal blood vessel change feature data. The method comprises: acquiring an eye fundus image of a patient, extracting and identifying feature data of retinal blood vessel changes from the eye fundus image, the retinal blood vessel change feature comprising: limiting retinal artery narrowing; analyzing and comparing retinal blood vessel change feature data in different time periods of the patient; and further acquiring the change situation of the eye fundus screening feature data of the patient, and analyzing situations of blood pressure control and related prevention and therapeutic effects of hypertension of the patient in the recent period. The present invention provides a powerful excitation mechanism for enhancing the compliance of the patient to intervene with an underlying therapy by means of lifestyle, facilitating a user to perform blood pressure detection periodically and controlling blood pressure consciously, having great significance in evaluating the therapeutic effect of hypertension and managing chronic diseases.
Description
Method and System for Analyzing Hypertensive Retinal Vascular Change Characteristic Data
Technical Field
The invention relates to the technical field of image analysis, health service, and data processing, in particular to a method and a system for analyzing hypertensive retinal vascular change characteristic data.
Background Art
According to the latest results of China's hypertension sampling survey, there are about 250 million hypertension patients in our country with a rising prevalence rate. The prevalence rate increases with age and hypertension is further a concomitant disease of many diabetic patients. 1 in 3 adults has hypertension. Although the awareness and control rate of hypertension have been improved over the years, compared with the data from 2002 to 2015, the awareness rate has risen from 30.2% to 42.7%, the therapy rate has risen from 24.6% to 38.3%, but the control rate is still less than 14 5% Research conducted by Goto et al., as early as 1975, demonstrated that the fundus circulation and intracranial vessels share common embryological anatomy and physiological basis. Retinal vessels can be directly observed by a non-invasive method, and objective conditions are provided for observing specific manifestations of systemic vascular abnormalities; in recent years, a number of population-based epidemiological studies have shown that the evaluation of retinal abnormal characteristic data, including local retinal anew constriction (FN), retinal arteriovenous crossing compression (AVM and retinopathy, can provide good observation indicators for the early onset and progression of hypertension. Hypertension is strongly associated with the incidence rate and longitudinal change of retinal microvasculai-abnormalities, especially local retinal artery constriction (FN), in the non-diabetic population. The Guidelines for the Classification and Prevention of Atherosclerotic Cerebro-cardiovascular Disease in Chinese Adults with Type 2 Diabetes published in 2016 further points out the importance of blood pressure monitoring: diabetes is one of the uppermost chronic non-infectious diseases and one of the independent risk factors of atherosclerotic cerebro-cardiovascular disease (ASCCVD). Evidence suggests that stroke is the main outcome and the main cause of death and disability in Chinese adult diabetic patients. In order to effectively prevent ASCCVD of adult diabetic patients in China, the guideline explicitly recommends that: patients with blood pressure>120/80imung change their lifestyle to control their blood pressure; the diabetic patients should have their blood pressure measured at every follow-up; lo improve blood pressure management, self-blood-pressure monitoring is recommended.
The guideline further points out that: in newly diagnosed diabetic patients, the use of intensive blood pressure control can not only significantly reduce the risk of diabetic macroangiopathy, but further significantly reduce the risk of microvascular disease in that keeping the blood pressure stable for a long time is essential; diabetic patients with blood pressure>120/80 mmHg further need to change their lifestyle and begin intensive blood pressure control from the day of a new diagnosis.
Severe hypertension target organ damage can cause disability and even endanger life. Hypertension and its related cerebro-cardiovascular disease are the most important diseases causing death. It is of great saliency for early diagnosis, evaluation and therapeutic intervention of hy pertension.
According to the principle of hypertension therapy in National Guidelines 16r the Basie-level Hypertension Prevention and Management (2017 Edition), the main purpose of hypertension therapy is to reduce the incidence and the risk of death of cerebro-cardiovascular complications, so the first step is to reduce blood pressure to reach the standard. At the same time, it is necessary to inform patients that they should initiate and adhere to lifestyle intervention and drug therapy for a long time, and it is essential to maintain long-term stability of the blood pressure.
However, since the most important or necessary lifestyle intervention basic therapy such as diet, exercise and the like lacks incentive means or methods so far, patients' compliance is low, and lifestyle intervention basic therapy is difficult to achieve the effect. Generally, before their blood pressure is greater than 120/80mmElg or less than 140/90mmElg, or even serious complications occur, early hypertension patients and a large number of patients with type 2 diabetes have no feeling. It is difficult for them to consciously do regular self-blood-pressure monitoring or measure ment.
Summary of the Invention
Therefore, there is a need to provide a method for analyzing hypertensive retinal vascular change characteristic data to solve the above-mentioned technical problems. The specific technical scheme is as follows.
A method for analyzing hypertensive retinal vascular change characteristic data, characterized by comprising the following steps: acquiring and storing a fundus image of a hypertension patient;extracting and identifying structural parameter and retinal vascular change characteristic data of the fundus image: and storing the structural parameter and retinal vascular change characteristic data of the fundus image;wherein the retinal vascular change characteristic data comprises: local retinal artery constriction; judging whether retinal vascular change characteristic data of an early stage of a patient is stored or not, if yes, analyzing and comparing die retinal vascular change characteristic data of different stages of the patient, and acquiring change condition of fluidus screening characteristic data this time of the patient: and analyzing and processing the change condition of the fundus screening characteristic data.
Further,the "analyzing and comparing the retinal vascular change characteristic data of different stages of the patient, and acquiring change condition of fundus screening characteristic data this time of the patient" further comprises steps of: preprocessing the fundus image, wherein the preprocessing comprises: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale; establishing a morphological filter to determine a macular fovea and an optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image; aligning a fundus image according to the fundus structural panimeter, and correcting an identification of the retinal vascular change characteristic data, wherein the fundus structural parameters comprise: macular fovea, optic disk and main blood vessel information; and automatically analyzing a change of the retinal abnormality characteristic data.
Further,the "analyzing and processing change condition of the fundus screening characteristic data" further comprises steps of: analyzing and calculating to obtain blood pressure control effect and body health condition of hypertension patient within a preset time period; giving corresponding health service suggestion according to an analysis result; and generating a report of the blood pressure control effect, the physical health condition, and the health service suggestion, and sending related information of the report to related personnel. Furtherthe "segmenting a retinal vascular network of the preprocessed fundus image" further comprises steps of: segmenting a fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carrying out arteriovenous segmentation according to the segmented fundus vascular network.
Further,the "identifying structural parameter and retinal vascular change characteristic data of the fundus image" further comprises steps of extracting a center of the optic disk in the preprocessed fluidus image, and determining a size of the optic disk; determining a measurement area by positioning the optic disk; and obtaining the retinal vascular change characteristic data within the measurement area or within the measurement area by an automated or a semi-automated interactive blood vessel diameter measurement method.
In order to solve the above problem.
A system for analyzing hypertensive retinal vascular change characteristic data, characterized by comprising a fundus image acquisition terminal and a fundus image processing terminal; wherein the fimdus image processing terminal comprises: a data storage module, a fundus image analysis and comparison module, and a result analysis module; the fundus image acquisition terminal is connected with the fundus image processing terminal; the fundus image acquisition terminal is used for: acquiring a fundus image of a patient, and sending the fundus image to the fundus image processing terminal; the data storage module is used for: storing the fundus image; the fundus image analysis and comparison module is used for: extracting and identifying structural parameter and retinal vascular change characteristic data of the fundus image: judging whether the retinal vascular change characteristic data of an early stage of the patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring change condition of fundus screening characteristic data this time of the patient; the data storage module is used for: storing the structural parameter and retinal vascular change characteristic data of the fundus image; and the result analysis module is used for: analyzing and processing the change condition of the fundus screening characteristic data.
Further,the fundus image analysis and comparison module is further used for: preprocessing the fundus image, wherein the preprocessing comprises: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale; establishing a morphological filter to determine a macular fovea and an optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image; aligning a fundus iniage according to the fundus structural parameter, and correcting an identification of the retinal vascular change characteristic data, wherein the fundus structural parameters comprise: macular fovea, optic disk and main blood vessel information; and automatically analyzing a change of the retinal abnormality characteristic data.
Further,the result analysis module is further used for: analyzing and calculating to obtain blood pressure control effect and body health condition of hypertension patient within a preset time period; giving corresponding health service suggestion according to an analysis result; and generating a report of the blood pressure control effect, the physical health condition and the health service suggestion, and sending related information of the report to related personnel. Further,the fundus image analysis and comparison module is further used for: segmenting a fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carrying out arteriovenous segmentation according to the segmented fundus vascular network.
Further,the fundus image analysis and comparison module is further used for: extracting a center of the optic disk in the preprocessed fundus image, and determining a size of the optic disk: determining a measurement area by positioning the optic disk; and obtaining the retinal vascular change characteristic data within the measurement area or within the measurement area by an automated or a semi-automated interactive blood vessel diameter measurement method.
The invention has the beneficial effects of: acquiring a fundus image of a hypertension patient to be analyzed after fundus photography screening to identify the retinal vascular change characteristic data of the fundus image, wherein the retinal vascular change characteristics comprise: local retinal artery constriction, analyzing and comparing the retinal vascular change characteristic data of different stages of the patient, and acquiring the change condition of the fundus screening characteristic data this time of the patient, and further analyzing and calculating to obtain the blood pressure control effect and body health condition of hypertension patient within a preset time period, Which allows the analysis result to be sent to the patient user himself/herself to provide an incentive mechanism for lifestyle intervention so that the user can know the blood pressure control or therapy condition of the patient in recent time and experience an impressive education, the compliance of the lifestyle intervention of the patient is enhanced, or corresponding health service suggestion are given by a health service professional or a family doctor of the patient, thereby customizing personalized service for the patient user. The overall method realizes the goal of acquiring a fundus image, obtaining the key parameter of the change data of the local retinal artery constriction, and analyzing the key parameter whose analysis result can be applied to various occasions, so that a user can be greatly helped to better control hypertension, primary medical therapy or health management is assisted, a health service institution can track and know the diagnosis and therapeutic effects of hypertension, providing great welfare for staff and patients in related health medical fields.
Brief Description of the Drawings
Fig. 1 is a flowchart of a method for data analysis on the quantitative characteristic of the vascular change in a hypertensive fundus image according to a preferred embodiment; Fig. 2 is a schematic view of a vascular structure of a fundus according to a preferred embodiment; Fig. 3 is a view for sequence acquisition of a preferred embodiment; Fig. 4 is a view for searching a boundary point according to a preferred embodiment: Fig. 5 is a view of a measured pipe diameter according to a preferred embodiment; Fig. 6 is a schematic view of a module of a system for analyzing hypertensive retinal vascular change characteristic data according to a preferred embodiment.
Detailed Description of the Invention
In order to explain the tecluncal content, structural characteristic, achieved object, and effects of the technical schemes in detail, the detailed description will be given below in conjunction with specific examples and accompanying drawings Referring to Fig. 1, in the present embodiment, an analysis method for a diabetic retinopathy fundus characteristic data change may be applied to a computing device or a related storage device, which includes, but not limited to: personal computer, server, general purpose computer, computer workstation, network device, cloud computing or cloud storage, intelligent mobile terminal, and the like. In the embodiment, taking a general purpose computer as an example, the general purpose computer is provided with a fundus screening characteristic data change analysis system, or a general purpose computer or an image analysis workstation of a remote fundus image data analysis center, or a browser through which a web page can be opened such that a related cloud health service system or fundus image data analysis center can be logged. In the embodiment, a preferred embodiment of a method for data analysis on the hypertensive retinal vascular change characteristic is as follows.
Step S101: a fundus image of a hypertension patient is acquired and stored. Die following mode can be adopted: the fundus image of a patient with hypertension is acquired through regular fundus photographic screening by fundus camera in a primary application institution (such as primary medical institution, health checkup, health management, or primary community clinic). The acquired fundus image is transferred to a PC through a USB cable and processed by fundus image data analysis workstation software, or transferred to a PC through a network and sent to an fundus image data analysis center through the PC; the patient may further upload a fundus image via a mobile terminal device. It should be noted that in the present embodiment, the primary application institute may be in remote areas without professional ophthalmologist personnel, or places equipped with professional ophthalmologist personnel with very high cost. If the acquired fundus image is sent to a fundus image data analysis center, the fundus image of the hypertension patient is acquired and stored at the same time.
After the fundus image of the hypertension patient is acquired by the fundus image data analysis center or the fundus image data analysis workstation software, step S102 is executed: extracting and identifying the structural parameter and retinal vascular change characteristic data of the fundus image.
Before the step, a step of preprocessing die fundus image is further comprised. The pretherapy comprises the following steps: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale. They are specifically as follows.
Green channel selection, median filtering finite contrast enhancement and normalization processing of gray scale are carried out on the fundus image to be checked. By preprocessing the fundus image, redundant background in the fundus image can be removed and noise is effectively removed such that the subsequent fundus image analysis is facilitated. Specifically: in any color fundus image, the blue channel has plenty of noise and useful information therein is substantially lost, the red channel has two prominent spots and plenty of information of dark blood vessels, micro henumgiomas, and the like is lost therein, so that the color fundus image to be checked is subjected to green channel selection in the embodiment, and the fundus blood vessel is reserved and highlighted to the greatest extent.
In order to remove the noise and well preserve the boundary information, in the embodiment, median filtering is carried out on the fundus image under the green channel so as to remove noise; in order to obtain a better blood vessel extraction effect, contrast enhancement is carried out on the demised image. In order to avoid an over-bright situation after image enhancement, a limited contrast enhancement method CLARE is adopted in the embodiment. And finally, normalization processing is carried out so as to enable pixel values of all pixel points in one image to fall between 0-1.
The preprocessed fundus image is uniform hi brightness, good M. vascular contrast, and favorable for the subsequent fundus image analysis, greatly improving the accuracy of the fundus image analysis. After preprocessing the fundus image, retinal vascular change characteristic data of the preprocessed fundus image, local retinal artery constriction characteristic data, is extracted and identified, A number of population-based epidemiologic studies have shown that the evaluation of retinal vasculopathy or abnormality, including local retinal artery constriction (FN.) and retinopathy (including retinal hemorrhage, micro-aneurysms, hard exudation, cotton wool spot) can provide good observation indicator for the study related to the incidence and progression of hypertension. Satisfactory blood pressure control can reduce the extent of FN in patients, and the regression rate of the local retinal artery constriction can reflect the situation of blood pressure control. Hypertension is strongly associated with the incidence and longitudinal change of retinal microvascular abnormality in the non-diabetic population. The better the control of hypertension, the lower die incidence of retinal microvascular abnormality and the higher the rate of FN improvement, suggesting that FN is reversible as an early manifestation of retinal microvascular abnormality if hypertension is controlled.
Extracting the local retinal artery constriction characteristic data can be carried out by: extracting the center of the optic disk of the preprocessed fundus image, and determining the size of the optic disk; determining a measurement area through a positioning optic disk; obtaining the retinal vascular change characteristic within the measurement area by automated or semi-automated interactive vascular diameter measurement method.
See fig.2 for details as follows: fundus vascular change characteristic extraction is based on evidence-based medicine to determine retinal vascular change characteristic data related to the effect of hypertension therapy, namely FN.
FN is checked in the optic disk region (region within the central circle of Fig. 2), region A (which may be closer to the artery in vascular nature), and regions outside region A (which is arteriolar in vascular nature), respectively. FN means that the vessel diameter is less than 501mi (or about 1/3 of the diameter of the main vein at the edge of the optic disk) and the pipe diameter of the constricted portion is less than 2/3 of the pipe diameter of the proximal end and distal end of the artery. In the optic disk region and region A, the severity of local arterial constriction is determined by the number of affected macrovascular. If there are multiple local constrictions in one quadrant, the lengths of all constrictions are summed. If FN extends from one quadrant to another, the affected length is evaluated separately in each quadrant. When the total length of the constricted portion <1 /2PD, it is mild; >1/2PD and <2PD, it is moderate; >2PD, it is severe. (PD is the diameter of an optic disk) An interactive method for measuring the diameter of a blood vessel in a certain section is described as folio w s Step 1: firstly, four points are collected on two sides of a blood vessel, wherein the collection sequence adopts N-shaped sequence collection, namely the two points on two sides of the blood vessel are in consistent sequence (relative to the U-shaped sequence, the collection sequences on two sides are reverse). Automatically calculating points at 1/3 and 2/3 positions between the points respectively according to the two points on two sides of the blood vessel, the two sides are expanded into 8 points together; The reason for manually clicking only four points instead of eight points is to prevent that it may not be possible to satisfy the requirement that the midpeipendicular must pass between the opposite two points. As shown in Fig. 3, the eight points A' to H' are sequentially selected in a certain order on both sides of the blood vessel. The selection order determines the subsequent selection of the corresponding point on the other side of the blood vessel. As in the order of Fig. 3,A corresponds to E'.
Step 2: a boundary is searched by using the eight points, two points on the same horizontal line on two sides of the blood vessel are connected, the two points are respectively moved along the connecting direction to the boundary direction of the blood vessel and the pixel value of each passing pixel point is calculated, and when the pixel value is not zero, it is considered that the boundarv pixel point is reached. The eight extravascular points are changed to eight points on the boundary of the blood vessel by the step. As in fig.4. A' is moved to A, E' is moved to E, and so on.
Step 3: finally, the distance from the midpoint between the immediately adjacent two points to the point of intersection of the midperpendicular of the midpoint and the opposite two corresponding line segments is calculated as one calculation. As shown in Fig. 5, taking line segment AB and the midpoint X of line segment AB, a vertical line of AB is drawn by passing X, and the vertical line intersects line segment EF at point X' (note that it is not the midpoint). The length of XX' is one pipe diameter length. As such, in the figure with eight points, there are in total six pipe diameter lengths like XX', the average value is taken and a certain correction value is added, and the final measured value is obtained and stored.
By local retinal artery constriction is meant that the blood vessel diameter is less than 50ton (or about 1/3 of the diameter of the main vein at the edge of the optic disk) and the pipe diameter of the constricted portion is less than 2/3 of the pipe diameter of the proximal end and distal end of the artety. Therefore, to determine FN, it is necessary to measure the pipe diameter of the constricted portion and the proximal end and distal end of the artery using an automated or a semi-automated interactive blood vessel diameter measurement method.
The "identifying the retinal vascular change characteristic data" further comprises the following steps of: identifying the local retinal artery constriction characteristic data and the affected position of a macrovascular, the range of the affected position of the macrovascular and the length of the blood vessel, and the relative position of the affected position of the nmcrovascular and the center of the optic disk The extracting the optic disk center of the preprocessed fundus image further comprises the following steps of: selecting a fundns image with a clear image showing clearly the optic disk, the macula, and the blood vessel from the images to be analyzed as a standard reference image, and processing the standard image to generate a standard gray scale histogram; and mapping the gray scale of the rest fundus images to be analyzed according to the gray scale distribution of the standard gray scale histogram to obtain a fundus image with the same gray scale distribution as that of the standard reference image.
Further steps are carded out: establishing a morphological filter according to the brightness of the macula and the optic disk, the shape of the macula and the optic disk and the position distance between the macula and the optic disk in the preprocessed fundus image, and determining the positions of the macula and the optic disk. That is: in the preprocessed fundus image, the macula has extremely low brightness, the optic disk has extremely high brightness, the shapes of the macula and the optic disk tend to be circular, and the relative distance and position of the macula and the optic disk are fixed, so that a morphological filter is realized. A circular or elliptical area with extremely high brightness in the fundus image is checked, the circular or elliptical area is considered as a candidate area of the optic disk, and wrong candidate areas are filtered according to the distance and position of the macula and the optic disk, thereby determining the center position of the optic disk.
After structural parameter and retinal vascular change characteristic data of the fundus image are extracted, step S103 is executed: storing the structural parameter and retinal vascular change characteristic data of the fundus image, the retinal vascular change characteristic data comprising local retinal artery constriction. After storing, step 5104 is executed: judging whether retinal vascular change characteristic data of the early stage of the patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring the change condition of the fundus screening characteristic data this time of the patient. The following mode can be adopted: The "analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring the change condition of the fundus screening characteristic data this time of the patient" further comprises the steps of: preprocessing the fundus image, wherein the preprocessing comprises the following steps: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale; establishing a morphological filter to determine the macular fovea and the optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image; aligning a fundus image according to the fundus structural parameter, and correcting the identification of the retinal vascular change characteristic data, wherein the fimdus stmctural parameters comprise: macular fovea, optic disk, and main blood vessel information (the MMus structure parameters are the above-mentioned structural parameters of the fundus image); and automatically analyzing the change of the retinal abnormality characteristic data.
In die present embodiment, the fundus image can be aligned and a change area of the retinal vessel change characteristic data in the fundus image can be identified according to the position of the macula, the position of the optic disk, and the information of the main blood vessel. By the change area, the change condition of the range of the affected position of the macrovascular, the length of the blood vessel, and the relative position of the affected position of the macrovascular and the center of the optic disk can be rapidly seen.
The position of the macula and main blood vessel information are extracted and specifically the following mode is adopted: selecting a fundus image with a clear image showing clearly the optic disk, the macula and the blood vessel from the images to be analyzed as a standard reference image, and processing the standard image to generate a standard gray scale histogram; and mapping the gray scale of the rest fundus images to be analyzed according to the gray scale distribution of the standard gray scale histogram to obtain a fundus image with the same gray scale distribution as that of the standard reference image.
Further steps are carried out: establishing a morphological filter according to the brightness of the macula, the shape of the macula, and the position distance between the macula and the optic disk in the preprocessed fundus image, and determining the position of the macula. That is: in the preprocessed fundus image, the macula has extremely low brightness, the shapes of the macula and the optic disk tend to be circular, and the relative distance and positions of the macula and the optic disk are fixed, so that a morphological filter is realized. A circular area with extremely low brightness in the fundus image is detected and used as a candidate area of the macula. Wrong candidate areas are filtered out according to the distance and the positions of the macula and the optic disk, and then the central position of the macula is determined.
According to the preprocessed fundus image, the fundus main blood vessels have similar gray scale information and high contrast with the background. The main blood vessel is segmented by using a threshold segmentation method in combination with the extraction method of the retinal vascular network, Fundus images are aligned according to fundus stmcture parameters. Namely, according to the positions of the macula fovea and the optic disk, and the main blood vessel information, fundus images of the same user at different periods are aligned and the fundus image change area is identified. The following mode can be adopted: aligning the macula and the optic disk of different fundus images, and roughly aligning pair MMus images; calculating a correlation coefficient on the main blood vessel information, and finely adjusting the offset position of the fundus image until the correlation coefficient is maximum; the main blood vessel information including main blood vessel b na ri /all on information, Specifically: overlapping two fundus images to be analyzed and compared, mid substantially coinciding the macula and the optic disk according to the detection and positioning results of the optic disk and the macula position; according to the segmented main blood vessel binarization image information, calculating the correlation coefficient thereof, and properly adjusting the relative positions of the two fundus images; when the correlation coefficient is maximum, the two fundus images achieving a certain alignment. Specifically: denoting the binarized blood vessel segmentation image of the eye fimdus image which is basically aligned according to the positions of the optic disc and the macula to be 41 and /v2 respectively, the position offset of the transverse direction and the longitudinal direction to be At and 41 respectively, and finely adjusting AZ and tr and calculating the correlation coefficient VW m0) When the correlation coefficient is maximum, the corresponding °sive%) is the offset position when the two images are aligned.
= ir (St, ) In other embodiments, the definition of change may be modified as required to find other changing circumstances in i he fundus image.
In other embodiments, the range of arterial blood vessel, and the position thereof affected by the local retinal artery constriction in the fundus image may further be identified by drawing a rectangular. Different colors may represent different ranges of the affected arterial blood vessel and the position thereof, such as pink for the affected arterial blood vessel and green for the range of the affected arterial blood vessel positions. Then the fundus images are aligned according to fundus parameters. The fundus parameters include: the position of the macula, the position of the optic disk and main blood vessel information. The fundus image change area or the change area of the retinal vascular change characteristic data is identified with white.
Step 5105: analyzing and processing the change condition of the fundus screening characteristic data, and adopting the following mode: analyzing and comparing the retinal vascular change characteristic data of the patient in different periods, acquiring the change condition of the fundus screening characteristic data of the patient, further analyzing and calculating to obtain the blood pressure control effect and the physical health condition of hypertension patient in a preset time period, and sending the analysis result to the patient user; wherein in one implementation, augmented reality (AR) technology may be used to animate these fundus characteristic changes and their continued development, which may affect vision or general health, into a simple presentation that is superimposed on a real photo of the fundus image to achieve a visual educational effect, allowing the user to understand his or her blood pressure control or therapy for a recent period of dine and experience a profound education and stimulating timely screening of patient lifestyle intervention basic therapy, and the compliance or consciousness of timely prevention and therapy; or providing corresponding health service suggestion through a health service professional or a family doctor of the patient so as to customize personalized service for the patient User Guidelines for the prevention and therapy of hypertension and diabetes in China suggest that patients with hypertension and diabetes should be subjected to fundus photography screening regularly or at least once every year or half a year, or even three months. As one application or implementation, the invention can extract and identify,' the structural parameter and retinal vascular change characteristic data of the fundus image by utilizing the fundus image obtained after fundus screening wherein the retinal vascular change characteristic comprises: local retinal artery constriction; retinal vascular change characteristic data of the patient in different periods is analyzed and compared; the change condition of the fundus screening characteristic data of the patient is further acquired, related prevention and therapeutic effect condition such as blood pressure control, lifestyle intervention therapeutic effects, and the like of the patient in a recent period is analyzed, and related blood pressure control condition and health condition evaluation data is obtained.
The "analyzing and processing the change condition of the fundus screening characteristic data" further comprises the following steps: analyzing and calculating to obtain the blood pressure control effect and body health condition of hypertension patient within a preset time period; giving corresponding health service suggestion according to the analysis result: and generating a report of the blood pressure control effect, the physical health condition, and the health service suggestion, and sending related information of the report to related personnel. Further, in the embodiment, the "segmenting the retinal vascular network of the preprocessed fundus images" further comprises the following steps: segmenting the fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carrying out arteriovenous segmentation according to the segmented fundus vascular network. The following mode can be adopted as follows: the fundus blood vessel of the fundus image is segmented through a saliency model and an area optimization method to obtain a fundus vascular network, and arteriovenous segmentation is carried out according to the segmented fundus vascular network. It is specifically as follows.
Step 1: color is the most important characteristic in analyzing image saliency. Meanwhile, considering that blood vessels contain texture characteristics, as the texture can reflect visual characteristics in an image, two saliency characteristics of color and texture are used in this algorithm.
The texture characteristic of the fundus image is extracted: texture characteristic is a kind of visual characteristic that does not depend on the homogeneous phenomenon in a reflected image of color or brightness. In this issue, considering that the two-dimensional Gabor filter can capture the local structure corresponding to dimension, spatial position, and direction selectivity. Gabor filter is used to extract texture characteristic. The position of Gabor filter is determined by two parameters of direction and dimension, and the texture characteristic of the image can be expressed substantially by setting the parameter. The Gabor filtering function can be expressed as follows: (1) where the Fourier transform is obtained front (2) 2x, cry where: W is the complex modulated frequency of the Gaussian function. In general, the directions of blood vessels are different, so the Gabor filtering must adopt different directions. Herein six different directions are adopted respectively, i.e. Oo, 30o, 60o, 90o, 120o, 150. After die Gabor filtering images with different directions and dimensions are obtained, the maximum value is adopted to respond to image fusion to obtain one Gabor transform diagram.
Color characteristic extraction of the fundus image: color is the most sensitive in the visual system and is easily noticed if the target is different from the surrounding color. Considering overall and local characteristics, for the color contrast characteristic at each pixel point, the effect on the characteristic is controlled by defining the ratio of the largest rectangular neighborhood of the pixel point to the size of the entire image area. The algorithm is represented as follows: asp(d, A teemiOn$2,4 arfr,01 (3) where U denotes the largest circumscribed rectangular neighborhood of a pixel (x., y), and w and h are the width and height of the image. A is the area of the rectangle U, d is the ratio of A to the entire image area, and d can be adjusted according to the distance between the pixel (x, y) and the center of the image.
After the color characteristic and texture characteristic are extracted, they need to be fused. Considering that two different color spaces selected by us have six color channels in total, the two-dimensional information entropy is used as a standard for measuring the performance of a saliency map, and two groups of optimal color characteristic maps and texture characteristic maps are selected therefrom. For color characteristic fusion, the inverse of information entropy is used as the linear fusion method of the weight coefficient. For the fusion of the texture characteristic, the maximum value fusion method is adopted. Finally, color contrast characteristic and texture characteristic are fused, and information entropy fusion based on two dimension is still adopted. Step 2: since the saliency image is a gray scale image, the gray scale value range is limited. Region optimization is adopted to enhance the contrast in order to highlight the contrast intensity in the saliency image. This makes it possible to make the high saliency value higher and the low saliency value lower in the image. The optimization function is represented as follows: cep't a naval (4) rn-Wpo0) ni® c.5(,g(p) -naval); miival -1 K and 8 are control factors, and when 4°'±- 4 < 120 8 is a logarithmic function and when 1;0 dval < is an exponential function.
Step 3: a region-based one-dimensional histogram threshold method is adopted for threshold segmenting the saliency map. The image used for the statistical histogram is selected according to the relationship between the original image and the neighborhood thereof. The original image for the statistical histogram is represented as follows: where f(m, n) represents the original image, g(m, n) represents its 5*5 neighborhood, and t1=40. Step 4: after threshold segmentation, some fine blood vessels will be lost, which is repaired by morphological method in the algorithm.
After the retinal vascular change characteristic data is stored, judging whether the retinal vascular change characteristic data of the early stage of the patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring the change condition of the fundus screening characteristic data this time of the patient; the following mode can be adopted: inquiring a database according to the name and the identity card of the patient to find whether the fundus image and fimdus image characteristic data of the early stage of the diabetic retinopathy patient is stored, if yes, analyzing and comparing the titans image and fundus image characteristic data of the diabetic retinopathy patient in different periods to obtain the change condition of fundus screening characteristic data.
Further, the quantification parameter of the bitamporal of the optic disk and the macula fovea can be calculated according to the calibrated optic disk and the macula. Since the absolute distance values of the two of a normal person are almost the same, parameters of subsequent quantitative analysis are obtained according to the obtained absolute distance from the bitamporal of the optic disk to the macula fovea and the optic disk diameter, the obtained data is converted from an absolute representation mode to a relative representation mode, and meaningful and comparable data is formed through normalization processing. The fundus images from different sources can form meaningful and comparable structured quantitative analysis indexes such that all fundus images can substantially be compared; at the same time, in one application, other lesions or abnormalities of retinal vessel, including diffuse retinal artery constriction, retinal arteriovenous cross-compression, silver-wire-like change, copper-wire-like change, retinopathy (including retinal hemorrhage, micro-aneurysms, hard exudation, cotton wool spot, defects and degrees of local Helve fiber layer), patient's consultation information and other evaluation of personal information such as height and weight, etc. can provide a better observation index for screening hypertensive retinopathy and the correlation with cardiovascular and cerebrovascular diseases. That lays a foundation for realizing the health big data service.
Referring to Fig. 6, in the present embodiment, a preferred embodiment of a system 600 for data analysis on the hypertensive retinal vascular change characteristic is as follows: A system 600 for data analysis on the hypertensive retinal vascular change characteristic includes: a fundus image acquisition terminal 601 and a fundus image processing terminal 602; wherein, the fundus image processing terminal 602 includes: a data storage module 6021, a fundus image analysis and comparison module 6022, and a result analysis module 6023; the fundus image acquisition terminal 601 is connected with the fundus image processing terminal 602; the fundus image acquisition terminal 601 is used for: acquiring a fundus image of the patient and sending the fundus image to the fundus image processing terminal 602; the data storage module 6021 is used for: storing the fundus image; the fundus image analysis and comparison module 6022 is used for: extracting and identifa,,ing structural parameter and retinal vascular change characteristic data of the fimdus image; judging whether the retinal vascular change characteristic data of the early stage of the patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring the change condition of the fundus screening characteristic data this time of the patient; (he data storage module 6021 is used for: storing the structural parameter and retinal vascular change characteristic data of the fundus image: the result analysis module 6023 is used for: analyzing and processing the change condition of the fundus screening characteristic data.
The following mode can be adopted as follows: the fundus image of a patient with hypertension is acquired through regular fundus photographic screening by a fundus camera in a primary application institution (such as primary medical institution, health checkup, health nmnagement, or primary coimnunity clinic); the acquired fundus image is transferred to a PC through a USB cable and processed by fundus image data analysis workstation software, or transferred to a PC through a network and sent to a fundus image data analysis center through the PC; the patient may further upload a fundus image via a mobile terminal device. It should be noted that in the present embodiment, the primary application institute may be in remote areas without professional ophthalmologist personnel, or places equipped with professional ophthalmologist personnel with very high cost. If the acquired fundus image is sent to a fundus image data analysis center, the fundus image of the hypertension patient is acquired and stored at the same time.
The structural parameter and retinal vascular change characteristic data of the fundus image are extracted and identified.
Before the step, a step of preprocessing (he fundus image is further comprised. The prelherapy comprises the following steps: green channel selection, median filtering, finite contrast enhancement, and nonnalization processing of gray scale. The details are the same as the example of (he above method, and the description is not repeated here.
A number of population-based epidemiologic studies have shown that the evaluation of retinal vasculopathy or abnormality, including local retinal artery constriction (FN) and retinopathy (including retinal hemorrhage, micro-aneurysms, hard exudation, cotton wool spot) can provide good observation indicator for the study related to the incidence and progression of hypertension. Satisfactory blood pressure control can reduce the extent of FN in patients, and the regression rate of the local retinal artery constriction can reflect the situation of blood pressure control. Hypertension is strongly associated with the incidence and longitudinal change of retinal microvascular abnormality in the non-diabetic population. The better the control of hypertension, the lower the incidence of retinal microvascular abnormality and the higher the rate of FN improvement, suggesting that FN is reversible as an early manifestation of retinal microvascular abnormality if hypertension is controlled.
Extracting the local retinal artery constriction characteristic data can be carried out by: extracting the center of the optic disk of the preprocessed fundus image, and determining the size of the optic disk; determining a measurement area through a positioning optic disk; obtaining the retinal vascular change characteristic within the measurement area by automated or semi-automated interactive vascular diameter measurement method.
See fig.2 for details as follows: ftmdus vascular change characteristic extraction is based on evidence-based medicine to determine retinal vascular change characteristic data related to the effect of hypertension therapy, namely FN. The specific description is the same as the above method example, and will not be repeated here.
The "identifying the retinal vascular change characteristic data" further comprises the following steps of: identifying the local retinal artery constriction characteristic data and the affected position of a nutcrovascular, the range of the affected position of the nutcrovascular and the length of the blood vessel, and the relative position of the affected position of the macrovascular and the center of the optic disk The extracting the optic disk center of the preprocessed fundus image further comprises the following steps of: selecting a fundus image with a clear image showing clearly the optic disk, the macula, and the blood vessel from the images to be analyzed as a standard reference image, and processing the standard image to generate a standard gray scale histogram; and mapping the gray scale of the rest fundus images to be analyzed according to the gray scale distribution of the standard gray scale histogram to obtain a fundus image with the same gray scale distribution as that of the standard reference image.
Further steps are carried out: establishing a morphological filter according to the brightness of the macula and the optic disk, the shape of the macula and the optic disk and the position distance between the macula and the optic disk in the preprocessed fundus image, and determining the positions of the macula and the optic disk. That is: in the preprocessed fundus image, the macula has extremely low brightness, the optic disk has extremely high brightness, the shapes of the macula and the optic disk tend to be circular, and the relative distance and positions of the macula and the optic disk are fixed, so that a morphological filter is realized. A circular or ellipse area with extremely high brightness in the fundus image is detected and used as a candidate area of the optic disk. Wrong candidate areas are filtered out according to the distance and the positions of the macula and the optic disk, and then the central position of the optic disk is determined.
Further, the fundus image analysis and comparison module 6022 is further used for: preprocessing the fundus image, wherein the preprocessing comprises the following steps: green channel selection, median filtering, finite contrast enhancement, and normalization processing of gray scale; establishing a morphological filter to determine the macular fovea and the optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image: aligning a fundus image according to the fundus structural parameter, and correcting the identification of the retinal vascular change characteristic data, wherein the fitndus structural parameters comprise: macular fovea, optic disk, and main blood vessel information: and automatically analyzing the change of the retinal abnormality characteristic data.
In the present embodiment, the fundus image can be aligned and a change area of the retinal vessel change characteristic data in the fundus image can be identified according to the position of the mactda, the position of the optic disk, and the information of the main blood vessel. By the change area, the change condition of the range of the affected position of the macrovascular, the length of the blood vessel, and the relative position of the affected position of the macrovascular and the center of the optic disk can be rapidly seen.
The position of the macula and main blood vessel information are extracted, and specifically, the following mode is adopted: selecting a fundus image with a clear image showing clearly the optic disk, the macula, and the blood vessel from the images to be analyzed as a standard reference image, and processing the standard image to generate a standard gray scale histogram; and mapping the gray scale of the rest fundus images to be analyzed according to the gray scale distribution of the standard gray scale histogram to obtain a fundus image with the same gray scale distribution as that of the standard reference image.
Further steps are carried out: establishing a morphological filter according to the brightness of the macula, the shape of the macula, and the position distance between the macula and the optic disk in the preprocessed fundus image, and determining the position of the macula. That is: in the preprocessed fundus image, the macula has extremely low brightness, the shapes of the macula and the optic disk tend to be circular, and the relative distance and positions of the macula and the optic disk are fixed, so that a morphological filter is realized. A circular area with extremely low brightness in the fundus image is detected and used as a candidate area of the macukt. Wrong candidate areas are filtered out according to the distance and the positions of the macula and the optic disk, and then the central position of the macula is determined.
According to the preprocessed MMus image, the fundus main blood vessels have similar gray scale infomiation and high contrast with the background. The main blood vessel is segmented by using a threshold segmentation method in combination with the extraction method of the retinal vascular network, The fundus images are aligned according to the fundus structural parameter. According to the positions of the macula fovea and the optic disk, and the main blood vessel information, fundus images of the same user at different periods are aligned and the fundus image change area is identified. The following mode can be adopted aligning the macula and the optic disk of different fundus images, and roughly aligning pair fundus images; calculating a correlation coefficient on the main blood vessel information, and finely adjusting the offset position of the fundus image until the correlation coefficient is maximum; the main blood vessel information including main blood vessel binarization information. It is specifically: overlapping two fundus images to be analyzed and compared, and substantially coinciding the macula and the optic disk according to the detection and positioning results of the optic disk and the macula position; according to the segmented main blood vessel binarization image information, calculating the correlation coefficient thereof, and properly adjusting the relative positions of the two fundus images; and when the correlation coefficient is maximum, the two fundus images achieving a certain alignment. It is specifically: denoting the binarized blood vessel segmentation image of the eve fundus image which is basically aligned according to the positions of the optic disc and the macula to be 41-and v2 respectively, the position offset of the transverse direction and the longitudinal direction to be LT and 4Y respectively, and finely adjusting AM and elY and calculating the correlation coefficient Iltiff '4Y) When the correlation coefficient is maximum, the corresponding °sive%) is the offset position when the two images are aligned.
In other embodiments, the definition of change may be modified as required to find other changing circumstances in the fundus image.
In other embodiments, the range of arterial blood vessel and the position thereof affected by the local retinal artery constriction in the fundus image may further be identified by drawing a rectangular. Different colors may represent different ranges of the affected arterial blood vessel and the position thereof, such as pink for the affected arterial blood vessel and green for the range of the affected arterial blood vessel positions. Then the fundus images are aligned according to fundus parameters. The fundus parameters include: the position of the macula, the position of the optic disk, and main blood vessel information. The fundus image change area or the change area of the retinal vascular change characteristic data is identified with white.
Further, the result analysis module 6023 is further used for: analyzing and calculating to obtain the blood pressure control effect and body health condition of hypertension patient within a preset time period: giving corresponding health service suggestion according to the analysis result; and generating a report of the blood pressure control effect, the physical health condition, and the health service suggestion, and sending related information of the report to related personnel.
Further steps are analyzing and comparing the retinal vascular change characteristic data of the patient in different periods, acquiring the change condition of the fundus screening characteristic data of the patient, further analyzing and calculating to obtain the blood pressure control effect and the physical health condition of hypertension patient in a preset time period, and sending the analysis result to the patient user; wherein in one implementation, augmented reality (AR) technology may be used to animate these fimdus characteristic changes and their continued development, which may affect vision or general health, into a simple presentation that is superimposed on a real photo of the fundus image to achieve a visual educational effect, allowing the user to understand his or her blood pressure control or therapy for a recent period of time and experience a profound education and stimulating timely screening of patient lifestyle intervention basic therapy, and the compliance or consciousness of timely prevention and therapy; or providing corresponding health service suggestion through a health service professional or a family doctor of the patient so as to make personalized service for the patient user.
Guidelines for the prevention and therapy of hypertension and diabetes in China suggest that patients with hypertension and diabetes should be subjected to fundus photography screening regularly or at least once every year or half a year, or even three months. As one application or implementation, the invention can extract and identify the structural parameter and retinal vascular change characteristic data of the fundus image by utilizing the fundus image obtained after fundus screening wherein the retinal vascular change characteristic comprises: local retinal artery constriction; retinal vascular change characteristic data of the patient in different periods is analyzed and compared: the change condition of the fundus screening characteristic data of the patient is further acquired, related prevention and therapeutic effect condition such as blood pressure control, lifestyle intervention therapeutic effects and the like of the patient in a recent period is analyzed, and related blood pressure control condition and health condition evaluation data is obtained.
Further, the fundus image analysis and comparison module 6022 is further used for: segmenting the fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carry ing out arteriovenous segmentation according to the segmented fundus vascular network. The preferred embodiment is the same as the example of the method, and will not be repeated here.
Further, the fundus image analysis and comparison module 6022 is further used for: extracting the center of the optic disk in the preprocessed fundus image, and determining the size of the optic disk; determining a measurement area by positioning the optic disk; and obtaining the retinal vascular change characteristic data within the measurement area or within the measurement area by an automated or a semi-automated interactive blood vessel diameter measurement method.
It should be noted that although the above embodiments have been described herein, the patent protection scope of the invention is not limited. Therefore, based on the innovative concept of the invention, the changes and modifications to the embodiments described herein, or the use of the equivalent structure or equivalent process transformation of the description and the attached drawings of the invention to directly or indirectly apply the above technical solutions to other related technical fields are included in the scope of patent protection of the invention.
Claims (10)
- Claims 1. A method for analyzing hypertensive retinal vascular change characteristic data, characterized by comprising the following steps: acquiring and storing a MMus image of a hypertension patient; extracting and identifying structural parameter and retinal vascular change characteristic data of the fundus image; and storing the structural parameter and retinal vascular change characteristic data of the fundus image; wherein the retinal vascular change characteristic data comprises: local retinal artery constriction; judging whether retinal vascular change characteristic data of an early stage of a patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of different stages of the patient, and acquiring change condition of fundus screening characteristic data this time of the patient; and analyzing and processing the change condition of the fundus screening characteristic data.
- 2. The method for analyzing hypertensive retinal vascular change characteristic data according to claim 1, characterized in that the "analyzing and comparing the retinal vascular change characteristic data of different stages of the patient, and acquiring change condition of fundus screening characteristic data this time of the patient" further comprises steps of: preprocessing the fundus image, wherein the preprocessing comprises: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale; establishing a morphological filter to determine a macular fovea and an optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image; aligning a fundus image according to the fundus structural parameter, and correcting an identification of the retinal vascular change characteristic data, wherein die finidus structural parameters comprise: macular fovea, optic disk and main blood vessel information; and automatically analyzing a change of the retinal abnormality characteristic &la.
- 3. The method for analyzing hypertensive retinal vascular change characteristic data according to claim 1, characterized in that the "analyzing and processing change condition of the fundus screening characteristic data" further comprises steps of: analyzing and calculating to obtain blood pressure control effect and body health condition of hypertension patient within a preset time period; giving corresponding health service suggestion according to an analysis result; and generating a report of the blood pressure control effect, the physical health condition, and the health service suggestion, and sending related information of the report to related personnel.
- 4. The method for analyzing hypertensive retinal vascular change characteristic data according to claim 2, characterized in that the "segmenting a retinal vascular network of the preprocessed fundus image" further comprises steps of: segmenting a fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carrying out arteriovenous segmentation according to the segmented fundus vascular network.
- 5. The method for analyzing hypertensive retinal vascular change characteristic data according to claim 1, characterized in that the "identifying structural parameter and retinal vascular change characteristic data of the fundus image" further comprises steps of: extracting a center of the optic disk in the preprocessed fundus image, and determining a size of the optic disk; determining a measurement area by positioning the optic disk; and obtaining the retinal vascular change characteristic data within the measurement area or within the measurement area by an automated or a semi-automated interactive blood vessel diameter measurement method.
- 6. A system for analyzing hypertensive retinal -vascular change characteristic data, characterized by comprising a fundus image acquisition terminal and a fundus image processing terminal; wherein the fundus image processing terminal comprises: a data storage module, a fundus image analysis and comparison module, and a result analysis module; the fundus image acquisition terminal is connected with the fundus image processing terminal; the fundus image acquisition terminal is used for: acquiring a fundus image of a patient, and sending the fundus image to the fundus image processing terminal; the data storage module is used for: storing the fundus image; the fundus image analysis and comparison module is used for: extracting and identifying structural parameter and retinal vascular change characteristic data of the fundns image; judging whether the retinal vascular change characteristic data of an early stage of the patient is stored or not, if yes, analyzing and comparing the retinal vascular change characteristic data of the different stages of the patient, and acquiring change condition of fundus screening characteristic data this time of the patient; the data storage module is used for storing the structural parameter and retinal vascular change characteristic data of the fundus image; and the result analysis module is used for: analyzing and processing the change condition of the fundus screening characteristic data.
- 7. The system for analyzing hypertensive retinal vascular change characteristic data according to claim 6, characterized in that the fundus image analysis and comparison module is further used for: preprocessing the fundus image, wherein the preprocessing comprises: green channel selection, median filtering, finite contrast enhancement and normalization processing of gray scale; establishing a morphological filter to determine a macular fovea and an optic disk in the preprocessed fundus image; segmenting a retinal vascular network and a main blood vessel of the preprocessed fundus image; aligning a fundus image according to the fundus structural parameter, and correcting an identification of the retinal vascular change characteristic data, wherein the fimdus structural parameters comprise: macular fovea, optic disk and main blood vessel information; and automatically analyzing a change of the retinal abnormality characteristic data.
- 8. The system for analyzing hypertensive retinal vascular change characteristic data according to claim 6, characterized in that the result analysis module is further used for: analyzing and calculating to obtain blood pressure control effect and body health condition of hypertension patient within a preset time period; giving corresponding health service suggestion according to an analysis result; and generating a report of the blood pressure control effect, the physical health condition and the health service suggestion, and sending related information of the report to related personnel.
- 9. The system for analyzing hypertensive retinal vascular change characteristic data according to claim?, characterized in that the fundus image analysis and comparison module is further used for: segmenting a fundus blood vessel of the fundus image through a saliency model and a region optimization method to obtain a fundus vascular network, and carrying out arteriovenous segmentation according to the segmented fundus vascular network.
- 10. The system for analyzing hypertensive retinal vascular change chanicteristic data according to claim 6, characterized in that the fundus image analysis and comparison module is further used for: extracting a center of the optic disk in the preprocessed fundus image, and determining a size of the optic disk: determining a measurement area by positioning the optic disk; and obtaining the retinal vascular change characteristic data within the measurement area or within the measurement area by an automated or a semi-automated interactive blood vessel diameter measurement method.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811408427.XA CN111222361B (en) | 2018-11-23 | 2018-11-23 | Method and system for analyzing characteristic data of change of blood vessel of retina in hypertension |
| PCT/CN2018/124503 WO2020103289A1 (en) | 2018-11-23 | 2018-12-27 | Method and system for analyzing hypertensive retinal blood vessel change feature data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| GB202104436D0 GB202104436D0 (en) | 2021-05-12 |
| GB2591919A true GB2591919A (en) | 2021-08-11 |
Family
ID=70774240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB2104436.7A Withdrawn GB2591919A (en) | 2018-11-23 | 2018-12-27 | Method and system for analyzing hypertensive retinal blood vessel change feature data |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN111222361B (en) |
| GB (1) | GB2591919A (en) |
| WO (1) | WO2020103289A1 (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109166117B (en) * | 2018-08-31 | 2022-04-12 | 福州依影健康科技有限公司 | Automatic eye fundus image analysis and comparison method and storage device |
| CN113781381B (en) * | 2020-06-05 | 2023-09-26 | 中山大学中山眼科中心 | System for discernment chronic kidney disease image |
| CN111899272B (en) * | 2020-08-11 | 2023-09-19 | 上海海事大学 | Fundus image blood vessel segmentation method based on coupling neural network and line connector |
| CN112330610B (en) * | 2020-10-21 | 2024-03-29 | 郑州诚优成电子科技有限公司 | Accurate positioning method based on microvascular position cornea endothelial cell counting acquisition |
| CN112508919A (en) * | 2020-12-11 | 2021-03-16 | 北京大恒普信医疗技术有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN116236150A (en) * | 2020-12-28 | 2023-06-09 | 深圳硅基智能科技有限公司 | Arteriovenous blood vessel image segmentation method based on fundus image |
| CN112862804B (en) * | 2021-03-01 | 2023-04-07 | 河南科技大学第一附属医院 | System and method for processing retina blood vessel image |
| CN113010722B (en) * | 2021-04-18 | 2023-10-03 | 南通大学 | Slow clinical research queue query system and method for fusing fundus images |
| CN113222927B (en) * | 2021-04-30 | 2023-08-01 | 汕头大学·香港中文大学联合汕头国际眼科中心 | Automatic checking machine for retinopathy of Prematurity (PEM) additional lesions |
| CN113269737B (en) * | 2021-05-17 | 2024-03-19 | 北京鹰瞳科技发展股份有限公司 | Fundus retina artery and vein vessel diameter calculation method and system |
| CN113486925A (en) * | 2021-06-07 | 2021-10-08 | 北京鹰瞳科技发展股份有限公司 | Model training method, fundus image generation method, model evaluation method and device |
| CN114847871B (en) * | 2022-07-06 | 2022-10-18 | 北京鹰瞳科技发展股份有限公司 | Method, system and related product for analyzing fundus variation trend of subject |
| CN115482933B (en) * | 2022-11-01 | 2023-11-28 | 北京鹰瞳科技发展股份有限公司 | Method for evaluating driving risk of driver and related product thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1145213A (en) * | 1996-06-04 | 1997-03-19 | 浙江大学 | Harmless quantitative diagnosis system for cardiovascular disease and its use |
| CN102112044A (en) * | 2008-05-14 | 2011-06-29 | 科学、技术与研究机构 | Automatic cup-to-disc ratio measurement system |
| CN103458772A (en) * | 2011-04-07 | 2013-12-18 | 香港中文大学 | Method and device for retinal image analysis |
| CN108230276A (en) * | 2018-02-06 | 2018-06-29 | 江西理工大学 | It is a kind of to merge the natural scene image deblurring method without ginseng image quality evaluation |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2009234503B2 (en) * | 2008-04-08 | 2014-01-16 | National University Of Singapore | Retinal image analysis systems and methods |
| CN105513077B (en) * | 2015-12-11 | 2019-01-04 | 北京大恒图像视觉有限公司 | A kind of system for diabetic retinopathy screening |
| CN106651827B (en) * | 2016-09-09 | 2019-05-07 | 浙江大学 | A kind of ocular fundus image registration method based on SIFT feature |
| CN107657612A (en) * | 2017-10-16 | 2018-02-02 | 西安交通大学 | Suitable for full-automatic the retinal vessel analysis method and system of intelligent and portable equipment |
| CN108416371A (en) * | 2018-02-11 | 2018-08-17 | 艾视医疗科技成都有限公司 | A kind of diabetic retinopathy automatic testing method |
-
2018
- 2018-11-23 CN CN201811408427.XA patent/CN111222361B/en active Active
- 2018-12-27 GB GB2104436.7A patent/GB2591919A/en not_active Withdrawn
- 2018-12-27 WO PCT/CN2018/124503 patent/WO2020103289A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1145213A (en) * | 1996-06-04 | 1997-03-19 | 浙江大学 | Harmless quantitative diagnosis system for cardiovascular disease and its use |
| CN102112044A (en) * | 2008-05-14 | 2011-06-29 | 科学、技术与研究机构 | Automatic cup-to-disc ratio measurement system |
| CN103458772A (en) * | 2011-04-07 | 2013-12-18 | 香港中文大学 | Method and device for retinal image analysis |
| CN108230276A (en) * | 2018-02-06 | 2018-06-29 | 江西理工大学 | It is a kind of to merge the natural scene image deblurring method without ginseng image quality evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| GB202104436D0 (en) | 2021-05-12 |
| WO2020103289A1 (en) | 2020-05-28 |
| CN111222361B (en) | 2023-12-19 |
| CN111222361A (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2591919A (en) | Method and system for analyzing hypertensive retinal blood vessel change feature data | |
| McGrory et al. | Towards standardization of quantitative retinal vascular parameters: comparison of SIVA and VAMPIRE measurements in the Lothian Birth Cohort 1936 | |
| Gelman et al. | Diagnosis of plus disease in retinopathy of prematurity using Retinal Image multiScale Analysis | |
| Trucco et al. | Validating retinal fundus image analysis algorithms: issues and a proposal | |
| US9848765B2 (en) | Quantifying a blood vessel reflection parameter of the retina | |
| Kalitzeos et al. | Retinal vessel tortuosity measures and their applications | |
| CN110875092B (en) | Health big data service method and system based on remote fundus screening | |
| Abdel-Ghafar et al. | Progress towards automated detection and characterization of the optic disc in glaucoma and diabetic retinopathy | |
| KR101492803B1 (en) | Apparatus and method for breast tumor detection using tactile and near infrared hybrid imaging | |
| US20020196965A1 (en) | Image transformation and analysis system and method | |
| Lin et al. | Reliability of foveal avascular zone metrics automatically measured by Cirrus optical coherence tomography angiography in healthy subjects | |
| Demir et al. | An automated method for analysis of microcirculation videos for accurate assessment of tissue perfusion | |
| Agrawal et al. | Choroidal structural changes in sympathetic ophthalmia on swept-source optical coherence tomography | |
| CN111402184B (en) | Method and system for realizing remote fundus screening and health service | |
| Kumar et al. | Automated detection of eye related diseases using digital image processing | |
| KR20170128236A (en) | Non-invasive evaluation method and apparatus for intracranial pressure | |
| WO2020103288A1 (en) | Analysis method and system for feature data change of diabetic retinopathy fundus, and storage device | |
| CN111383775A (en) | Member user anonymous communication method based on fundus screening and storage device | |
| Camara et al. | A comprehensive review of methods and equipment for aiding automatic glaucoma tracking | |
| CN111435612B (en) | Method and system for personalized health service of mobile medical treatment | |
| CN111325631B (en) | Health insurance fee control method and system based on fundus images | |
| Wang et al. | Analysis of retinal images associated with hypertension and diabetes | |
| CN114847871B (en) | Method, system and related product for analyzing fundus variation trend of subject | |
| CN110875094B (en) | Healthy lifestyle motivation method and system for diabetes and storage device | |
| EP3954272A1 (en) | Fundus imaging for microvascular assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 789A | Request for publication of translation (sect. 89(a)/1977) |
Ref document number: 2020103289 Country of ref document: WO |
|
| WAP | Application withdrawn, taken to be withdrawn or refused ** after publication under section 16(1) |