CN111325631A - Health insurance fee control method and system based on fundus images - Google Patents
Health insurance fee control method and system based on fundus images Download PDFInfo
- Publication number
- CN111325631A CN111325631A CN201811536492.0A CN201811536492A CN111325631A CN 111325631 A CN111325631 A CN 111325631A CN 201811536492 A CN201811536492 A CN 201811536492A CN 111325631 A CN111325631 A CN 111325631A
- Authority
- CN
- China
- Prior art keywords
- data
- retinal
- fundus
- analyzed
- fundus image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 125
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000002207 retinal effect Effects 0.000 claims abstract description 84
- 238000013139 quantization Methods 0.000 claims abstract description 55
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 41
- 206010025421 Macule Diseases 0.000 claims abstract description 11
- 230000002792 vascular Effects 0.000 claims abstract description 11
- 238000012954 risk control Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 54
- 210000001525 retina Anatomy 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 32
- 238000012216 screening Methods 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 22
- 210000001210 retinal vessel Anatomy 0.000 claims description 22
- 210000000873 fovea centralis Anatomy 0.000 claims description 15
- 210000000056 organ Anatomy 0.000 claims description 15
- 210000001508 eye Anatomy 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 14
- 230000002123 temporal effect Effects 0.000 claims description 13
- 230000036772 blood pressure Effects 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 11
- 201000001320 Atherosclerosis Diseases 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 10
- 210000004556 brain Anatomy 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 210000003734 kidney Anatomy 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 210000001927 retinal artery Anatomy 0.000 claims description 8
- 230000009956 central mechanism Effects 0.000 claims description 7
- 210000002216 heart Anatomy 0.000 claims description 7
- 239000003814 drug Substances 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000740 bleeding effect Effects 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 5
- 210000004369 blood Anatomy 0.000 claims description 5
- 235000005911 diet Nutrition 0.000 claims description 5
- 230000004438 eyesight Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 4
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 claims description 4
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 229910052802 copper Inorganic materials 0.000 claims description 4
- 239000010949 copper Substances 0.000 claims description 4
- 230000037213 diet Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000008816 organ damage Effects 0.000 claims description 4
- 229910052709 silver Inorganic materials 0.000 claims description 4
- 239000004332 silver Substances 0.000 claims description 4
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 3
- 206010030113 Oedema Diseases 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims description 3
- 229940079593 drug Drugs 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 239000008103 glucose Substances 0.000 claims description 3
- 210000004126 nerve fiber Anatomy 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 abstract description 5
- 238000010191 image analysis Methods 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 22
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 22
- 206010012689 Diabetic retinopathy Diseases 0.000 description 21
- 206010012601 diabetes mellitus Diseases 0.000 description 20
- 238000007726 management method Methods 0.000 description 19
- 206010020772 Hypertension Diseases 0.000 description 17
- 208000007342 Diabetic Nephropathies Diseases 0.000 description 12
- 208000033679 diabetic kidney disease Diseases 0.000 description 12
- 230000002265 prevention Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 10
- 208000006011 Stroke Diseases 0.000 description 9
- 208000017667 Chronic Disease Diseases 0.000 description 8
- 210000001367 artery Anatomy 0.000 description 7
- 238000011161 development Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 208000032843 Hemorrhage Diseases 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 230000006806 disease prevention Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 210000002189 macula lutea Anatomy 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000009885 systemic effect Effects 0.000 description 4
- 208000017442 Retinal disease Diseases 0.000 description 3
- 206010038923 Retinopathy Diseases 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000005728 strengthening Methods 0.000 description 3
- 208000032598 susceptibility microvascular complications of diabetes Diseases 0.000 description 3
- 201000004569 Blindness Diseases 0.000 description 2
- 208000002177 Cataract Diseases 0.000 description 2
- 208000010412 Glaucoma Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000003143 atherosclerotic effect Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 230000002490 cerebral effect Effects 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002526 effect on cardiovascular system Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000001631 hypertensive effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004393 prognosis Methods 0.000 description 2
- 238000000275 quality assurance Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- 206010002329 Aneurysm Diseases 0.000 description 1
- 206010003210 Arteriosclerosis Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010067671 Disease complication Diseases 0.000 description 1
- 206010010164 Hypertension complications Diseases 0.000 description 1
- 208000001344 Macular Edema Diseases 0.000 description 1
- 206010025415 Macular oedema Diseases 0.000 description 1
- 208000009857 Microaneurysm Diseases 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 208000031662 Noncommunicable disease Diseases 0.000 description 1
- 208000037111 Retinal Hemorrhage Diseases 0.000 description 1
- 208000014139 Retinal vascular disease Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 208000030533 eye disease Diseases 0.000 description 1
- 210000004220 fundus oculi Anatomy 0.000 description 1
- 150000004676 glycans Chemical class 0.000 description 1
- 238000001631 haemodialysis Methods 0.000 description 1
- 230000000322 hemodialysis Effects 0.000 description 1
- 201000001421 hyperglycemia Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 231100000518 lethal Toxicity 0.000 description 1
- 230000001665 lethal effect Effects 0.000 description 1
- 201000010230 macular retinal edema Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 229920001282 polysaccharide Polymers 0.000 description 1
- 239000005017 polysaccharide Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000006496 vascular abnormality Effects 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
- 230000004393 visual impairment Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/94—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- 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
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2107—File encryption
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention relates to the technical field of fundus image analysis and health big data service, in particular to a method and a system for health insurance fee control based on fundus images. The health insurance fee control method based on the fundus image comprises the following steps: acquiring a fundus image file and related body index data; encrypting the relevant private data; delineating the optic disc and macula; segmenting the retinal vascular network and the main blood vessels; extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data; identifying fundus image changes and implementing quantitative analysis; and relevant health insurance risk control, fee control and personalized health big data service and health management suggestions are given.
Description
Technical Field
The invention relates to the technical field of fundus image analysis and health big data service, in particular to a method and a system for health insurance fee control based on fundus images.
Background
With the rapid development of economy in China, the living standard is continuously improved, and the dietary structure and the living style of residents are greatly changed. The prevalence of chronic diseases such as diabetes and hypertension is also increasing year by year and is in a tendency of getting younger. These chronic diseases and their complications pose a serious socio-economic burden. At present, Chinese chronic disease patients are over 2 hundred million, and the burden of the caused diseases accounts for more than 70 percent of the total burden of the diseases. These changes in population structure and specific population are opportunities for the development of commercial health insurance and also pose significant difficulties in controlling costs of commercial health medical insurance.
The whole health risk is in China continent, the claim condition is high, and the profit condition is not optimistic. In fact, health risks in many countries and regions are in a micro-profit situation, and cost control becomes a major bottleneck in the development of health insurance industry.
Currently, a major disease insurance system is generally established in China, economic guarantee is provided for critical diseases, and financial burden of patients is reduced to a certain extent. However, the big data analysis of medical insurance claims can find that many big diseases occur, and the chronic diseases are not effectively controlled, and various complications occur, which is the root cause of the big diseases and the big medical expenses. How to effectively establish a chronic disease prevention mechanism and control the risk of a large disease is an important problem to be solved by the health insurance industry.
The charge control means of the health medical insurance is continuously updated, and the practicability and the long-term effectiveness of charge control are obviously improved from the traditional manual inspection and medical rule audit to the current big data technology. The medical insurance control fee in the higher stage is a health care insurance model of a learning management type, and the health management is performed to control the fee before the occurrence of diseases, which is an important target in the health care insurance industry, but no mature or effective method or technology report is seen in the current practice.
In the face of health insurance control cost and profit problems, many people call for solving the problems of accurate analysis of big data, data sharing and the like, but no industry consensus is formed at present, and many barriers including hospitals are to be broken.
Some companies can help insurance companies to do accurate analysis of big data, because the companies have mass data, the insurance companies can compare the consumption habits of customers and products purchased by the customers, and then the insurance companies can be assisted to urge to pay and renew premium. However, this method is difficult to be promoted, and the most important problem is the security of the client information, which violates the promise of the insurance company not doing any things to reveal the client information, and there is another important barrier, which is an important problem difficult to be solved.
In the design process of health insurance products, in view of the current situation of the medical health system of China, the difficulty of acquiring a large amount of medical case data from a medical service organization or a social insurance organization by an insurance company is high, and the imperfect data directly influences the accurate determination of health insurance rates, which is another important problem to be solved urgently.
Commercial health care insurance puts disease prevention and health improvement in the insured as the focus of health insurance. In the United states, administrative medical treatment mainly based on health management organizations integrates insurance companies, hospitals and health management service organizations, and particularly introduces a health management idea at the front end, so that prevention is mainly performed, prevention and treatment are combined, the disease incidence is effectively reduced, and the effect of reasonably controlling fees is achieved. Many commercial insurance companies in China are exploring the management medical path, some companies establish funds for investing and setting up medical institutions, and other companies are combining insurance, management and medical care and pay attention to the major health engineering construction. The Chinese insurance industry is participating in the field of medical health management in various forms such as self-construction, investment, participation, parallel purchase, strategic cooperation and the like, and cooperation and information sharing among insurance institutions, medical institutions, health management institutions and social security institutions are likely to further promote the development of Chinese business health insurance. However, even internationally, no successful technical method or effective technical assistance system has been found.
Commercial health insurance should focus on changes in the customer population, such as 1.58 million people in 2017 in China at 65 years of age and above, and 3.29 million people in 2050 in China at 65 years of age and above. The increasing aging of the population has led to an increasing need for incapacitating insurance and care insurance. With the release of birth control policies, the health care of children and women is also an area worth health insurance attention. If people can pay attention to the health requirements of old people and women and children, the Chinese characteristics are met, and a technical method or a system which can use a health care community service center combined with medical care or a basic community clinic is successfully built or developed, important breakthrough can be made, and the system becomes an advanced health service provider for the old people and the women and the children or a basic community health medical service provider.
Clinical guidelines for Diabetic Retinopathy (DR) show that, due to microvascular complications of diabetes, in our country, DR has a prevalence of 25% to 37.5% in diabetic patients, 8% of whom are at risk of visual loss and 30% to 50% of whom may be associated with renal complications.
Today, Diabetic Retinopathy (DR) has become the leading blinding eye disease, with Diabetic Nephropathy (DN) rising to near first in hemodialysis patients; according to Chinese data of 2010 global disease burden, the Chinese stroke death rate exceeds that of coronary heart disease and malignant tumor, and becomes the leading factor of death and disability of adults and diabetics in China! The prevalence rate reaches 0.83%! In our country, 70% of glaucoma patients are undiagnosed, over 6,000 million cataract patients, and increase at a rate of 10% per year, and nearly half of these patients are associated with diabetes or its hypertension complications. All located in front of the 25 classes of "major diseases" defined by commercial insurance in China! These patients face huge payments once they are blind, lethal or disabling, and may be unacceptably serious in terms of both actuarial insurance and health care insurance control.
The importance of blood pressure monitoring is also pointed out by the Chinese guidelines for the graded prevention of atherosclerotic cerebrovascular and cardiovascular diseases in adult type 2 diabetic patients published in 2016: diabetes is one of the most major chronic non-infectious diseases and is one of the independent risk factors of atherosclerotic cardiovascular and cerebrovascular diseases (ASCCVD), and evidence indicates that stroke is the main fatality and the main cause of disability of adult diabetics in China. In this new situation, if many diabetic patients, especially the elderly, choose to purchase insurance, the relevant health or life commercial insurance companies face a significant risk.
China lacks an efficient early warning or large-scale screening platform for severe complications or major diseases such as stroke, DR, DN and the like so far; aiming at chronic diseases such as diabetes, hypertension and the like, dozens of mobile medical APPs can be used in China, but most of the mobile medical APPs are centered on blood sugar or blood pressure, individualized information such as systemic blood vessels, nerves and the like cannot be obtained, clinically, if stroke prediction is needed, nuclear Magnetic Resonance (MR) can only be used, thousands of yuan is needed, accuracy is limited, the individualized information such as the hypertension or the hypertension accompanied by the diabetes, damage to target organs such as brain, cardiovascular, kidney, eyes and the like or the damaged condition of systemic health cannot be known! Health prevention is difficult to achieve.
Diabetic Retinopathy (DR) is one of the major complications of diabetes and may ultimately lead to irreversible blindness. Both the American diabetes Association and the national diabetes prevention and treatment guidelines recommend that type II diabetics should be screened for DR fundus oculi on a regular or at least once a year basis. The risk of blindness can be reduced by 94.4% through DR screening by fundus photography, but the screening rate in China is not more than 10! Diabetic Nephropathy (DN) and Diabetic Retinopathy (DR) are both microvascular complications of diabetes, and when a person is screened and detected that microalbumin exceeds a normal value, a DR screening and DN specific examination means or method can be realized through a simple fundus photography method.
The life can be threatened when the target organ of hypertension is seriously damaged, and the method has important significance for early diagnosis, disease evaluation and treatment intervention of hypertension. The retinal vessels of the eyeground can be directly observed by a non-invasive method, and objective conditions are provided for observing the specific manifestations of systemic vascular abnormalities, so the eyeground screening is always one of simple, convenient and economic screening and monitoring tools for systemic vascular diseases.
The national guidelines for the prevention and treatment of hypertension and diabetes recommend that patients with hypertension and diabetes be screened periodically or at least by fundus photography every year, half a year or even 3 months. Facing the requirement of screening the eyeground of one hundred million polysaccharide uropathic patients, hundreds of millions of hypertension and other chronic patients in China, the service capability of the existing health medical institution is extremely limited!
The fundus photography can enable people to obtain individualized health medical information under accurate medicine, and individualized health services are realized; therefore, how to obtain the structured or quantitative characteristic data of a large amount of unstructured data in the remote fundus image screening of patients with diabetes and hypertension, and further realize rapid analysis and follow-up is a problem to be solved urgently.
In addition, due to the differences in the various types of fundus cameras and their different operating modes, photographic view angles, and fixation points, the relative sizes, resolutions, view angles, and fixation point structures of obtained fundus images are all different. Even if the same eye is acquired by different equipment or different service personnel at different time, the obtained fundus images can be difficult to compare with personal multiple examination images due to different equipment, visual angles and resolutions; statistical analysis, law recognition, quantitative analysis and big data service of the structured characteristic data of the fundus images among people are more difficult to achieve.
The prevention and control of the charge by health management is the natural appeal of insurance company! The lower the patient treatment cost, the less the insurance company pays, and the more profitable it can be. 1 yuan is added in prevention, and 8.5 yuan treatment cost or 100 yuan rescue cost is reduced! Therefore, if a low-cost, efficient, safe and convenient major disease early warning and personalized health big data service system can solve the problem, huge economic benefits and social benefits are certainly brought.
Disclosure of Invention
Therefore, a method and a system for health insurance control fee based on fundus images are needed to be provided, retina feature data of the fundus images are extracted and identified, a structured quantitative index of the retina feature data is formed, fundus image change is identified, quantitative analysis is achieved, and therefore establishment of a health big data system and big data service are further achieved, and related health insurance risk control, fee control and personalized health service and health management schemes and suggestions are given. The specific technical scheme is as follows:
a method of health insurance cost control based on fundus images, comprising the steps of: the method comprises the following steps that a terminal mechanism obtains target data to be analyzed, wherein the target data comprises: private data and fundus images; the terminal mechanism encrypts the target data to obtain an encrypted file to be analyzed, and sends the encrypted file to be analyzed to a remote eyeground screening and interpretation central mechanism; the fundus screening interpretation central mechanism receives the encrypted file to be analyzed and stores the encrypted file to be analyzed; decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: relevant necessary physical indicator data; preprocessing the fundus image; performing optic disc positioning and macular fovea positioning on the preprocessed fundus image; segmenting a retinal blood vessel network and a main blood vessel of the preprocessed fundus image; extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data; storing the quantitative index of the retina characteristic data structuralization; analyzing and processing the quantitative index of the retina characteristic data structuralization; judging whether a quantization index of the user's early retina feature data structuralization is stored, if so, analyzing and comparing the quantization index of the user's early retina feature data structuralization to obtain the change condition of the quantization index; and analyzing and processing the change condition.
Further, the step of preprocessing the fundus image; and performing optic disc positioning and macular fovea positioning on the preprocessed fundus image, and further comprising the following steps of: the pretreatment comprises the following steps: green channel selection, median filtering, limited contrast enhancement and gray scale normalization processing; extracting a binary vessel map from the preprocessed fundus image through an Otsu algorithm, and corroding the binary vessel map through a morphological method to obtain main vessel information; carrying out parabolic fitting calculation on the main blood vessel, and positioning the center of the optic disc and delineating the edge of the optic disc according to the calculation result; constructing a circle by taking the center of the optic disc as the circle center and the first preset radius value and the second preset radius value to form an annular area; foveal macular location is performed within the annular region according to macular brightness characteristics.
Further, the step of "analyzing the quantization index structured with the retinal feature data of the user at different periods again" further includes the steps of: aligning the fundus image according to fundus structure parameters, and correcting the identification of the retina characteristic data, wherein the fundus structure parameters comprise: the position of the fovea maculae, the position of the optic disc, and the main vessel information; automatically analyzing changes in the structured quantitative indicators.
Further, the "analyzing and processing the quantization index structured by the retinal feature data" further includes the steps of: comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, evaluating and prognostically estimating the atherosclerosis and the damaged condition of target organs of the user, and giving related health insurance risk control, fee control and personalized health service suggestions, wherein the target organs comprise brain, heart, eyes and kidney.
Further, if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, the quantization index of the retinal feature data structuralization of the user in different periods is analyzed and compared again to obtain the change condition, and the method further includes the following steps: comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, the change condition and the change trend thereof, evaluating and prognostically estimating the atherosclerosis and the target organ damage condition of the user, and providing related health insurance risk control, fee control and personalized health service suggestions; the target organs include brain, heart, eye and kidney.
Further, the "extracting and identifying retinal feature data of the fundus image" further includes the steps of: extracting the center of the optic disc according to the result of the optic disc positioning, and determining the radius of the optic disc; determining a measurement area; obtaining the identification of the retinal vessel change characteristic data and the quantitative index of the structure of the retinal vessel change characteristic data in the measuring region or outside the measuring region by an automatic or semi-automatic interactive vessel diameter measuring method; the retinal vascular change characteristic data includes: localized retinal artery constriction, diffuse retinal artery constriction, arteriovenous cross compression, copper wire-like or silver wire-like change; and forming a quantitative index and identification of the retinal blood vessel change characteristic data structuralization.
Further, the "extracting and identifying retinal feature data of the fundus image" further includes the steps of: the mark of the relative position of the microangioma and the fovea maculata; identification of the size of the bleeding spot and its relative position to the fovea centralis; identification or analysis of the hard exudation range and its minimum distance from the fovea maculata; identification of the extent of the lint spot and its relative position to the fovea centralis; identification of localized retinal nerve fiber layer defects and disc edema levels; and forming the retinal feature data structured quantization index identification through an automatic or semi-automatic interactive feature extraction method.
Further, the step of extracting and identifying the retinal feature data of the fundus image and forming the structured quantization index of the retinal feature data further comprises the following steps: calculating the pixel dot matrix number of the distance from the fovea of the macula to the temporal side of the optic disc according to the circled optic disc and the macula; taking the pixel lattice number as a denominator parameter of a quantization index; and calculating to obtain the quantization index of the retina characteristic data structuralization.
Further, if the target data to be analyzed is transmitted and stored by using the DICOM standard, private data can be constructed in the DICOM header file before transmission.
Further, the relevant necessary physical metric data includes: the user unique ID number, height, weight, waist circumference, family genetic history, medication, blood glucose, blood pressure, vision, and lifestyle, the lifestyle including: one or more of exercise condition, diet condition, life habit and whether to smoke or drink.
In order to solve the technical problem, the health insurance fee control system based on the fundus image is further provided, and the specific technical scheme is as follows:
a system for health insurance premiums based on fundus images, comprising: data acquisition terminal and data interpretation analysis terminal, data acquisition terminal includes: data acquisition module and data encryption module, data interpretation analysis terminal includes: the device comprises a data storage module, a data decryption module, a data processing module and a data analysis module; the data acquisition module is used for: target data to be analyzed, the target data to be analyzed comprising: private data and fundus images; the data encryption module is used for: encrypting the target data to obtain an encrypted file to be analyzed, and sending the encrypted file to be analyzed to a data interpretation analysis terminal; the data storage module is used for: receiving and storing the encrypted file to be analyzed; the data decryption module is used for: decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: relevant necessary physical indicator data; the data processing module is used for: preprocessing the fundus image; performing optic disc positioning and macular fovea positioning on the preprocessed fundus image; segmenting a retinal blood vessel network and a main blood vessel of the preprocessed fundus image; extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data; the data storage module is further configured to: storing the retina characteristic data and the structured quantitative indexes thereof; the data processing module is further configured to: judging whether a quantization index of the user's previous retina feature data structuralization is stored; the data analysis module is configured to: analyzing and processing the quantitative index of the retina characteristic data structuralization; if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, the quantization index of the retinal feature data structuralization of the user in different periods is analyzed and compared again to obtain the change condition of the user.
Further, the data analysis module is further configured to: comprehensively analyzing the related necessary body index data and the quantitative index of the retina characteristic data structuralization, evaluating and prognostically estimating the atherosclerosis of the user and the damaged condition of the target organ, and giving related health insurance control fee suggestions.
The invention has the beneficial effects that: by applying the related technical method and the related technical system provided by the invention, the fundus camera and the computer are arranged, so that the fundus image and the related necessary body index data can be obtained, and the fundus image interpretation and analysis mechanism which is locally or remotely arranged interprets and analyzes the fundus image and the related necessary body index data; establishing a stroke and DR, DN and other serious complications or an efficient and large-scale serious disease early warning and health insurance fee control service platform; by arranging the remote major disease early warning and health insurance fee control service platform in the health insurance group institution, the difficulty that the eyeground working eyeground image interpretation and analysis is difficult to carry out due to the lack of ophthalmologists or professional image readers in branch institutions or bottom layer health insurance institutions can be overcome; a complete closed-loop quality assurance system can be further formed by positioning the optic disc and the macular fovea of the fundus image and analyzing the image definition, so that the fundus image finally obtained by the remote fundus screening and interpreting mechanism and relevant necessary body index information are fully available, the back-and-forth wave of a patient is avoided, and the user experience is enhanced; meanwhile, the characteristics that the distances from the fovea centralis to the temporal side of the optic disc are approximately the same among different people are utilized, and the like, the comparison, the statistical analysis, the law recognition and the quantitative analysis of the structured characteristic data of the eye fundus image among people are realized through the dot matrix conversion, so that a foundation is laid for finally forming a large data knowledge base which can be analyzed, updated and has low manufacturing cost; the main blood vessels of the preprocessed fundus image are segmented, the fundus images of the same user in different periods are aligned according to the positions of the fovea centralis and the optic disc and the main blood vessel information, the change region of the retinopathy characteristics of the fundus images can be rapidly identified, and the health assessment service personnel can be assisted to rapidly give remote interpretation or health medical insurance control fees. The system can send the data of the analysis result to professional health medical service institutions, assist the medical institutions to better understand the conditions of diabetes or hypertension of the user, and further establish personalized health service for the user. Effectively establishes a chronic disease prevention mechanism and controls the risk of major diseases, so that an important problem which needs to be solved urgently in the health management or health insurance industry can be conveniently solved. The process of remotely acquiring the fundus image and analyzing and processing the fundus image data enables the user to enjoy the services of fundus screening, glaucoma and cataract operation maturity remote screening diagnosis and the like even in the laggard remote area; can form a high-efficiency early warning or large-scale screening platform for screening serious complications such as diabetes, hyperglycemia and the like or target organ damage condition assessment or prognosis estimation in stroke and DR and DN specificity; the method comprises the steps of obtaining individual accurate information of target organs such as brain, heart, eyes, kidneys and the like under accurate medicine damage assessment or prognosis estimation, realizing individual health big data service, strengthening health management, obviously improving the practicability and the long-term effectiveness of charge control by the big data technology, realizing medical insurance charge of a higher-level stage, being a learning management type health medical insurance mode, performing health management, and controlling the charge before diseases occur; the system participates in the field of health management, establishes personalized health big data service under precise medicine, and has great significance for further promoting the development of Chinese health management and commercial health insurance. After the technical method and the system are popularized, the important social benefit and economic benefit can be obtained!
Drawings
FIG. 1 is a flow chart of a method for insurance control based on fundus images according to an embodiment;
FIG. 2 is a schematic diagram of a retinal vascular network according to an embodiment;
fig. 3 is a block diagram of a system for controlling insurance premiums based on fundus images according to an embodiment.
Description of reference numerals:
300. a health insurance fee control system based on fundus images,
301. a data acquisition terminal for acquiring data from a plurality of data acquisition terminals,
302. a data interpretation and analysis terminal is used for interpreting and analyzing the data,
3011. a data acquisition module for acquiring the data of the user,
3012. a data encryption module for encrypting the data,
3021. a data storage module for storing the data of the electronic device,
3022. a data decryption module for decrypting the data received from the data receiving module,
3023. a data processing module for processing the data of the mobile phone,
3024. and a data analysis module.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1, in the present embodiment, a health insurance fee control method based on fundus images can be applied to the following modes in particular: by arranging or cooperating with the outside in the health insurance mechanism, applying an eyeground camera, strengthening the health management or physical examination or health management center for strengthening health management or internal charge control, independently constructing an eyeground image detection center, or cooperating with a third-party medical image detection center with large MR equipment in or outside the mechanism, establishing a medical image detection center which can be used for five-year risk prediction of cerebral and cardiovascular atherosclerotic diseases such as cerebral apoplexy and the like and is more efficient; by arranging the remote major disease early warning and health insurance fee control service platform in the health insurance group institution, the difficulty that the eyeground working eyeground image interpretation and analysis is difficult to carry out due to the lack of ophthalmologists or professional image readers in branch institutions or bottom layer health insurance institutions can be overcome; effectively establishes a chronic disease prevention mechanism and controls major disease risks such as major complications and the like.
In this embodiment, the fundus camera is used to capture fundus images and relevant necessary body index data include, but are not limited to: the user unique ID number, height, weight, waist circumference, family genetic history, medication, blood glucose, blood pressure, vision, and lifestyle, the lifestyle including: one or more of exercise condition, diet condition, life habit and whether to smoke or drink.
In the present embodiment, a specific embodiment of a health insurance fee control method based on fundus images is as follows:
step S101: the method comprises the following steps that a terminal mechanism obtains target data to be analyzed, wherein the target data comprises: private data and fundus images.
Step S102: and the terminal mechanism encrypts the target data to obtain an encrypted file to be analyzed, and sends the encrypted file to be analyzed to a remote eyeground screening and interpretation central mechanism.
Step S103: and the fundus screening and interpretation central mechanism receives the encrypted file to be analyzed and stores the encrypted file to be analyzed.
Step S104: decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: and (5) relevant necessary body index data.
Step S105: and preprocessing the fundus image.
Step S106: and performing optic disc positioning and macular foveal positioning on the preprocessed fundus images.
Step S107: and segmenting the retinal blood vessel network and the main blood vessel of the preprocessed fundus image.
Step S108: extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data.
Step S109: and storing the quantitative index of the retinal feature data structuralization.
Step S110: and analyzing and processing the quantitative index of the retinal feature data structuralization.
Step S111: and judging whether the quantization index of the retinal feature data structuralization of the user in the previous period is stored, if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, analyzing and comparing the quantization index of the retinal feature data structuralization of the user in different periods to obtain the change condition of the quantization index.
Step S112: and analyzing and processing the change condition.
Medical evidence has shown that if a fundus camera for DR screening is used in combination with an MR device with a physical examination facility built into the insurance facility, the relative risk of stroke risk detection in five years is more than 5 times that of the MR examination alone! Diabetic Nephropathy (DN) and Diabetic Retinopathy (DR) are microvascular complications of diabetes, and when a person is screened and detected that microalbumin exceeds a normal value, DN specific examination can be carried out while DR screening is realized through a simple fundus photography method. The fundus image and the relevant necessary body index data can be obtained through the fundus camera and the computer or the fundus image detection platform, the fundus image and the relevant necessary body index data are interpreted and analyzed by a local or remote fundus image interpretation and analysis central mechanism or a remote interpretation and analysis center, and a severe disease complication screening or efficient and large-scale severe disease early warning and health insurance fee control service platform for treating stroke, DR, DN and the like serious complications is established.
In this embodiment, the performing of optic disc positioning and macular foveal positioning on the preprocessed fundus image further includes: the pretreatment comprises the following steps: green channel selection, median filtering, limited contrast enhancement and gray scale normalization processing; extracting a binary vessel map from the preprocessed fundus image through an Otsu algorithm, and corroding the binary vessel map through a morphological method to obtain main vessel information; carrying out parabolic fitting calculation on the main blood vessel, and positioning the center of the optic disc and delineating the edge of the optic disc according to the calculation result; constructing a circle by taking the center of the optic disc as the circle center and the first preset radius value and the second preset radius value to form an annular area; foveal macular location is performed within the annular region according to macular brightness characteristics.
The method comprises the following specific steps: in any color fundus image, noise is more in the blue channel, useful information is basically lost, two spots are more prominent in the red channel, and information such as dark blood vessels and microangiomas is lost more, so that the green channel selection is performed on the color fundus image to be examined in the embodiment, and fundus blood vessels are retained and highlighted to the greatest extent.
In order to remove noise and well retain boundary information, the fundus image under the green channel is subjected to median filtering in the embodiment to realize denoising;
in order to obtain a better blood vessel extraction effect, the contrast of the denoised image is enhanced. In order to avoid the situation of over-brightness after image enhancement, a limited contrast enhancement method CLAHE is adopted in the present embodiment. And finally, carrying out normalization processing to enable the pixel values of all pixel points in one image to fall between 0 and 1.
And extracting a binary blood vessel map from the preprocessed fundus image by an Otsu algorithm, and corroding the binary blood vessel map by a morphological method to obtain a main blood vessel. The following may be used: calculating a threshold value of the preprocessed fundus image through an Otsu algorithm, and determining pixels with gray values larger than the threshold value as blood vessels according to the following formula;
and constructing structural elements according to 1/8-1/5 with the optic disc diameter being the image width and 1/4 with the main blood vessel width being the optic disc diameter, and performing corrosion operation on the extracted blood vessels by using the structural elements to remove the tiny blood vessels to obtain the main blood vessels.
And after the main blood vessel is obtained, parabolic fitting calculation is carried out on the main blood vessel, and the center of the optic disc is positioned according to the calculation result. The following may be used: establishing a coordinate system by taking the upper left corner of the fundus image as an origin, the horizontal direction as an X axis and the vertical direction as a Y axis;
mapping each pixel point in the main blood vessel to be the coordinate of the coordinate system;
as shown in the following formula, parabolic fitting is performed on the main vessel according to the least square method, parameters of the parabola are determined, and the vertex of the parabola is calculated,
f(x)＝ax2+bx+c
and judging whether the vertex of the parabola falls in the original fundus image, and if the vertex of the parabola falls in the original fundus image, defining the vertex of the parabola as the center of the optic disc.
Macular location based on appearance and structural features: according to the position relation between the macula lutea and the optic disc, firstly, the searching range of the fovea centralis is further narrowed on the basis of the determined optic disc center. In a preferred mode, because the distance between the fovea centralis of the macula and the center of the optic disc is generally 2 times to 3 times of the diameter of the optic disc, an annular mask is constructed by taking the center of the optic disc as the center of a circle and is defined as a fovea searching range; and then, in the search range area, positioning the fovea according to the characteristic that the brightness of the fovea is the lowest. In a preferred mode, a fast searching mode based on brightness contrast among the regions is adopted to determine the position of the fovea; and finally, according to the brightness information, taking the fovea centralis as the center of a circle and fitting the macular region in a circular manner.
The step of extracting and identifying the retinal feature data of the fundus image further comprises the steps of: extracting the optic disc center of the preprocessed fundus image, and determining the optic disc radius; determining the measurement area by positioning the optic disc, please refer to fig. 2; obtaining the retinal vessel change characteristic data by an automatic or semi-automatic interactive vessel diameter measurement method within the measurement region or outside the measurement region; the retinal vascular change characteristic data includes: localized retinal artery constriction, diffuse retinal artery constriction, arteriovenous cross compression, copper wire-like or silver wire-like change; and forming a quantitative index and identification of the retinal blood vessel change characteristic data structuralization.
The regional retinal artery constriction is respectively checked in a disc area (an area in a central circle of fig. 2), an area A (a blood vessel of the area is possibly closer to an artery in nature) and an area outside the area A (a blood vessel of the area is a small artery in nature), the diffuse retinal artery constriction is checked in 6 sections of arteries selected in the area B, and blood vessel changes such as arteriovenous cross compression signs, copper wire-like or silver wire-like changes and the like can be checked in all areas mainly outside the area B; and forming a structured quantitative index identification of the retinal vessel change characteristic data.
In other embodiments, the range of artery vessels and their portions involved in retinal vessel change features in the fundus image may be respectively identified by rectangles, different colors may represent different ranges of artery vessels and portions involved, such as pink for artery vessels involved, green for artery vessels involved, and then the fundus image may be aligned according to fundus parameters including: position of macula lutea, position of optic disc and main vessel information; and marking a changed area of the fundus image or the changed area of the retinal blood vessel change characteristic data by white.
The step of extracting and identifying the retinal feature data of the fundus image further comprises the steps of:
the mark of the relative position of the microangioma and the fovea maculata;
identification of the size of the bleeding spot and its relative position to the fovea centralis;
identification or analysis of the hard exudation range and its minimum distance from the fovea maculata;
identification of the extent of the lint spot and its relative position to the fovea centralis;
identification of localized retinal nerve fiber layer defects and disc edema levels;
and forming a structured quantitative index identification of the retina feature data through an automatic or semi-automatic interactive feature extraction method.
In this embodiment, the identification includes: and selecting the mark by frames or highlight display marks with different colors.
In other embodiments, the relevant retinal feature data in the fundus image may also be respectively identified in a rectangular manner: microangioma area, bleeding point area, hard effusion area (the size of these characteristic areas and the relative position to the fovea in the macula are recorded in the database at the same time), different colors may represent different DR characteristics and areas, e.g. white for hard effusion, pink for microangioma, green for bleeding point; the fundus images are then aligned according to fundus parameters including: position of macula lutea, position of optic disc and main vessel information; the fundus image change region is identified.
In this embodiment, the "analyzing and processing the quantization index structured with the retinal feature data" further includes:
analyzing and comparing the retinal blood vessel change characteristic data of the patient at different periods to obtain the change condition of the fundus characteristic data, and further analyzing and calculating to obtain the blood pressure control effect and the physical health condition of the hypertensive within a preset time period; in one embodiment, the Augmented Reality (AR) technology can be utilized to make simple demonstration animation on the change conditions of the characteristics of the eyeground and the conditions that the continuous development of the change conditions possibly affects the eyesight or the general health, and the simple demonstration animation is superposed on the real eyeground image picture to realize the visual education effect, so that the user can know the blood pressure control or treatment condition of the user in a near period of time, and the user can experience a deep education to stimulate the timely screening of the life style intervention basic treatment of the patient and the compliance or the consciousness of the timely prevention treatment; or corresponding health service suggestions are given by health service professionals or family doctors of the patients, and personalized services are customized for the patients.
In this embodiment, the "analyzing and processing the quantization index structured with the retinal feature data" further includes:
comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, evaluating and prognostically estimating the atherosclerosis and the damaged condition of target organs of the user, and giving related health insurance risk control, fee control and personalized health service suggestions, wherein the target organs comprise brain, heart, eyes and kidney.
In this embodiment, the "extracting and identifying the retinal feature data of the fundus image and forming the structured quantization index of the retinal feature data" further includes:
calculating the pixel dot matrix number of the distance from the fovea of the macula to the temporal side of the optic disc according to the circled optic disc and the macula; taking the pixel lattice number as a denominator parameter of a quantization index; and calculating to obtain the quantization index of the retina characteristic data structuralization. The following method can be specifically adopted:
obtaining the coordinates of each point on the edge of the temporal side of the optic disc and each pixel point and the gravity center or the center point of each pixel point in the area of the optic disc according to the central coordinates of the optic disc, the radius of the optic disc and the circled edge of the optic disc; calculating or obtaining the absolute distance between the temporal side of the optic disc and the center of the fovea centralis according to the connecting straight line of the center of gravity or the center point of the optic disc to the center point coordinate of the fovea centralis and the coordinate of the edge point of the temporal side of the optic disc on the straight line; and calculating to obtain a quantization parameter according to the absolute distance and the diameter of the optic disc. The method comprises the following specific steps:
a. automatically judging whether the fundus image is a fundus image of a left eye or a right eye according to the determined central coordinates of the optic disc and the central foveal coordinates of the macula lutea;
wherein, flag is a left-eye and right-eye flag, and taking 0 indicates the right eye, and taking 1 indicates the left eye.
b. Calculating the temporal coordinates (ODX, ODY) of the optic disc according to the central coordinates and the radius of the optic disc; calculating the absolute distance between the temporal side of the optic disc and the fovea maculata according to the coordinates of the temporal side of the optic disc and the central fovea maculata, and calculating the Euclidean distance between the temporal side of the optic disc and the central fovea maculata in the fundus image according to the following formula as the absolute distance between the center of the optic disc and the central fovea maculata in the image;
wherein, all coordinate values use the upper left pixel of the fundus image as an origin.
c. Since the pixel number of each person of the fovea centralis is generally approximately the same value from the temporal edge of the disc, the standard d of the subsequent quantitative analysis is obtained according to the obtained absolute distance from the temporal side of the disc to the fovea centralis and the disc diameter according to the following formula:
d-DMD-ODD equation 3
In the present embodiment, the obtained data is converted from an absolute representation to a relative representation using d as a scale, and meaningful, comparable data is formed by this normalization processing.
In the present embodiment, if a hard exudation is detected, the distance Di to the fovea of the macula is calculated for each hard exudation. At this time, normalization processing may be performed according to equation 1. On the basis of this, a standard minimum distance which is hard to exude to the fovea of the macula in the present fundus image is obtained.
As an application, the minimal distance from the hard exudation to the fovea maculata can be used for realizing comparison of two examinations in sequence and making a screening judgment result of macular edema.
In this embodiment, the analyzing and comparing the retinal feature data and the structured quantitative index of the retinal feature data of the user at different periods further includes:
aligning the fundus image according to fundus structure parameters, and correcting the identification of the retina characteristic data, wherein the fundus structure parameters comprise: the position of the fovea maculae, the position of the optic disc, and the main vessel information;
as an application example, a health insurance fee control method based on fundus images can analyze the related prevention and treatment effect conditions of blood pressure control, life style intervention treatment effect and the like of a patient in a near period according to the change condition of fundus screening characteristic data of a diabetic or hypertensive patient to obtain the evaluation data of the related blood pressure control condition and health condition.
In the present application example, the result of the retinal feature data processing analysis includes: whether the number or size of microangiomas is increased, whether the area of hard effusion is enlarged, whether the macular area is involved; and the auxiliary judgment is carried out on the basic treatment conditions of the living mode by referring to relevant necessary body index data accompanying the fundus images, such as whether the weight and the waist circumference are obviously increased or reduced, diet, exercise, no smoking and little drinking and the like; if the phenomena of increased microangiomas and enlarged hard exudation range exist, the blood sugar control level is poor in the period, the retinopathy still continues to develop, further control is needed, and good life style is guaranteed. The change conditions of the characteristics of the eyeground and the conditions that the continuous development of the change conditions possibly affects the vision or the general health can be made into simple demonstration animation by utilizing an Augmented Reality (AR) technology and superposed on a real eyeground picture to realize the visual education effect and stimulate the compliance or the consciousness of timely screening and timely preventing and treating the basic treatment of the life style intervention of a patient.
In addition, as a result of a number of population-based epidemiological studies showing the assessment of retinal vascular disease or abnormalities, including local retinal arterial constriction (FN) and retinopathy, including retinal hemorrhage, microaneurysms, hard exudation, lint patches, a good observation of studies relating to the onset and progression of hypertension is provided. In non-diabetic populations, hypertension has a strong correlation with the incidence and longitudinal changes of retinal microvascular abnormalities. The national guidelines for the prevention and treatment of hypertension and diabetes recommend that patients with hypertension and diabetes be screened periodically or at least by fundus photography every year, half a year or even 3 months. As one application or embodiment, the invention can utilize the fundus image obtained after fundus screening to extract and identify the structural parameters and retinal vessel change characteristic data of the fundus image, and analyze and compare the retinal vessel change characteristic data of the patient at different periods; and further acquiring the change condition of the fundus screening characteristic data of the patient, analyzing the related prevention and treatment effect conditions of the blood pressure control, the life style intervention treatment effect and the like of the patient in the near period, and acquiring the evaluation data of the related blood pressure control condition and the health condition.
As an embodiment, the "segmenting the retinal blood vessel network of the preprocessed fundus image" further includes the steps of: the fundus blood vessels of the fundus image are segmented through a significance model and a region optimization method to obtain a fundus blood vessel network, and the mobile veins are segmented according to the segmented fundus blood vessel network. The following may be used: the fundus blood vessels of the fundus image are segmented through a significance model and a region optimization method, and a fundus blood vessel network is obtained and the mobile veins are segmented. The method comprises the following specific steps:
step 1: color is the most important feature in analyzing the image significance, and meanwhile, the blood vessels contain texture features, and the texture can reflect the visual features in the image, and the algorithm adopts two significant features of color and texture.
Extracting texture features of the fundus image: the texture feature is a visual feature reflecting a homogeneity phenomenon in an image independent of color or brightness, and in the subject, a two-dimensional Gabor filter is used for extracting the texture feature in consideration of capturing a local structure corresponding to scale, spatial position and direction selectivity, and the position of the Gabor filter is determined by two parameters, namely direction and scale, so that the texture feature of the image can be expressed basically by setting the parameters. The Gabor filter function can be expressed as follows:
wherein the Fourier transform is derived from:
wherein:
w is the complex modulated frequency of the gaussian function. Usually, the directions of blood vessels are different, so the Gabor filtering must adopt different directions, six different directions of 0o, 30o, 60o, 90o, 120o and 150o are adopted in the text, the small scale can be used for detecting small blood vessels, the large scale can be used for detecting large blood vessels, and five different scales are adopted in the text for extracting blood vessel contours. After Gabor filter graphs in different directions and scales are obtained, image fusion is carried out on the Gabor filter graphs by adopting maximum response to obtain a Gabor transformation graph.
Extracting the color characteristics of the fundus image: the visual system is most sensitive to color and is easily noticeable if the target is a different color than the surrounding. Considering the global and local characteristics, for the color contrast characteristic at each pixel point, the ratio of the maximum rectangular neighborhood of the pixel point to the whole image area is defined to control the influence on the characteristic. The algorithm is represented as follows:
where U represents the maximum circumscribed rectangular neighborhood of 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 area of the entire image, and d can be adjusted according to the distance between the pixel (x, y) and the center of the image.
After the color features and texture features are extracted, they need to be fused. Considering that two different color spaces selected by people have six color channels, the two-dimensional information entropy is adopted as a standard for measuring the performance of the saliency map, and two groups of optimal color feature maps and texture feature maps are selected from the two-dimensional information entropy. For the fusion of the color features, a linear fusion method using the inverse of the information entropy as a weight coefficient is adopted. For the fusion of the texture features, a maximum fusion method is adopted. And finally, fusing the color contrast characteristic and the texture characteristic, and still adopting two-dimensional information entropy fusion.
Step 2: since the saliency image is a grayscale image, the grayscale range is limited, and in order to highlight the contrast intensity in the saliency image, region optimization is employed to enhance the contrast. This makes it possible to make the saliency value high higher and the saliency value low lower in the image. The optimization function is represented as follows:
k and delta are control factors, when the value of midval is more than or equal to 40 and less than or equal to 120, delta is a logarithmic function, and when the value of midval is more than 120 and less than or equal to 160, delta is an exponential function.
And step 3: and performing threshold segmentation on the saliency map by adopting a region-based one-dimensional histogram threshold method. The image used for the statistical histogram is selected based on the relationship of the original image and its neighborhood. The original image for the statistical histogram is represented as follows:
where f (m, n) denotes the original image, g (m, n) denotes its 5 × 5 neighborhood, and t1 is 40.
And 4, step 4: after threshold segmentation, part of tiny blood vessels are lost, and the algorithm adopts a morphological method for repairing.
In this embodiment, the step of "if the quantization index of the structured retinal feature data of the user in the previous period is stored, further analyzing and comparing the quantization index of the structured retinal feature data of the user in different periods to obtain the change condition thereof" further includes:
comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, the change condition and the change trend thereof, evaluating and prognostically estimating the atherosclerosis and the target organ damage condition of the user, and providing related health insurance risk control, fee control and personalized health service suggestions; the target organs include brain, heart, eye and kidney.
In this embodiment, the "analyzing the quantization index structured with the retinal feature data of the user at different time periods again" further includes:
aligning the fundus image according to fundus structure parameters, and correcting the identification of the retina characteristic data, wherein the fundus structure parameters comprise: the position of the fovea maculae, the position of the optic disc, and the main vessel information;
automatically analyzing changes in the structured quantitative indicators.
In this embodiment, if the target data to be analyzed is transmitted and stored according to the DICOM standard, private data may be fictionally constructed in the DICOM header file before transmission.
Referring to fig. 3, in this embodiment, a health insurance fee control system 300 based on fundus images is implemented as follows:
a system 300 for health insurance premiums based on fundus images, comprising: data acquisition terminal 301 and data interpretation analysis terminal 302, data acquisition terminal 301 includes: the data acquisition module 3011 and the data encryption module 3012, the data interpretation analysis terminal 302 includes: a data storage module 3021, a data decryption module 3022, a data processing module 3023, and a data analysis module 3024; the data acquisition module 3011 is configured to: target data to be analyzed, the target data to be analyzed comprising: private data and fundus images; the data encryption module 3012 is configured to: encrypting the target data to obtain an encrypted file to be analyzed, and sending the encrypted file to be analyzed to a data interpretation analysis terminal 302; the data storage module 3021 is configured to: receiving and storing the encrypted file to be analyzed; the data decryption module 3022 is configured to: decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: relevant necessary physical indicator data; the data processing module 3023 is configured to: preprocessing the fundus image; performing optic disc positioning and macular fovea positioning on the preprocessed fundus image; segmenting a retinal blood vessel network and a main blood vessel of the preprocessed fundus image; extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data; the data storage module 3021 is further configured to: storing the retina characteristic data and the structured quantitative indexes thereof; the data processing module 3023 is further configured to: judging whether a quantization index of the user's previous retina feature data structuralization is stored; the data analysis module 3024 is configured to: analyzing and processing the quantitative index of the retina characteristic data structuralization; if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, the quantization index of the retinal feature data structuralization of the user in different periods is analyzed and compared again to obtain the change condition of the user.
Further, the data analysis module 3024 is further configured to: comprehensively analyzing the related necessary body index data and the quantitative index of the retina characteristic data structuralization, evaluating and prognostically estimating the atherosclerosis of the user and the damaged condition of the target organ, and giving related health insurance control fee suggestions.
It should be noted that any of the steps mentioned in the above method steps can be executed one by one in the fee control system of the health insurance based on the fundus image, and a repeated description is not made herein.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. For example, a complete closed-loop quality assurance system can be further formed by positioning the optic disc and the macular fovea of the fundus image and analyzing the image definition, so that the fundus image finally obtained by the remote fundus screening and interpreting mechanism and relevant necessary body index information are fully available, the back-and-forth wave of a patient is avoided, and the user experience is enhanced; therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.
Claims (12)
1. A method for health insurance fee control based on fundus images, characterized by comprising the steps of:
the method comprises the following steps that a terminal mechanism obtains target data to be analyzed, wherein the target data comprises: private data and fundus images;
the terminal mechanism encrypts the target data to obtain an encrypted file to be analyzed, and sends the encrypted file to be analyzed to a remote eyeground screening and interpretation central mechanism;
the fundus screening interpretation central mechanism receives the encrypted file to be analyzed and stores the encrypted file to be analyzed;
decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: relevant necessary physical indicator data;
preprocessing the fundus image;
performing optic disc positioning and macular fovea positioning on the preprocessed fundus image;
segmenting a retinal blood vessel network and a main blood vessel of the preprocessed fundus image;
extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data;
storing the quantitative index of the retina characteristic data structuralization;
analyzing and processing the quantitative index of the retina characteristic data structuralization;
judging whether a quantization index of the user's early retina feature data structuralization is stored, if so, analyzing and comparing the quantization index of the user's early retina feature data structuralization to obtain the change condition of the quantization index;
and analyzing and processing the change condition.
2. A method of controlling health insurance premiums based on fundus images according to claim 1,
the step of preprocessing the fundus image; and performing optic disc positioning and macular fovea positioning on the preprocessed fundus image, and further comprising the following steps of:
the pretreatment comprises the following steps: green channel selection, median filtering, limited contrast enhancement and gray scale normalization processing;
extracting a binary vessel map from the preprocessed fundus image through an Otsu algorithm, and corroding the binary vessel map through a morphological method to obtain main vessel information;
carrying out parabolic fitting calculation on the main blood vessel, and positioning the center of the optic disc and delineating the edge of the optic disc according to the calculation result;
constructing a circle by taking the center of the optic disc as the circle center and the first preset radius value and the second preset radius value to form an annular area;
foveal macular location is performed within the annular region according to macular brightness characteristics.
3. A method of controlling health insurance premiums based on fundus images according to claim 1,
and if so, analyzing the quantitative indexes structured by comparing the retinal feature data of the user at different periods, and further comprising the following steps of:
aligning the fundus image according to fundus structure parameters, and correcting the identification of the retina characteristic data, wherein the fundus structure parameters comprise: the position of the fovea maculae, the position of the optic disc, and the main vessel information;
automatically analyzing changes in the structured quantitative indicators.
4. A method of controlling health insurance premiums based on fundus images according to claim 1,
the method for analyzing and processing the quantitative index of the retinal feature data structuralization further comprises the following steps:
comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, evaluating and prognostically estimating the atherosclerosis and the damaged condition of target organs of the user, and giving related health insurance risk control, fee control and personalized health service suggestions, wherein the target organs comprise brain, heart, eyes and kidney.
5. A method of controlling health insurance premiums based on fundus images according to claim 1,
if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, the quantization index of the retinal feature data structuralization of the user in different periods is analyzed and compared again to obtain the change condition, and the method further comprises the following steps:
comprehensively analyzing the related necessary body index data and the quantitative index structured by the retina characteristic data, the change condition and the change trend thereof, evaluating and prognostically estimating the atherosclerosis and the target organ damage condition of the user, and providing related health insurance risk control, fee control and personalized health service suggestions; the target organs include brain, heart, eye and kidney.
6. A method of controlling health insurance premiums based on fundus images according to claim 1,
the step of extracting and identifying the retinal feature data of the fundus image further comprises the steps of:
extracting the center of the optic disc according to the result of the optic disc positioning, and determining the radius of the optic disc;
determining a measurement area;
obtaining the identification of the retinal vessel change characteristic data and the quantitative index of the structure of the retinal vessel change characteristic data in the measuring region or outside the measuring region by an automatic or semi-automatic interactive vessel diameter measuring method; the retinal vascular change characteristic data includes: localized retinal artery constriction, diffuse retinal artery constriction, arteriovenous cross compression, copper wire-like or silver wire-like change;
and forming a quantitative index and identification of the retinal blood vessel change characteristic data structuralization.
7. A method of controlling health insurance premiums based on fundus images according to claim 1,
the step of extracting and identifying the retinal feature data of the fundus image further comprises the steps of:
the mark of the relative position of the microangioma and the fovea maculata;
identification of the size of the bleeding spot and its relative position to the fovea centralis;
identification or analysis of the hard exudation range and its minimum distance from the fovea maculata;
identification of the extent of the lint spot and its relative position to the fovea centralis;
identification of localized retinal nerve fiber layer defects and disc edema levels;
and forming the retinal feature data structured quantization index identification through an automatic or semi-automatic interactive feature extraction method.
8. A method for controlling health insurance premiums based on fundus images as claimed in claim 1, wherein said step of extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data further comprises the steps of:
calculating the pixel dot matrix number of the distance from the fovea of the macula to the temporal side of the optic disc according to the circled optic disc and the macula;
taking the pixel lattice number as a denominator parameter of a quantization index; and calculating to obtain the quantization index of the retina characteristic data structuralization.
9. A method of controlling health insurance premiums based on fundus images according to claim 1,
if the target data to be analyzed is transmitted and stored by using the DICOM standard, before transmission, private data can be fictionally constructed in a DICOM header file.
10. A method of controlling health insurance premiums based on fundus images according to claim 1,
the relevant necessary physical metric data comprises: the user unique ID number, height, weight, waist circumference, family genetic history, medication, blood glucose, blood pressure, vision, and lifestyle, the lifestyle including: one or more of exercise condition, diet condition, life habit and whether to smoke or drink.
11. A system for health insurance fee control based on fundus images, comprising: data acquisition terminal and data interpretation analysis terminal, data acquisition terminal includes: data acquisition module and data encryption module, data interpretation analysis terminal includes: the device comprises a data storage module, a data decryption module, a data processing module and a data analysis module;
the data acquisition module is used for: target data to be analyzed, the target data to be analyzed comprising: private data and fundus images;
the data encryption module is used for: encrypting the target data to obtain an encrypted file to be analyzed, and sending the encrypted file to be analyzed to a data interpretation analysis terminal;
the data storage module is used for: receiving and storing the encrypted file to be analyzed;
the data decryption module is used for: decrypting the encrypted file to be analyzed to obtain decrypted privacy data and an eyeground image, and extracting information to be analyzed from the privacy data, wherein the information to be analyzed comprises: relevant necessary physical indicator data;
the data processing module is used for: preprocessing the fundus image; performing optic disc positioning and macular fovea positioning on the preprocessed fundus image; segmenting a retinal blood vessel network and a main blood vessel of the preprocessed fundus image; extracting and identifying retinal feature data of the fundus image and forming a structured quantization index of the retinal feature data, wherein the structured quantization index of the retinal feature data comprises: retinal vascular change characteristic data and retinal characteristic data;
the data storage module is further configured to: storing the retina characteristic data and the structured quantitative indexes thereof;
the data processing module is further configured to: judging whether a quantization index of the user's previous retina feature data structuralization is stored;
the data analysis module is configured to: analyzing and processing the quantitative index of the retina characteristic data structuralization; if the quantization index of the retinal feature data structuralization of the user in the previous period is stored, the quantization index of the retinal feature data structuralization of the user in different periods is analyzed and compared again to obtain the change condition of the user.
12. A fundus image-based health insurance premiums system according to claim 11, wherein:
the data analysis module is further configured to: comprehensively analyzing the related necessary body index data and the quantitative index of the retina characteristic data structuralization, evaluating and prognostically estimating the atherosclerosis of the user and the damaged condition of the target organ, and giving related health insurance control fee suggestions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536492.0A CN111325631B (en) | 2018-12-14 | 2018-12-14 | Health insurance fee control method and system based on fundus images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536492.0A CN111325631B (en) | 2018-12-14 | 2018-12-14 | Health insurance fee control method and system based on fundus images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325631A true CN111325631A (en) | 2020-06-23 |
| CN111325631B CN111325631B (en) | 2022-06-24 |
Family
ID=71168775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811536492.0A Active CN111325631B (en) | 2018-12-14 | 2018-12-14 | Health insurance fee control method and system based on fundus images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325631B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114972462A (en) * | 2022-07-27 | 2022-08-30 | 北京鹰瞳科技发展股份有限公司 | Method for optimizing working distance alignment effect of fundus camera and related product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150104087A1 (en) * | 2013-10-10 | 2015-04-16 | University Of Rochester | Automated Fundus Image Field Detection and Quality Assessment |
| CN104657620A (en) * | 2015-03-09 | 2015-05-27 | 上海国通视光医疗科技发展有限公司 | Eye health cloud data platform based on Internet |
| CN105243669A (en) * | 2015-10-15 | 2016-01-13 | 四川和生视界医药技术开发有限公司 | Method for automatically identifying and distinguishing eye fundus images |
| CN107209933A (en) * | 2014-08-25 | 2017-09-26 | 新加坡科技研究局 | For assessing retinal images and the method and system of information being obtained from retinal images |
| CN208065172U (en) * | 2017-11-11 | 2018-11-09 | 深圳市前海安测信息技术有限公司 | Self-service health monitoring all-in-one machine with fundus camera |
-
2018
- 2018-12-14 CN CN201811536492.0A patent/CN111325631B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150104087A1 (en) * | 2013-10-10 | 2015-04-16 | University Of Rochester | Automated Fundus Image Field Detection and Quality Assessment |
| CN107209933A (en) * | 2014-08-25 | 2017-09-26 | 新加坡科技研究局 | For assessing retinal images and the method and system of information being obtained from retinal images |
| CN104657620A (en) * | 2015-03-09 | 2015-05-27 | 上海国通视光医疗科技发展有限公司 | Eye health cloud data platform based on Internet |
| CN105243669A (en) * | 2015-10-15 | 2016-01-13 | 四川和生视界医药技术开发有限公司 | Method for automatically identifying and distinguishing eye fundus images |
| CN208065172U (en) * | 2017-11-11 | 2018-11-09 | 深圳市前海安测信息技术有限公司 | Self-service health monitoring all-in-one machine with fundus camera |
Non-Patent Citations (1)
| Title |
|---|
| 龚滢欣等: "移动互联网医疗在眼科的应用现状及分析", 《转化医学电子杂志》, no. 05, 31 May 2018 (2018-05-31) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114972462A (en) * | 2022-07-27 | 2022-08-30 | 北京鹰瞳科技发展股份有限公司 | Method for optimizing working distance alignment effect of fundus camera and related product |
| CN114972462B (en) * | 2022-07-27 | 2023-08-15 | 北京鹰瞳科技发展股份有限公司 | Method for optimizing working distance alignment effect of eye bottom camera and related products thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325631B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222361B (en) | Method and system for analyzing characteristic data of change of blood vessel of retina in hypertension | |
| US9898659B2 (en) | System and method for remote medical diagnosis | |
| Sánchez et al. | Evaluation of a computer-aided diagnosis system for diabetic retinopathy screening on public data | |
| Trucco et al. | Validating retinal fundus image analysis algorithms: issues and a proposal | |
| US10441160B2 (en) | Method and system for classifying optic nerve head | |
| CN110875092B (en) | Health big data service method and system based on remote fundus screening | |
| Silva et al. | Peripheral lesions identified by mydriatic ultrawide field imaging: distribution and potential impact on diabetic retinopathy severity | |
| CN105426695B (en) | A kind of health status detecting system based on iris | |
| Abdel-Ghafar et al. | Progress towards automated detection and characterization of the optic disc in glaucoma and diabetic retinopathy | |
| Kauppi | Eye fundus image analysis for automatic detection of diabetic retinopathy | |
| Jan et al. | Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration | |
| Cleland et al. | Quantification of geographic atrophy using spectral domain OCT in age-related macular degeneration | |
| TWI719587B (en) | Pre-processing method and storage device for quantitative analysis of fundus image | |
| WO2022129591A1 (en) | System for determining one or more characteristics of a user based on an image of their eye using an ar/vr headset | |
| CN111383775B (en) | Member user anonymous communication method based on fundus screening and storage device | |
| CN111402184B (en) | Method and system for realizing remote fundus screening and health service | |
| CN111292286B (en) | Analysis method and system for change of characteristic data of sugar mesh bottom and storage device | |
| CN111325631B (en) | Health insurance fee control method and system based on fundus images | |
| CN111435612B (en) | Method and system for personalized health service of mobile medical treatment | |
| Escorcia-Gutierrez et al. | A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images | |
| Kaur et al. | Construction of benchmark retinal image database for diabetic retinopathy analysis | |
| Kandamkumarath et al. | Quantitative Analysis of Retinal Vasculature for Eye Disease Identification Using Deep Learning | |
| KR102466792B1 (en) | Artificial intelligence based macular degeneration disease deterioration prediction devices and methods | |
| Kalkonde | Diagnosis of Diabetic Retinopathy Using Wavelet Based Contourlet Transform and k-NN Algorithm | |
| Kapsala et al. | Assessment of a Novel Semi-Automated Algorithm for the Quantification of the Parafoveal Capillary Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |