WO2020103288A1 - Procédé et système d'analyse pour changement de données de caractéristiques d'un fond d'œil à rétinopathie diabétique, et dispositif de mémoire - Google Patents

Procédé et système d'analyse pour changement de données de caractéristiques d'un fond d'œil à rétinopathie diabétique, et dispositif de mémoire

Info

Publication number
WO2020103288A1
WO2020103288A1 PCT/CN2018/124487 CN2018124487W WO2020103288A1 WO 2020103288 A1 WO2020103288 A1 WO 2020103288A1 CN 2018124487 W CN2018124487 W CN 2018124487W WO 2020103288 A1 WO2020103288 A1 WO 2020103288A1
Authority
WO
WIPO (PCT)
Prior art keywords
fundus image
fundus
sugar
feature data
patient
Prior art date
Application number
PCT/CN2018/124487
Other languages
English (en)
Chinese (zh)
Inventor
余轮
曹新容
王丽钠
林嘉雯
Original Assignee
福州依影健康科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 福州依影健康科技有限公司 filed Critical 福州依影健康科技有限公司
Priority to GB2104798.0A priority Critical patent/GB2593824A/en
Publication of WO2020103288A1 publication Critical patent/WO2020103288A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • 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
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
    • 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
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20036—Morphological image processing
    • 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
    • G06T2207/30096—Tumor; Lesion
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the invention relates to the field of fundus image processing, in particular to a method and system for analyzing changes in characteristic data of a sugar net fundus, and a storage device.
  • Diabetic retinopathy (sugar reticulum) is one of the main complications of diabetes and the leading cause of irreversible blindness in working-age people. As the course of diabetes grows, the risk of sugar webs continues to increase, which may eventually lead to irreversible blindness.
  • the retinopathy characteristics obtained after annual fundus screening can be compared and analyzed through the comparison and analysis of the annual changes in sugar reticulum data to further evaluate patients with diabetic retinopathy
  • Changes in fundus conditions can be used to obtain evaluation data on the effects of prevention and treatment, including the damage of diabetes to the eyes, the overall level of blood sugar control and the treatment effect over a period of time, in order to enhance the compliance of basic treatments for diabetes patients with lifestyle interventions, Provide a deterrent "incentive" mechanism!
  • the fundus is the only part of the human body where blood vessels and nerves can be directly observed without surgery. Fundus photography allows us to obtain personalized health medical information under precision medicine; if we can screen the data of diabetic patients every time fundus screening By implementing structured feature data processing, storage and follow-up, it is possible to achieve comparison and analysis of changes in fundus images and related body index feature data acquired in different periods, combined with interrogation data, in order to achieve the health of diabetic patients Management or health big data service, provide a new method! .
  • a method for analyzing the changes of the fundus characteristic data of the sugar mesh including the steps of: obtaining the fundus image of the sugar mesh patient; extracting and identifying the feature data of the fundus image; storing the feature data of the fundus image; determining whether the sugar mesh is stored
  • the fundus image feature data of the early stage of the patient if the fundus image feature data of the early stage of the sugar mesh patient is stored, analyze and compare the fundus image feature data of the sugar mesh patient at different periods to obtain the fundus sieve of the sugar mesh patient Check the change of the characteristic data; analyze and process the change of the fundus screening characteristic data.
  • the "then analyze and compare the fundus image feature data of the sugar net patient at different periods to obtain the changes of the fundus screening feature data of the sugar net patient at this time” further includes the step of: establishing a brightness histogram equalization Pre-process the fundus image; establish a morphological filter to determine the position of the macula and optic disc in the pre-processed fundus image; segment the main vessels of the pre-processed fundus image; align the fundus image according to the fundus structure parameters and correct the characteristics of the fundus image
  • the fundus structure parameters include: the position of the macula, the position of the optic disc, and the information of the main blood vessel; and automatically analyze the changes of the feature data of the fundus image.
  • analyzing and processing the changes in the fundus screening characteristic data further includes the steps of: analyzing and calculating the sugar control effect and physical health status of the sugar net patient within a preset time period; and according to the analysis results Corresponding health service recommendations; generate a report of the sugar control effect, physical health status, and health service recommendations, and send the report-related information to the mobile terminal device of the sugar net patient.
  • the "identifying the feature data of the fundus image” further includes the steps of: identifying the microhemangioma and its relative position to the fovea; identifying the size of the bleeding spot and its relative position to the fovea; identifying and analyzing the rigidity The extent of exudation and its minimum distance from the fovea of the macula.
  • a storage device in which an instruction set is stored, the instruction set is used to perform: acquiring a fundus image of a sugar net patient; extracting and identifying feature data of the fundus image; storing the feature data of the fundus image; judging whether to store There is the fundus image feature data of the early stage of the sugar net patient, if the fundus image feature data of the early stage of the sugar net patient is stored, the fundus image feature data of the sugar net patient at different periods are analyzed and compared to obtain the sugar net patient The changes of the fundus screening characteristic data at this time; analyzing and processing the changes of the fundus screening characteristic data.
  • the instruction set is also used to execute: "then analyze and compare the fundus image feature data of the sugar net patient at different periods to obtain the changes of the fundus screening feature data of the sugar net patient at this time", It also includes the steps of: establishing a brightness histogram equalization to preprocess the fundus image; establishing a morphological filter to determine the position of the macula and optic disc in the preprocessed fundus image; segmenting the main blood vessels of the preprocessed fundus image; aligning according to the fundus structure parameters The fundus image corrects the identification of the feature data of the fundus image.
  • the fundus structure parameters include: the position of the macula, the position of the optic disc, and the information of the main blood vessel; and automatically analyze the changes of the feature data of the fundus image.
  • the instruction set is also used to execute: "analyze and analyze the changes in the fundus screening characteristic data", and further includes the steps of: analyzing and calculating the sugar control effect within a preset time period of the sugar net patient and Physical health status; and give corresponding health service recommendations based on the analysis results; generate reports on the sugar control effect, physical health status, and health service recommendations, and send the report-related information to the mobile patients of the sugar net Terminal Equipment.
  • the instruction set is also used to execute: "Identify the characteristic data of the fundus image", further comprising the steps of: identifying microhemangioma and its relative position to the fovea; identifying the size of the bleeding spot and its center The relative position of the fovea; identify and analyze the range of hard exudation and its minimum distance from the fovea of the macula.
  • a sugar net fundus characteristic data change analysis system including: a fundus image acquisition terminal and a fundus image processing terminal, the fundus image processing terminal includes: a data storage module, a fundus image analysis comparison module and a result analysis module;
  • the fundus An image acquisition terminal is connected to the fundus image processing terminal;
  • the fundus image acquisition terminal is used to: acquire a fundus image of a sugar net patient and send the fundus image to the fundus image processing terminal;
  • the fundus image processing terminal is used to: extract and Identify the fundus image feature data;
  • the data storage module is used to store the fundus image feature data, and the fundus image analysis and comparison module is used to determine whether the fundus image feature of the early stage of the sugar net patient is stored Data, if the fundus image feature data of the early stage of the sugar mesh patient is stored, analyze and compare the fundus image feature data of the sugar mesh patient at different periods, and obtain the changes of the fundus image feature data of the sugar mesh patient at this screening Situation;
  • the result analysis module is used to
  • the fundus image analysis and comparison module is also used to: establish a brightness histogram equalization to preprocess the fundus image; establish a morphological filter to determine the position of the macula and optic disc in the preprocessed fundus image; segment the preprocessed The main blood vessel of the fundus image; align the fundus image according to the fundus structure parameters and correct the identification of the feature data of the fundus image.
  • the fundus structure parameters include: the position of the macula, the position of the optic disc and the information of the main blood vessel; automatically analyze the features of the fundus image Data changes; the fundus image processing terminal is also used to: identify microhemangioma and its relative position to the macular fovea; identify the size of the bleeding spot and its relative position to the macular fovea; identify and analyze the range of rigid exudation and its The minimum distance from the fovea.
  • the beneficial effects of the present invention are: by automatically acquiring fundus images of patients in different periods of the sugar net, storing the fundus image and the structured processed fundus image feature data; by automatically analyzing and comparing the fundus image feature data of different periods, Obtain the changes in the characteristics of the fundus image of the patient in the sugar mesh; analyze and process the changes in the characteristics of the fundus image of the patient in the sugar mesh.
  • sugar-net patients can collect their own fundus images at any place where the fundus image acquisition device is installed, and then upload the corresponding fundus images to the fundus image processing terminal, which will store the fundus images , And automatically compare and analyze the changes of fundus image feature data acquired in different periods.
  • diabetic retinopathy is one of the major serious complications of diabetic patients, it is also the leading blinding eye disease in China. If patients do not take basic interventions of lifestyle intervention and other effective blood sugar control measures, their condition must continue to develop, It's getting worse! Therefore, observing the relevant conditions of fundus retinopathy, under certain circumstances, you can get diabetes prevention, treatment effect evaluation data, diabetes damage to the eye and even systemic vascular changes, including the overall level and effect of blood sugar control over time , Combined with the changes in fundus image feature data, professional health managers can also combine sugar net patients' recent sugar control effects and physical health analysis; give relevant health services or suggestions for the prevention of major complications of diabetes, To achieve the effect of curing the disease.
  • the sugar net patient can go to any place where the image acquisition terminal is set, collect and upload his own fundus image at this moment to the fundus image processing terminal, the fundus image processing terminal automatically reads the fundus image of the sugar net patient at different periods before this, and It is analyzed and processed, the whole process is high in efficiency, the cost of charging is low, and the experience of the sugar net patient is good, and the data after analysis and processing can be sent to the sugar net patient himself, so that the sugar net patient has the development of their eyes and fundus retinopathy Understand; the above analysis report and health service suggestions implemented by this system can even continuously improve the net patients' own understanding of their systemic health and the effect of sugar control therapy, enhance the consciousness of lifestyle intervention, and achieve personalized health Big data service!
  • FIG. 1 is a flowchart of a method for analyzing changes in characteristic data of a sugar mesh fundus according to a specific embodiment
  • FIG. 2 is a block diagram of a storage device according to a specific embodiment
  • FIG. 3 is a schematic diagram of an analysis system of the change of characteristic data of a sugar net fundus according to the specific embodiment.
  • Terminal for acquiring fundus image Terminal for acquiring fundus image
  • a method for analyzing changes in characteristic data of a sugar net fundus can be applied to a storage device, which includes but is not limited to: a personal computer, a server, a general-purpose computer, and a dedicated computer , Network equipment, intelligent mobile terminals, etc.
  • a general-purpose computer is taken as an example.
  • the general-purpose computer is installed with a fundus screening feature data change analysis system or a remote fundus image data analysis center, or a browser is provided, which can open a webpage through the browser to log in related Fundus image data analysis center of cloud health service system.
  • a specific implementation method of a method for analyzing changes in the characteristic data of the fundus fundus is as follows:
  • Step S101 Acquire a fundus image of a sugar net patient.
  • the fundus camera of the sugar net patient is obtained through the fundus camera of the grassroots application institution (such as a grassroots medical institution, health examination, health management or grassroots community clinic), and the obtained fundus image is transmitted to the PC through the data line
  • the upper part is processed by the fundus image data analysis workstation software, or sent to the PC through the network, and the PC is sent to the fundus image data analysis center; sugar net patients can also upload the fundus image through the mobile terminal device.
  • the grassroots application institutions may be those remote areas where there is no professional ophthalmologist staff, or where the cost of staffing professional ophthalmologists is very high.
  • step S102 extracting and identifying the fundus image feature data, and storing the fundus image feature data.
  • the following methods can be adopted: through automatic or semi-automatic human-computer interactive methods, the DR microhemangioma, bleeding spot, and rigid exudative fundus image feature data are extracted and stored, wherein the fundus image and fundus image feature data can be stored to
  • the cloud server can also store the fundus image and the fundus image feature data to a specific server, and can also store the fundus image and the fundus image feature data to a local storage device.
  • the purpose of storing the fundus image and the fundus image feature data is to facilitate the same sugar net patient to come over for inspection or screening every time, and compare the currently collected data with the previously collected data, which is better Data analysis.
  • step S103 After storing the fundus image feature data, step S103 is performed: it is judged whether the sugar net patient's previous fundus image feature data is stored, and if the sugar net patient's early fundus image feature data is stored, the analysis and comparison The fundus image feature data of the sugar net patient in different periods is obtained, and the changes of the fundus screening feature data of the sugar net patient at this time are acquired.
  • the following methods can be used: according to the patient's name and ID card to query the database, whether the early stage fundus image and fundus image feature data of the sugar mesh patient are stored, if the early stage fundus image and fundus image feature data of the sugar mesh patient are stored , Then analyze and compare the fundus image and fundus image feature data in different periods of the sugar net patients to obtain the changes of fundus screening feature data. details as follows:
  • the fundus image corrects the identification of the feature data of the fundus image.
  • the fundus structure parameters include: the position of the macula, the position of the optic disc, and the information of the main blood vessel; and automatically analyze the changes of the feature data of the fundus image.
  • the "identifying the fundus image feature data” further includes the steps of: identifying microhemangioma and its relative position to the macular fovea; identifying the size of the bleeding spot and its relative position to the macular fovea; identifying and analyzing hard exudation The range and the minimum distance from the fovea.
  • a fundus image with a clear image and a clear observation of the optic disc, macular, and blood vessels in the image to be analyzed is used as a standard reference image, and the standard image is processed to generate a standard grayscale histogram;
  • the grayscale distribution of the standard grayscale histogram maps the grayscale of the rest of the fundus image to be analyzed to obtain a fundus image with the same grayscale distribution as the standard reference image.
  • a morphological filter is established to determine the position of the macula and optic disc. That is: after preprocessing, the macula has extremely low brightness, the optic disc has extremely high brightness, the shape of the two tends to be round, and the relative distance and position of the two are fixed. In this way, the morphological filter is implemented to detect the The circular area with extremely low brightness and extremely high brightness is used as a candidate area for the macula and the optic disc, and the wrong candidate area is filtered according to the distance and position of the two, and then the central positions of the macula and the optic disc are determined.
  • the preprocessed fundus image, the main vessels of the fundus have similar grayscale information, and have a high contrast with the background, the main vessels can be segmented by the above features.
  • the main blood vessel can be segmented by using a threshold segmentation method. After segmenting the main blood vessel, according to the position of the macula, the position of the optic disc, and the information of the main blood vessel, identify the change area of the fundus image for the fundus image. By changing the area, you can quickly see whether the number of microhemangiomas, bleeding points, or rigid exudation has increased, and whether the range of rigid exudation has expanded or further approached the macular condition.
  • the characteristic data of the fundus image in the fundus image can also be identified by rectangles: microhemangioma area, bleeding area, and hard exudation area (at the same time, the size of these characteristic areas and the macular area are recorded in the database
  • the relative position of the fovea) can represent different DR features and regions, such as white for hard exudation, pink for microhemangioma, and green for bleeding points; then align the fundus image according to fundus parameters, which include: macular The position of the optic disc, the position of the optic disc and the information of the main blood vessel; identify the area of the fundus image change.
  • Step S104 Analyze and process the changes in the fundus screening feature data.
  • the following methods may be used: analysis and calculation of the sugar control effect and physical health status of the sugar net patient within a preset time period; and giving corresponding health service suggestions according to the analysis results; generating the sugar control effect, physical health status and The report of the health service recommendation, and send the report-related information to the mobile terminal device of the sugar net patient.
  • the obtained data can be sent directly to the sugar net patient, so that the sugar net patient can better understand their own health status, and can also be sent to professional medical staff with the consent of the sugar net patient. Institutions, assist medical personnel to quickly have an understanding of the conditions of sugar net patients, and provide follow-up disease control recommendations for sugar net patients.
  • the results of data processing and analysis include: whether the number or size of microhemangioma increases, whether the area of rigid exudation expands, and whether the macular area is involved; if there are conditions, you can refer to the basic application organization to accompany the fundus image.
  • Related physical examination data such as relevant medical consultation data, such as whether there is a significant increase or decrease in weight and waist circumference, diet, exercise, non-smoking and drinking less, etc., to assist in the assessment of basic lifestyle treatment; if there is an increase in the number of microhemangioma, rigid exudation
  • the phenomenon of the expansion of the range indicates that the blood glucose control level is poor during this period, and the condition of retinopathy continues to develop, and further control is needed to ensure a good lifestyle; if there is a significant increase in the number of microhemangioma or bleeding spots, the area of hard exudation Expanding and affecting the macular area, it is recommended to conduct further follow-up visits and treatment; if there is no obvious change in microhemangioma and rigid exudation, it means that the level of control is good, and you should continue to maintain a good lifestyle and continue treatment as directed by your doctor; in particular, when the number of hemangioma Decrease or disappearance of some hemangioma
  • sugar-net patients can collect their own fundus images at any place where the fundus image acquisition device is installed, and then upload the corresponding fundus images to the fundus image processing terminal, which will store the fundus images , And automatically analyze and compare the fundus images of the patients with the sugar mesh in different periods to obtain the changes in the features of the fundus image, and analyze and process the changes in the features of the fundus images of the sugar mesh patient.
  • the processing process has high efficiency, low cost, and a good experience for sugar net patients, and the data after analysis and processing can be sent to the sugar net patients themselves, so that the sugar net patients can understand their own fundus health, or professional medical staff can let medical staff According to the analysis results, give the sugar net patients better treatment suggestions, etc.
  • the method further includes the steps of generating an analysis report and sending information related to the analysis report to the mobile terminal device of the sugar net patient.
  • the analysis report related information includes: one of the analysis report, the analysis report download link, and the recommendation report One or more.
  • a specific implementation of a storage device 200 is as follows:
  • a storage device 200 in which an instruction set is stored, the instruction set is used to perform: acquiring a fundus image of a sugar net patient; extracting and identifying feature data of the fundus image; storing the feature data of the fundus image; judging whether or not Store the fundus image feature data of the early stage of the sugar net patient, and if store the fundus image feature data of the early stage of the sugar net patient, analyze and compare the fundus image feature data of the sugar net patient at different periods to obtain the sugar net
  • the following methods can be used:
  • the fundus image of the sugar net patient through the fundus camera of the basic application institution (such as: primary medical institution, health checkup, health management or basic community clinic), and transfer the obtained fundus image to the PC through the data line to the fundus image data
  • the analysis workstation software is used for processing, or sent to the PC through the network, and the PC sends it to the fundus image data analysis center; sugar net patients can also upload the fundus image through the mobile terminal device.
  • the community application institutions may be those remote areas where there is no professional ophthalmologist staff, or where the cost of staffing professional ophthalmologists is very high.
  • the fundus image data analysis center or the above-mentioned fundus image data analysis workstation software acquires the fundus image of the sugar net patient, the fundus image feature data is extracted and identified, and the fundus image feature data is stored.
  • the following methods can be adopted: through automatic or semi-automatic human-computer interactive methods, the DR microhemangioma, bleeding spot, and rigid exudative fundus image feature data are extracted and stored, wherein the fundus image and fundus image feature data can be stored to
  • the cloud server can also store the fundus image and the fundus image feature data to a specific server, and can also store the fundus image and the fundus image feature data to a local storage device.
  • the purpose of storing the fundus image and the fundus image feature data is to facilitate the same sugar net patient to come over for inspection or screening every time, and compare the currently collected data with the previously collected data, which is better Data analysis.
  • the fundus image feature data After storing the fundus image feature data, determine whether the early stage fundus image feature data of the sugar mesh patient is stored, and if the feature fundus image feature data of the early stage of the sugar mesh patient are stored, analyze and compare the sugar mesh patient The fundus image feature data in different periods, to obtain the changes of the fundus screening feature data of the sugar net patient at this time.
  • the following methods can be used: according to the patient's name and ID card to query the database, whether the early stage fundus image and the fundus image feature data of the sugar net patient are stored, if the early stage fundus image and the fundus image of the sugar net patient are stored
  • For feature data analyze and compare the fundus image and the fundus image feature data of the patients in different periods of the sugar net to obtain the changes of fundus screening feature data. details as follows:
  • the fundus image corrects the identification of the feature data of the fundus image.
  • the fundus structure parameters include: the position of the macula, the position of the optic disc, and the information of the main blood vessel; and automatically analyze the changes of the feature data of the fundus image.
  • the "identifying the fundus image feature data” further includes the steps of: identifying microhemangioma and its relative position to the macular fovea; identifying the size of the bleeding spot and its relative position to the macular fovea; identifying and analyzing hard exudation The range and the minimum distance from the fovea.
  • a fundus image with a clear image and a clear observation of the optic disc, macular, and blood vessels in the image to be analyzed is used as a standard reference image, and the standard image is processed to generate a standard grayscale histogram;
  • the grayscale distribution of the standard grayscale histogram maps the grayscale of the rest of the fundus image to be analyzed to obtain a fundus image with the same grayscale distribution as the standard reference image.
  • a morphological filter is established to determine the position of the macula and optic disc. That is: after preprocessing, the macula has extremely low brightness, the optic disc has extremely high brightness, the shape of the two tends to be round, and the relative distance and position of the two are fixed. In this way, the morphological filter is implemented to detect the The circular area with extremely low brightness and extremely high brightness is used as a candidate area for the macula and the optic disc, and the wrong candidate area is filtered according to the distance and position of the two, and then the central positions of the macula and the optic disc are determined.
  • the preprocessed fundus image, the main vessels of the fundus have similar grayscale information, and have a high contrast with the background, the main vessels can be segmented by the above features.
  • the main blood vessel can be segmented by using a threshold segmentation method. After the main blood vessel is segmented, according to the position of the macula, the position of the optic disc, and the information of the main blood vessel, the change area of the fundus image is identified for the fundus image. By changing the area, you can quickly see whether the number of microhemangiomas, bleeding points, or rigid exudation has increased, and whether the range of rigid exudation has expanded or further approached the macular condition.
  • the characteristic data of the fundus image in the fundus image can also be identified by rectangles: microhemangioma area, bleeding area, and hard exudation area (at the same time, the size of these characteristic areas and the macular area are recorded in the database
  • the relative position of the fovea) can represent different DR features and regions, such as white for hard exudation, pink for microhemangioma, and green for bleeding points; then align the fundus image according to fundus parameters, which include: macular The position of the optic disc, the position of the optic disc and the information of the main blood vessel; identify the area of the fundus image change.
  • Analyze and process the changes in the fundus screening characteristic data The following methods may be used: analysis and calculation of the sugar control effect and physical health status of the sugar net patient within a preset time period; and giving corresponding health service suggestions according to the analysis results; generating the sugar control effect, physical health status and The report of the health service recommendation, and send the report-related information to the mobile terminal device of the sugar net patient.
  • the obtained data can be sent directly to the sugar net patient, so that the sugar net patient can better understand their own health status, and can also be sent to professional medical staff with the consent of the sugar net patient. Institutions, assist medical personnel to quickly have an understanding of the conditions of sugar net patients, and provide follow-up disease control recommendations for sugar net patients.
  • the results of data processing and analysis include: whether the number or size of microhemangioma increases, whether the area of rigid exudation expands, and whether the macular area is involved; if there are conditions, you can refer to the basic application organization to accompany the fundus image.
  • Related physical examination data such as relevant medical consultation data, such as whether there is a significant increase or decrease in weight and waist circumference, diet, exercise, non-smoking and drinking less, etc., to assist in the assessment of basic lifestyle treatment; if there is an increase in the number of microhemangioma, rigid exudation
  • the phenomenon of the expansion of the range indicates that the blood glucose control level is poor during this period, and the condition of retinopathy continues to develop, and further control is needed to ensure a good lifestyle; if there is a significant increase in the number of microhemangioma or bleeding spots, the area of hard exudation Expanding and affecting the macular area, it is recommended to conduct further follow-up visits and treatment; if there is no obvious change in microhemangioma and rigid exudation, it means that the level of control is good, and you should continue to maintain a good lifestyle and continue treatment as directed by your doctor; in particular, when the number of hemangioma Decrease or disappearance of some hemangioma
  • Steps are executed through the instruction set on the storage device 200: by acquiring fundus images of the patients with the sugar net at different periods, storing the fundus images and their structured processed fundus image feature data; by automatically analyzing and comparing the different periods
  • the fundus feature image is used to obtain the changes of the fundus image feature of the sugar net patient; the feature change of the fundus image feature of the sugar net patient is analyzed and processed.
  • sugar-net patients can collect their own fundus images at any place where the fundus image acquisition device is installed, and then upload the corresponding fundus images to the fundus image processing terminal, which will store the fundus images , And automatically analyze and compare the fundus images of the patients with the sugar mesh in different periods to obtain the changes in the features of the fundus image, and analyze and process the changes in the features of the fundus images of the sugar mesh patient.
  • the processing process has high efficiency, low cost, and a good experience for sugar net patients, and the data after analysis and processing can be sent to the sugar net patients themselves, so that the sugar net patients can understand their own fundus health, or professional medical staff can let medical staff According to the analysis results, give the sugar net patients better treatment suggestions, etc.
  • the method further includes the steps of generating an analysis report and sending information related to the analysis report to the mobile terminal device of the sugar net patient.
  • the analysis report related information includes: one of the analysis report, the analysis report download link, and the recommendation report One or more.
  • an analysis system 300 for the change of the characteristic data of the fundus fundus is as follows:
  • a sugar net fundus characteristic data change analysis system 300 includes: a fundus image acquisition terminal 301 and a fundus image processing terminal 302, the fundus image processing terminal 302 includes: a data storage module 3021, a fundus image analysis and comparison module 3022, and a result Analysis module 3023; the fundus image acquisition terminal 301 is connected to the fundus image processing terminal 302; the fundus image acquisition terminal 301 is used to: acquire a fundus image of a sugar net patient and send the fundus image to the fundus image processing terminal 302; The fundus image processing terminal 302 is used to: extract and identify the fundus image feature data; the data storage module 3021 is used to: store the fundus image feature data; the fundus image analysis comparison module 3022 is used to : Determine whether the fundus image feature data of the early stage of the sugar net patient is stored.
  • the fundus image feature data of the early stage of the sugar net patient is stored, analyze and compare the fundus image feature data of the sugar net patient at different periods to obtain The changes of the characteristic data of the fundus image of the sugar net patient during the screening; the result analysis module 3023 is used for analyzing and processing the changes of the characteristic data of the fundus screening.
  • the fundus image acquisition terminal 301 includes: a fundus image acquisition terminal and a PC, the fundus image acquisition terminal is preferably a fundus camera, and the fundus image processing terminal 302 includes but is not limited to: a personal computer, a server, a general-purpose computer, a dedicated Computers, network equipment, smart mobile terminals, smart home equipment, etc.
  • the fundus image of the sugar net patient can be obtained by the fundus camera, and the obtained fundus image can be transmitted to the PC through the data line for processing by the fundus image data analysis workstation software, or sent to the PC through the network, and the PC can send the fundus image Data analysis center; sugar net patients can also upload fundus images through mobile terminal devices.
  • the grassroots application institutions may be those remote areas where there is no professional ophthalmologist staff, or where the cost of staffing professional ophthalmologists is very high.
  • the data storage module 3021 inquires whether the early stage fundus image and the fundus image feature data of the sugar net patient are stored. If the early stage fundus image and the fundus image feature data of the sugar net patient are stored, The fundus image analysis and comparison module 3022 analyzes and compares the fundus image feature data in different periods of the sugar net patient to obtain the changes in the fundus image feature of the sugar net patient.
  • the fundus image analysis and comparison module 3022 is also used to: establish a brightness histogram equalization to preprocess the fundus image; establish a morphological filter to determine the position of the macula and optic disc in the preprocessed fundus image; segmentation The main vessels of the pre-treated fundus image; align the fundus image according to the fundus structure parameters and correct the identification of the feature data of the fundus image.
  • the fundus structure parameters include: the position of the macula, the position of the optic disc and the information of the main vessel; The characteristic data of the fundus image changes. The following methods can be used:
  • a morphological filter is established to determine the position of the macula and optic disc. That is: after preprocessing, the macula has extremely low brightness, the optic disc has extremely high brightness, the shape of the two tends to be round, and the relative distance and position of the two are fixed. In this way, the morphological filter is implemented to detect the The circular area with extremely low brightness and extremely high brightness is used as a candidate area for the macula and the optic disc, and the wrong candidate area is filtered according to the distance and position of the two, and then the central positions of the macula and the optic disc are determined.
  • the main blood vessels of the fundus have similar gray-scale information and a high contrast with the background.
  • the main blood vessels can be segmented by the above features.
  • the main blood vessel can be segmented by using a threshold segmentation method. After the main blood vessel is segmented, according to the position of the macula, the position of the optic disc, and the information of the main blood vessel, the change area of the fundus image is identified for the fundus image. By changing the area, you can quickly see whether the number of microhemangiomas, bleeding points, or rigid exudation has increased, and whether the range of rigid exudation has expanded or further approached the macular condition.
  • the characteristic data of the fundus image in the fundus image can also be identified by rectangles: microhemangioma area, bleeding area, and hard exudation area (at the same time, the size of these characteristic areas and the macular area are recorded in the database
  • the relative position of the fovea) can represent different DR features and regions, such as white for hard exudation, pink for microhemangioma, and green for bleeding points; then align the fundus image according to fundus parameters, which include: macular The position of the optic disc, the position of the optic disc and the information of the main blood vessel; identify the area of the fundus image change.
  • the result analysis module 3023 is also used to:
  • the obtained data can be sent directly to the sugar net patient, so that the sugar net patient can better understand their own health status, and can also be sent to a professional medical institution with the consent of the sugar net patient to assist medical care.
  • the staff quickly had an understanding of the conditions of the patients with sugar reticulum, and provided follow-up disease control recommendations for patients with sugar reticulum.
  • the results of data processing and analysis include: whether the number or size of microhemangioma increases, whether the area of rigid exudation expands, and whether the macular area is involved; if there are conditions, you can refer to the basic application organization to accompany the fundus image.
  • Related physical examination data such as relevant medical consultation data, such as whether there is a significant increase or decrease in weight and waist circumference, diet, exercise, non-smoking and drinking less, etc., to assist in the evaluation of basic lifestyle treatment; if there are increased numbers of microhemangioma, rigid exudation
  • the phenomenon of the expansion of the range indicates that the blood glucose control level is poor during this period, and the condition of retinopathy continues to develop, and further control is needed to ensure a good lifestyle; if there is a significant increase in the number of microhemangioma or bleeding spots, the area of hard exudation Expanding and affecting the macular area, it is recommended to conduct further follow-up visits and treatment; if there is no obvious change in microhemangioma and rigid exudation, it means that the level of control is good, and you should continue to maintain a good lifestyle and continue treatment as directed by your doctor; in particular, when the number of hemangioma Decrease or disappearance of some hemangioma means that the
  • the fundus image acquisition terminal 301 automatically acquires the fundus images of the patients of the sugar net at different periods, and the data storage module 3021 stores the fundus images; the fundus image analysis and comparison module 3022 automatically analyzes and compares the fundus images of different periods to obtain sugar Changes in the characteristics of the fundus image of the net patient; the result analysis module 3023 analyzes and processes the changes in the characteristics of the fundus image of the sugar net patient.
  • sugar-net patients can collect their own fundus images at any place where the fundus image acquisition device is installed, upload them to the fundus image processing terminal 302, and the fundus image processing terminal 302 will store the fundus images and automatically Analyze and compare the fundus images of the patients with the sugar mesh in different periods, obtain the changes of the fundus image features, and analyze and process the changes of the features of the fundus images of the sugar mesh patient.
  • the sugar net patient can go to any place where an image acquisition terminal is provided, collect and upload his own fundus image to the fundus image processing terminal 302, and the fundus image processing terminal 302 automatically reads the fundus image of the sugar net patient at different periods before that, And analyze and process it, the data analysis process is high in efficiency, low in cost, and the sugar net patient has a good experience, and the analyzed data can be sent to the sugar net patient himself, so that the sugar net patient can understand their fundus health, Or send it to a professional medical staff, and let the medical staff give the sugar net patients better treatment suggestions based on the analysis results.
  • the result analysis module 3023 can also be used to generate an analysis report and send the analysis report related information to the mobile terminal device of the sugar net patient.
  • the analysis report related information includes: analysis report, analysis report One or more of the download links and recommendation reports.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Epidemiology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Eye Examination Apparatus (AREA)

Abstract

L'invention concerne un procédé et un système d'analyse pour un changement de données de caractéristique d'une image de fond d'œil à rétinopathie diabétique, et un dispositif de mémoire, se rapportant au domaine du traitement d'image de fond d'œil. Le procédé d'analyse pour le changement de données de caractéristique du fond d'œil à rétinopathie diabétique comprend les étapes consistant : à obtenir l'image de fond d'œil d'un patient de rétinopathie diabétique (S101) ; à extraire et mémoriser les données de caractéristiques de l'image de fond d'œil (S102) ; à analyser et comparer les données de caractéristiques des images de fond d'œil de différents stades du patient de rétinopathie diabétique, et à obtenir le changement de données de caractéristiques de dépistage de fond d'œil du patient de rétinopathie diabétique pour cette fois (S103) ; et à analyser et traiter le changement de données de caractéristiques de dépistage de fond d'œil (S104). Pendant un processus entier, le patient de rétinopathie diabétique peut passer à n'importe quel endroit où un dispositif d'obtention d'image de fond d'œil est disposé de façon à collecter l'image de fond d'œil du patient, puis téléverser l'image de fond d'œil correspondante vers un terminal de traitement d'image de fond d'œil ; le terminal de traitement d'image de fond d'œil mémorise l'image de fond d'œil, et compare et analyse automatiquement le changement de données de caractéristiques d'image de fond d'œil obtenu à différents stades.
PCT/CN2018/124487 2018-11-21 2018-12-27 Procédé et système d'analyse pour changement de données de caractéristiques d'un fond d'œil à rétinopathie diabétique, et dispositif de mémoire WO2020103288A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB2104798.0A GB2593824A (en) 2018-11-21 2018-12-27 Analysis method and system for feature data change of diabetic retinopathy fundus, and storage device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811390709.1A CN111292286B (zh) 2018-11-21 2018-11-21 糖网眼底特征数据变化的分析方法与***，及存储设备
CN201811390709.1 2018-11-21

Publications (1)

Publication Number Publication Date
WO2020103288A1 true WO2020103288A1 (fr) 2020-05-28

Family

ID=70774249

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/124487 WO2020103288A1 (fr) 2018-11-21 2018-12-27 Procédé et système d'analyse pour changement de données de caractéristiques d'un fond d'œil à rétinopathie diabétique, et dispositif de mémoire

Country Status (3)

Country Link
CN (1) CN111292286B (fr)
GB (1) GB2593824A (fr)
WO (1) WO2020103288A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112686855A (zh) * 2020-12-28 2021-04-20 博奥生物集团有限公司 一种眼象与症状信息的信息关联方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109166117B (zh) * 2018-08-31 2022-04-12 福州依影健康科技有限公司 一种眼底图像自动分析比对方法及一种存储设备
CN111696100A (zh) * 2020-06-17 2020-09-22 上海鹰瞳医疗科技有限公司 基于眼底影像确定吸烟程度的方法及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105513077A (zh) * 2015-12-11 2016-04-20 北京大恒图像视觉有限公司 一种用于糖尿病性视网膜病变筛查的***
CN106651827A (zh) * 2016-09-09 2017-05-10 浙江大学 一种基于sift特征的眼底图像配准方法
CN106846293A (zh) * 2016-12-14 2017-06-13 海纳医信（北京）软件科技有限责任公司 图像处理方法和装置
CN107423571A (zh) * 2017-05-04 2017-12-01 深圳硅基仿生科技有限公司 基于眼底图像的糖尿病视网膜病变识别***
CN107680683A (zh) * 2017-10-09 2018-02-09 上海睦清视觉科技有限公司 一种ai眼部健康评估方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103870838A (zh) * 2014-03-05 2014-06-18 南京航空航天大学 糖尿病视网膜病变的眼底图像特征提取方法
JP6745496B2 (ja) * 2016-08-19 2020-08-26 学校法人自治医科大学 糖尿病網膜症の病期判定支援システムおよび糖尿病網膜症の病期の判定を支援する方法
CN106530295A (zh) * 2016-11-07 2017-03-22 首都医科大学 一种视网膜病变的眼底图像分类方法和装置
CN108272434B (zh) * 2017-12-07 2020-06-19 柯鑫 对眼底图像进行处理的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105513077A (zh) * 2015-12-11 2016-04-20 北京大恒图像视觉有限公司 一种用于糖尿病性视网膜病变筛查的***
CN106651827A (zh) * 2016-09-09 2017-05-10 浙江大学 一种基于sift特征的眼底图像配准方法
CN106846293A (zh) * 2016-12-14 2017-06-13 海纳医信（北京）软件科技有限责任公司 图像处理方法和装置
CN107423571A (zh) * 2017-05-04 2017-12-01 深圳硅基仿生科技有限公司 基于眼底图像的糖尿病视网膜病变识别***
CN107680683A (zh) * 2017-10-09 2018-02-09 上海睦清视觉科技有限公司 一种ai眼部健康评估方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112686855A (zh) * 2020-12-28 2021-04-20 博奥生物集团有限公司 一种眼象与症状信息的信息关联方法
CN112686855B (zh) * 2020-12-28 2024-04-16 博奥生物集团有限公司 一种眼象与症状信息的信息关联方法

Also Published As

Publication number Publication date
GB2593824A (en) 2021-10-06
CN111292286A (zh) 2020-06-16
CN111292286B (zh) 2023-07-11
GB202104798D0 (en) 2021-05-19

Similar Documents

Publication Publication Date Title
WO2020103289A1 (fr) Méthode et système d'analyse de données de caractéristique de changement de vaisseau sanguin rétinien hypertendu
US11210789B2 (en) Diabetic retinopathy recognition system based on fundus image
US11213197B2 (en) Artificial neural network and system for identifying lesion in retinal fundus image
US10441160B2 (en) Method and system for classifying optic nerve head
US20210391056A1 (en) Health big data service method and system based on remote fundus screening
WO2020103288A1 (fr) Procédé et système d'analyse pour changement de données de caractéristiques d'un fond d'œil à rétinopathie diabétique, et dispositif de mémoire
Abdel-Ghafar et al. Progress towards automated detection and characterization of the optic disc in glaucoma and diabetic retinopathy
WO2020042404A1 (fr) Procédé et système de contrôle de qualité pour un dépistage sur fond d'œil à distance, et dispositif de stockage
CN109994173A (zh) 一种眼底病监测***
CN111402184B (zh) 一种实现远程眼底筛查和健康服务的方法和***
CN111383775A (zh) 一种基于眼底筛查的会员用户匿名交流方法及存储设备
KR20160002516A (ko) 홍채차트를 이용한 건강진단 시스템 및 그 방법
CN111435612A (zh) 一种移动医疗个性化健康服务的方法和***
CN111325631B (zh) 一种基于眼底图像的健康保险控费的方法和***
Mir et al. Portable smart healthcare solution to eye examination for diabetic retinopathy detection at an earlier stage
CN110875094B (zh) 糖尿病的健康生活方式激励方法和***、及存储设备
CN115274102B (zh) 静脉血栓栓塞症人工智能防治***、方法、装置及介质
Li et al. Dual-mode Imaging System for Early Detection and Monitoring of Ocular Surface Diseases
Kochina et al. Clinical decision support system for extraocular muscle pathology
Charters Telemedicine ushers in new chapter in eye care
Kumari et al. Role of Artificial Intelligence in mode of Diabetic Retinopathy Imaging Techniques: A Review Artificial Intelligence in Diabetic Retinopathy
KR20190132161A (ko) 건강검진을 위한 인공지능시스템의 학습방법, 인공지능시스템 및 이를 이용한 건강검진정보 제공방법
Aquino Automated Diagnosis of Diabetic Retinopathy: Fundamentals, Current State of Art and Perspectives

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940927

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 202104798

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20181227

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18940927

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18940927

Country of ref document: EP

Kind code of ref document: A1